How to fix the deprecated issue of ffmpeg? - c

I try to compile the example code "transcoding" of ffmpeg. However, I encounter one deprecated issue of ffmpeg. After I added a inline=__inline and _CRT_SECURE_NO_DEPRECATE to the preprocessor definition, the following error still exists. I don't know how to fix that. Please help.
The error shows that error C4996: 'avcodec_encode_video2': was declared deprecated for the line
int(*enc_func)(AVCodecContext *, AVPacket *, const AVFrame *, int *) =
(ifmt_ctx->streams[stream_index]->codecpar->codec_type ==
AVMEDIA_TYPE_VIDEO) ? avcodec_encode_video2 : avcodec_encode_audio2;
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavfilter/avfiltergraph.h>
#include <libavfilter/buffersink.h>
#include <libavfilter/buffersrc.h>
#include <libavutil/opt.h>
#include <libavutil/pixdesc.h>
#pragma warning(disable 4996)
#ifdef _MSC_VER
#define snprintf _snprintf
#endif
static AVFormatContext *ifmt_ctx;
static AVFormatContext *ofmt_ctx;
typedef struct FilteringContext {
AVFilterContext *buffersink_ctx;
AVFilterContext *buffersrc_ctx;
AVFilterGraph *filter_graph;
} FilteringContext;
static FilteringContext *filter_ctx;
typedef struct StreamContext {
AVCodecContext *dec_ctx;
AVCodecContext *enc_ctx;
} StreamContext;
static StreamContext *stream_ctx;
static int open_input_file(const char *filename)
{
int ret;
unsigned int i;
ifmt_ctx = NULL;
if ((ret = avformat_open_input(&ifmt_ctx, filename, NULL, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n");
return ret;
}
if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
return ret;
}
stream_ctx = (StreamContext *)av_mallocz_array(ifmt_ctx->nb_streams, sizeof(*stream_ctx));
if (!stream_ctx)
return AVERROR(ENOMEM);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
AVStream *stream = ifmt_ctx->streams[i];
AVCodec *dec = avcodec_find_decoder(stream->codecpar->codec_id);
AVCodecContext *codec_ctx;
if (!dec) {
av_log(NULL, AV_LOG_ERROR, "Failed to find decoder for stream #%u\n", i);
return AVERROR_DECODER_NOT_FOUND;
}
codec_ctx = avcodec_alloc_context3(dec);
if (!codec_ctx) {
av_log(NULL, AV_LOG_ERROR, "Failed to allocate the decoder context for stream #%u\n", i);
return AVERROR(ENOMEM);
}
ret = avcodec_parameters_to_context(codec_ctx, stream->codecpar);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to copy decoder parameters to input decoder context "
"for stream #%u\n", i);
return ret;
}
/* Reencode video & audio and remux subtitles etc. */
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO)
codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, stream, NULL);
/* Open decoder */
ret = avcodec_open2(codec_ctx, dec, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i);
return ret;
}
}
stream_ctx[i].dec_ctx = codec_ctx;
}
av_dump_format(ifmt_ctx, 0, filename, 0);
return 0;
}
static int open_output_file(const char *filename)
{
AVStream *out_stream;
AVStream *in_stream;
AVCodecContext *dec_ctx, *enc_ctx;
AVCodec *encoder;
int ret;
unsigned int i;
ofmt_ctx = NULL;
avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, filename);
if (!ofmt_ctx) {
av_log(NULL, AV_LOG_ERROR, "Could not create output context\n");
return AVERROR_UNKNOWN;
}
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
out_stream = avformat_new_stream(ofmt_ctx, NULL);
if (!out_stream) {
av_log(NULL, AV_LOG_ERROR, "Failed allocating output stream\n");
return AVERROR_UNKNOWN;
}
in_stream = ifmt_ctx->streams[i];
dec_ctx = stream_ctx[i].dec_ctx;
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
/* in this example, we choose transcoding to same codec */
encoder = avcodec_find_encoder(dec_ctx->codec_id);
if (!encoder) {
av_log(NULL, AV_LOG_FATAL, "Necessary encoder not found\n");
return AVERROR_INVALIDDATA;
}
enc_ctx = avcodec_alloc_context3(encoder);
if (!enc_ctx) {
av_log(NULL, AV_LOG_FATAL, "Failed to allocate the encoder context\n");
return AVERROR(ENOMEM);
}
/* In this example, we transcode to same properties (picture size,
* sample rate etc.). These properties can be changed for output
* streams easily using filters */
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
enc_ctx->height = dec_ctx->height;
enc_ctx->width = dec_ctx->width;
enc_ctx->sample_aspect_ratio = dec_ctx->sample_aspect_ratio;
/* take first format from list of supported formats */
if (encoder->pix_fmts)
enc_ctx->pix_fmt = encoder->pix_fmts[0];
else
enc_ctx->pix_fmt = dec_ctx->pix_fmt;
/* video time_base can be set to whatever is handy and supported by encoder */
enc_ctx->time_base = av_inv_q(dec_ctx->framerate);
}
else {
enc_ctx->sample_rate = dec_ctx->sample_rate;
enc_ctx->channel_layout = dec_ctx->channel_layout;
enc_ctx->channels = av_get_channel_layout_nb_channels(enc_ctx->channel_layout);
/* take first format from list of supported formats */
enc_ctx->sample_fmt = encoder->sample_fmts[0];
enc_ctx->time_base = (AVRational){ 1, enc_ctx->sample_rate };
}
/* Third parameter can be used to pass settings to encoder */
ret = avcodec_open2(enc_ctx, encoder, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open video encoder for stream #%u\n", i);
return ret;
}
ret = avcodec_parameters_from_context(out_stream->codecpar, enc_ctx);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to copy encoder parameters to output stream #%u\n", i);
return ret;
}
if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
enc_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
out_stream->time_base = enc_ctx->time_base;
stream_ctx[i].enc_ctx = enc_ctx;
}
else if (dec_ctx->codec_type == AVMEDIA_TYPE_UNKNOWN) {
av_log(NULL, AV_LOG_FATAL, "Elementary stream #%d is of unknown type, cannot proceed\n", i);
return AVERROR_INVALIDDATA;
}
else {
/* if this stream must be remuxed */
ret = avcodec_parameters_copy(out_stream->codecpar, in_stream->codecpar);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Copying parameters for stream #%u failed\n", i);
return ret;
}
out_stream->time_base = in_stream->time_base;
}
}
av_dump_format(ofmt_ctx, 0, filename, 1);
if (!(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) {
ret = avio_open(&ofmt_ctx->pb, filename, AVIO_FLAG_WRITE);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Could not open output file '%s'", filename);
return ret;
}
}
/* init muxer, write output file header */
ret = avformat_write_header(ofmt_ctx, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error occurred when opening output file\n");
return ret;
}
return 0;
}
static int init_filter(FilteringContext* fctx, AVCodecContext *dec_ctx,
AVCodecContext *enc_ctx, const char *filter_spec)
{
char args[512];
int ret = 0;
AVFilter *buffersrc = NULL;
AVFilter *buffersink = NULL;
AVFilterContext *buffersrc_ctx = NULL;
AVFilterContext *buffersink_ctx = NULL;
AVFilterInOut *outputs = avfilter_inout_alloc();
AVFilterInOut *inputs = avfilter_inout_alloc();
AVFilterGraph *filter_graph = avfilter_graph_alloc();
if (!outputs || !inputs || !filter_graph) {
ret = AVERROR(ENOMEM);
goto end;
}
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
buffersrc = avfilter_get_by_name("buffer");
buffersink = avfilter_get_by_name("buffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}
snprintf(args, sizeof(args),
"video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt,
dec_ctx->time_base.num, dec_ctx->time_base.den,
dec_ctx->sample_aspect_ratio.num,
dec_ctx->sample_aspect_ratio.den);
ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer source\n");
goto end;
}
ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer sink\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "pix_fmts",
(uint8_t*)&enc_ctx->pix_fmt, sizeof(enc_ctx->pix_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output pixel format\n");
goto end;
}
}
else if (dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
buffersrc = avfilter_get_by_name("abuffer");
buffersink = avfilter_get_by_name("abuffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}
if (!dec_ctx->channel_layout)
dec_ctx->channel_layout =
av_get_default_channel_layout(dec_ctx->channels);
snprintf(args, sizeof(args),
"time_base=%d/%d:sample_rate=%d:sample_fmt=%s:channel_layout=0x%"PRIx64,
dec_ctx->time_base.num, dec_ctx->time_base.den, dec_ctx->sample_rate,
av_get_sample_fmt_name(dec_ctx->sample_fmt),
dec_ctx->channel_layout);
ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer source\n");
goto end;
}
ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer sink\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "sample_fmts",
(uint8_t*)&enc_ctx->sample_fmt, sizeof(enc_ctx->sample_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output sample format\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "channel_layouts",
(uint8_t*)&enc_ctx->channel_layout,
sizeof(enc_ctx->channel_layout), AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output channel layout\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "sample_rates",
(uint8_t*)&enc_ctx->sample_rate, sizeof(enc_ctx->sample_rate),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output sample rate\n");
goto end;
}
}
else {
ret = AVERROR_UNKNOWN;
goto end;
}
/* Endpoints for the filter graph. */
outputs->name = av_strdup("in");
outputs->filter_ctx = buffersrc_ctx;
outputs->pad_idx = 0;
outputs->next = NULL;
inputs->name = av_strdup("out");
inputs->filter_ctx = buffersink_ctx;
inputs->pad_idx = 0;
inputs->next = NULL;
if (!outputs->name || !inputs->name) {
ret = AVERROR(ENOMEM);
goto end;
}
if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec,
&inputs, &outputs, NULL)) < 0)
goto end;
if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0)
goto end;
/* Fill FilteringContext */
fctx->buffersrc_ctx = buffersrc_ctx;
fctx->buffersink_ctx = buffersink_ctx;
fctx->filter_graph = filter_graph;
end:
avfilter_inout_free(&inputs);
avfilter_inout_free(&outputs);
return ret;
}
static int init_filters(void)
{
const char *filter_spec;
unsigned int i;
int ret;
filter_ctx = (FilteringContext *)av_malloc_array(ifmt_ctx->nb_streams, sizeof(*filter_ctx));
if (!filter_ctx)
return AVERROR(ENOMEM);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
filter_ctx[i].buffersrc_ctx = NULL;
filter_ctx[i].buffersink_ctx = NULL;
filter_ctx[i].filter_graph = NULL;
if (!(ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO
|| ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO))
continue;
if (ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO)
filter_spec = "null"; /* passthrough (dummy) filter for video */
else
filter_spec = "anull"; /* passthrough (dummy) filter for audio */
ret = init_filter(&filter_ctx[i], stream_ctx[i].dec_ctx,
stream_ctx[i].enc_ctx, filter_spec);
if (ret)
return ret;
}
return 0;
}
static int encode_write_frame(AVFrame *filt_frame, unsigned int stream_index, int *got_frame) {
int ret;
int got_frame_local;
AVPacket enc_pkt;
int(*enc_func)(AVCodecContext *, AVPacket *, const AVFrame *, int *) =
(ifmt_ctx->streams[stream_index]->codecpar->codec_type ==
AVMEDIA_TYPE_VIDEO) ? avcodec_encode_video2 : avcodec_encode_audio2;
if (!got_frame)
got_frame = &got_frame_local;
av_log(NULL, AV_LOG_INFO, "Encoding frame\n");
/* encode filtered frame */
enc_pkt.data = NULL;
enc_pkt.size = 0;
av_init_packet(&enc_pkt);
ret = enc_func(stream_ctx[stream_index].enc_ctx, &enc_pkt,
filt_frame, got_frame);
av_frame_free(&filt_frame);
if (ret < 0)
return ret;
if (!(*got_frame))
return 0;
/* prepare packet for muxing */
enc_pkt.stream_index = stream_index;
av_packet_rescale_ts(&enc_pkt,
stream_ctx[stream_index].enc_ctx->time_base,
ofmt_ctx->streams[stream_index]->time_base);
av_log(NULL, AV_LOG_DEBUG, "Muxing frame\n");
/* mux encoded frame */
ret = av_interleaved_write_frame(ofmt_ctx, &enc_pkt);
return ret;
}
static int filter_encode_write_frame(AVFrame *frame, unsigned int stream_index)
{
int ret;
AVFrame *filt_frame;
av_log(NULL, AV_LOG_INFO, "Pushing decoded frame to filters\n");
/* push the decoded frame into the filtergraph */
ret = av_buffersrc_add_frame_flags(filter_ctx[stream_index].buffersrc_ctx,
frame, 0);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while feeding the filtergraph\n");
return ret;
}
/* pull filtered frames from the filtergraph */
while (1) {
filt_frame = av_frame_alloc();
if (!filt_frame) {
ret = AVERROR(ENOMEM);
break;
}
av_log(NULL, AV_LOG_INFO, "Pulling filtered frame from filters\n");
ret = av_buffersink_get_frame(filter_ctx[stream_index].buffersink_ctx,
filt_frame);
if (ret < 0) {
/* if no more frames for output - returns AVERROR(EAGAIN)
* if flushed and no more frames for output - returns AVERROR_EOF
* rewrite retcode to 0 to show it as normal procedure completion
*/
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
ret = 0;
av_frame_free(&filt_frame);
break;
}
filt_frame->pict_type = AV_PICTURE_TYPE_NONE;
ret = encode_write_frame(filt_frame, stream_index, NULL);
if (ret < 0)
break;
}
return ret;
}
static int flush_encoder(unsigned int stream_index)
{
int ret;
int got_frame;
if (!(stream_ctx[stream_index].enc_ctx->codec->capabilities &
AV_CODEC_CAP_DELAY))
return 0;
while (1) {
av_log(NULL, AV_LOG_INFO, "Flushing stream #%u encoder\n", stream_index);
ret = encode_write_frame(NULL, stream_index, &got_frame);
if (ret < 0)
break;
if (!got_frame)
return 0;
}
return ret;
}
int main(int argc, char **argv)
{
int ret;
AVPacket packet = { .data = NULL, .size = 0 };
AVFrame *frame = NULL;
enum AVMediaType type;
unsigned int stream_index;
unsigned int i;
int got_frame;
int(*dec_func)(AVCodecContext *, AVFrame *, int *, const AVPacket *);
if (argc != 3) {
av_log(NULL, AV_LOG_ERROR, "Usage: %s <input file> <output file>\n", argv[0]);
return 1;
}
av_register_all();
avfilter_register_all();
if ((ret = open_input_file(argv[1])) < 0)
goto end;
if ((ret = open_output_file(argv[2])) < 0)
goto end;
if ((ret = init_filters()) < 0)
goto end;
/* read all packets */
while (1) {
if ((ret = av_read_frame(ifmt_ctx, &packet)) < 0)
break;
stream_index = packet.stream_index;
type = ifmt_ctx->streams[packet.stream_index]->codecpar->codec_type;
av_log(NULL, AV_LOG_DEBUG, "Demuxer gave frame of stream_index %u\n",
stream_index);
if (filter_ctx[stream_index].filter_graph) {
av_log(NULL, AV_LOG_DEBUG, "Going to reencode&filter the frame\n");
frame = av_frame_alloc();
if (!frame) {
ret = AVERROR(ENOMEM);
break;
}
av_packet_rescale_ts(&packet,
ifmt_ctx->streams[stream_index]->time_base,
stream_ctx[stream_index].dec_ctx->time_base);
dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 :
avcodec_decode_audio4;
ret = dec_func(stream_ctx[stream_index].dec_ctx, frame,
&got_frame, &packet);
if (ret < 0) {
av_frame_free(&frame);
av_log(NULL, AV_LOG_ERROR, "Decoding failed\n");
break;
}
if (got_frame) {
frame->pts = frame->best_effort_timestamp;
ret = filter_encode_write_frame(frame, stream_index);
av_frame_free(&frame);
if (ret < 0)
goto end;
}
else {
av_frame_free(&frame);
}
}
else {
/* remux this frame without reencoding */
av_packet_rescale_ts(&packet,
ifmt_ctx->streams[stream_index]->time_base,
ofmt_ctx->streams[stream_index]->time_base);
ret = av_interleaved_write_frame(ofmt_ctx, &packet);
if (ret < 0)
goto end;
}
av_packet_unref(&packet);
}
/* flush filters and encoders */
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
/* flush filter */
if (!filter_ctx[i].filter_graph)
continue;
ret = filter_encode_write_frame(NULL, i);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Flushing filter failed\n");
goto end;
}
/* flush encoder */
ret = flush_encoder(i);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Flushing encoder failed\n");
goto end;
}
}
av_write_trailer(ofmt_ctx);
end:
av_packet_unref(&packet);
av_frame_free(&frame);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
avcodec_free_context(&stream_ctx[i].dec_ctx);
if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && stream_ctx[i].enc_ctx)
avcodec_free_context(&stream_ctx[i].enc_ctx);
if (filter_ctx && filter_ctx[i].filter_graph)
avfilter_graph_free(&filter_ctx[i].filter_graph);
}
av_free(filter_ctx);
av_free(stream_ctx);
avformat_close_input(&ifmt_ctx);
if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE))
avio_closep(&ofmt_ctx->pb);
avformat_free_context(ofmt_ctx);
if (ret < 0)
av_log(NULL, AV_LOG_ERROR, "Error occurred: %s\n", av_err2str(ret));
return ret ? 1 : 0;
}

Best would be to find the replacement function for avcodec_encode_video2 and use it instead of the deprecated one.
Unfortunately ffmpeg deprecation warnings do not give an idea what is the replacement, so you'll have to dig through ffmpeg release notes and documentation to find the actual replacement.

From avcodec.h of the libavcodec library
avcodec_encode_video2() is deprecated use avcodec_send_frame()/avcodec_receive_packet() instead

We can check the FFMPEG's deprecated list from the official page. Choose your FFMPEG version and find the deprecated functions as well their respective replacements (if any)
sample links
version 4.0
version 3.4

You can comment key word deprecated in file header ffmpeg lib

Related

Ffmpeg transcoding to H264 MP4 is not producing smooth video

We have app where we record, depending on the configuration, from a camera/desktop or IP camera. The example is in C running under Ubuntu, but our app is windows based one so instead of x11grab we use gdigrab and instead of v4l2 we use 'dshow'.
The idea is no matter what we record from to be encoded to H264 and mp4 container. The code is based on transcoding.c example from ffmpeg.
Everything works so far, videos are playable everywhere, but the client is saying that the produced videos are not smooth and are choppy, even if the reported framerate is 29.97.
I've edited transcoding.c to be the same as our app code.
#include <libavcodec/avcodec.h>
#include <libavdevice/avdevice.h>
#include <libavformat/avformat.h>
#include <libavfilter/buffersink.h>
#include <libavfilter/buffersrc.h>
#include <libavutil/channel_layout.h>
#include <libavutil/opt.h>
#include <libavutil/pixdesc.h>
static AVFormatContext *ifmt_ctx;
static AVFormatContext *ofmt_ctx;
typedef struct FilteringContext {
AVFilterContext *buffersink_ctx;
AVFilterContext *buffersrc_ctx;
AVFilterGraph *filter_graph;
AVPacket *enc_pkt;
AVFrame *filtered_frame;
} FilteringContext;
static FilteringContext *filter_ctx;
typedef struct StreamContext {
AVCodecContext *dec_ctx;
AVCodecContext *enc_ctx;
AVFrame *dec_frame;
} StreamContext;
static StreamContext *stream_ctx;
static int open_input_file()
{
int ret;
unsigned int i;
const AVInputFormat *format = av_find_input_format("x11grab");
ifmt_ctx = NULL;
if ((ret = avformat_open_input(&ifmt_ctx, ":0.0+0,0", format, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n");
return ret;
}
if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
return ret;
}
stream_ctx = av_calloc(ifmt_ctx->nb_streams, sizeof(*stream_ctx));
if (!stream_ctx)
return AVERROR(ENOMEM);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
AVStream *stream = ifmt_ctx->streams[i];
const AVCodec *dec = avcodec_find_decoder(stream->codecpar->codec_id);
AVCodecContext *codec_ctx;
if (!dec) {
av_log(NULL, AV_LOG_ERROR, "Failed to find decoder for stream #%u\n", i);
return AVERROR_DECODER_NOT_FOUND;
}
codec_ctx = avcodec_alloc_context3(dec);
if (!codec_ctx) {
av_log(NULL, AV_LOG_ERROR, "Failed to allocate the decoder context for stream #%u\n", i);
return AVERROR(ENOMEM);
}
ret = avcodec_parameters_to_context(codec_ctx, stream->codecpar);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to copy decoder parameters to input decoder context "
"for stream #%u\n", i);
return ret;
}
/* Reencode video & audio and remux subtitles etc. */
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO)
codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, stream, NULL);
/* Open decoder */
ret = avcodec_open2(codec_ctx, dec, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i);
return ret;
}
}
stream_ctx[i].dec_ctx = codec_ctx;
stream_ctx[i].dec_frame = av_frame_alloc();
if (!stream_ctx[i].dec_frame)
return AVERROR(ENOMEM);
}
//av_dump_format(ifmt_ctx, 0, "/dev/video0", 0);
return 0;
}
static int open_output_file(const char *filename)
{
AVStream *out_stream;
AVStream *in_stream;
AVCodecContext *dec_ctx, *enc_ctx;
const AVCodec *encoder;
int ret;
unsigned int i;
ofmt_ctx = NULL;
avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, filename);
if (!ofmt_ctx) {
av_log(NULL, AV_LOG_ERROR, "Could not create output context\n");
return AVERROR_UNKNOWN;
}
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
out_stream = avformat_new_stream(ofmt_ctx, NULL);
if (!out_stream) {
av_log(NULL, AV_LOG_ERROR, "Failed allocating output stream\n");
return AVERROR_UNKNOWN;
}
in_stream = ifmt_ctx->streams[i];
dec_ctx = stream_ctx[i].dec_ctx;
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO || dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
encoder = avcodec_find_encoder_by_name("libx264");
if (!encoder) {
av_log(NULL, AV_LOG_FATAL, "Necessary encoder not found\n");
return AVERROR_INVALIDDATA;
}
enc_ctx = avcodec_alloc_context3(encoder);
if (!enc_ctx) {
av_log(NULL, AV_LOG_FATAL, "Failed to allocate the encoder context\n");
return AVERROR(ENOMEM);
}
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
enc_ctx->height = dec_ctx->height;
enc_ctx->width = dec_ctx->width;
enc_ctx->sample_aspect_ratio = dec_ctx->sample_aspect_ratio;
if (encoder->pix_fmts)
enc_ctx->pix_fmt = encoder->pix_fmts[0];
else
enc_ctx->pix_fmt = dec_ctx->pix_fmt;
enc_ctx->time_base = dec_ctx->time_base;
enc_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
av_opt_set(enc_ctx->priv_data, "crf", "18", 0);
av_opt_set(enc_ctx->priv_data, "preset", "slow", 0);
} else {
enc_ctx->sample_rate = dec_ctx->sample_rate;
ret = av_channel_layout_copy(&enc_ctx->ch_layout, &dec_ctx->ch_layout);
if (ret < 0)
return ret;
enc_ctx->sample_fmt = encoder->sample_fmts[0];
enc_ctx->time_base = (AVRational){1, enc_ctx->sample_rate};
}
if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
enc_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
/* Third parameter can be used to pass settings to encoder */
ret = avcodec_open2(enc_ctx, encoder, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open video encoder for stream #%u\n", i);
return ret;
}
ret = avcodec_parameters_from_context(out_stream->codecpar, enc_ctx);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to copy encoder parameters to output stream #%u\n", i);
return ret;
}
out_stream->time_base = enc_ctx->time_base;
stream_ctx[i].enc_ctx = enc_ctx;
} else if (dec_ctx->codec_type == AVMEDIA_TYPE_UNKNOWN) {
av_log(NULL, AV_LOG_FATAL, "Elementary stream #%d is of unknown type, cannot proceed\n", i);
return AVERROR_INVALIDDATA;
} else {
/* if this stream must be remuxed */
ret = avcodec_parameters_copy(out_stream->codecpar, in_stream->codecpar);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Copying parameters for stream #%u failed\n", i);
return ret;
}
out_stream->time_base = in_stream->time_base;
}
}
av_dump_format(ofmt_ctx, 0, filename, 1);
if (!(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) {
ret = avio_open(&ofmt_ctx->pb, filename, AVIO_FLAG_WRITE);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Could not open output file '%s'", filename);
return ret;
}
}
/* init muxer, write output file header */
ret = avformat_write_header(ofmt_ctx, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error occurred when opening output file\n");
return ret;
}
return 0;
}
static int init_filter(FilteringContext* fctx, AVCodecContext *dec_ctx,
AVCodecContext *enc_ctx, const char *filter_spec)
{
char args[512];
int ret = 0;
const AVFilter *buffersrc = NULL;
const AVFilter *buffersink = NULL;
AVFilterContext *buffersrc_ctx = NULL;
AVFilterContext *buffersink_ctx = NULL;
AVFilterInOut *outputs = avfilter_inout_alloc();
AVFilterInOut *inputs = avfilter_inout_alloc();
AVFilterGraph *filter_graph = avfilter_graph_alloc();
if (!outputs || !inputs || !filter_graph) {
ret = AVERROR(ENOMEM);
goto end;
}
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
buffersrc = avfilter_get_by_name("buffer");
buffersink = avfilter_get_by_name("buffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}
snprintf(args, sizeof(args),
"video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt,
dec_ctx->time_base.num, dec_ctx->time_base.den,
dec_ctx->sample_aspect_ratio.num,
dec_ctx->sample_aspect_ratio.den);
ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer source\n");
goto end;
}
ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer sink\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "pix_fmts",
(uint8_t*)&enc_ctx->pix_fmt, sizeof(enc_ctx->pix_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output pixel format\n");
goto end;
}
} else if (dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
char buf[64];
buffersrc = avfilter_get_by_name("abuffer");
buffersink = avfilter_get_by_name("abuffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}
if (dec_ctx->ch_layout.order == AV_CHANNEL_ORDER_UNSPEC)
av_channel_layout_default(&dec_ctx->ch_layout, dec_ctx->ch_layout.nb_channels);
av_channel_layout_describe(&dec_ctx->ch_layout, buf, sizeof(buf));
snprintf(args, sizeof(args),
"time_base=%d/%d:sample_rate=%d:sample_fmt=%s:channel_layout=%s",
dec_ctx->time_base.num, dec_ctx->time_base.den, dec_ctx->sample_rate,
av_get_sample_fmt_name(dec_ctx->sample_fmt),
buf);
ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer source\n");
goto end;
}
ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer sink\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "sample_fmts",
(uint8_t*)&enc_ctx->sample_fmt, sizeof(enc_ctx->sample_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output sample format\n");
goto end;
}
av_channel_layout_describe(&enc_ctx->ch_layout, buf, sizeof(buf));
ret = av_opt_set(buffersink_ctx, "ch_layouts",
buf, AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output channel layout\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "sample_rates",
(uint8_t*)&enc_ctx->sample_rate, sizeof(enc_ctx->sample_rate),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output sample rate\n");
goto end;
}
} else {
ret = AVERROR_UNKNOWN;
goto end;
}
/* Endpoints for the filter graph. */
outputs->name = av_strdup("in");
outputs->filter_ctx = buffersrc_ctx;
outputs->pad_idx = 0;
outputs->next = NULL;
inputs->name = av_strdup("out");
inputs->filter_ctx = buffersink_ctx;
inputs->pad_idx = 0;
inputs->next = NULL;
if (!outputs->name || !inputs->name) {
ret = AVERROR(ENOMEM);
goto end;
}
if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec,
&inputs, &outputs, NULL)) < 0)
goto end;
if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0)
goto end;
/* Fill FilteringContext */
fctx->buffersrc_ctx = buffersrc_ctx;
fctx->buffersink_ctx = buffersink_ctx;
fctx->filter_graph = filter_graph;
end:
avfilter_inout_free(&inputs);
avfilter_inout_free(&outputs);
return ret;
}
static int init_filters(void)
{
const char *filter_spec;
unsigned int i;
int ret;
filter_ctx = av_malloc_array(ifmt_ctx->nb_streams, sizeof(*filter_ctx));
if (!filter_ctx)
return AVERROR(ENOMEM);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
filter_ctx[i].buffersrc_ctx = NULL;
filter_ctx[i].buffersink_ctx = NULL;
filter_ctx[i].filter_graph = NULL;
if (!(ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO
|| ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO))
continue;
if (ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO)
filter_spec = "fps=fps=29.97,setpts=PTS-STARTPTS,format=yuv420p";
else
filter_spec = "anull"; /* passthrough (dummy) filter for audio */
ret = init_filter(&filter_ctx[i], stream_ctx[i].dec_ctx,
stream_ctx[i].enc_ctx, filter_spec);
if (ret)
return ret;
filter_ctx[i].enc_pkt = av_packet_alloc();
if (!filter_ctx[i].enc_pkt)
return AVERROR(ENOMEM);
filter_ctx[i].filtered_frame = av_frame_alloc();
if (!filter_ctx[i].filtered_frame)
return AVERROR(ENOMEM);
}
return 0;
}
static int encode_write_frame(unsigned int stream_index, int flush)
{
StreamContext *stream = &stream_ctx[stream_index];
FilteringContext *filter = &filter_ctx[stream_index];
AVFrame *filt_frame = flush ? NULL : filter->filtered_frame;
AVPacket *enc_pkt = filter->enc_pkt;
int ret;
av_log(NULL, AV_LOG_INFO, "Encoding frame\n");
/* encode filtered frame */
av_packet_unref(enc_pkt);
ret = avcodec_send_frame(stream->enc_ctx, filt_frame);
if (ret < 0)
return ret;
while (ret >= 0) {
ret = avcodec_receive_packet(stream->enc_ctx, enc_pkt);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
return 0;
/* prepare packet for muxing */
enc_pkt->stream_index = stream_index;
av_packet_rescale_ts(enc_pkt,
stream->enc_ctx->time_base,
ofmt_ctx->streams[stream_index]->time_base);
av_log(NULL, AV_LOG_DEBUG, "Muxing frame\n");
/* mux encoded frame */
ret = av_interleaved_write_frame(ofmt_ctx, enc_pkt);
}
return ret;
}
static int filter_encode_write_frame(AVFrame *frame, unsigned int stream_index)
{
FilteringContext *filter = &filter_ctx[stream_index];
int ret;
av_log(NULL, AV_LOG_INFO, "Pushing decoded frame to filters\n");
/* push the decoded frame into the filtergraph */
ret = av_buffersrc_add_frame_flags(filter->buffersrc_ctx,
frame, 0);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while feeding the filtergraph\n");
return ret;
}
/* pull filtered frames from the filtergraph */
while (1) {
av_log(NULL, AV_LOG_INFO, "Pulling filtered frame from filters\n");
ret = av_buffersink_get_frame(filter->buffersink_ctx,
filter->filtered_frame);
if (ret < 0) {
/* if no more frames for output - returns AVERROR(EAGAIN)
* if flushed and no more frames for output - returns AVERROR_EOF
* rewrite retcode to 0 to show it as normal procedure completion
*/
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
ret = 0;
break;
}
filter->filtered_frame->pict_type = AV_PICTURE_TYPE_NONE;
ret = encode_write_frame(stream_index, 0);
av_frame_unref(filter->filtered_frame);
if (ret < 0)
break;
}
return ret;
}
static int flush_encoder(unsigned int stream_index)
{
if (!(stream_ctx[stream_index].enc_ctx->codec->capabilities &
AV_CODEC_CAP_DELAY))
return 0;
av_log(NULL, AV_LOG_INFO, "Flushing stream #%u encoder\n", stream_index);
return encode_write_frame(stream_index, 1);
}
int main(int argc, char **argv)
{
int ret;
AVPacket *packet = NULL;
unsigned int stream_index;
unsigned int i;
avdevice_register_all();
if ((ret = open_input_file()) < 0)
goto end;
if ((ret = open_output_file("test.mp4")) < 0)
goto end;
if ((ret = init_filters()) < 0)
goto end;
if (!(packet = av_packet_alloc()))
goto end;
int frameCount = 0;
/* read all packets */
while (frameCount < 300) {
if ((ret = av_read_frame(ifmt_ctx, packet)) < 0)
break;
frameCount++;
stream_index = packet->stream_index;
av_log(NULL, AV_LOG_DEBUG, "Demuxer gave frame of stream_index %u\n",
stream_index);
if (filter_ctx[stream_index].filter_graph) {
StreamContext *stream = &stream_ctx[stream_index];
av_log(NULL, AV_LOG_DEBUG, "Going to reencode&filter the frame\n");
av_packet_rescale_ts(packet,
ifmt_ctx->streams[stream_index]->time_base,
stream->dec_ctx->time_base);
ret = avcodec_send_packet(stream->dec_ctx, packet);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Decoding failed\n");
break;
}
while (ret >= 0) {
ret = avcodec_receive_frame(stream->dec_ctx, stream->dec_frame);
if (ret == AVERROR_EOF || ret == AVERROR(EAGAIN))
break;
else if (ret < 0)
goto end;
stream->dec_frame->pts = stream->dec_frame->best_effort_timestamp;
ret = filter_encode_write_frame(stream->dec_frame, stream_index);
if (ret < 0)
goto end;
}
} else {
/* remux this frame without reencoding */
av_packet_rescale_ts(packet,
ifmt_ctx->streams[stream_index]->time_base,
ofmt_ctx->streams[stream_index]->time_base);
ret = av_interleaved_write_frame(ofmt_ctx, packet);
if (ret < 0)
goto end;
}
av_packet_unref(packet);
}
/* flush filters and encoders */
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
/* flush filter */
if (!filter_ctx[i].filter_graph)
continue;
ret = filter_encode_write_frame(NULL, i);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Flushing filter failed\n");
goto end;
}
/* flush encoder */
ret = flush_encoder(i);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Flushing encoder failed\n");
goto end;
}
}
av_write_trailer(ofmt_ctx);
end:
av_packet_free(&packet);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
avcodec_free_context(&stream_ctx[i].dec_ctx);
if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && stream_ctx[i].enc_ctx)
avcodec_free_context(&stream_ctx[i].enc_ctx);
if (filter_ctx && filter_ctx[i].filter_graph) {
avfilter_graph_free(&filter_ctx[i].filter_graph);
av_packet_free(&filter_ctx[i].enc_pkt);
av_frame_free(&filter_ctx[i].filtered_frame);
}
av_frame_free(&stream_ctx[i].dec_frame);
}
av_free(filter_ctx);
av_free(stream_ctx);
avformat_close_input(&ifmt_ctx);
if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE))
avio_closep(&ofmt_ctx->pb);
avformat_free_context(ofmt_ctx);
if (ret < 0)
av_log(NULL, AV_LOG_ERROR, "Error occurred: %s\n", av_err2str(ret));
return ret ? 1 : 0;
}
I'm using the fps filter to keep the framerate/duration of the video if there is variable frame rate. setpts filter is used to generate the pts without making the encoder complain. Also I'm not sure how I can calculate the pts correctly with audio.
What is wrong with my code? Why the videos are not really smooth and choppy?

FFMPEG - Encode a .wav file to G711

My question is the following: how to encode a .wav file to G.711/PCM A-law?
I tried to edit this example file, but I got an EINVAL error when tried to call av_frame_get_buffer(frame, 0) with frame->nb_samples = c->frame_size which is 0 (I think this is the problem) because of pcm.c:37 (at least I think because of it).
So with which parameters allocate an audio data buffer by myself if av_frame_get_buffer() doesn't do this for me and how to use it?
Thanks for reply!
EDIT:
My code:
#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <libavcodec/avcodec.h>
#include <libavutil/channel_layout.h>
#include <libavutil/common.h>
#include <libavutil/frame.h>
#include <libavutil/samplefmt.h>
/* check that a given sample format is supported by the encoder */
static int check_sample_fmt(const AVCodec *codec, enum AVSampleFormat sample_fmt)
{
const enum AVSampleFormat *p = codec->sample_fmts;
while (*p != AV_SAMPLE_FMT_NONE) {
if (*p == sample_fmt)
return 1;
p++;
}
return 0;
}
/* just pick the highest supported samplerate */
static int select_sample_rate(const AVCodec *codec)
{
const int *p;
int best_samplerate = 0;
if (!codec->supported_samplerates)
return 44100;
p = codec->supported_samplerates;
while (*p) {
if (!best_samplerate || abs(44100 - *p) < abs(44100 - best_samplerate))
best_samplerate = *p;
p++;
}
return best_samplerate;
}
/* select layout with the highest channel count */
static int select_channel_layout(const AVCodec *codec)
{
const uint64_t *p;
uint64_t best_ch_layout = 0;
int best_nb_channels = 0;
if (!codec->channel_layouts)
return AV_CH_LAYOUT_STEREO;
p = codec->channel_layouts;
while (*p) {
int nb_channels = av_get_channel_layout_nb_channels(*p);
if (nb_channels > best_nb_channels) {
best_ch_layout = *p;
best_nb_channels = nb_channels;
}
p++;
}
return best_ch_layout;
}
static void encode(AVCodecContext *ctx, AVFrame *frame, AVPacket *pkt,
FILE *output)
{
int ret;
/* send the frame for encoding */
ret = avcodec_send_frame(ctx, frame);
if (ret < 0) {
fprintf(stderr, "Error sending the frame to the encoder\n");
exit(1);
}
/* read all the available output packets (in general there may be any
* number of them */
while (ret >= 0) {
ret = avcodec_receive_packet(ctx, pkt);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
return;
else if (ret < 0) {
fprintf(stderr, "Error encoding audio frame\n");
exit(1);
}
fwrite(pkt->data, 1, pkt->size, output);
av_packet_unref(pkt);
}
}
int main(int argc, char **argv)
{
const char *filename;
const AVCodec *codec;
AVCodecContext *c = NULL;
AVFrame *frame;
AVPacket *pkt;
int i, j, k, ret;
FILE *f;
uint16_t *samples;
float t, tincr;
if (argc <= 1)
{
fprintf(stderr, "Usage: %s <output file>\n", argv[0]);
return 0;
}
filename = argv[1];
codec = avcodec_find_encoder(AV_CODEC_ID_PCM_ALAW);
if (!codec)
{
fprintf(stderr, "Codec not found\n");
exit(1);
}
c = avcodec_alloc_context3(codec);
if (!c)
{
fprintf(stderr, "Could not allocate audio codec context\n");
exit(1);
}
c->bit_rate = 128000;
c->sample_fmt = AV_SAMPLE_FMT_S16;
if (!check_sample_fmt(codec, c->sample_fmt))
{
fprintf(stderr, "Encoder does not support sample format %s",
av_get_sample_fmt_name(c->sample_fmt));
exit(1);
}
c->sample_rate = select_sample_rate(codec);
c->channel_layout = select_channel_layout(codec);
c->channels = av_get_channel_layout_nb_channels(c->channel_layout);
if (avcodec_open2(c, codec, NULL) < 0)
{
fprintf(stderr, "Could not open codec\n");
exit(1);
}
f = fopen(filename, "wb");
if (!f)
{
fprintf(stderr, "Could not open %s\n", filename);
exit(1);
}
pkt = av_packet_alloc();
if (!pkt)
{
fprintf(stderr, "Could not allocate the packet\n");
exit(1);
}
frame = av_frame_alloc();
if (!frame)
{
fprintf(stderr, "Could not allocate audio frame\n");
exit(1);
}
frame->nb_samples = c->frame_size;
frame->format = c->sample_fmt;
frame->channel_layout = c->channel_layout;
// ERROR Here
ret = av_frame_get_buffer(frame, 0);
if (ret < 0)
{
fprintf(stderr, "Could not allocate audio data buffers\n");
exit(1);
}
t = 0;
tincr = 2 * M_PI * 440.0 / c->sample_rate;
for (i = 0; i < 200; i++)
{
ret = av_frame_make_writable(frame);
if (ret < 0)
{
exit(1);
}
samples = (uint16_t*)frame->data[0];
for (j = 0; j < c->frame_size; j++)
{
samples[2*j] = (int)(sin(t)*10000);
for (k = 1; k < c->channels; k++)
{
samples[2*j + k] = samples[2*j];
}
t += tincr;
}
encode(c, frame, pkt, f);
}
encode(c, NULL, pkt, f);
fclose(f);
av_frame_free(&frame);
av_packet_free(&pkt);
avcodec_free_context(&c);
return 0;
}

How to use ffmpeg lib transform mp4(h264&aac) to m3u8 (hls) by C code?

I used official examples transcoding.c but console print pkt->duration = 0, maybe the hls segment duration will not precise.
I use this code to set duration but invalid。
av_opt_set_int(ofmt_ctx->priv_data, "hls_time", 5, AV_OPT_SEARCH_CHILDREN);
In command line
ffmpeg -i a.mp4 -codec copy -vbsf h264_mp4toannexb -map 0 -f segment -segment_list a.m3u8 -segment_time 10 a-%03d.ts
How to use C code to achieve this command?
this is my code:
/**
* #file
* API example for demuxing, decoding, filtering, encoding and muxing
* #example transcoding.c
*/
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavfilter/buffersink.h>
#include <libavfilter/buffersrc.h>
#include <libavutil/opt.h>
#include <libavutil/pixdesc.h>
static AVFormatContext *ifmt_ctx;
static AVFormatContext *ofmt_ctx;
typedef struct FilteringContext {
AVFilterContext *buffersink_ctx;
AVFilterContext *buffersrc_ctx;
AVFilterGraph *filter_graph;
} FilteringContext;
static FilteringContext *filter_ctx;
typedef struct StreamContext {
AVCodecContext *dec_ctx;
AVCodecContext *enc_ctx;
} StreamContext;
static StreamContext *stream_ctx;
static int open_input_file(const char *filename) {
int ret;
unsigned int i;
ifmt_ctx = NULL;
if ((ret = avformat_open_input(&ifmt_ctx, filename, NULL, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n");
return ret;
}
if ((ret = avformat_find_stream_info(ifmt_ctx, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
return ret;
}
stream_ctx = av_mallocz_array(ifmt_ctx->nb_streams, sizeof(*stream_ctx));
if (!stream_ctx)
return AVERROR(ENOMEM);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
AVStream *stream = ifmt_ctx->streams[i];
AVCodec *dec = avcodec_find_decoder(stream->codecpar->codec_id);
AVCodecContext *codec_ctx;
if (!dec) {
av_log(NULL, AV_LOG_ERROR, "Failed to find decoder for stream #%u\n", i);
return AVERROR_DECODER_NOT_FOUND;
}
codec_ctx = avcodec_alloc_context3(dec);
if (!codec_ctx) {
av_log(NULL, AV_LOG_ERROR, "Failed to allocate the decoder context for stream #%u\n", i);
return AVERROR(ENOMEM);
}
ret = avcodec_parameters_to_context(codec_ctx, stream->codecpar);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to copy decoder parameters to input decoder context "
"for stream #%u\n", i);
return ret;
}
/* Reencode video & audio and remux subtitles etc. */
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| codec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
if (codec_ctx->codec_type == AVMEDIA_TYPE_VIDEO)
codec_ctx->framerate = av_guess_frame_rate(ifmt_ctx, stream, NULL);
/* Open decoder */
ret = avcodec_open2(codec_ctx, dec, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to open decoder for stream #%u\n", i);
return ret;
}
}
stream_ctx[i].dec_ctx = codec_ctx;
}
av_dump_format(ifmt_ctx, 0, filename, 0);
return 0;
}
static int open_output_file(const char *filename, enum AVCodecID videoCodecId, enum AVCodecID audioCodecId) {
AVStream *out_stream;
AVStream *in_stream;
AVCodecContext *dec_ctx, *enc_ctx;
AVCodec *encoder;
int ret;
unsigned int i;
ofmt_ctx = NULL;
avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, filename);
if (!ofmt_ctx) {
av_log(NULL, AV_LOG_ERROR, "Could not create output context\n");
return AVERROR_UNKNOWN;
}
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
out_stream = avformat_new_stream(ofmt_ctx, NULL);
if (!out_stream) {
av_log(NULL, AV_LOG_ERROR, "Failed allocating output stream\n");
return AVERROR_UNKNOWN;
}
in_stream = ifmt_ctx->streams[i];
dec_ctx = stream_ctx[i].dec_ctx;
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO
|| dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
encoder = avcodec_find_encoder(videoCodecId);
} else {
encoder = avcodec_find_encoder(audioCodecId);
}
//encoder = avcodec_find_encoder(dec_ctx->codec_id);
if (!encoder) {
av_log(NULL, AV_LOG_FATAL, "Necessary encoder not found\n");
return AVERROR_INVALIDDATA;
}
enc_ctx = avcodec_alloc_context3(encoder);
if (!enc_ctx) {
av_log(NULL, AV_LOG_FATAL, "Failed to allocate the encoder context\n");
return AVERROR(ENOMEM);
}
/* In this example, we transcode to same properties (picture size,
* sample rate etc.). These properties can be changed for output
* streams easily using filters */
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
enc_ctx->height = dec_ctx->height;
enc_ctx->width = dec_ctx->width;
enc_ctx->sample_aspect_ratio = dec_ctx->sample_aspect_ratio;
/* take first format from list of supported formats */
if (encoder->pix_fmts)
enc_ctx->pix_fmt = encoder->pix_fmts[0];
else
enc_ctx->pix_fmt = dec_ctx->pix_fmt;
/* video time_base can be set to whatever is handy and supported by encoder */
enc_ctx->time_base = av_inv_q(dec_ctx->framerate);
} else {
enc_ctx->sample_rate = dec_ctx->sample_rate;
enc_ctx->channel_layout = dec_ctx->channel_layout;
enc_ctx->channels = av_get_channel_layout_nb_channels(enc_ctx->channel_layout);
/* take first format from list of supported formats */
enc_ctx->sample_fmt = encoder->sample_fmts[0];
enc_ctx->time_base = (AVRational) {1, enc_ctx->sample_rate};
}
if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
enc_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
/* Third parameter can be used to pass settings to encoder */
ret = avcodec_open2(enc_ctx, encoder, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open video encoder for stream #%u\n", i);
return ret;
}
ret = avcodec_parameters_from_context(out_stream->codecpar, enc_ctx);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Failed to copy encoder parameters to output stream #%u\n", i);
return ret;
}
out_stream->time_base = enc_ctx->time_base;
stream_ctx[i].enc_ctx = enc_ctx;
} else if (dec_ctx->codec_type == AVMEDIA_TYPE_UNKNOWN) {
av_log(NULL, AV_LOG_FATAL, "Elementary stream #%d is of unknown type, cannot proceed\n", i);
return AVERROR_INVALIDDATA;
} else {
/* if this stream must be remuxed */
ret = avcodec_parameters_copy(out_stream->codecpar, in_stream->codecpar);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Copying parameters for stream #%u failed\n", i);
return ret;
}
out_stream->time_base = in_stream->time_base;
}
}
av_dump_format(ofmt_ctx, 0, filename, 1);
av_opt_set_int(ofmt_ctx->priv_data, "hls_time", 5, AV_OPT_SEARCH_CHILDREN);
if (!(ofmt_ctx->oformat->flags & AVFMT_NOFILE)) {
ret = avio_open(&ofmt_ctx->pb, filename, AVIO_FLAG_WRITE);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Could not open output file '%s'", filename);
return ret;
}
}
/* init muxer, write output file header */
ret = avformat_write_header(ofmt_ctx, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error occurred when opening output file\n");
return ret;
}
return 0;
}
static int init_filter(FilteringContext *fctx, AVCodecContext *dec_ctx,
AVCodecContext *enc_ctx, const char *filter_spec) {
char args[512];
int ret = 0;
const AVFilter *buffersrc = NULL;
const AVFilter *buffersink = NULL;
AVFilterContext *buffersrc_ctx = NULL;
AVFilterContext *buffersink_ctx = NULL;
AVFilterInOut *outputs = avfilter_inout_alloc();
AVFilterInOut *inputs = avfilter_inout_alloc();
AVFilterGraph *filter_graph = avfilter_graph_alloc();
if (!outputs || !inputs || !filter_graph) {
ret = AVERROR(ENOMEM);
goto end;
}
if (dec_ctx->codec_type == AVMEDIA_TYPE_VIDEO) {
buffersrc = avfilter_get_by_name("buffer");
buffersink = avfilter_get_by_name("buffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}
snprintf(args, sizeof(args),
"video_size=%dx%d:pix_fmt=%d:time_base=%d/%d:pixel_aspect=%d/%d",
dec_ctx->width, dec_ctx->height, dec_ctx->pix_fmt,
dec_ctx->time_base.num, dec_ctx->time_base.den,
dec_ctx->sample_aspect_ratio.num,
dec_ctx->sample_aspect_ratio.den);
ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer source\n");
goto end;
}
ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create buffer sink\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "pix_fmts",
(uint8_t *) &enc_ctx->pix_fmt, sizeof(enc_ctx->pix_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output pixel format\n");
goto end;
}
} else if (dec_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
buffersrc = avfilter_get_by_name("abuffer");
buffersink = avfilter_get_by_name("abuffersink");
if (!buffersrc || !buffersink) {
av_log(NULL, AV_LOG_ERROR, "filtering source or sink element not found\n");
ret = AVERROR_UNKNOWN;
goto end;
}
if (!dec_ctx->channel_layout)
dec_ctx->channel_layout =
av_get_default_channel_layout(dec_ctx->channels);
snprintf(args, sizeof(args),
"time_base=%d/%d:sample_rate=%d:sample_fmt=%s:channel_layout=0x%"PRIx64,
dec_ctx->time_base.num, dec_ctx->time_base.den, dec_ctx->sample_rate,
av_get_sample_fmt_name(dec_ctx->sample_fmt),
dec_ctx->channel_layout);
ret = avfilter_graph_create_filter(&buffersrc_ctx, buffersrc, "in",
args, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer source\n");
goto end;
}
ret = avfilter_graph_create_filter(&buffersink_ctx, buffersink, "out",
NULL, NULL, filter_graph);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot create audio buffer sink\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "sample_fmts",
(uint8_t *) &enc_ctx->sample_fmt, sizeof(enc_ctx->sample_fmt),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output sample format\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "channel_layouts",
(uint8_t *) &enc_ctx->channel_layout,
sizeof(enc_ctx->channel_layout), AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output channel layout\n");
goto end;
}
ret = av_opt_set_bin(buffersink_ctx, "sample_rates",
(uint8_t *) &enc_ctx->sample_rate, sizeof(enc_ctx->sample_rate),
AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output sample rate\n");
goto end;
}
} else {
ret = AVERROR_UNKNOWN;
goto end;
}
/* Endpoints for the filter graph. */
outputs->name = av_strdup("in");
outputs->filter_ctx = buffersrc_ctx;
outputs->pad_idx = 0;
outputs->next = NULL;
inputs->name = av_strdup("out");
inputs->filter_ctx = buffersink_ctx;
inputs->pad_idx = 0;
inputs->next = NULL;
if (!outputs->name || !inputs->name) {
ret = AVERROR(ENOMEM);
goto end;
}
if ((ret = avfilter_graph_parse_ptr(filter_graph, filter_spec,
&inputs, &outputs, NULL)) < 0)
goto end;
if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0)
goto end;
/* Fill FilteringContext */
fctx->buffersrc_ctx = buffersrc_ctx;
fctx->buffersink_ctx = buffersink_ctx;
fctx->filter_graph = filter_graph;
end:
avfilter_inout_free(&inputs);
avfilter_inout_free(&outputs);
return ret;
}
static int init_filters(void) {
const char *filter_spec;
unsigned int i;
int ret;
filter_ctx = av_malloc_array(ifmt_ctx->nb_streams, sizeof(*filter_ctx));
if (!filter_ctx)
return AVERROR(ENOMEM);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
filter_ctx[i].buffersrc_ctx = NULL;
filter_ctx[i].buffersink_ctx = NULL;
filter_ctx[i].filter_graph = NULL;
if (!(ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO
|| ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO))
continue;
if (ifmt_ctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO)
filter_spec = "null"; /* passthrough (dummy) filter for video */
else
filter_spec = "anull"; /* passthrough (dummy) filter for audio */
ret = init_filter(&filter_ctx[i], stream_ctx[i].dec_ctx,
stream_ctx[i].enc_ctx, filter_spec);
if (ret)
return ret;
}
return 0;
}
static int encode_write_frame(AVFrame *filt_frame, unsigned int stream_index, int *got_frame) {
int ret;
int got_frame_local;
AVPacket enc_pkt;
int (*enc_func)(AVCodecContext *, AVPacket *, const AVFrame *, int *) =
(ifmt_ctx->streams[stream_index]->codecpar->codec_type ==
AVMEDIA_TYPE_VIDEO) ? avcodec_encode_video2 : avcodec_encode_audio2;
if (!got_frame)
got_frame = &got_frame_local;
av_log(NULL, AV_LOG_INFO, "Encoding frame\n");
/* encode filtered frame */
enc_pkt.data = NULL;
enc_pkt.size = 0;
av_init_packet(&enc_pkt);
ret = enc_func(stream_ctx[stream_index].enc_ctx, &enc_pkt,
filt_frame, got_frame);
av_frame_free(&filt_frame);
if (ret < 0)
return ret;
if (!(*got_frame))
return 0;
/* prepare packet for muxing */
enc_pkt.stream_index = stream_index;
av_packet_rescale_ts(&enc_pkt,
stream_ctx[stream_index].enc_ctx->time_base,
ofmt_ctx->streams[stream_index]->time_base);
av_log(NULL, AV_LOG_DEBUG, "Muxing frame\n");
/* mux encoded frame */
ret = av_interleaved_write_frame(ofmt_ctx, &enc_pkt);
return ret;
}
static int filter_encode_write_frame(AVFrame *frame, unsigned int stream_index) {
int ret;
AVFrame *filt_frame;
av_log(NULL, AV_LOG_INFO, "Pushing decoded frame to filters\n");
/* push the decoded frame into the filtergraph */
ret = av_buffersrc_add_frame_flags(filter_ctx[stream_index].buffersrc_ctx,
frame, 0);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while feeding the filtergraph\n");
return ret;
}
/* pull filtered frames from the filtergraph */
while (1) {
filt_frame = av_frame_alloc();
if (!filt_frame) {
ret = AVERROR(ENOMEM);
break;
}
av_log(NULL, AV_LOG_INFO, "Pulling filtered frame from filters\n");
ret = av_buffersink_get_frame(filter_ctx[stream_index].buffersink_ctx,
filt_frame);
if (ret < 0) {
/* if no more frames for output - returns AVERROR(EAGAIN)
* if flushed and no more frames for output - returns AVERROR_EOF
* rewrite retcode to 0 to show it as normal procedure completion
*/
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
ret = 0;
av_frame_free(&filt_frame);
break;
}
filt_frame->pict_type = AV_PICTURE_TYPE_NONE;
ret = encode_write_frame(filt_frame, stream_index, NULL);
if (ret < 0)
break;
}
return ret;
}
static int flush_encoder(unsigned int stream_index) {
int ret;
int got_frame;
if (!(stream_ctx[stream_index].enc_ctx->codec->capabilities &
AV_CODEC_CAP_DELAY))
return 0;
while (1) {
av_log(NULL, AV_LOG_INFO, "Flushing stream #%u encoder\n", stream_index);
ret = encode_write_frame(NULL, stream_index, &got_frame);
if (ret < 0)
break;
if (!got_frame)
return 0;
}
return ret;
}
int main() {
char *inputFile = "D:/20200623_094923.mp4";
char *outputFile = "D:/test/te.m3u8";
enum AVCodecID videoCodec = AV_CODEC_ID_H264;
enum AVCodecID audioCodec = AV_CODEC_ID_AAC;
int ret;
AVPacket packet = {.data = NULL, .size = 0};
AVFrame *frame = NULL;
enum AVMediaType type;
unsigned int stream_index;
unsigned int i;
int got_frame;
int (*dec_func)(AVCodecContext *, AVFrame *, int *, const AVPacket *);
if ((ret = open_input_file(inputFile)) < 0)
goto end;
if ((ret = open_output_file(outputFile, videoCodec, audioCodec)) < 0)
goto end;
if ((ret = init_filters()) < 0)
goto end;
/* read all packets */
while (1) {
if ((ret = av_read_frame(ifmt_ctx, &packet)) < 0)
break;
stream_index = packet.stream_index;
type = ifmt_ctx->streams[packet.stream_index]->codecpar->codec_type;
av_log(NULL, AV_LOG_DEBUG, "Demuxer gave frame of stream_index %u\n",
stream_index);
if (filter_ctx[stream_index].filter_graph) {
av_log(NULL, AV_LOG_DEBUG, "Going to reencode&filter the frame\n");
frame = av_frame_alloc();
if (!frame) {
ret = AVERROR(ENOMEM);
break;
}
av_packet_rescale_ts(&packet,
ifmt_ctx->streams[stream_index]->time_base,
stream_ctx[stream_index].dec_ctx->time_base);
dec_func = (type == AVMEDIA_TYPE_VIDEO) ? avcodec_decode_video2 :
avcodec_decode_audio4;
ret = dec_func(stream_ctx[stream_index].dec_ctx, frame,
&got_frame, &packet);
if (ret < 0) {
av_frame_free(&frame);
av_log(NULL, AV_LOG_ERROR, "Decoding failed\n");
break;
}
if (got_frame) {
frame->pts = frame->best_effort_timestamp;
ret = filter_encode_write_frame(frame, stream_index);
av_frame_free(&frame);
if (ret < 0)
goto end;
} else {
av_frame_free(&frame);
}
} else {
/* remux this frame without reencoding */
av_packet_rescale_ts(&packet,
ifmt_ctx->streams[stream_index]->time_base,
ofmt_ctx->streams[stream_index]->time_base);
ret = av_interleaved_write_frame(ofmt_ctx, &packet);
if (ret < 0)
goto end;
}
av_packet_unref(&packet);
}
/* flush filters and encoders */
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
/* flush filter */
if (!filter_ctx[i].filter_graph)
continue;
ret = filter_encode_write_frame(NULL, i);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Flushing filter failed\n");
goto end;
}
/* flush encoder */
ret = flush_encoder(i);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Flushing encoder failed\n");
goto end;
}
}
av_write_trailer(ofmt_ctx);
end:
av_packet_unref(&packet);
av_frame_free(&frame);
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
avcodec_free_context(&stream_ctx[i].dec_ctx);
if (ofmt_ctx && ofmt_ctx->nb_streams > i && ofmt_ctx->streams[i] && stream_ctx[i].enc_ctx)
avcodec_free_context(&stream_ctx[i].enc_ctx);
if (filter_ctx && filter_ctx[i].filter_graph)
avfilter_graph_free(&filter_ctx[i].filter_graph);
}
av_free(filter_ctx);
av_free(stream_ctx);
avformat_close_input(&ifmt_ctx);
if (ofmt_ctx && !(ofmt_ctx->oformat->flags & AVFMT_NOFILE))
avio_closep(&ofmt_ctx->pb);
avformat_free_context(ofmt_ctx);
if (ret < 0)
av_log(NULL, AV_LOG_ERROR, "Error occurred: %s\n", av_err2str(ret));
return ret ? 1 : 0;
}

Reading motion vectors of every 60th frame in video file

I have the following code which reads a video files and extracts motion vectors from each frame and outputs them to stdout:
#include <libavutil/motion_vector.h>
#include <libavformat/avformat.h>
static AVFormatContext *fmt_ctx = NULL;
static AVCodecContext *video_dec_ctx = NULL;
static AVStream *video_stream = NULL;
static const char *src_filename = NULL;
static int video_stream_idx = -1;
static AVFrame *frame = NULL;
static int video_frame_count = 0;
static int decode_packet(const AVPacket *pkt)
{
//fprintf(stderr, "%d\n", video_dec_ctx->width);
int ret = avcodec_send_packet(video_dec_ctx, pkt);
if (ret < 0) {
fprintf(stderr, "Error while sending a packet to the decoder: %s\n", av_err2str(ret));
return ret;
}
while (ret >= 0) {
ret = avcodec_receive_frame(video_dec_ctx, frame);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {
break;
} else if (ret < 0) {
fprintf(stderr, "Error while receiving a frame from the decoder: %s\n", av_err2str(ret));
return ret;
}
if (ret >= 0) {
int i;
AVFrameSideData *sd;
video_frame_count++;
sd = av_frame_get_side_data(frame, AV_FRAME_DATA_MOTION_VECTORS);
if (sd) {
const AVMotionVector *mvs = (const AVMotionVector *)sd->data;
for (i = 0; i < sd->size / sizeof(*mvs); i++) {
const AVMotionVector *mv = &mvs[i];
printf("%d,%4d,%4d,%4d\n",
video_frame_count,
abs(mv->src_x - mv->dst_x),
abs(mv->src_y - mv->dst_y));
}
}
av_frame_unref(frame);
}
}
return 0;
}
static int open_codec_context(AVFormatContext *fmt_ctx, enum AVMediaType type)
{
int ret;
AVStream *st;
AVCodecContext *dec_ctx = NULL;
AVCodec *dec = NULL;
AVDictionary *opts = NULL;
ret = av_find_best_stream(fmt_ctx, type, -1, -1, &dec, 0);
if (ret < 0) {
fprintf(stderr, "Could not find %s stream in input file '%s'\n",
av_get_media_type_string(type), src_filename);
return ret;
} else {
int stream_idx = ret;
st = fmt_ctx->streams[stream_idx];
dec_ctx = avcodec_alloc_context3(dec);
if (!dec_ctx) {
fprintf(stderr, "Failed to allocate codec\n");
return AVERROR(EINVAL);
}
ret = avcodec_parameters_to_context(dec_ctx, st->codecpar);
if (ret < 0) {
fprintf(stderr, "Failed to copy codec parameters to codec context\n");
return ret;
}
/* Init the video decoder */
av_dict_set(&opts, "flags2", "+export_mvs", 0);
if ((ret = avcodec_open2(dec_ctx, dec, &opts)) < 0) {
fprintf(stderr, "Failed to open %s codec\n",
av_get_media_type_string(type));
return ret;
}
video_stream_idx = stream_idx;
video_stream = fmt_ctx->streams[video_stream_idx];
video_dec_ctx = dec_ctx;
}
return 0;
}
int main(int argc, char **argv)
{
int ret = 0;
AVPacket pkt = { 0 };
if (argc != 2) {
fprintf(stderr, "Usage: %s <video>\n", argv[0]);
exit(1);
}
src_filename = argv[1];
if (avformat_open_input(&fmt_ctx, src_filename, NULL, NULL) < 0) {
fprintf(stderr, "Could not open source file %s\n", src_filename);
exit(1);
}
if (avformat_find_stream_info(fmt_ctx, NULL) < 0) {
fprintf(stderr, "Could not find stream information\n");
exit(1);
}
open_codec_context(fmt_ctx, AVMEDIA_TYPE_VIDEO);
av_dump_format(fmt_ctx, 0, src_filename, 0);
if (!video_stream) {
fprintf(stderr, "Could not find video stream in the input, aborting\n");
ret = 1;
goto end;
}
frame = av_frame_alloc();
if (!frame) {
fprintf(stderr, "Could not allocate frame\n");
ret = AVERROR(ENOMEM);
goto end;
}
printf("framenum,dx,dy\n");
/* read frames from the file */
while (av_read_frame(fmt_ctx, &pkt) >= 0) {
if (pkt.stream_index == video_stream_idx)
ret = decode_packet(&pkt);
av_packet_unref(&pkt);
if (ret < 0)
break;
}
/* flush cached frames */
decode_packet(NULL);
end:
avcodec_free_context(&video_dec_ctx);
avformat_close_input(&fmt_ctx);
av_frame_free(&frame);
return ret < 0;
}
Instead and outputting every frame, I only want to read one frame every 60 frames. The speed of the program is very important so I want to eliminate as much unnecessary code as possible. The problem is I'm having a hard time understanding how to advance the video stream without reading in new frames. I call av_read_frame(fmt_ctx, &pkt) to get packet info that is decoded by decode_packet and then goes on to read the next, but I can't find a way to only get packet info for one frame out of each 60.
Use av_seek_frame() to read every 60th frame.

How to cut video with FFmpeg C API

How can I cut video with FFmpeg C API? From 00:10:00 to 00:20:00 for example.
What functions I need to use?
I convert video using this function:
int convert(char *file) {
AVFrame *frame;
AVPacket inPacket, outPacket;
if(avio_open(&outFormatContext->pb, file, AVIO_FLAG_WRITE) < 0) {
fprintf(stderr, "convert(): cannot open out file\n");
return 0;
}
avformat_write_header(outFormatContext, NULL);
frame = avcodec_alloc_frame();
av_init_packet(&inPacket);
while(av_read_frame(inFormatContext, &inPacket) >= 0) {
if(inPacket.stream_index == inVideoStreamIndex) {
avcodec_decode_video2(inCodecContext, frame, &frameFinished, &inPacket);
if(frameFinished) {
av_init_packet(&outPacket);
avcodec_encode_video2(outCodecContext, &outPacket, frame, &outputed);
if(outputed) {
if (av_write_frame(outFormatContext, &outPacket) != 0) {
fprintf(stderr, "convert(): error while writing video frame\n");
return 0;
}
}
av_free_packet(&outPacket);
}
}
}
av_write_trailer(outFormatContext);
av_free_packet(&inPacket);
return 1;
}
As Wagner Patriota says, "if you just wanna cut the video, you don't need to reencode the video if you want". Here is the code based on ffmpeg remuxing.c example that you don't need to reencode the video.
#include <libavutil/timestamp.h>
#include <libavformat/avformat.h>
static void log_packet(const AVFormatContext *fmt_ctx, const AVPacket *pkt, const char *tag)
{
AVRational *time_base = &fmt_ctx->streams[pkt->stream_index]->time_base;
printf("%s: pts:%s pts_time:%s dts:%s dts_time:%s duration:%s duration_time:%s stream_index:%d\n",
tag,
av_ts2str(pkt->pts), av_ts2timestr(pkt->pts, time_base),
av_ts2str(pkt->dts), av_ts2timestr(pkt->dts, time_base),
av_ts2str(pkt->duration), av_ts2timestr(pkt->duration, time_base),
pkt->stream_index);
}
int cut_video(double from_seconds, double end_seconds, const char* in_filename, const char* out_filename) {
AVOutputFormat *ofmt = NULL;
AVFormatContext *ifmt_ctx = NULL, *ofmt_ctx = NULL;
AVPacket pkt;
int ret, i;
av_register_all();
if ((ret = avformat_open_input(&ifmt_ctx, in_filename, 0, 0)) < 0) {
fprintf(stderr, "Could not open input file '%s'", in_filename);
goto end;
}
if ((ret = avformat_find_stream_info(ifmt_ctx, 0)) < 0) {
fprintf(stderr, "Failed to retrieve input stream information");
goto end;
}
av_dump_format(ifmt_ctx, 0, in_filename, 0);
avformat_alloc_output_context2(&ofmt_ctx, NULL, NULL, out_filename);
if (!ofmt_ctx) {
fprintf(stderr, "Could not create output context\n");
ret = AVERROR_UNKNOWN;
goto end;
}
ofmt = ofmt_ctx->oformat;
for (i = 0; i < ifmt_ctx->nb_streams; i++) {
AVStream *in_stream = ifmt_ctx->streams[i];
AVStream *out_stream = avformat_new_stream(ofmt_ctx, in_stream->codec->codec);
if (!out_stream) {
fprintf(stderr, "Failed allocating output stream\n");
ret = AVERROR_UNKNOWN;
goto end;
}
ret = avcodec_copy_context(out_stream->codec, in_stream->codec);
if (ret < 0) {
fprintf(stderr, "Failed to copy context from input to output stream codec context\n");
goto end;
}
out_stream->codec->codec_tag = 0;
if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER)
out_stream->codec->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
}
av_dump_format(ofmt_ctx, 0, out_filename, 1);
if (!(ofmt->flags & AVFMT_NOFILE)) {
ret = avio_open(&ofmt_ctx->pb, out_filename, AVIO_FLAG_WRITE);
if (ret < 0) {
fprintf(stderr, "Could not open output file '%s'", out_filename);
goto end;
}
}
ret = avformat_write_header(ofmt_ctx, NULL);
if (ret < 0) {
fprintf(stderr, "Error occurred when opening output file\n");
goto end;
}
// int indexs[8] = {0};
// int64_t start_from = 8*AV_TIME_BASE;
ret = av_seek_frame(ifmt_ctx, -1, from_seconds*AV_TIME_BASE, AVSEEK_FLAG_ANY);
if (ret < 0) {
fprintf(stderr, "Error seek\n");
goto end;
}
int64_t *dts_start_from = malloc(sizeof(int64_t) * ifmt_ctx->nb_streams);
memset(dts_start_from, 0, sizeof(int64_t) * ifmt_ctx->nb_streams);
int64_t *pts_start_from = malloc(sizeof(int64_t) * ifmt_ctx->nb_streams);
memset(pts_start_from, 0, sizeof(int64_t) * ifmt_ctx->nb_streams);
while (1) {
AVStream *in_stream, *out_stream;
ret = av_read_frame(ifmt_ctx, &pkt);
if (ret < 0)
break;
in_stream = ifmt_ctx->streams[pkt.stream_index];
out_stream = ofmt_ctx->streams[pkt.stream_index];
log_packet(ifmt_ctx, &pkt, "in");
if (av_q2d(in_stream->time_base) * pkt.pts > end_seconds) {
av_free_packet(&pkt);
break;
}
if (dts_start_from[pkt.stream_index] == 0) {
dts_start_from[pkt.stream_index] = pkt.dts;
printf("dts_start_from: %s\n", av_ts2str(dts_start_from[pkt.stream_index]));
}
if (pts_start_from[pkt.stream_index] == 0) {
pts_start_from[pkt.stream_index] = pkt.pts;
printf("pts_start_from: %s\n", av_ts2str(pts_start_from[pkt.stream_index]));
}
/* copy packet */
pkt.pts = av_rescale_q_rnd(pkt.pts - pts_start_from[pkt.stream_index], in_stream->time_base, out_stream->time_base, AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX);
pkt.dts = av_rescale_q_rnd(pkt.dts - dts_start_from[pkt.stream_index], in_stream->time_base, out_stream->time_base, AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX);
if (pkt.pts < 0) {
pkt.pts = 0;
}
if (pkt.dts < 0) {
pkt.dts = 0;
}
pkt.duration = (int)av_rescale_q((int64_t)pkt.duration, in_stream->time_base, out_stream->time_base);
pkt.pos = -1;
log_packet(ofmt_ctx, &pkt, "out");
printf("\n");
ret = av_interleaved_write_frame(ofmt_ctx, &pkt);
if (ret < 0) {
fprintf(stderr, "Error muxing packet\n");
break;
}
av_free_packet(&pkt);
}
free(dts_start_from);
free(pts_start_from);
av_write_trailer(ofmt_ctx);
end:
avformat_close_input(&ifmt_ctx);
/* close output */
if (ofmt_ctx && !(ofmt->flags & AVFMT_NOFILE))
avio_closep(&ofmt_ctx->pb);
avformat_free_context(ofmt_ctx);
if (ret < 0 && ret != AVERROR_EOF) {
fprintf(stderr, "Error occurred: %s\n", av_err2str(ret));
return 1;
}
return 0;
}
If you just wanna cut the video, you don't need to reencode the video if you want.
So I am supposing you wanna cut and reencode for some reason. So, based on your code:
Observe you must to have access to the video AVStream* structure... I named it as inVideoStream.
int convert_and_cut(char *file, float starttime, float endtime) {
AVFrame *frame;
AVPacket inPacket, outPacket;
if(avio_open(&outFormatContext->pb, file, AVIO_FLAG_WRITE) < 0) {
fprintf(stderr, "convert(): cannot open out file\n");
return 0;
}
// seek to the start time you wish.
// BEGIN
AVRational default_timebase;
default_timebase.num = 1;
default_timebase.den = AV_TIME_BASE;
// suppose you have access to the "inVideoStream" of course
int64_t starttime_int64 = av_rescale_q((int64_t)( starttime * AV_TIME_BASE ), default_timebase, inVideoStream->time_base);
int64_t endtime_int64 = av_rescale_q((int64_t)( endtime * AV_TIME_BASE ), default_timebase, inVideoStream->time_base);
if(avformat_seek_file(inFormatContext, inVideoStreamIndex, INT64_MIN, starttime_int64, INT64_MAX, 0) < 0) {
// error... do something...
return 0; // usually 0 is used for success in C, but I am following your code.
}
avcodec_flush_buffers( inVideoStream->codec );
// END
avformat_write_header(outFormatContext, NULL);
frame = avcodec_alloc_frame();
av_init_packet(&inPacket);
// you used avformat_seek_file() to seek CLOSE to the point you want... in order to give precision to your seek,
// just go on reading the packets and checking the packets PTS (presentation timestamp)
while(av_read_frame(inFormatContext, &inPacket) >= 0) {
if(inPacket.stream_index == inVideoStreamIndex) {
avcodec_decode_video2(inCodecContext, frame, &frameFinished, &inPacket);
// this line guarantees you are getting what you really want.
if(frameFinished && frame->pkt_pts >= starttime_int64 && frame->pkt_pts <= endtime_int64) {
av_init_packet(&outPacket);
avcodec_encode_video2(outCodecContext, &outPacket, frame, &outputed);
if(outputed) {
if (av_write_frame(outFormatContext, &outPacket) != 0) {
fprintf(stderr, "convert(): error while writing video frame\n");
return 0;
}
}
av_free_packet(&outPacket);
}
// exit the loop if you got the frames you want.
if(frame->pkt_pts > endtime_int64) {
break;
}
}
}
av_write_trailer(outFormatContext);
av_free_packet(&inPacket);
return 1;
}
In addition, as ustin says, the code based on ffmpeg remuxing.c example.
add out_stream->time_base = in_stream->time_base; before out_stream->codec->codec_tag = 0;
add int64_t *start_from = NULL; after int stream_mapping_size = 0;
add start_from = av_mallocz_array(stream_mapping_size, sizeof(*start_from)); after stream_mapping = av_mallocz_array(stream_mapping_size, sizeof(*stream_mapping));
add start_from[stream_mapping[i]] = INT16_MIN; after stream_mapping[i] = stream_index++;
add
if (start_from[pkt.stream_index] == INT16_MIN) {
int64_t dts = pkt.dts;
int64_t pts = pkt.pts;
int64_t min_ts = dts > pts ? pts : dts;
start_from[pkt.stream_index] = min_ts < 0 ? 0 : min_ts;
}
After
if (pkt.stream_index >= stream_mapping_size ||
stream_mapping[pkt.stream_index] < 0) {
av_packet_unref(&pkt);
continue;
}
change justin code, about pts/dst set value to this:
pkt.pts = av_rescale_q_rnd(pkt.pts - start_from[pkt.stream_index], in_stream->time_base, out_stream->time_base, AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX);
pkt.dts = av_rescale_q_rnd(pkt.dts - start_from[pkt.stream_index], in_stream->time_base, out_stream->time_base, AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX);
add free(start_from); before end:
Tips: start/end timestamp like justin says

Resources