Memory leak while opening encoders in ffmpeg - ffmpeg

I'm getting memory leaks in avcodec_find_encoder. Although I'm cleaning the resources properly
still I'm not able to get rid of the leak. By successive commenting the code I found that memory leaks happen only after the call of avcodec_find_encoder(). I've tried my code with different video files and I found that memory leaks blocks are always same. Also if I open only audio or video then I get just one memory leaks block.
Below is the part of Init and Clean-up code from the application.
Note that this is just part of code which contains initialization and resource release.
AVFormatContext *m_informat;
AVFormatContext *m_outformat;
AVStream *m_in_vid_strm, *m_out_vid_strm;
AVStream *m_in_aud_strm, *m_out_aud_strm;
int VideoClipper::Init(const wxString& filename)
{
int ret = 0;
char errbuf[64];
av_register_all();
if ((ret = avformat_open_input( &m_informat, filename.mb_str(), 0, 0)) != 0 )
{
av_strerror(ret,errbuf,sizeof(errbuf));
PRINT_VAL("Not able to Open file;; ", errbuf)
ret = -1;
return ret;
}
else
{
PRINT_MSG("Opened File ")
}
if ((ret = avformat_find_stream_info(m_informat, 0))< 0 )
{
av_strerror(ret,errbuf,sizeof(errbuf));
PRINT_VAL("Not Able to find stream info:: ", errbuf)
ret = -1;
return ret;
}
else
{
PRINT_MSG("Got stream Info ")
}
for(unsigned int i = 0; i<m_informat->nb_streams; i++)
{
if(m_informat->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO)
{
PRINT_MSG("Found Video Stream ")
m_in_vid_strm_idx = i;
m_in_vid_strm = m_informat->streams[i];
}
if(m_informat->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO)
{
PRINT_MSG("Found Audio Stream ")
m_in_aud_strm_idx = i;
m_in_aud_strm = m_informat->streams[i];
}
}
AVOutputFormat *outfmt = NULL;
std::string outfile = std::string(filename) + "clip_out.avi";
outfmt = av_guess_format(NULL,outfile.c_str(),NULL);
if(outfmt == NULL)
{
ret = -1;
return ret;
}
else
{
m_outformat = avformat_alloc_context();
if(m_outformat)
{
m_outformat->oformat = outfmt;
_snprintf(m_outformat->filename, sizeof(m_outformat->filename), "%s", outfile.c_str());
}
else
{
ret = -1;
return ret;
}
}
AVCodec *out_vid_codec,*out_aud_codec;
out_vid_codec = out_aud_codec = NULL;
if(outfmt->video_codec != AV_CODEC_ID_NONE && m_in_vid_strm != NULL)
{
out_vid_codec = avcodec_find_encoder(outfmt->video_codec);
if(NULL == out_vid_codec)
{
PRINT_MSG("Could Not Find Vid Encoder")
ret = -1;
return ret;
}
else
{
PRINT_MSG("Found Out Vid Encoder ")
m_out_vid_strm = avformat_new_stream(m_outformat, out_vid_codec);
if(NULL == m_out_vid_strm)
{
PRINT_MSG("Failed to Allocate Output Vid Strm ")
ret = -1;
return ret;
}
else
{
PRINT_MSG("Allocated Video Stream ")
if(avcodec_copy_context(m_out_vid_strm->codec, m_informat->streams[m_in_vid_strm_idx]->codec) != 0)
{
PRINT_MSG("Failed to Copy Context ")
ret = -1;
return ret;
}
}
}
}
if(outfmt->audio_codec != AV_CODEC_ID_NONE && m_in_aud_strm != NULL)
{
out_aud_codec = avcodec_find_encoder(outfmt->audio_codec);
if(NULL == out_aud_codec)
{
PRINT_MSG("Could Not Find Out Aud Encoder ")
ret = -1;
return ret;
}
else
{
PRINT_MSG("Found Out Aud Encoder ")
m_out_aud_strm = avformat_new_stream(m_outformat, out_aud_codec);
if(NULL == m_out_aud_strm)
{
PRINT_MSG("Failed to Allocate Out Vid Strm ")
ret = -1;
return ret;
}
else
{
if(avcodec_copy_context(m_out_aud_strm->codec, m_informat->streams[m_in_aud_strm_idx]->codec) != 0)
{
PRINT_MSG("Failed to Copy Context ")
ret = -1;
return ret;
}
}
}
}
if (!(outfmt->flags & AVFMT_NOFILE))
{
if (avio_open2(&m_outformat->pb, outfile.c_str(), AVIO_FLAG_WRITE,NULL, NULL) < 0)
{
PRINT_VAL("Could Not Open File ", outfile)
ret = -1;
return ret;
}
}
/* Write the stream header, if any. */
if (avformat_write_header(m_outformat, NULL) < 0)
{
PRINT_VAL("Error Occurred While Writing Header ", outfile)
ret = -1;
return ret;
}
else
{
PRINT_MSG("Written Output header ")
m_init_done = true;
}
return ret;
}
Here is the Clean-up part
void VideoClipper::ReleaseResource(void)
{
if(m_in_aud_strm && m_in_aud_strm->codec)
{
avcodec_close(m_in_aud_strm->codec);
PRINT_MSG("Closed Input Audio Codec ")
}
if(m_in_vid_strm && m_in_vid_strm->codec)
{
avcodec_close(m_in_vid_strm->codec);
PRINT_MSG("Closed Input Video Codec ")
}
if(m_informat)
{
avformat_close_input(&m_informat);
PRINT_MSG("Freed Input Format Contex ")
}
if(m_out_aud_strm && m_out_aud_strm->codec)
{
avcodec_close(m_out_aud_strm->codec);
PRINT_MSG("Closed Output Audio Codec ")
}
if(m_out_vid_strm && m_out_vid_strm->codec)
{
avcodec_close(m_out_vid_strm->codec);
PRINT_MSG("Closed Output Audio Codec ")
}
if(m_outformat)
{
avformat_close_input(&m_outformat);
m_outformat = NULL;
PRINT_MSG("Closed Output Format ")
}
}
Memory Leaks message
Detected memory leaks!
Dumping objects ->
{13691} normal block at 0x01046A60, 4479 bytes long.
Data: < > CD CD CD CD CD CD CD CD CD CD CD CD CD CD CD CD
{13685} normal block at 0x01043FD0, 10831 bytes long.
Data: < ? > CD CD CD CD CD CD CD CD D0 3F 04 01 ED ED ED ED
Object dump complete.
I'm using latest version of ffmpeg on Visual Studio 2012.
Please suggest where I'm missing.
Thanks
Pradeep

There are lots of thing that matters here
first you need to close io
if (!(fmt->flags & AVFMT_NOFILE))
{
/* Close the output file. */
avio_close(ctx->oc->pb);
}
you should also call
avformat_free_context(ctx->oc);
There is always 24 bytes memory leakage at my system due to allocation pthread_mutex in libavcodec/utils.c of ffmpeg, and there is no way to free that memory.atleast till I or someone fix the code.

Related

FFmpeg remuxing parts of an audio file

I'm trying to remux individual tracks from a FLAC file using the FFmpeg libraries.
I get the starting timestamps from a Cue sheet, I seek to the timestamps using avformat_seek_file. However after writing the packets to output files, they only have data from the beginning of the input file.
This is the code snippet which opens the input FLAC and also creates an output AVFormatContext for each track. I'm guessing the issue is avformat_seek_file, it doesn't seem to do anything, since even though I seek to the beginning of a track, the output file contains data from the beginning of the input.
for(int i = 0; i <= sheet.ntracks; i++) {
sheet.avfmtctx = avformat_alloc_context();
if(avformat_open_input(&sheet.avfmtctx, sheet.file, NULL, NULL) < 0) {
fprintf(stderr,
"avformat_open_input(): failed to open %s\n",
sheet.file);
return 1;
}
int audio_stream_idx = -1;
for(int i = 0; i < sheet.avfmtctx->nb_streams; i++) {
if(sheet.avfmtctx->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_AUDIO) {
audio_stream_idx = i;
break;
}
}
avformat_find_stream_info(sheet.avfmtctx, NULL);
AVFormatContext *output;
char *filepath = title_to_filepath(&sheet.tracks[i], sheet.file);
avformat_alloc_output_context2(&output, NULL, NULL, filepath);
AVStream *out_audio_stream = avformat_new_stream(output, NULL);
avcodec_parameters_copy(out_audio_stream->codecpar,
sheet.avfmtctx->streams[audio_stream_idx]->codecpar);
if(avio_open(&output->pb, filepath, AVIO_FLAG_WRITE) < 0) {
fprintf(stderr, "Failed to open %s for writing\n", filepath);
return 1;
}
if(avformat_write_header(output, NULL) < 0) {
fprintf(stderr, "avformat_write_header() failed\n");
return 1;
}
int64_t current_frame = sheet.tracks[i].index;
int64_t next_track_index = (i < sheet.ntracks) ?
sheet.tracks[i + 1].index :
INT64_MAX;
if(avformat_seek_file(sheet.avfmtctx,
-1,
INT64_MIN,
current_frame,
current_frame,
0) < 0) {
fprintf(stderr, "Failed to seek to the index of track %d\n", i);
avformat_free_context(sheet.avfmtctx);
sheet.avfmtctx = NULL;
av_write_trailer(output);
avio_closep(&output->pb);
avformat_free_context(output);
free(filepath);
continue;
}
AVPacket *pkt = av_packet_alloc();
int64_t pts_diff = AV_NOPTS_VALUE, dts_diff = AV_NOPTS_VALUE;
while(current_frame < next_track_index && !avio_feof(output->pb)) {
int ret;
if((ret = av_read_frame(sheet.avfmtctx, pkt)) < 0) {
if(ret != AVERROR_EOF)
fprintf(stderr, "av_read_frame() failed: %s\n", av_err2str(ret));
break;
}
if(pkt->stream_index != audio_stream_idx)
continue;
// runs only once
if(pts_diff == AV_NOPTS_VALUE && dts_diff == AV_NOPTS_VALUE) {
pts_diff = pkt->pts;
dts_diff = pkt->dts;
}
pkt->stream_index = 0; // first and only stream
pkt->pts -= pts_diff;
pkt->dts -= dts_diff;
pkt->pos = -1;
av_interleaved_write_frame(output, pkt);
current_frame++;
}
avformat_free_context(sheet.avfmtctx);
sheet.avfmtctx = NULL;
av_write_trailer(output);
av_packet_free(&pkt);
avio_closep(&output->pb);
avformat_free_context(output);
free(filepath);
}
current_frame and next_track_index are calculated from the INDEX lines in the Cue sheet: MM * 60 * 75 + SS * 75 + FF.
Can someone tell me what I'm doing wrong, and how to get the data I need from the input?

FFMPEG AAC encoding causes audio to be lower in pitch

I built a sample application that encodes AAC (from PortAudio) into a MP4 container (no video stream).
The resulting audio is lower in pitch.
#include "stdafx.h"
#include "TestRecording.h"
#include "libffmpeg.h"
TestRecording::TestRecording()
{
}
TestRecording::~TestRecording()
{
}
struct RecordingContext
{
RecordingContext()
{
formatContext = NULL;
audioStream = NULL;
audioFrame = NULL;
audioFrameframeNumber = 0;
}
libffmpeg::AVFormatContext* formatContext;
libffmpeg::AVStream* audioStream;
libffmpeg::AVFrame* audioFrame;
int audioFrameframeNumber;
};
static int AudioRecordCallback(const void *inputBuffer, void *outputBuffer,
unsigned long framesPerBuffer,
const PaStreamCallbackTimeInfo* timeInfo,
PaStreamCallbackFlags statusFlags,
void *userData)
{
RecordingContext* recordingContext = (RecordingContext*)userData;
libffmpeg::avcodec_fill_audio_frame(recordingContext->audioFrame,
recordingContext->audioFrame->channels,
recordingContext->audioStream->codec->sample_fmt,
static_cast<const unsigned char*>(inputBuffer),
(framesPerBuffer * sizeof(float) * recordingContext->audioFrame->channels),
0);
libffmpeg::AVPacket pkt;
libffmpeg::av_init_packet(&pkt);
pkt.data = NULL;
pkt.size = 0;
int gotpacket;
int result = avcodec_encode_audio2(recordingContext->audioStream->codec, &pkt, recordingContext->audioFrame, &gotpacket);
if (result < 0)
{
LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't encode the audio frame to acc");
return paContinue;
}
if (gotpacket)
{
pkt.stream_index = recordingContext->audioStream->index;
recordingContext->audioFrameframeNumber++;
// this codec requires no bitstream filter, just send it to the muxer!
result = libffmpeg::av_write_frame(recordingContext->formatContext, &pkt);
if (result < 0)
{
LOG(ERROR) << "Couldn't write the encoded audio frame";
libffmpeg::av_free_packet(&pkt);
return paContinue;
}
libffmpeg::av_free_packet(&pkt);
}
return paContinue;
}
static bool InitializeRecordingContext(RecordingContext* recordingContext)
{
int result = libffmpeg::avformat_alloc_output_context2(&recordingContext->formatContext, NULL, NULL, "C:\\Users\\Paul\\Desktop\\test.mp4");
if (result < 0)
{
LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't create output format context");
return false;
}
libffmpeg::AVCodec *audioCodec;
audioCodec = libffmpeg::avcodec_find_encoder(libffmpeg::AV_CODEC_ID_AAC);
if (audioCodec == NULL)
{
LOG(ERROR) << "Couldn't find the encoder for AAC";
}
recordingContext->audioStream = libffmpeg::avformat_new_stream(recordingContext->formatContext, audioCodec);
if (!recordingContext->audioStream)
{
LOG(ERROR) << "Couldn't create the audio stream";
return false;
}
recordingContext->audioStream->codec->bit_rate = 64000;
recordingContext->audioStream->codec->sample_fmt = libffmpeg::AV_SAMPLE_FMT_FLTP;
recordingContext->audioStream->codec->sample_rate = 48000;
recordingContext->audioStream->codec->channel_layout = AV_CH_LAYOUT_STEREO;
recordingContext->audioStream->codec->channels = libffmpeg::av_get_channel_layout_nb_channels(recordingContext->audioStream->codec->channel_layout);
recordingContext->audioStream->codecpar->bit_rate = recordingContext->audioStream->codec->bit_rate;
recordingContext->audioStream->codecpar->format = recordingContext->audioStream->codec->sample_fmt;
recordingContext->audioStream->codecpar->sample_rate = recordingContext->audioStream->codec->sample_rate;
recordingContext->audioStream->codecpar->channel_layout = recordingContext->audioStream->codec->channel_layout;
recordingContext->audioStream->codecpar->channels = recordingContext->audioStream->codec->channels;
result = libffmpeg::avcodec_open2(recordingContext->audioStream->codec, audioCodec, NULL);
if (result < 0)
{
LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't open the audio codec");
return false;
}
// create a new frame to store the audio samples
recordingContext->audioFrame = libffmpeg::av_frame_alloc();
if (!recordingContext->audioFrame)
{
LOG(ERROR) << "Couldn't alloce the output audio frame";
return false;
}
recordingContext->audioFrame->nb_samples = recordingContext->audioStream->codec->frame_size;
recordingContext->audioFrame->channel_layout = recordingContext->audioStream->codec->channel_layout;
recordingContext->audioFrame->channels = recordingContext->audioStream->codec->channels;
recordingContext->audioFrame->format = recordingContext->audioStream->codec->sample_fmt;
recordingContext->audioFrame->sample_rate = recordingContext->audioStream->codec->sample_rate;
result = libffmpeg::av_frame_get_buffer(recordingContext->audioFrame, 0);
if (result < 0)
{
LOG(ERROR) << "Coudln't initialize the output audio frame buffer";
return false;
}
// some formats want video_stream headers to be separate
if (!strcmp(recordingContext->formatContext->oformat->name, "mp4") || !strcmp(recordingContext->formatContext->oformat->name, "mov") || !strcmp(recordingContext->formatContext->oformat->name, "3gp"))
{
recordingContext->audioStream->codec->flags |= CODEC_FLAG_GLOBAL_HEADER;
}
// open the ouput file
if (!(recordingContext->formatContext->oformat->flags & AVFMT_NOFILE))
{
result = libffmpeg::avio_open(&recordingContext->formatContext->pb, recordingContext->formatContext->filename, AVIO_FLAG_WRITE);
if (result < 0)
{
LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't open the output file");
return false;
}
}
// write the stream headers
result = libffmpeg::avformat_write_header(recordingContext->formatContext, NULL);
if (result < 0)
{
LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't write the headers to the file");
return false;
}
return true;
}
static bool FinalizeRecordingContext(RecordingContext* recordingContext)
{
int result = 0;
// write the trailing information
if (recordingContext->formatContext->pb)
{
result = libffmpeg::av_write_trailer(recordingContext->formatContext);
if (result < 0)
{
LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't write the trailer information");
return false;
}
}
// close all the codes
for (int i = 0; i < (int)recordingContext->formatContext->nb_streams; i++)
{
result = libffmpeg::avcodec_close(recordingContext->formatContext->streams[i]->codec);
if (result < 0)
{
LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't close the codec");
return false;
}
}
// close the output file
if (recordingContext->formatContext->pb)
{
if (!(recordingContext->formatContext->oformat->flags & AVFMT_NOFILE))
{
result = libffmpeg::avio_close(recordingContext->formatContext->pb);
if (result < 0)
{
LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't close the output file");
return false;
}
}
}
// free the format context and all of its data
libffmpeg::avformat_free_context(recordingContext->formatContext);
recordingContext->formatContext = NULL;
recordingContext->audioStream = NULL;
if (recordingContext->audioFrame)
{
libffmpeg::av_frame_free(&recordingContext->audioFrame);
recordingContext->audioFrame = NULL;
}
return true;
}
int TestRecording::Test()
{
PaError result = paNoError;
result = Pa_Initialize();
if (result != paNoError) LOGINT_WITH_MESSAGE(ERROR, result, "Error initializing audio device framework");
RecordingContext recordingContext;
if (!InitializeRecordingContext(&recordingContext))
{
LOG(ERROR) << "Couldn't start recording file";
return 0;
}
auto defaultDevice = Pa_GetDefaultInputDevice();
auto deviceInfo = Pa_GetDeviceInfo(defaultDevice);
PaStreamParameters inputParameters;
inputParameters.device = defaultDevice;
inputParameters.channelCount = 2;
inputParameters.sampleFormat = paFloat32;
inputParameters.suggestedLatency = deviceInfo->defaultLowInputLatency;
inputParameters.hostApiSpecificStreamInfo = NULL;
PaStream* stream = NULL;
result = Pa_OpenStream(
&stream,
&inputParameters,
NULL,
48000,
1024,
paClipOff,
AudioRecordCallback,
&recordingContext);
if (result != paNoError)LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't open the audio stream");
result = Pa_StartStream(stream);
if (result != paNoError)LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't start the audio stream");
Sleep(1000 * 5);
result = Pa_StopStream(stream);
if (result != paNoError)LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't stop the audio stream");
if (!FinalizeRecordingContext(&recordingContext)) LOG(ERROR) << "Couldn't stop recording file";
result = Pa_CloseStream(stream);
if (result != paNoError)LOGINT_WITH_MESSAGE(ERROR, result, "Couldn't stop the audio stream");
return 0;
}
Here is the stdout, in case it helps.
https://gist.github.com/pauldotknopf/9f24a604ce1f8a081aa68da1bf169e98
Why is the audio lower in pitch? I assume I am overlooking a parameter that needs to be configured between PortAudio and FFMPEG. Is there something super obvious that I am missing?

How to understand the given ffplay C code snippet?

The following code snippet is from ffplay:
static int decoder_decode_frame(Decoder *d, AVFrame *frame, AVSubtitle *sub) {
int got_frame = 0;
do {
int ret = -1;
if (d->queue->abort_request)
return -1;
if (!d->packet_pending || d->queue->serial != d->pkt_serial) {
AVPacket pkt;
do {
if (d->queue->nb_packets == 0)
SDL_CondSignal(d->empty_queue_cond);
if (packet_queue_get(d->queue, &pkt, 1, &d->pkt_serial) < 0)
return -1;
if (pkt.data == flush_pkt.data) {
avcodec_flush_buffers(d->avctx);
d->finished = 0;
d->next_pts = d->start_pts;
d->next_pts_tb = d->start_pts_tb;
}
} while (pkt.data == flush_pkt.data || d->queue->serial != d->pkt_serial);
av_free_packet(&d->pkt);
d->pkt_temp = d->pkt = pkt;
d->packet_pending = 1;
}
switch (d->avctx->codec_type) {
case AVMEDIA_TYPE_VIDEO:
ret = avcodec_decode_video2(d->avctx, frame, &got_frame, &d->pkt_temp);
if (got_frame) {
if (decoder_reorder_pts == -1) {
frame->pts = av_frame_get_best_effort_timestamp(frame);
} else if (decoder_reorder_pts) {
frame->pts = frame->pkt_pts;
} else {
frame->pts = frame->pkt_dts;
}
}
break;
case AVMEDIA_TYPE_AUDIO:
ret = avcodec_decode_audio4(d->avctx, frame, &got_frame, &d->pkt_temp);
if (got_frame) {
AVRational tb = (AVRational){1, frame->sample_rate};
if (frame->pts != AV_NOPTS_VALUE)
frame->pts = av_rescale_q(frame->pts, d->avctx->time_base, tb);
else if (frame->pkt_pts != AV_NOPTS_VALUE)
frame->pts = av_rescale_q(frame->pkt_pts, av_codec_get_pkt_timebase(d->avctx), tb);
else if (d->next_pts != AV_NOPTS_VALUE)
frame->pts = av_rescale_q(d->next_pts, d->next_pts_tb, tb);
if (frame->pts != AV_NOPTS_VALUE) {
d->next_pts = frame->pts + frame->nb_samples;
d->next_pts_tb = tb;
}
}
break;
case AVMEDIA_TYPE_SUBTITLE:
ret = avcodec_decode_subtitle2(d->avctx, sub, &got_frame, &d->pkt_temp);
break;
}
if (ret < 0) {
d->packet_pending = 0;
} else {
d->pkt_temp.dts =
d->pkt_temp.pts = AV_NOPTS_VALUE;
if (d->pkt_temp.data) {
if (d->avctx->codec_type != AVMEDIA_TYPE_AUDIO)
ret = d->pkt_temp.size;
d->pkt_temp.data += ret;
d->pkt_temp.size -= ret;
if (d->pkt_temp.size <= 0)
d->packet_pending = 0;
} else {
if (!got_frame) {
d->packet_pending = 0;
d->finished = d->pkt_serial; // FLAG
}
}
}
} while (!got_frame && !d->finished);
return got_frame;
}
It's difficult for me to understand the following code:
d->finished = d->pkt_serial; // FLAG
Can anyone help me ?
Thanks.
See this commit.
Serial has two purposes nowadays: the initial purpose in the commit was to be able to distinguish packets in the packet queue from before and after a seek. The demuxer (input for packet queue) runs in a separate thread. After a seek, we want to flush it, but we don't want to stop the producer thread because overhead. However, we also don't want to flush too few or too many packets. So, the serial field tells us which packets are pre- and post-flush and thus which packets to drop without having to stop the producer thread while we're dropping those packets.
The second purpose is your line of code: it tells us when EOF occurs. Finished is set to the last serial number of a packet from the packet queue used to decode a frame. If that serial number is also the tail of the packet queue (and no more packets are produced), it means we stopped producing packets and decoded the frame belonging to that packet. In other words: end-of-file. Elsewhere, you'll find a test along those lines, and then either playback stops or (if looping is enabled) we seek back to the beginning of the file (i.e. invoke the looping behaviour).
(This write-up was helpfully assisted by several FFmpeg developers on IRC.)

FFMpeg - How to copy codec ( video and audio ) from 'mp4' container to 'ts' container

i have this ffmpeg command
ffmpeg -i c:\input.mp4 -vcodec copy -acodec copy -vbsf h264_mp4toannexb c:\output.ts.
The above command successfully converts input.mp4 to output.ts.
I need to implement the same functionality via code (using the ffmpeg library).
Does anybody know how to copy from one container to another without decoding and encoding?
If you are looking just for stream copy you can do this quite easily.
You can refer following steps.
//1. Do initialization using
av_register_all();
// 2. Open input file using
avformat_open_input( &m_informat, filename.c_str(), 0, 0));
//3. Find input stream info.
if ((ret = avformat_find_stream_info(m_informat, 0))< 0)
{
av_strerror(ret,errbuf,sizeof(errbuf));
PRINT_VAL("Not Able to find stream info:: ", errbuf)
ret = -1;
return ret;
}
for (unsigned int i = 0; i<m_informat->nb_streams; i++)
{
if(m_informat->streams[i]->codec->codec_type == AVMEDIA_TYPE_VIDEO)
{
PRINT_MSG("Found Video Stream ")
m_in_vid_strm_idx = i;
m_in_vid_strm = m_informat->streams[i];
}
if(m_informat->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO)
{
m_in_aud_strm_idx = i;
m_in_aud_strm = m_informat->streams[i];
}
// 4. Create ouputfile and allocate output format.
AVOutputFormat *outfmt = NULL;
std::string outfile = std::string(filename) + "clip_out.ts";
outfmt = av_guess_format(NULL,outfile.c_str(),NULL);
if(outfmt == NULL)
{
ret = -1;
return ret;
}
else
{
m_outformat = avformat_alloc_context();
if(m_outformat)
{
m_outformat->oformat = outfmt;
_snprintf(m_outformat->filename,
sizeof(m_outformat->filename), "%s", outfile.c_str());
}
else
{
ret = -1;
return ret;
}
}
//5. Add audio and video stream to output format.
AVCodec *out_vid_codec,*out_aud_codec;
out_vid_codec = out_aud_codec = NULL;
if(outfmt->video_codec != AV_CODEC_ID_NONE && m_in_vid_strm != NULL)
{
out_vid_codec = avcodec_find_encoder(outfmt->video_codec);
if(NULL == out_vid_codec)
{
PRINT_MSG("Could Not Find Vid Encoder")
ret = -1;
return ret;
}
else
{
PRINT_MSG("Found Out Vid Encoder ")
m_out_vid_strm = avformat_new_stream(m_outformat, out_vid_codec);
if(NULL == m_out_vid_strm)
{
PRINT_MSG("Failed to Allocate Output Vid Strm ")
ret = -1;
return ret;
}
else
{
PRINT_MSG("Allocated Video Stream ")
if(avcodec_copy_context(m_out_vid_strm->codec,
m_informat->streams[m_in_vid_strm_idx]->codec) != 0)
{
PRINT_MSG("Failed to Copy Context ")
ret = -1;
return ret;
}
else
{
m_out_vid_strm->sample_aspect_ratio.den =
m_out_vid_strm->codec->sample_aspect_ratio.den;
m_out_vid_strm->sample_aspect_ratio.num =
m_in_vid_strm->codec->sample_aspect_ratio.num;
PRINT_MSG("Copied Context ")
m_out_vid_strm->codec->codec_id = m_in_vid_strm->codec->codec_id;
m_out_vid_strm->codec->time_base.num = 1;
m_out_vid_strm->codec->time_base.den =
m_fps*(m_in_vid_strm->codec->ticks_per_frame);
m_out_vid_strm->time_base.num = 1;
m_out_vid_strm->time_base.den = 1000;
m_out_vid_strm->r_frame_rate.num = m_fps;
m_out_vid_strm->r_frame_rate.den = 1;
m_out_vid_strm->avg_frame_rate.den = 1;
m_out_vid_strm->avg_frame_rate.num = m_fps;
m_out_vid_strm->duration = (m_out_end_time - m_out_start_time)*1000;
}
}
}
}
if(outfmt->audio_codec != AV_CODEC_ID_NONE && m_in_aud_strm != NULL)
{
out_aud_codec = avcodec_find_encoder(outfmt->audio_codec);
if(NULL == out_aud_codec)
{
PRINT_MSG("Could Not Find Out Aud Encoder ")
ret = -1;
return ret;
}
else
{
PRINT_MSG("Found Out Aud Encoder ")
m_out_aud_strm = avformat_new_stream(m_outformat, out_aud_codec);
if(NULL == m_out_aud_strm)
{
PRINT_MSG("Failed to Allocate Out Vid Strm ")
ret = -1;
return ret;
}
else
{
if(avcodec_copy_context(m_out_aud_strm->codec,
m_informat->streams[m_in_aud_strm_idx]->codec) != 0)
{
PRINT_MSG("Failed to Copy Context ")
ret = -1;
return ret;
}
else
{
PRINT_MSG("Copied Context ")
m_out_aud_strm->codec->codec_id = m_in_aud_strm->codec->codec_id;
m_out_aud_strm->codec->codec_tag = 0;
m_out_aud_strm->pts = m_in_aud_strm->pts;
m_out_aud_strm->duration = m_in_aud_strm->duration;
m_out_aud_strm->time_base.num = m_in_aud_strm->time_base.num;
m_out_aud_strm->time_base.den = m_in_aud_strm->time_base.den;
}
}
}
}
// 6. Finally output header.
if (!(outfmt->flags & AVFMT_NOFILE))
{
if (avio_open2(&m_outformat->pb, outfile.c_str(), AVIO_FLAG_WRITE,NULL, NULL) < 0)
{
PRINT_VAL("Could Not Open File ", outfile)
ret = -1;
return ret;
}
}
/* Write the stream header, if any. */
if (avformat_write_header(m_outformat, NULL) < 0)
{
PRINT_VAL("Error Occurred While Writing Header ", outfile)
ret = -1;
return ret;
}
else
{
PRINT_MSG("Written Output header ")
m_init_done = true;
}
// 7. Now in while loop read frame using av_read_frame and write to output format using
// av_interleaved_write_frame(). You can use following loop
while(av_read_frame(m_informat, &pkt) >= 0 && (m_num_frames-- > 0))
{
if(pkt.stream_index == m_in_vid_strm_idx)
{
PRINT_VAL("ACTUAL VID Pkt PTS ",av_rescale_q(pkt.pts,m_in_vid_strm->time_base, m_in_vid_strm->codec->time_base))
PRINT_VAL("ACTUAL VID Pkt DTS ", av_rescale_q(pkt.dts, m_in_vid_strm->time_base, m_in_vid_strm->codec->time_base ))
av_init_packet(&outpkt);
if(pkt.pts != AV_NOPTS_VALUE)
{
if(last_vid_pts == vid_pts)
{
vid_pts++;
last_vid_pts = vid_pts;
}
outpkt.pts = vid_pts;
PRINT_VAL("ReScaled VID Pts ", outpkt.pts)
}
else
{
outpkt.pts = AV_NOPTS_VALUE;
}
if(pkt.dts == AV_NOPTS_VALUE)
{
outpkt.dts = AV_NOPTS_VALUE;
}
else
{
outpkt.dts = vid_pts;
PRINT_VAL("ReScaled VID Dts ", outpkt.dts)
PRINT_MSG("=======================================")
}
outpkt.data = pkt.data;
outpkt.size = pkt.size;
outpkt.stream_index = pkt.stream_index;
outpkt.flags |= AV_PKT_FLAG_KEY;
last_vid_pts = vid_pts;
if(av_interleaved_write_frame(m_outformat, &outpkt) < 0)
{
PRINT_MSG("Failed Video Write ")
}
else
{
m_out_vid_strm->codec->frame_number++;
}
av_free_packet(&outpkt);
av_free_packet(&pkt);
}
else if(pkt.stream_index == m_in_aud_strm_idx)
{
PRINT_VAL("ACTUAL AUD Pkt PTS ", av_rescale_q(pkt.pts, m_in_aud_strm->time_base, m_in_aud_strm->codec->time_base))
PRINT_VAL("ACTUAL AUD Pkt DTS ", av_rescale_q(pkt.dts, m_in_aud_strm->time_base, m_in_aud_strm->codec->time_base))
//num_aud_pkt++;
av_init_packet(&outpkt);
if(pkt.pts != AV_NOPTS_VALUE)
{
outpkt.pts = aud_pts;
PRINT_VAL("ReScaled AUD PTS ", outpkt.pts)
}
else
{
outpkt.pts = AV_NOPTS_VALUE;
}
if(pkt.dts == AV_NOPTS_VALUE)
{
outpkt.dts = AV_NOPTS_VALUE;
}
else
{
outpkt.dts = aud_pts;
PRINT_VAL("ReScaled AUD DTS ", outpkt.dts)
PRINT_MSG("====================================")
if( outpkt.pts >= outpkt.dts)
{
outpkt.dts = outpkt.pts;
}
if(outpkt.dts == aud_dts)
{
outpkt.dts++;
}
if(outpkt.pts < outpkt.dts)
{
outpkt.pts = outpkt.dts;
aud_pts = outpkt.pts;
}
}
outpkt.data = pkt.data;
outpkt.size = pkt.size;
outpkt.stream_index = pkt.stream_index;
outpkt.flags |= AV_PKT_FLAG_KEY;
vid_pts = aud_pts;
aud_pts++;
if(av_interleaved_write_frame(m_outformat, &outpkt) < 0)
{
PRINT_MSG("Faile Audio Write ")
}
else
{
m_out_aud_strm->codec->frame_number++;
}
av_free_packet(&outpkt);
av_free_packet(&pkt);
}
else
{
PRINT_MSG("Got Unknown Pkt ")
//num_unkwn_pkt++;
}
//num_total_pkt++;
}
//8. Finally write trailer and clean up everything
av_write_trailer(m_outformat);
av_free_packet(&outpkt);
av_free_packet(&pkt);

The .mp4 video does not play, which is created from ffmpeg library (not command line)

I use ffmpeg library to encode frames to a .mp4 video. The program runs smoothly without error. But the output .mp4 video does not play. Properties of the file does not even show it is a video file, no any information of video stream.
The related code is:
const char* ouVideoFileName = "output.mp4";
AVCodecID ouCodec_id = CODEC_ID_H264;
But if I change it to:
const char* ouVideoFileName = "output.avi";
AVCodecID ouCodec_id = CODEC_ID_H264;
The .avi video plays correctly.
What's wrong with .mp4 video?
You will need to share more of your code to find exact issue. Normally once you specify the container format in output file name, you will need to use av_guess_format to get the output format. After that you can use av_find_encoder for suggest codec_id
You will need to do something like this
AVFormatContext *m_outformat = NULL;
AVOutputFormat *outfmt = NULL;
std::string outfile = "clip_out.mp4";
outfmt = av_guess_format(NULL,outfile.c_str(),NULL);
if(outfmt == NULL)
{
ret = -1;
return ret;
}
else
{
m_outformat = avformat_alloc_context();
if(m_outformat)
{
m_outformat->oformat = outfmt;
_snprintf(m_outformat->filename, sizeof(m_outformat->filename), "%s", outfile.c_str());
}
else
{
ret = -1;
return ret;
}
}
AVCodec *out_vid_codec,*out_aud_codec;
out_vid_codec = out_aud_codec = NULL;
if(outfmt->video_codec != AV_CODEC_ID_NONE && m_in_vid_strm != NULL)
{
out_vid_codec = avcodec_find_encoder(outfmt->video_codec);
if(NULL == out_vid_codec)
{
PRINT_MSG("Could Not Find Vid Encoder")
ret = -1;
return ret;
}
else
{
PRINT_MSG("Found Out Vid Encoder ")
m_out_vid_strm = avformat_new_stream(m_outformat, out_vid_codec);
if(NULL == m_out_vid_strm)
{
PRINT_MSG("Failed to Allocate Output Vid Strm ")
ret = -1;
return ret;
}
else
{
PRINT_MSG("Allocated Video Stream ")
if(avcodec_copy_context(m_out_vid_strm->codec, m_informat->streams[m_in_vid_strm_idx]->codec) != 0)
{
PRINT_MSG("Failed to Copy Context ")
ret = -1;
return ret;
}
else
{
m_out_vid_strm->sample_aspect_ratio.den = m_out_vid_strm->codec->sample_aspect_ratio.den;
m_out_vid_strm->sample_aspect_ratio.num = m_in_vid_strm->codec->sample_aspect_ratio.num;
PRINT_MSG("Copied Context ")
m_out_vid_strm->codec->codec_id = m_in_vid_strm->codec->codec_id;
m_out_vid_strm->codec->time_base.num = 1;
m_out_vid_strm->codec->time_base.den = m_fps*(m_in_vid_strm->codec->ticks_per_frame);
m_out_vid_strm->time_base.num = 1;
m_out_vid_strm->time_base.den = 1000;
m_out_vid_strm->r_frame_rate.num = m_fps;
m_out_vid_strm->r_frame_rate.den = 1;
m_out_vid_strm->avg_frame_rate.den = 1;
m_out_vid_strm->avg_frame_rate.num = m_fps;
m_out_vid_strm->duration = (m_out_end_time - m_out_start_time)*1000;
}
}
}
}
if(outfmt->audio_codec != AV_CODEC_ID_NONE && m_in_aud_strm != NULL)
{
out_aud_codec = avcodec_find_encoder(outfmt->audio_codec);
if(NULL == out_aud_codec)
{
PRINT_MSG("Could Not Find Out Aud Encoder ")
ret = -1;
return ret;
}
else
{
PRINT_MSG("Found Out Aud Encoder ")
m_out_aud_strm = avformat_new_stream(m_outformat, out_aud_codec);
if(NULL == m_out_aud_strm)
{
PRINT_MSG("Failed to Allocate Out Vid Strm ")
ret = -1;
return ret;
}
else
{
if(avcodec_copy_context(m_out_aud_strm->codec, m_informat->streams[m_in_aud_strm_idx]->codec) != 0)
{
PRINT_MSG("Failed to Copy Context ")
ret = -1;
return ret;
}
else
{
PRINT_MSG("Copied Context ")
m_out_aud_strm->codec->codec_id = m_in_aud_strm->codec->codec_id;
m_out_aud_strm->codec->codec_tag = 0;
m_out_aud_strm->pts = m_in_aud_strm->pts;
m_out_aud_strm->duration = m_in_aud_strm->duration;
m_out_aud_strm->time_base.num = m_in_aud_strm->time_base.num;
m_out_aud_strm->time_base.den = m_in_aud_strm->time_base.den;
}
}
}
}
if (!(outfmt->flags & AVFMT_NOFILE))
{
if (avio_open2(&m_outformat->pb, outfile.c_str(), AVIO_FLAG_WRITE,NULL, NULL) < 0)
{
PRINT_VAL("Could Not Open File ", outfile)
ret = -1;
return ret;
}
}
/* Write the stream header, if any. */
if (avformat_write_header(m_outformat, NULL) < 0)
{
PRINT_VAL("Error Occurred While Writing Header ", outfile)
ret = -1;
return ret;
}
else
{
PRINT_MSG("Written Output header ")
m_init_done = true;
}
Now you can start the encoding of frames
I previously followed the example of decoding_encoding.c in FFmpeg documentation.
Later on, I followed the example of muxing.c, now it works!

Resources