Context
Hello !
I'm currently working on the development of a small library allowing to cut an h.264 video on any frame, but without re-encoding (transcoding) the whole video. The idea is to re-encode only the GOP on which we want to cut, and to rewrite (remux) directly the others GOP.
The avcut project (https://github.com/anyc/avcut) allows to do that, but requires a systematic decoding of each package, and seems to not work with the recent versions of ffmpeg from the tests I could do and from the recent feedbacks in the github issues.
As a beginner, I started from the code examples provided in the ffmpeg documentation, in particular: transcoding.c and remuxing.c.
Problem encountered
The problem I'm having is that I can't get both transcoding and remuxing to work properly at the same time. In particular, depending on the method I use to initialize the AVCodecParameters of the output video stream, transcoding works, or remuxing works:
avcodec_parameters_copyworks well for remuxingavcodec_parameters_from_contextworks well for transcoding
In case I choose avcodec_parameters_from_context, the transcoded GOP are correctly read by my video player (parole), but the remuxed packets are not read, and ffprobe does not show/detect them.
In case I choose avcodec_parameters_from_context, the remuxing GOP are correctly read by my video player, but the transcoding key_frame are bugged (I have the impression that the b-frame and p-frame are ok), and ffprobe -i return an error about the NAL of the key-frames:
[h264 @ 0x55ec8a079300] sps_id 32 out of range
[h264 @ 0x55ec8a079300] Invalid NAL unit size (1677727148 > 735).
[h264 @ 0x55ec8a079300] missing picture in access unit with size 744
I suspect that the problem is related to the extradata of the packets. Through some experiments on the different attributes of the output AVCodecParameters, it seems that it is the extradata and extradata_size attributes that are responsible for the functioning of one method or the other.
Version
ffmpeg development branch retrieved on 2022-05-17 from https://github.com/FFmpeg/FFmpeg.
Compiled with --enable-libx264 --enable-gpl --enable-decoder=png --enable-encoder=png
Code
My code is written in c++ and is based on two classes: a class defining the parameters and methods on the input file (InputContexts) and a class defining them for the output file (OutputContexts). The code of these two classes is defined in the following files:
The code normally involved in the problem is the following:
- stream initialization
int OutputContexts::init(const char* out_filename, InputContexts* input_contexts){
int ret;
int stream_index = 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;
return ret;
}
av_dump_format(ofmt_ctx, 0, out_filename, 1);
encoders.resize(input_contexts->ifmt_ctx->nb_streams, nullptr);
codecs.resize(input_contexts->ifmt_ctx->nb_streams, nullptr);
// stream mapping
for (int i = 0; i < input_contexts->ifmt_ctx->nb_streams; i++) {
AVStream *out_stream;
AVStream *in_stream = input_contexts->ifmt_ctx->streams[i];
AVCodecContext* decoder_ctx = input_contexts->decoders[i];
// add new stream to output context
out_stream = avformat_new_stream(ofmt_ctx, NULL);
if (!out_stream) {
fprintf(stderr, "Failed allocating output stream\n");
ret = AVERROR_UNKNOWN;
return ret;
}
// from avcut blog
av_dict_copy(&out_stream->metadata, in_stream->metadata, 0);
out_stream->time_base = in_stream->time_base;
// encoder
if (decoder_ctx->codec_type == AVMEDIA_TYPE_VIDEO){
ret = prepare_encoder_video(i, input_contexts);
if (ret < 0){
fprintf(stderr, "Error while preparing encoder for stream #%u\n", i);
return ret;
}
// from avcut
out_stream->sample_aspect_ratio = in_stream->sample_aspect_ratio;
// works well for remuxing
ret = avcodec_parameters_copy(out_stream->codecpar, in_stream->codecpar);
if (ret < 0) {
fprintf(stderr, "Failed to copy codec parameters\n");
return ret;
}
// works well for transcoding
// ret = avcodec_parameters_from_context(out_stream->codecpar, encoders[i]);
// if (ret < 0) {
// av_log(NULL, AV_LOG_ERROR, "Failed to copy encoder parameters to output stream #%u\n", i);
// return ret;
// }
} else if (decoder_ctx->codec_type == AVMEDIA_TYPE_AUDIO) {
...
} else {
...
}
// TODO useful ???
// set current stream position to 0
// out_stream->codecpar->codec_tag = 0;
}
// opening output file in write mode with the ouput context
if (!(ofmt_ctx->oformat->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);
return ret;
}
}
// write headers from output context in output file
ret = avformat_write_header(ofmt_ctx, NULL);
if (ret < 0) {
fprintf(stderr, "Error occurred when opening output file\n");
return ret;
}
return ret;
}
- AVCodecContext initialization for encoder
int OutputContexts::prepare_encoder_video(int stream_index, InputContexts* input_contexts){
int ret;
const AVCodec* encoder;
AVCodecContext* decoder_ctx = input_contexts->decoders[stream_index];
AVCodecContext* encoder_ctx;
if (video_index >= 0){
fprintf(stderr, "Impossible to mark stream #%u as video, stream #%u is already registered as video stream.\n",
stream_index, video_index);
return -1; //TODO change this value for correct error code
}
video_index = stream_index;
if(decoder_ctx->codec_id == AV_CODEC_ID_H264){
encoder = avcodec_find_encoder_by_name("libx264");
if (!encoder) {
av_log(NULL, AV_LOG_FATAL, "Encoder libx264 not found\n");
return AVERROR_INVALIDDATA;
}
fmt::print("Encoder libx264 will be used for stream {}.\n", stream_index);
} else {
std::string s = fmt::format("No video encoder found for the given codec_id: {}\n", avcodec_get_name(decoder_ctx->codec_id));
av_log(NULL, AV_LOG_FATAL, s.c_str());
return AVERROR_INVALIDDATA;
}
encoder_ctx = avcodec_alloc_context3(encoder);
if (!encoder_ctx) {
av_log(NULL, AV_LOG_FATAL, "Failed to allocate the encoder context\n");
return AVERROR(ENOMEM);
}
// from avcut
encoder_ctx->time_base = decoder_ctx->time_base;
encoder_ctx->ticks_per_frame = decoder_ctx->ticks_per_frame;
encoder_ctx->delay = decoder_ctx->delay;
encoder_ctx->width = decoder_ctx->width;
encoder_ctx->height = decoder_ctx->height;
encoder_ctx->pix_fmt = decoder_ctx->pix_fmt;
encoder_ctx->sample_aspect_ratio = decoder_ctx->sample_aspect_ratio;
encoder_ctx->color_primaries = decoder_ctx->color_primaries;
encoder_ctx->color_trc = decoder_ctx->color_trc;
encoder_ctx->colorspace = decoder_ctx->colorspace;
encoder_ctx->color_range = decoder_ctx->color_range;
encoder_ctx->chroma_sample_location = decoder_ctx->chroma_sample_location;
encoder_ctx->profile = decoder_ctx->profile;
encoder_ctx->level = decoder_ctx->level;
encoder_ctx->thread_count = 1; // spawning more threads causes avcodec_close to free threads multiple times
encoder_ctx->codec_tag = 0;
// correct values ???
encoder_ctx->qmin = 16;
encoder_ctx->qmax = 26;
encoder_ctx->max_qdiff = 4;
// end from avcut
// according to avcut, should not be set
// if (ofmt_ctx->oformat->flags & AVFMT_GLOBALHEADER){
// encoder_ctx->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;
// }
ret = avcodec_open2(encoder_ctx, encoder, NULL);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open video encoder for stream #%u\n", stream_index);
return ret;
}
codecs[stream_index] = encoder;
encoders[stream_index] = encoder_ctx;
return ret;
}
Example
To illustrate my problem, I provide here a test code using the two classes that alternates between transcoding and remuxing at each key-frame encountered in the file using my classes.
To compile the code:
g++ -o trans_remux trans_remux.cpp contexts.cpp -D__STDC_CONSTANT_MACROS `pkg-config --libs libavfilter` -lfmt -g
Currently the code is using avcodec_parameters_copy (contexts.cpp:333), so it works well for remuxing. If you want to test the version with avcodec_parameters_from_context, pls comment from line 333 to 337 in contexts.cpp and uncomment from line 340 to 344 and recompile.