Libav (ffmpeg) copying decoded video timestamps to encoder

I am writing an application that decodes a single video stream from an input file (any codec, any container), does a bunch of image processing, and encodes the results to an output file (single video stream, Quicktime RLE, MOV). I am using ffmpeg's libav 3.1.5 (Windows build for now, but the application will be cross-platform).

There is a 1:1 correspondence between input and output frames and I want the frame timing in the output to be identical to the input. I am having a really, really hard time accomplishing this. So my general question is: How do I reliably (as in, in all cases of inputs) set the output frame timing identical to the input?

It took me a very long time to slog through the API and get to the point I am at now. I put together a minimal test program to work with:

#include <cstdio>

extern "C" {
#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libavutil/avutil.h>
#include <libavutil/imgutils.h>
#include <libswscale/swscale.h>
}

using namespace std;


struct DecoderStuff {
    AVFormatContext *formatx;
    int nstream;
    AVCodec *codec;
    AVStream *stream;
    AVCodecContext *codecx;
    AVFrame *rawframe;
    AVFrame *rgbframe;
    SwsContext *swsx;
};


struct EncoderStuff {
    AVFormatContext *formatx;
    AVCodec *codec;
    AVStream *stream;
    AVCodecContext *codecx;
};


template <typename T>
static void dump_timebase (const char *what, const T *o) {
    if (o)
        printf("%s timebase: %d/%dn", what, o->time_base.num, o->time_base.den);
    else
        printf("%s timebase: null objectn", what);
}


// reads next frame into d.rawframe and d.rgbframe. returns false on error/eof.
static bool read_frame (DecoderStuff &d) {

    AVPacket packet;
    int err = 0, haveframe = 0;

    // read
    while (!haveframe && err >= 0 && ((err = av_read_frame(d.formatx, &packet)) >= 0)) {
       if (packet.stream_index == d.nstream) {
           err = avcodec_decode_video2(d.codecx, d.rawframe, &haveframe, &packet);
       }
       av_packet_unref(&packet);
    }

    // error output
    if (!haveframe && err != AVERROR_EOF) {
        char buf[500];
        av_strerror(err, buf, sizeof(buf) - 1);
        buf[499] = 0;
        printf("read_frame: %sn", buf);
    }

    // convert to rgb
    if (haveframe) {
        sws_scale(d.swsx, d.rawframe->data, d.rawframe->linesize, 0, d.rawframe->height,
                  d.rgbframe->data, d.rgbframe->linesize);
    }

    return haveframe;

}


// writes an output frame, returns false on error.
static bool write_frame (EncoderStuff &e, AVFrame *inframe) {

    // see note in so post about outframe here
    AVFrame *outframe = av_frame_alloc();
    outframe->format = inframe->format;
    outframe->width = inframe->width;
    outframe->height = inframe->height;
    av_image_alloc(outframe->data, outframe->linesize, outframe->width, outframe->height,
                   AV_PIX_FMT_RGB24, 1);
    //av_frame_copy(outframe, inframe);
    static int count = 0;
    for (int n = 0; n < outframe->width * outframe->height; ++ n) {
        outframe->data[0][n*3+0] = ((n+count) % 100) ? 0 : 255;
        outframe->data[0][n*3+1] = ((n+count) % 100) ? 0 : 255;
        outframe->data[0][n*3+2] = ((n+count) % 100) ? 0 : 255;
    }
    ++ count;

    AVPacket packet;
    av_init_packet(&packet);
    packet.size = 0;
    packet.data = NULL;

    int err, havepacket = 0;
    if ((err = avcodec_encode_video2(e.codecx, &packet, outframe, &havepacket)) >= 0 && havepacket) {
        packet.stream_index = e.stream->index;
        err = av_interleaved_write_frame(e.formatx, &packet);
    }

    if (err < 0) {
        char buf[500];
        av_strerror(err, buf, sizeof(buf) - 1);
        buf[499] = 0;
        printf("write_frame: %sn", buf);
    }

    av_packet_unref(&packet);
    av_freep(&outframe->data[0]);
    av_frame_free(&outframe);

    return err >= 0;

}


int main (int argc, char *argv[]) {

    const char *infile = "wildlife.wmv";
    const char *outfile = "test.mov";
    DecoderStuff d = {};
    EncoderStuff e = {};

    av_register_all();

    // decoder
    avformat_open_input(&d.formatx, infile, NULL, NULL);
    avformat_find_stream_info(d.formatx, NULL);
    d.nstream = av_find_best_stream(d.formatx, AVMEDIA_TYPE_VIDEO, -1, -1, &d.codec, 0);
    d.stream = d.formatx->streams[d.nstream];
    d.codecx = avcodec_alloc_context3(d.codec);
    avcodec_parameters_to_context(d.codecx, d.stream->codecpar);
    avcodec_open2(d.codecx, NULL, NULL);
    d.rawframe = av_frame_alloc();
    d.rgbframe = av_frame_alloc();
    d.rgbframe->format = AV_PIX_FMT_RGB24;
    d.rgbframe->width = d.codecx->width;
    d.rgbframe->height = d.codecx->height;
    av_frame_get_buffer(d.rgbframe, 1);
    d.swsx = sws_getContext(d.codecx->width, d.codecx->height, d.codecx->pix_fmt,
                            d.codecx->width, d.codecx->height, AV_PIX_FMT_RGB24,
                            SWS_POINT, NULL, NULL, NULL);
    //av_dump_format(d.formatx, 0, infile, 0);
    dump_timebase("in stream", d.stream);
    dump_timebase("in stream:codec", d.stream->codec); // note: deprecated
    dump_timebase("in codec", d.codecx);

    // encoder
    avformat_alloc_output_context2(&e.formatx, NULL, NULL, outfile);
    e.codec = avcodec_find_encoder(AV_CODEC_ID_QTRLE);
    e.stream = avformat_new_stream(e.formatx, e.codec);
    e.codecx = avcodec_alloc_context3(e.codec);
    e.codecx->bit_rate = 4000000; // arbitrary for qtrle
    e.codecx->width = d.codecx->width;
    e.codecx->height = d.codecx->height;
    e.codecx->gop_size = 30; // 99% sure this is arbitrary for qtrle
    e.codecx->pix_fmt = AV_PIX_FMT_RGB24;
    e.codecx->time_base = d.stream->time_base; // ???
    e.codecx->flags |= (e.formatx->flags & AVFMT_GLOBALHEADER) ? AV_CODEC_FLAG_GLOBAL_HEADER : 0;
    avcodec_open2(e.codecx, NULL, NULL);
    avcodec_parameters_from_context(e.stream->codecpar, e.codecx); 
    //av_dump_format(e.formatx, 0, outfile, 1);
    dump_timebase("out stream", e.stream);
    dump_timebase("out stream:codec", e.stream->codec); // note: deprecated
    dump_timebase("out codec", e.codecx);

    // open file and write header
    avio_open(&e.formatx->pb, outfile, AVIO_FLAG_WRITE); 
    avformat_write_header(e.formatx, NULL);

    // frames
    while (read_frame(d) && write_frame(e, d.rgbframe))
        ;

    // write trailer and close file
    av_write_trailer(e.formatx);
    avio_closep(&e.formatx->pb); 

}

A few notes about that:

Now, as for my current attempts. The following timing related fields are present in the above code, with details/confusion in bold. There's a lot of them, because the API is mind-bogglingly convoluted:

I have tried the following, with the described results. Note that inframe is d.rgbframe :

I tried various other hand-wavey permutations of the above and nothing worked. What I want to do is create an output file that plays back with the same timing and frame rate as the input (29.97 constant frame rate in this case).

So how do I do this? Of the zillions of timing related fields here, what do I do to make the output be the same as the input? And how do I do it in such a way that handles arbitrary video input formats that may store their time stamps and time bases in different places? I need this to always work.

For reference, here is a table of all the packet and frame timestamps read from the video stream of my test input file, to give a sense of what my test file looks like. None of the input packet pts' are set, same with frame pts, and for some reason the duration of the first 108 frames is 0. VLC plays the file fine and reports the frame rate as 29.9700089:

I think your issue here is with time bases which are at first a bit confusing.

So you need to do following:

Now for each frame:

This might be an overkill, in particular maybe encoders doesn't change their timebase on open (in which case you don't need to convert raw frames' pts ).

Regarding flushing - frames you pass to encoder are not necessarily encoded and output right away, so yes you are supposed to call avcodec_encode_video2 with NULL as a frame to let the encoder know you are done and make it output all the remaining data (which you need to pass through muxer as with all the other packets). In fact, you are supposed to do so repeatedly until it stops spewing out packets. See one of encoding examples in doc/examples folder inside ffmpeg for some samples.

So, thanks 100% to Andrey Turkin's amazingly clear and helpful answer, I've got this working properly, I'd like to share the exact things I did:

During initialization, with the understanding that any of these initial time bases may be changed by libav at some point:

d.codecx->time_base = { 1, 10000 };

e.stream->time_base = d.stream->time_base;

e.codecx->time_base = d.codecx->time_base;

One of the things I was missing is that I can set these timestamps, and libav will obey. There are no constraints, it's up to me, and no matter what I set the decoded timestamps will be in the time base that I choose. I didn't realize this.

Then while decoding:

d.rawframe->pts = av_frame_get_best_effort_timestamp(d.rawframe);

d.rgbframe->pts = d.rawframe->pts;

Then, encoding:

outframe->pts = inframe->pts;

av_packet_rescale_ts(&packet, d.stream->time_base, e.stream->time_base);

And it works like a charm, mostly: I noticed is VLC reports the input as 29.97 FPS but the output at 30.03 FPS, which I can't quite figure out. But, everything seems to play fine in all media players I've tested with.

上一篇: 为什么我的数据绑定看到的是真实值而不是强制值？

下一篇: Libav（ffmpeg）将解码的视频时间戳复制到编码器