Recherche avancée
Autres articles (100)
-
MediaSPIP 0.1 Beta version
25 avril 2011, parMediaSPIP 0.1 beta is the first version of MediaSPIP proclaimed as "usable".
The zip file provided here only contains the sources of MediaSPIP in its standalone version.
To get a working installation, you must manually install all-software dependencies on the server.
If you want to use this archive for an installation in "farm mode", you will also need to proceed to other manual (...) -
MediaSPIP v0.2
21 juin 2013, parMediaSPIP 0.2 est la première version de MediaSPIP stable.
Sa date de sortie officielle est le 21 juin 2013 et est annoncée ici.
Le fichier zip ici présent contient uniquement les sources de MediaSPIP en version standalone.
Comme pour la version précédente, il est nécessaire d’installer manuellement l’ensemble des dépendances logicielles sur le serveur.
Si vous souhaitez utiliser cette archive pour une installation en mode ferme, il vous faudra également procéder à d’autres modifications (...) -
MediaSPIP version 0.1 Beta
16 avril 2011, parMediaSPIP 0.1 beta est la première version de MediaSPIP décrétée comme "utilisable".
Le fichier zip ici présent contient uniquement les sources de MediaSPIP en version standalone.
Pour avoir une installation fonctionnelle, il est nécessaire d’installer manuellement l’ensemble des dépendances logicielles sur le serveur.
Si vous souhaitez utiliser cette archive pour une installation en mode ferme, il vous faudra également procéder à d’autres modifications (...)
Sur d’autres sites (11507)
-
Libav (ffmpeg) copying decoded video timestamps to encoder
31 octobre 2016, par Jason CI 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></libavcodec>avcodec.h>
#include <libavformat></libavformat>avformat.h>
#include <libavutil></libavutil>avutil.h>
#include <libavutil></libavutil>imgutils.h>
#include <libswscale></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="t">
static void dump_timebase (const char *what, const T *o) {
if (o)
printf("%s timebase: %d/%d\n", what, o->time_base.num, o->time_base.den);
else
printf("%s timebase: null object\n", 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: %s\n", 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: %s\n", 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);
}
</typename></cstdio>A few notes about that :
- Since all of my attempts at frame timing so far have failed, I’ve removed almost all timing-related stuff from this code to start with a clean slate.
- Almost all error checking and cleanup omitted for brevity.
- The reason I allocate a new output frame with a new buffer in
write_frame, rather than usinginframedirectly, is because this is more representative of what my real application is doing. My real app also uses RGB24 internally, hence the conversions here. - The reason I generate a weird pattern in
outframe, rather than using e.g.av_copy_frame, is because I just wanted a test pattern that compressed well with Quicktime RLE (my test input ends up generating a 1.7GB output file otherwise). - The input video I am using, "wildlife.wmv", can be found here. I’ve hard-coded the filenames.
- I am aware that
avcodec_decode_video2andavcodec_encode_video2are deprecated, but don’t care. They work fine, I’ve already struggled too much getting my head around the latest version of the API, ffmpeg changes their API with nearly every release, and I really don’t feel like dealing withavcodec_send_*andavcodec_receive_*right now. - I think I’m supposed to be finishing off by passing a NULL frame to
avcodec_encode_video2to flush some buffers or something but I’m a bit confused about that. Unless somebody feels like explaining that let’s ignore it for now, it’s a separate question. The docs are as vague about this point as they are about everything else. - My test input file’s frame rate is 29.97.
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 :
main: d.stream->time_base: Input video stream time base. For my test input file this is 1/1000.main: d.stream->codec->time_base: Not sure what this is (I never could make sense of whyAVStreamhas anAVCodecContextfield when you always use your own new context anyways) and also thecodecfield is deprecated. For my test input file this is 1/1000.main: d.codecx->time_base: Input codec context time-base. For my test input file this is 0/1. Am I supposed to set it ?main: e.stream->time_base: Time base of the output stream I create. What do I set this to ?main: e.stream->codec->time_base: Time base of the deprecated and mysterious codec field of the output stream I create. Do I set this to anything ?main: e.codecx->time_base: Time base of the encoder context I create. What do I set this to ?read_frame: packet.dts: Decoding timestamp of packet read.read_frame: packet.pts: Presentation timestamp of packet read.read_frame: packet.duration: Duration of packet read.read_frame: d.rawframe->pts: Presentation timestamp of raw frame decoded. This is always 0. Why isn’t it read by the decoder...?read_frame: d.rgbframe->pts/write_frame: inframe->pts: Presentation timestamp of decoded frame converted to RGB. Not set to anything currently.read_frame: d.rawframe->pkt_*: Fields copied from packet, discovered after reading this post. They are set correctly but I don’t know if they are useful.write_frame: outframe->pts: Presentation timestamp of frame being encoded. Should I set this to something ?write_frame: outframe->pkt_*: Timing fields from a packet. Should I set these ? They seem to be ignored by the encoder.write_frame: packet.dts: Decoding timestamp of packet being encoded. What do I set it to ?write_frame: packet.pts: Presentation timestamp of packet being encoded. What do I set it to ?write_frame: packet.duration: Duration of packet being encoded. What do I set it to ?
I have tried the following, with the described results. Note that
inframeisd.rgbframe:-
- Init
e.stream->time_base = d.stream->time_base - Init
e.codecx->time_base = d.codecx->time_base - Set
d.rgbframe->pts = packet.dtsinread_frame - Set
outframe->pts = inframe->ptsinwrite_frame - Result : Warning that encoder time base is not set (since
d.codecx->time_base was 0/1), seg fault.
- Init
-
- Init
e.stream->time_base = d.stream->time_base - Init
e.codecx->time_base = d.stream->time_base - Set
d.rgbframe->pts = packet.dtsinread_frame - Set
outframe->pts = inframe->ptsinwrite_frame - Result : No warnings, but VLC reports frame rate as 480.048 (no idea where this number came from) and file plays too fast.
Also the encoder sets all the timing fields in(Edit : Turns out this is becausepacketto 0, which was not what I expected.av_interleaved_write_frame, unlikeav_write_frame, takes ownership of the packet and swaps it with a blank one, and I was printing the values after that call. So they are not ignored.)
- Init
-
- Init
e.stream->time_base = d.stream->time_base - Init
e.codecx->time_base = d.stream->time_base - Set
d.rgbframe->pts = packet.dtsinread_frame - Set any of pts/dts/duration in
packetinwrite_frameto anything. - Result : Warnings about packet timestamps not set. Encoder seems to reset all packet timing fields to 0, so none of this has any effect.
- Init
-
- Init
e.stream->time_base = d.stream->time_base - Init
e.codecx->time_base = d.stream->time_base - I found these fields,
pkt_pts,pkt_dts, andpkt_durationinAVFrameafter reading this post, so I tried copying those all the way through tooutframe. - Result : Really had my hopes up, but ended up with same results as attempt 3 (packet timestamp not set warning, incorrect results).
- Init
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 :
- Table is here since it was too large for this post.
-
FFmpeg filtergraph memory leak
5 juillet 2017, par Leif AndersenI have an FFmpeg program that :
- Demuxes and decodes a video file.
- Passes it through a filtergraph
- encodes and muxes the new video.
The filtergraph itself is rather complex, and can be run directly from the command line as such :
ffmpeg -i demo.mp4 -filter_complex \
"[audio3]atrim=end=30:start=10[audio2];\
[video5]trim=end=30:start=10[video4];[audio2]anull[audio6];\
[video4]scale=width=1920:height=1080[video7];[audio6]anull[audio8];\
[video7]fps=fps=30[video9];[audio8]anull[audio10];\
[video9]format=pix_fmts=yuv420p[video11];\
[audio10]asetpts=expr=PTS-STARTPTS[audio12];\
[video11]setpts=expr=PTS-STARTPTS[video13];\
[audio15]concat=v=0:a=1:n=1[audio14];\
[video17]concat=v=1:a=0:n=1[video16];\
[audio12]afifo[audio15];[video13]fifo[video17];\
[audio14]afifo[audio18];[video16]fifo[video19];\
[audio18]anull[audio20];\
[video19]pad=width=1920:height=1080[video21];\
[audio20]anull[audio22];[video21]fps=fps=25[video23];\
[audio22]aformat=sample_fmts=fltp:sample_rates=44100:channel_layouts=stereo[fa];\
[video23]format=pix_fmts=yuv420p[fv];[0:a]afifo[audio3];\
[0:v]fifo[video5]" \
-map "[fv]" -map "[fa]" out.mp4I realize this is a massive filtergraph with a lot of no-op filters, it was autogenerated rather than being hand written. Here is a more cleaner version of the graph. (Its a graphviz file, you can run it in the command line or here.)
Anyway, when I run the program that uses this filtergraph my memory usage spikes. I end up using about 7 GB of RAM for a 30 second clip. However, when I run the program using the ffmpeg command above, it peaks out at about 600 MB of RAM. This causes me to believe that the problem is not the ungodly size of the filtergraph, but a problem with how my program is using it.
The program sets up the filtergraph (using
av_filter_parse_ptr, giving the filtergraph string shown above), encoder, muxer, decoder, and demuxer, then spawns two threads, one that sends frames into the filtergraph, and one that receives them. The frame that sends them looks something like :void decode () {
while(... more_frames ...) {
AVFrame *frame = av_frame_alloc();
... fill next frame of stream ...
av_buffersrc_write_frame(ctx, frame);
av_frame_free(&frame);
}
}(I have elided the
av_send_packet/av_receive_framefunctions as they don’t seem to be leaking memory. I have also elided the process of flushing the buffersrc as that won’t happen until the end, and the memory spikes long before that.)And the encoder thread looks similar :
void encode() {
while(... nodes_in_graph ...) {
AVFrame *frame = av_frame_alloc();
av_buffersink_get_frame(ctx, frame);
... ensure frame actually was filled ...
... send frame to encoder ...
av_frame_free(&frame);
}
}As with the decoder, I have elided the
send_frame/receive_packetcombo as they don’t seem to be leaking memory. Additionally I have elided the details of ensuring that the frame actually was filled. The code loops until the frame eventually does get filled.Every frame I allocate I fairly quickly deallocate. I additionally handled all of the error cases that the ffmpeg can give (Elided in the example).
I have also tried having only one frame for the encoder and one for the decoder (and calling
av_frame_unrefin each iteration of the loop).Am I forgetting to free something, or am I just using the calls to libavfilter incorrectly such that it has to buffer all of the data ? I don’t think the leak is caused by the memory graph because running it from the command line doesn’t seem to cause the same memory explosion.
FWIW, the actual code is here, although its written in Racket. I do have a minimal example that also seems to duplicate this behavior (modified from the
doc/example/filtering_video.cfile from the ffmpeg code :#include
#include <libavcodec></libavcodec>avcodec.h>
#include <libavformat></libavformat>avformat.h>
#include <libavfilter></libavfilter>avfiltergraph.h>
#include <libavfilter></libavfilter>buffersink.h>
#include <libavfilter></libavfilter>buffersrc.h>
#include <libavutil></libavutil>opt.h>
const char *filter_descr = "trim=start=10:end=30,scale=78:24,transpose=cclock";
static AVFormatContext *fmt_ctx;
static AVCodecContext *dec_ctx;
AVFilterContext *buffersink_ctx;
AVFilterContext *buffersrc_ctx;
AVFilterGraph *filter_graph;
static int video_stream_index = -1;
static int64_t last_pts = AV_NOPTS_VALUE;
static int open_input_file(const char *filename)
{
int ret;
AVCodec *dec;
if ((ret = avformat_open_input(&fmt_ctx, filename, NULL, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open input file\n");
return ret;
}
if ((ret = avformat_find_stream_info(fmt_ctx, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot find stream information\n");
return ret;
}
/* select the video stream */
ret = av_find_best_stream(fmt_ctx, AVMEDIA_TYPE_VIDEO, -1, -1, &dec, 0);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot find a video stream in the input file\n");
return ret;
}
video_stream_index = ret;
/* create decoding context */
dec_ctx = avcodec_alloc_context3(dec);
if (!dec_ctx)
return AVERROR(ENOMEM);
avcodec_parameters_to_context(dec_ctx, fmt_ctx->streams[video_stream_index]->codecpar);
av_opt_set_int(dec_ctx, "refcounted_frames", 1, 0);
/* init the video decoder */
if ((ret = avcodec_open2(dec_ctx, dec, NULL)) < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot open video decoder\n");
return ret;
}
return 0;
}
static int init_filters(const char *filters_descr)
{
char args[512];
int ret = 0;
AVFilter *buffersrc = avfilter_get_by_name("buffer");
AVFilter *buffersink = avfilter_get_by_name("buffersink");
AVFilterInOut *outputs = avfilter_inout_alloc();
AVFilterInOut *inputs = avfilter_inout_alloc();
AVRational time_base = fmt_ctx->streams[video_stream_index]->time_base;
enum AVPixelFormat pix_fmts[] = { AV_PIX_FMT_GRAY8, AV_PIX_FMT_NONE };
filter_graph = avfilter_graph_alloc();
if (!outputs || !inputs || !filter_graph) {
ret = AVERROR(ENOMEM);
goto end;
}
/* buffer video source: the decoded frames from the decoder will be inserted here. */
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,
time_base.num, 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;
}
/* buffer video sink: to terminate the filter chain. */
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_int_list(buffersink_ctx, "pix_fmts", pix_fmts,
AV_PIX_FMT_NONE, AV_OPT_SEARCH_CHILDREN);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Cannot set output pixel format\n");
goto end;
}
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 ((ret = avfilter_graph_parse_ptr(filter_graph, filters_descr,
&inputs, &outputs, NULL)) < 0)
goto end;
if ((ret = avfilter_graph_config(filter_graph, NULL)) < 0)
goto end;
end:
avfilter_inout_free(&inputs);
avfilter_inout_free(&outputs);
return ret;
}
int main(int argc, char **argv)
{
int ret;
AVPacket packet;
AVFrame *frame = av_frame_alloc();
AVFrame *filt_frame = av_frame_alloc();
if (!frame || !filt_frame) {
perror("Could not allocate frame");
exit(1);
}
if (argc != 2) {
fprintf(stderr, "Usage: %s file\n", argv[0]);
exit(1);
}
av_register_all();
avfilter_register_all();
if ((ret = open_input_file(argv[1])) < 0)
goto end;
if ((ret = init_filters(filter_descr)) < 0)
goto end;
/* read all packets */
while (1) {
if ((ret = av_read_frame(fmt_ctx, &packet)) < 0)
break;
if (packet.stream_index == video_stream_index) {
ret = avcodec_send_packet(dec_ctx, &packet);
if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while sending a packet to the decoder\n");
break;
}
while (ret >= 0) {
ret = avcodec_receive_frame(dec_ctx, frame);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {
break;
} else if (ret < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while receiving a frame from the decoder\n");
goto end;
}
if (ret >= 0) {
frame->pts = av_frame_get_best_effort_timestamp(frame);
/* push the decoded frame into the filtergraph */
if (av_buffersrc_add_frame_flags(buffersrc_ctx, frame, AV_BUFFERSRC_FLAG_KEEP_REF) < 0) {
av_log(NULL, AV_LOG_ERROR, "Error while feeding the filtergraph\n");
break;
}
/* pull filtered frames from the filtergraph */
while (1) {
ret = av_buffersink_get_frame(buffersink_ctx, filt_frame);
if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
break;
if (ret < 0)
goto end;
av_frame_unref(filt_frame);
}
av_frame_unref(frame);
}
}
}
av_packet_unref(&packet);
}
end:
avfilter_graph_free(&filter_graph);
avcodec_free_context(&dec_ctx);
avformat_close_input(&fmt_ctx);
av_frame_free(&frame);
av_frame_free(&filt_frame);
return ret;
} -
Downscaling a video from 1080p to 480p using swscale and encoding to x265 gives a glitched output
5 mai 2023, par lokit khemkaI am basically first scaling a frame and then sending the frame to the encoder as below :


scaled_frame->pts = input_frame->pts;
scaled_frame->pkt_dts = input_frame->pkt_dts;
scaled_frame->pict_type = input_frame->pict_type;
sws_scale_frame(encoder->sws_ctx, scaled_frame, input_frame);
if (encode_video(decoder, encoder, scaled_frame))
 return -1;


The scaling context is configured as :


scaled_frame->width = 854;
scaled_frame->height=480; 
encoder->sws_ctx = sws_getContext(1920, 1080,
 decoder->video_avcc->pix_fmt, 
 scaled_frame->width, scaled_frame->height, decoder->video_avcc->pix_fmt, SWS_BICUBIC, NULL, NULL, NULL );
 if (!encoder->sws_ctx){logging("Cannot Create Scaling Context."); return -1;}


The encoder is configured as :


encoder_sc->video_avcc->height = decoder_ctx->height; //1080
 encoder_sc->video_avcc->width = decoder_ctx->width; //1920
 encoder_sc->video_avcc->bit_rate = 2 * 1000 * 1000;
 encoder_sc->video_avcc->rc_buffer_size = 4 * 1000 * 1000;
 encoder_sc->video_avcc->rc_max_rate = 2 * 1000 * 1000;
 encoder_sc->video_avcc->rc_min_rate = 2.5 * 1000 * 1000;

 encoder_sc->video_avcc->time_base = av_inv_q(input_framerate);
 encoder_sc->video_avs->time_base = encoder_sc->video_avcc->time_base;


When I get the output, the output video is 1080p and I have glitches like :


I changed the encoder avcc resolution to 480p (854 x 480). However, that is causing the video to get sliced to the top quarter of the original frame.
I am new to FFMPEG and video processing in general.


EDIT : I am adding the minimal reproducible code sample. However, it is really long because I need to include code for decoding, scaling and then encoding because the possible error is either in scaling or encoding :


#include <libavcodec></libavcodec>avcodec.h>
#include <libavformat></libavformat>avformat.h>
#include <libavutil></libavutil>timestamp.h>
#include <libavutil></libavutil>opt.h>
#include <libswscale></libswscale>swscale.h>

#include 
#include 

typedef struct StreamingContext{
 AVFormatContext* avfc;
 AVCodec *video_avc;
 AVCodec *audio_avc;
 AVStream *video_avs;
 AVStream *audio_avs;
 AVCodecContext *video_avcc;
 AVCodecContext *audio_avcc;
 int video_index;
 int audio_index;
 char* filename;
 struct SwsContext *sws_ctx;
}StreamingContext;


typedef struct StreamingParams{
 char copy_video;
 char copy_audio;
 char *output_extension;
 char *muxer_opt_key;
 char *muxer_opt_value;
 char *video_codec;
 char *audio_codec;
 char *codec_priv_key;
 char *codec_priv_value;
}StreamingParams;

void logging(const char *fmt, ...)
{
 va_list args;
 fprintf(stderr, "LOG: ");
 va_start(args, fmt);
 vfprintf(stderr, fmt, args);
 va_end(args);
 fprintf(stderr, "\n");
}

int fill_stream_info(AVStream *avs, AVCodec **avc, AVCodecContext **avcc)
{
 *avc = avcodec_find_decoder(avs->codecpar->codec_id);
 if (!*avc)
 {
 logging("Failed to find the codec.\n");
 return -1;
 }

 *avcc = avcodec_alloc_context3(*avc);
 if (!*avcc)
 {
 logging("Failed to alloc memory for codec context.");
 return -1;
 }

 if (avcodec_parameters_to_context(*avcc, avs->codecpar) < 0)
 {
 logging("Failed to fill Codec Context.");
 return -1;
 }

 if (avcodec_open2(*avcc, *avc, NULL) < 0)
 {
 logging("Failed to open Codec.");
 return -1;
 }

 return 0;
}

int open_media(const char *in_filename, AVFormatContext **avfc)
{
 *avfc = avformat_alloc_context();

 if (!*avfc)
 {
 logging("Failed to Allocate Memory for Format Context");
 return -1;
 }

 if (avformat_open_input(avfc, in_filename, NULL, NULL) != 0)
 {
 logging("Failed to open input file %s", in_filename);
 return -1;
 }

 if (avformat_find_stream_info(*avfc, NULL) < 0)
 {
 logging("Failed to get Stream Info.");
 return -1;
 }
}

int prepare_decoder(StreamingContext *sc)
{
 for (int i = 0; i < sc->avfc->nb_streams; i++)
 {
 if (sc->avfc->streams[i]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO)
 {
 sc->video_avs = sc->avfc->streams[i];
 sc->video_index = i;

 if (fill_stream_info(sc->video_avs, &sc->video_avc, &sc->video_avcc))
 {
 return -1;
 }
 }
 else
 {
 logging("Skipping Streams other than Video.");
 }
 }
 return 0;
}

int prepare_video_encoder(StreamingContext *encoder_sc, AVCodecContext *decoder_ctx, AVRational input_framerate,
 StreamingParams sp)
{
 encoder_sc->video_avs = avformat_new_stream(encoder_sc->avfc, NULL);
 encoder_sc->video_avc = avcodec_find_encoder_by_name(sp.video_codec);
 if (!encoder_sc->video_avc)
 {
 logging("Cannot find the Codec.");
 return -1;
 }

 encoder_sc->video_avcc = avcodec_alloc_context3(encoder_sc->video_avc);
 if (!encoder_sc->video_avcc)
 {
 logging("Could not allocate memory for Codec Context.");
 return -1;
 }

 av_opt_set(encoder_sc->video_avcc->priv_data, "preset", "fast", 0);
 if (sp.codec_priv_key && sp.codec_priv_value)
 av_opt_set(encoder_sc->video_avcc->priv_data, sp.codec_priv_key, sp.codec_priv_value, 0);

 encoder_sc->video_avcc->height = decoder_ctx->height;
 encoder_sc->video_avcc->width = decoder_ctx->width;
 encoder_sc->video_avcc->sample_aspect_ratio = decoder_ctx->sample_aspect_ratio;

 if (encoder_sc->video_avc->pix_fmts)
 encoder_sc->video_avcc->pix_fmt = encoder_sc->video_avc->pix_fmts[0];
 else
 encoder_sc->video_avcc->pix_fmt = decoder_ctx->pix_fmt;

 encoder_sc->video_avcc->bit_rate = 2 * 1000 * 1000;
 encoder_sc->video_avcc->rc_buffer_size = 4 * 1000 * 1000;
 encoder_sc->video_avcc->rc_max_rate = 2 * 1000 * 1000;
 encoder_sc->video_avcc->rc_min_rate = 2.5 * 1000 * 1000;

 encoder_sc->video_avcc->time_base = av_inv_q(input_framerate);
 encoder_sc->video_avs->time_base = encoder_sc->video_avcc->time_base;

 

 if (avcodec_open2(encoder_sc->video_avcc, encoder_sc->video_avc, NULL) < 0)
 {
 logging("Could not open the Codec.");
 return -1;
 }
 avcodec_parameters_from_context(encoder_sc->video_avs->codecpar, encoder_sc->video_avcc);
 return 0;
}

int encode_video(StreamingContext *decoder, StreamingContext *encoder, AVFrame *input_frame)
{
 if (input_frame)
 input_frame->pict_type = AV_PICTURE_TYPE_NONE;

 AVPacket *output_packet = av_packet_alloc();
 if (!output_packet)
 {
 logging("Could not allocate memory for Output Packet.");
 return -1;
 }

 int response = avcodec_send_frame(encoder->video_avcc, input_frame);

 while (response >= 0)
 {
 response = avcodec_receive_packet(encoder->video_avcc, output_packet);
 if (response == AVERROR(EAGAIN) || response == AVERROR_EOF)
 {
 break;
 }
 else if (response < 0)
 {
 logging("Error while receiving packet from encoder: %s", av_err2str(response));
 return -1;
 }

 output_packet->stream_index = decoder->video_index;
 output_packet->duration = encoder->video_avs->time_base.den / encoder->video_avs->time_base.num / decoder->video_avs->avg_frame_rate.num * decoder->video_avs->avg_frame_rate.den;

 av_packet_rescale_ts(output_packet, decoder->video_avs->time_base, encoder->video_avs->time_base);
 response = av_interleaved_write_frame(encoder->avfc, output_packet);
 if (response != 0)
 {
 logging("Error %d while receiving packet from decoder: %s", response, av_err2str(response));
 return -1;
 }
 }

 av_packet_unref(output_packet);
 av_packet_free(&output_packet);

 return 0;
}

int transcode_video(StreamingContext *decoder, StreamingContext *encoder, AVPacket *input_packet, AVFrame *input_frame, AVFrame *scaled_frame)
{
 int response = avcodec_send_packet(decoder->video_avcc, input_packet);
 if (response < 0)
 {
 logging("Error while sending the Packet to Decoder: %s", av_err2str(response));
 return response;
 }

 while (response >= 0)
 {
 response = avcodec_receive_frame(decoder->video_avcc, input_frame);
 
 if (response == AVERROR(EAGAIN) || response == AVERROR_EOF)
 {
 break;
 }
 else if (response < 0)
 {
 logging("Error while receiving frame from Decoder: %s", av_err2str(response));
 return response;
 }
 if (response >= 0)
 {
 scaled_frame->pts = input_frame->pts;
 scaled_frame->pkt_dts = input_frame->pkt_dts;
 scaled_frame->pict_type = input_frame->pict_type;
 sws_scale_frame(encoder->sws_ctx, scaled_frame, input_frame);
 if (encode_video(decoder, encoder, scaled_frame))
 return -1;
 }

 av_frame_unref(input_frame);
 }
 return 0;
}

int main(int argc, char *argv[])
{
 StreamingParams sp = {0};
 sp.copy_audio = 1;
 sp.copy_video = 0;
 sp.video_codec = "libx265";


 StreamingContext *decoder = (StreamingContext *)calloc(1, sizeof(StreamingContext));
 decoder->filename = argv[1];

 StreamingContext *encoder = (StreamingContext *)calloc(1, sizeof(StreamingContext));
 encoder->filename = argv[2];

 if (sp.output_extension)
 {
 strcat(encoder->filename, sp.output_extension);
 }

 if (open_media(decoder->filename, &decoder->avfc))
 return -1;
 if (prepare_decoder(decoder))
 return -1;

 avformat_alloc_output_context2(&encoder->avfc, NULL, NULL, encoder->filename);
 if (!encoder->avfc)
 {
 logging("Could not allocate memory for output Format Context.");
 return -1;
 }

 AVRational input_framerate = av_guess_frame_rate(decoder->avfc, decoder->video_avs, NULL);
 prepare_video_encoder(encoder, decoder->video_avcc, input_framerate, sp);


 if (encoder->avfc->oformat->flags & AVFMT_GLOBALHEADER)
 encoder->avfc->flags |= AV_CODEC_FLAG_GLOBAL_HEADER;

 if (!(encoder->avfc->oformat->flags & AVFMT_NOFILE))
 {
 if (avio_open(&encoder->avfc->pb, encoder->filename, AVIO_FLAG_WRITE) < 0)
 {
 logging("could not open the output file");
 return -1;
 }
 }

 AVDictionary *muxer_opts = NULL;

 if (sp.muxer_opt_key && sp.muxer_opt_value)
 {
 av_dict_set(&muxer_opts, sp.muxer_opt_key, sp.muxer_opt_value, 0);
 }

 if (avformat_write_header(encoder->avfc, &muxer_opts) < 0)
 {
 logging("an error occurred when opening output file");
 return -1;
 }

 AVFrame *input_frame = av_frame_alloc();
 AVFrame *scaled_frame = av_frame_alloc();
 if (!input_frame || !scaled_frame)
 {
 logging("Failed to allocate memory for AVFrame");
 return -1;
 }

 // scaled_frame->format = AV_PIX_FMT_YUV420P;
 scaled_frame->width = 854;
 scaled_frame->height=480; 

 //Creating Scaling Context
 encoder->sws_ctx = sws_getContext(1920, 1080,
 decoder->video_avcc->pix_fmt, 
 scaled_frame->width, scaled_frame->height, decoder->video_avcc->pix_fmt, SWS_BICUBIC, NULL, NULL, NULL );
 if (!encoder->sws_ctx){logging("Cannot Create Scaling Context."); return -1;}


 AVPacket *input_packet = av_packet_alloc();
 if (!input_packet)
 {
 logging("Failed to allocate memory for AVPacket.");
 return -1;
 }

 while (av_read_frame(decoder->avfc, input_packet) >= 0)
 {
 if (decoder->avfc->streams[input_packet->stream_index]->codecpar->codec_type == AVMEDIA_TYPE_VIDEO)
 {
 if (transcode_video(decoder, encoder, input_packet, input_frame, scaled_frame))
 return -1;
 av_packet_unref(input_packet);
 }
 else
 {
 logging("Ignoring all nonvideo packets.");
 }
 }

 if (encode_video(decoder, encoder, NULL))
 return -1;

 av_write_trailer(encoder->avfc);

 if (muxer_opts != NULL)
 {
 av_dict_free(&muxer_opts);
 muxer_opts = NULL;
 }

 if (input_frame != NULL)
 {
 av_frame_free(&input_frame);
 input_frame = NULL;
 }

 if (input_packet != NULL)
 {
 av_packet_free(&input_packet);
 input_packet = NULL;
 }

 avformat_close_input(&decoder->avfc);

 avformat_free_context(decoder->avfc);
 decoder->avfc = NULL;
 avformat_free_context(encoder->avfc);
 encoder->avfc = NULL;

 avcodec_free_context(&decoder->video_avcc);
 decoder->video_avcc = NULL;
 avcodec_free_context(&decoder->audio_avcc);
 decoder->audio_avcc = NULL;

 free(decoder);
 decoder = NULL;
 free(encoder);
 encoder = NULL;

 return 0;
}


The video I am using for testing is available at the repo : https://github.com/leandromoreira/ffmpeg-libav-tutorial


The file name is small_bunny_1080p_60fps.mp4


Syndiquer tout le site
