Recherche avancée
Autres articles (40)
-
Submit bugs and patches
13 avril 2011Unfortunately a software is never perfect.
If you think you have found a bug, report it using our ticket system. Please to help us to fix it by providing the following information : the browser you are using, including the exact version as precise an explanation as possible of the problem if possible, the steps taken resulting in the problem a link to the site / page in question
If you think you have solved the bug, fill in a ticket and attach to it a corrective patch.
You may also (...) -
MediaSPIP v0.2
21 juin 2013, parMediaSPIP 0.2 is the first MediaSPIP stable release.
Its official release date is June 21, 2013 and is announced here.
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 (...) -
Des sites réalisés avec MediaSPIP
2 mai 2011, parCette page présente quelques-uns des sites fonctionnant sous MediaSPIP.
Vous pouvez bien entendu ajouter le votre grâce au formulaire en bas de page.
Sur d’autres sites (6819)
-
How to use ffmpeg lib transform mp4(h264&aac) to m3u8 (hls) by C code ?
1er juillet 2020, par itningI used official examples
transcoding.cbut console printpkt->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></libavcodec>avcodec.h>
#include <libavformat></libavformat>avformat.h>
#include <libavfilter></libavfilter>buffersink.h>
#include <libavfilter></libavfilter>buffersrc.h>
#include <libavutil></libavutil>opt.h>
#include <libavutil></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;
}


-
Anatomy of an optimization : H.264 deblocking
As mentioned in the previous post, H.264 has an adaptive deblocking filter. But what exactly does that mean — and more importantly, what does it mean for performance ? And how can we make it as fast as possible ? In this post I’ll try to answer these questions, particularly in relation to my recent deblocking optimizations in x264.
H.264′s deblocking filter has two steps : strength calculation and the actual filter. The first step calculates the parameters for the second step. The filter runs on all the edges in each macroblock. That’s 4 vertical edges of length 16 pixels and 4 horizontal edges of length 16 pixels. The vertical edges are filtered first, from left to right, then the horizontal edges, from top to bottom (order matters !). The leftmost edge is the one between the current macroblock and the left macroblock, while the topmost edge is the one between the current macroblock and the top macroblock.
Here’s the formula for the strength calculation in progressive mode. The highest strength that applies is always selected.
If we’re on the edge between an intra macroblock and any other macroblock : Strength 4
If we’re on an internal edge of an intra macroblock : Strength 3
If either side of a 4-pixel-long edge has residual data : Strength 2
If the motion vectors on opposite sides of a 4-pixel-long edge are at least a pixel apart (in either x or y direction) or the reference frames aren’t the same : Strength 1
Otherwise : Strength 0 (no deblocking)These values are then thrown into a lookup table depending on the quantizer : higher quantizers have stronger deblocking. Then the actual filter is run with the appropriate parameters. Note that Strength 4 is actually a special deblocking mode that performs a much stronger filter and affects more pixels.
One can see somewhat intuitively why these strengths are chosen. The deblocker exists to get rid of sharp edges caused by the block-based nature of H.264, and so the strength depends on what exists that might cause such sharp edges. The strength calculation is a way to use existing data from the video stream to make better decisions during the deblocking process, improving compression and quality.
Both the strength calculation and the actual filter (not described here) are very complex if naively implemented. The latter can be SIMD’d with not too much difficulty ; no H.264 decoder can get away with reasonable performance without such a thing. But what about optimizing the strength calculation ? A quick analysis shows that this can be beneficial as well.
Since we have to check both horizontal and vertical edges, we have to check up to 32 pairs of coefficient counts (for residual), 16 pairs of reference frame indices, and 128 motion vector values (counting x and y as separate values). This is a lot of calculation ; a naive implementation can take 500-1000 clock cycles on a modern CPU. Of course, there’s a lot of shortcuts we can take. Here’s some examples :
- If the macroblock uses the 8×8 transform, we only need to check 2 edges in each direction instead of 4, because we don’t deblock inside of the 8×8 blocks.
- If the macroblock is a P-skip, we only have to check the first edge in each direction, since there’s guaranteed to be no motion vector differences, reference frame differences, or residual inside of the macroblock.
- If the macroblock has no residual at all, we can skip that check.
- If we know the partition type of the macroblock, we can do motion vector checks only along the edges of the partitions.
- If the effective quantizer is so low that no deblocking would be performed no matter what, don’t bother calculating the strength.
But even all of this doesn’t save us from ourselves. We still have to iterate over a ton of edges, checking each one. Stuff like the partition-checking logic greatly complicates the code and adds overhead even as it reduces the number of checks. And in many cases decoupling the checks to add such logic will make it slower : if the checks are coupled, we can avoid doing a motion vector check if there’s residual, since Strength 2 overrides Strength 1.
But wait. What if we could do this in SIMD, just like the actual loopfilter itself ? Sure, it seems more of a problem for C code than assembly, but there aren’t any obvious things in the way. Many years ago, Loren Merritt (pengvado) wrote the first SIMD implementation that I know of (for ffmpeg’s decoder) ; it is quite fast, so I decided to work on porting the idea to x264 to see if we could eke out a bit more speed here as well.
Before I go over what I had to do to make this change, let me first describe how deblocking is implemented in x264. Since the filter is a loopfilter, it acts “in loop” and must be done in both the encoder and decoder — hence why x264 has it too, not just decoders. At the end of encoding one row of macroblocks, x264 goes back and deblocks the row, then performs half-pixel interpolation for use in encoding the next frame.
We do it per-row for reasons of cache coherency : deblocking accesses a lot of pixels and a lot of code that wouldn’t otherwise be used, so it’s more efficient to do it in a single pass as opposed to deblocking each macroblock immediately after encoding. Then half-pixel interpolation can immediately re-use the resulting data.
Now to the change. First, I modified deblocking to implement a subset of the macroblock_cache_load function : spend an extra bit of effort loading the necessary data into a data structure which is much simpler to address — as an assembly implementation would need (x264_macroblock_cache_load_deblock). Then I massively cleaned up deblocking to move all of the core strength-calculation logic into a single, small function that could be converted to assembly (deblock_strength_c). Finally, I wrote the assembly functions and worked with Loren to optimize them. Here’s the result.
And the timings for the resulting assembly function on my Core i7, in cycles :
deblock_strength_c : 309
deblock_strength_mmx : 79
deblock_strength_sse2 : 37
deblock_strength_ssse3 : 33Now that is a seriously nice improvement. 33 cycles on average to perform that many comparisons–that’s absurdly low, especially considering the SIMD takes no branchy shortcuts : it always checks every single edge ! I walked over to my performance chart and happily crossed off a box.
But I had a hunch that I could do better. Remember, as mentioned earlier, we’re reloading all that data back into our data structures in order to address it. This isn’t that slow, but takes enough time to significantly cut down on the gain of the assembly code. And worse, less than a row ago, all this data was in the correct place to be used (when we just finished encoding the macroblock) ! But if we did the deblocking right after encoding each macroblock, the cache issues would make it too slow to be worth it (yes, I tested this). So I went back to other things, a bit annoyed that I couldn’t get the full benefit of the changes.
Then, yesterday, I was talking with Pascal, a former Xvid dev and current video hacker over at Google, about various possible x264 optimizations. He had seen my deblocking changes and we discussed that a bit as well. Then two lines hit me like a pile of bricks :
<_skal_> tried computing the strength at least ?
<_skal_> while it’s freshWhy hadn’t I thought of that ? Do the strength calculation immediately after encoding each macroblock, save the result, and then go pick it up later for the main deblocking filter. Then we can use the data right there and then for strength calculation, but we don’t have to do the whole deblock process until later.
I went and implemented it and, after working my way through a horde of bugs, eventually got a working implementation. A big catch was that of slices : deblocking normally acts between slices even though normal encoding does not, so I had to perform extra munging to get that to work. By midday today I was able to go cross yet another box off on the performance chart. And now it’s committed.
Sometimes chatting for 10 minutes with another developer is enough to spot the idea that your brain somehow managed to miss for nearly a straight week.
NB : the performance chart is on a specific test clip at a specific set of settings (super fast settings) relevant to the company I work at, so it isn’t accurate nor complete for, say, default settings.
Update : Here’s a higher resolution version of the current chart, as requested in the comments.
-
MPEG DASH : frame seeking
13 août 2014, par bisc8TL ;DR : Is it possible to achieve frame seeking using DASH ? How ?
I’m using ffmpeg to create non-multiplexed content :
ffmpeg -y -an -codec:v libx264 -profile:v baseline output_video.mp4 -i video.mp4
ffmpeg -y -vn -codec:a libvo_aacenc -ac 1 -ar 44100 output_audio.mp4 -i video.mp4Then I’m using mp4box to create DASH content :
mp4box -dash 10000 -frag 1000 -rap -dash-profile live -segment-name mp4-live-$RepresentationID$-$Number$ -out manifest.mpd output_video.mp4 output_audio.mp4Finally I open the generated content with Chrome, using dash.js. Everything works fine except that I can’t do frame seek. I keep on adding (1/frame_rate) seconds to the current time but nothing happens, the frame only changes after 10 seconds.
I suppose this has to do with the video’s key interval. However, I am able to do frame seek after the ffmpeg part, so I guess I’m missing something in the mp4box command.
Is it possible to achieve frame seeking using DASH or am I missing something ?
Thanks in advance.
Syndiquer tout le site
