Manual libav FFmpeg

Daftar Isi

• pengantar
  • Video adalah apa yang Anda lihat!
  • Audio adalah apa yang Anda dengar!
  • Codec - Kompresi Data
  • Wadah adalah cara mudah untuk menyimpan audio / video
• Baris perintah ffmpeg
  • Alat baris perintah FFmpeg 101
• Operasi dasar pada video
  • Transcoding
  • Transmultiplexing
  • Transisi
  • Transizing
  • Bonus: streaming adaptif
  • Melampaui
• FFmpeg libav
  • 0 — «Hello World»
    • FFmpeg libav
    • ,
  • 1 —
  • 2 —
  • 3 —

EDISON.

, , .

! ;-)

↑

— , ! ↑

Audio adalah apa yang Anda dengar! ↑

Codec - kompresi data ↑

toppf = 1080 * 1920 //    
cpp = 3 //  
tis = 30 * 60 //   
fps = 24 //   

required_storage = tis * fps * toppf * cpp

Wadah adalah cara mudah untuk menyimpan audio / video ↑

Baris perintah FFmpeg ↑

$ ffmpeg -i input.mp4 output.avi

Alat baris perintah FFmpeg 101 ↑

$ wget -O bunny_1080p_60fps.mp4 http://distribution.bbb3d.renderfarming.net/video/mp4/bbb_sunflower_1080p_60fps_normal.mp4

$ ffmpeg \
-y \ #  
-c: libfdk_aac -c: v libx264 \ #  
-i bunny_1080p_60fps.mp4 \ #  URL
-c: v libvpx-vp9 -c: libvorbis \ #  
bunny_1080p_60fps_vp9.webm #  URL

ffmpeg -i input.avi output.mp4

Operasi video dasar ↑

Transcoding (transcoding) ↑

$ ffmpeg \
-i bunny_1080p_60fps.mp4 \
-c:v libx265 \
bunny_1080p_60fps_h265.mp4

Transmultiplexing ↑

$ ffmpeg \
-i bunny_1080p_60fps.mp4 \
-c copy \ # just saying to ffmpeg to skip encoding
bunny_1080p_60fps.webm

Transisi ↑

$ ffmpeg \
-i bunny_1080p_60fps.mp4 \
-minrate 964K -maxrate 3856K -bufsize 2000K \
bunny_1080p_60fps_transrating_964_3856.mp4

Transizing (kalibrasi ulang) ↑

$ ffmpeg \
-i bunny_1080p_60fps.mp4 \
-vf scale=480:-1 \
bunny_1080p_60fps_transsizing_480.mp4

Bonus: streaming adaptif ↑

# video streams
$ ffmpeg -i bunny_1080p_60fps.mp4 -c:v libvpx-vp9 -s 160x90 -b:v 250k -keyint_min 150 -g 150 -an -f webm -dash 1 video_160x90_250k.webm

$ ffmpeg -i bunny_1080p_60fps.mp4 -c:v libvpx-vp9 -s 320x180 -b:v 500k -keyint_min 150 -g 150 -an -f webm -dash 1 video_320x180_500k.webm

$ ffmpeg -i bunny_1080p_60fps.mp4 -c:v libvpx-vp9 -s 640x360 -b:v 750k -keyint_min 150 -g 150 -an -f webm -dash 1 video_640x360_750k.webm

$ ffmpeg -i bunny_1080p_60fps.mp4 -c:v libvpx-vp9 -s 640x360 -b:v 1000k -keyint_min 150 -g 150 -an -f webm -dash 1 video_640x360_1000k.webm

$ ffmpeg -i bunny_1080p_60fps.mp4 -c:v libvpx-vp9 -s 1280x720 -b:v 1500k -keyint_min 150 -g 150 -an -f webm -dash 1 video_1280x720_1500k.webm

# audio streams
$ ffmpeg -i bunny_1080p_60fps.mp4 -c:a libvorbis -b:a 128k -vn -f webm -dash 1 audio_128k.webm

# the DASH manifest
$ ffmpeg \
 -f webm_dash_manifest -i video_160x90_250k.webm \
 -f webm_dash_manifest -i video_320x180_500k.webm \
 -f webm_dash_manifest -i video_640x360_750k.webm \
 -f webm_dash_manifest -i video_640x360_1000k.webm \
 -f webm_dash_manifest -i video_1280x720_500k.webm \
 -f webm_dash_manifest -i audio_128k.webm \
 -c copy -map 0 -map 1 -map 2 -map 3 -map 4 -map 5 \
 -f webm_dash_manifest \
 -adaptation_sets "id=0,streams=0,1,2,3,4 id=1,streams=5" \
 manifest.mpd

Melampaui ↑

Jalan yang sulit untuk belajar FFmpeg libav ↑

Bukankah menakjubkan dari waktu ke waktu yang dirasakan melalui pendengaran dan penglihatan?

Ahli biologi David Robert Jones

Bab 0 - Hello World Sederhana ↑

Arsitektur lmpav FFmpeg ↑

Persyaratan ↑

Sebenarnya, kode ↑

$ make run_hello

AVFormatContext *pFormatContext = avformat_alloc_context();

avformat_open_input(&pFormatContext, filename, NULL, NULL);

printf("Format %s, duration %lld us", pFormatContext->iformat->long_name, pFormatContext->duration);

avformat_find_stream_info(pFormatContext,  NULL);

for(int i = 0; i < pFormatContext->nb_streams; i++) {
  //
}

AVCodecParameters *pLocalCodecParameters = pFormatContext->streams[i]->codecpar;

AVCodec *pLocalCodec = avcodec_find_decoder(pLocalCodecParameters->codec_id);

// specific for video and audio
if (pLocalCodecParameters->codec_type == AVMEDIA_TYPE_VIDEO) {
  printf("Video Codec: resolution %d x %d", pLocalCodecParameters->width, pLocalCodecParameters->height);
} else if (pLocalCodecParameters->codec_type == AVMEDIA_TYPE_AUDIO) {
  printf("Audio Codec: %d channels, sample rate %d", pLocalCodecParameters->channels, pLocalCodecParameters->sample_rate);
}
// general
printf("\tCodec %s ID %d bit_rate %lld", pLocalCodec->long_name, pLocalCodec->id, pCodecParameters->bit_rate);

AVCodecContext *pCodecContext = avcodec_alloc_context3(pCodec);
avcodec_parameters_to_context(pCodecContext, pCodecParameters);
avcodec_open2(pCodecContext, pCodec, NULL);

AVPacket *pPacket = av_packet_alloc();
AVFrame *pFrame = av_frame_alloc();

while(av_read_frame(pFormatContext, pPacket) >= 0) {
  //...
}

avcodec_send_packet(pCodecContext, pPacket);

avcodec_receive_frame(pCodecContext, pFrame);

printf(
    "Frame %c (%d) pts %d dts %d key_frame %d [coded_picture_number %d, display_picture_number %d]",
    av_get_picture_type_char(pFrame->pict_type),
    pCodecContext->frame_number,
    pFrame->pts,
    pFrame->pkt_dts,
    pFrame->key_frame,
    pFrame->coded_picture_number,
    pFrame->display_picture_number
);

save_gray_frame(pFrame->data[0], pFrame->linesize[0], pFrame->width, pFrame->height, frame_filename);

static void save_gray_frame(unsigned char *buf, int wrap, int xsize, int ysize, char *filename)
{
    FILE *f;
    int i;
    f = fopen(filename,"w");
    // writing the minimal required header for a pgm file format
    // portable graymap format -> https://en.wikipedia.org/wiki/Netpbm_format#PGM_example
    fprintf(f, "P5\n%d %d\n%d\n", xsize, ysize, 255);

    // writing line by line
    for (i = 0; i < ysize; i++)
        fwrite(buf + i * wrap, 1, xsize, f);
    fclose(f);
}

Bab 1 - Sinkronisasi Audio dan Video ↑

Berada di dalam permainan adalah ketika pengembang muda JS menulis pemutar video MSE baru.

frame=0, PTS = 0, PTS_TIME = 0
frame=1, PTS = 1000, PTS_TIME = PTS * timebase = 0.016
frame=2, PTS = 2000, PTS_TIME = PTS * timebase = 0.033

frame=0, PTS = 0, PTS_TIME = 0
frame=1, PTS = 1, PTS_TIME = PTS * timebase = 0.016
frame=2, PTS = 2, PTS_TIME = PTS * timebase = 0.033
frame=3, PTS = 3, PTS_TIME = PTS * timebase = 0.050

frame=0, PTS = 0, PTS_TIME = 0
frame=1, PTS = 3, PTS_TIME = PTS * timebase = 0.04
frame=2, PTS = 6, PTS_TIME = PTS * timebase = 0.08
frame=3, PTS = 9, PTS_TIME = PTS * timebase = 0.12
...
frame=24, PTS = 72, PTS_TIME = PTS * timebase = 0.96
...
frame=4064, PTS = 12192, PTS_TIME = PTS * timebase = 162.56

fps = AVStream->avg_frame_rate
tbr = AVStream->r_frame_rate
tbn = AVStream->time_base

LOG: AVStream->r_frame_rate 60/1
LOG: AVStream->time_base 1/60000
...
LOG: Frame 1 (type=I, size=153797 bytes) pts 6000 key_frame 1 [DTS 0]
LOG: Frame 2 (type=B, size=8117 bytes) pts 7000 key_frame 0 [DTS 3]
LOG: Frame 3 (type=B, size=8226 bytes) pts 8000 key_frame 0 [DTS 4]
LOG: Frame 4 (type=B, size=17699 bytes) pts 9000 key_frame 0 [DTS 2]
LOG: Frame 5 (type=B, size=6253 bytes) pts 10000 key_frame 0 [DTS 5]
LOG: Frame 6 (type=P, size=34992 bytes) pts 11000 key_frame 0 [DTS 1]

Bab 2 - Remultiplexing ↑

ffmpeg input.mp4 -c copy output.ts

• tingkat protokol - menerima data input (misalnya, file, tetapi juga bisa berupa unduhan rtmp atau HTTP)
• — , , ,
• —
• — (, ),
• … :
• — ( )
• — ( ) ( )
• — , , ( , , )

ffmpeg input.mp4 -c copy output.ts

AVFormatContext *input_format_context = NULL;
AVFormatContext *output_format_context = NULL;

if ((ret = avformat_open_input(&input_format_context, in_filename, NULL, NULL)) < 0) {
  fprintf(stderr, "Could not open input file '%s'", in_filename);
  goto end;
}
if ((ret = avformat_find_stream_info(input_format_context, NULL)) < 0) {
  fprintf(stderr, "Failed to retrieve input stream information");
  goto end;
}

avformat_alloc_output_context2(&output_format_context, NULL, NULL, out_filename);
if (!output_format_context) {
  fprintf(stderr, "Could not create output context\n");
  ret = AVERROR_UNKNOWN;
  goto end;
}

number_of_streams = input_format_context->nb_streams;
streams_list = av_mallocz_array(number_of_streams, sizeof(*streams_list));

for (i = 0; i < input_format_context->nb_streams; i++) {
  AVStream *out_stream;
  AVStream *in_stream = input_format_context->streams[i];
  AVCodecParameters *in_codecpar = in_stream->codecpar;
  if (in_codecpar->codec_type != AVMEDIA_TYPE_AUDIO &&
      in_codecpar->codec_type != AVMEDIA_TYPE_VIDEO &&
      in_codecpar->codec_type != AVMEDIA_TYPE_SUBTITLE) {
    streams_list[i] = -1;
    continue;
  }
  streams_list[i] = stream_index++;
  out_stream = avformat_new_stream(output_format_context, NULL);
  if (!out_stream) {
    fprintf(stderr, "Failed allocating output stream\n");
    ret = AVERROR_UNKNOWN;
    goto end;
  }
  ret = avcodec_parameters_copy(out_stream->codecpar, in_codecpar);
  if (ret < 0) {
    fprintf(stderr, "Failed to copy codec parameters\n");
    goto end;
  }
}

if (!(output_format_context->oformat->flags & AVFMT_NOFILE)) {
  ret = avio_open(&output_format_context->pb, out_filename, AVIO_FLAG_WRITE);
  if (ret < 0) {
    fprintf(stderr, "Could not open output file '%s'", out_filename);
    goto end;
  }
}

ret = avformat_write_header(output_format_context, NULL);
if (ret < 0) {
  fprintf(stderr, "Error occurred when opening output file\n");
  goto end;
}

while (1) {
  AVStream *in_stream, *out_stream;
  ret = av_read_frame(input_format_context, &packet);
  if (ret < 0)
    break;
  in_stream  = input_format_context->streams[packet.stream_index];
  if (packet.stream_index >= number_of_streams || streams_list[packet.stream_index] < 0) {
    av_packet_unref(&packet);
    continue;
  }
  packet.stream_index = streams_list[packet.stream_index];
  out_stream = output_format_context->streams[packet.stream_index];
  /* copy packet */
  packet.pts = av_rescale_q_rnd(packet.pts, in_stream->time_base, out_stream->time_base, AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX);
  packet.dts = av_rescale_q_rnd(packet.dts, in_stream->time_base, out_stream->time_base, AV_ROUND_NEAR_INF|AV_ROUND_PASS_MINMAX);
  packet.duration = av_rescale_q(packet.duration, in_stream->time_base, out_stream->time_base);
  // https://ffmpeg.org/doxygen/trunk/structAVPacket.html#ab5793d8195cf4789dfb3913b7a693903
  packet.pos = -1;

  //https://ffmpeg.org/doxygen/trunk/group__lavf__encoding.html#ga37352ed2c63493c38219d935e71db6c1
  ret = av_interleaved_write_frame(output_format_context, &packet);
  if (ret < 0) {
    fprintf(stderr, "Error muxing packet\n");
    break;
  }
  av_packet_unref(&packet);
}

av_write_trailer(output_format_context);

make run_remuxing_ts

ffprobe -i remuxed_small_bunny_1080p_60fps.ts

Input #0, mpegts, from 'remuxed_small_bunny_1080p_60fps.ts':
  Duration: 00:00:10.03, start: 0.000000, bitrate: 2751 kb/s
  Program 1
    Metadata:
      service_name    : Service01
      service_provider: FFmpeg
    Stream #0:0[0x100]: Video: h264 (High) ([27][0][0][0] / 0x001B), yuv420p(progressive), 1920x1080 [SAR 1:1 DAR 16:9], 60 fps, 60 tbr, 90k tbn, 120 tbc
    Stream #0:1[0x101]: Audio: ac3 ([129][0][0][0] / 0x0081), 48000 Hz, 5.1(side), fltp, 320 kb/s

ffmpeg -i non_fragmented.mp4 -movflags frag_keyframe+empty_moov+default_base_moof fragmented.mp4

AVDictionary* opts = NULL;
av_dict_set(&opts, "movflags", "frag_keyframe+empty_moov+default_base_moof", 0);
ret = avformat_write_header(output_format_context, &opts);

make run_remuxing_fragmented_mp4

Bab 3 - Transkode ↑

$ make run_transcoding

Transmultiplexing ↑

// Allocate an AVFormatContext
avfc = avformat_alloc_context();
// Open an input stream and read the header.
avformat_open_input(avfc, in_filename, NULL, NULL);
// Read packets of a media file to get stream information.
avformat_find_stream_info(avfc, NULL);

for(int i = 0; i < avfc->nb_streams; i++) {
  AVStream *avs = avfc->streams[i];
  AVCodec *avc = avcodec_find_decoder(avs->codecpar->codec_id);
  AVCodecContext *avcc = avcodec_alloc_context3(*avc);
  avcodec_parameters_to_context(*avcc, avs->codecpar);
  avcodec_open2(*avcc, *avc, NULL);
}

avformat_alloc_output_context2(&encoder_avfc, NULL, NULL, out_filename);

AVStream *avs = avformat_new_stream(encoder_avfc, NULL);
avcodec_parameters_copy(avs->codecpar, decoder_avs->codecpar);

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

avio_open(&encoder_avfc->pb, encoder->filename, AVIO_FLAG_WRITE);
avformat_write_header(encoder->avfc, &muxer_opts);

AVFrame *input_frame = av_frame_alloc();
AVPacket *input_packet = av_packet_alloc();

while(av_read_frame(decoder_avfc, input_packet) >= 0) {
  av_packet_rescale_ts(input_packet, decoder_video_avs->time_base, encoder_video_avs->time_base);
  av_interleaved_write_frame(*avfc, input_packet) < 0));
}

av_write_trailer(encoder_avfc);

Transcoding ↑

• Buat AVStream video dalam encoder avformat_new_stream .
• Kami menggunakan AVCodec dengan nama libx265 , avcodec_find_encoder_by_name .
• Buat AVCodecContext berdasarkan pada codec avcodec_alloc_context3 yang dibuat .
• Tetapkan atribut dasar untuk sesi transkode dan ...
• ... buka codec dan salin parameter dari konteks ke aliran ( avcodec_open2 dan avcodec_parameters_from_context ).

AVRational input_framerate = av_guess_frame_rate(decoder_avfc, decoder_video_avs, NULL);
AVStream *video_avs = avformat_new_stream(encoder_avfc, NULL);

char *codec_name = "libx265";
char *codec_priv_key = "x265-params";
// we're going to use internal options for the x265
// it disables the scene change detection and fix then
// GOP on 60 frames.
char *codec_priv_value = "keyint=60:min-keyint=60:scenecut=0";

AVCodec *video_avc = avcodec_find_encoder_by_name(codec_name);
AVCodecContext *video_avcc = avcodec_alloc_context3(video_avc);
// encoder codec params
av_opt_set(sc->video_avcc->priv_data, codec_priv_key, codec_priv_value, 0);
video_avcc->height = decoder_ctx->height;
video_avcc->width = decoder_ctx->width;
video_avcc->pix_fmt = video_avc->pix_fmts[0];
// control rate
video_avcc->bit_rate = 2 * 1000 * 1000;
video_avcc->rc_buffer_size = 4 * 1000 * 1000;
video_avcc->rc_max_rate = 2 * 1000 * 1000;
video_avcc->rc_min_rate = 2.5 * 1000 * 1000;
// time base
video_avcc->time_base = av_inv_q(input_framerate);
video_avs->time_base = sc->video_avcc->time_base;

avcodec_open2(sc->video_avcc, sc->video_avc, NULL);
avcodec_parameters_from_context(sc->video_avs->codecpar, sc->video_avcc);

• Kami mengirim AVPacket kosong ke decoder ( avcodec_send_packet ).
• Dapatkan AVFrame yang tidak terkompresi ( avcodec_receive_frame ).
• Kami mulai mengkode ulang bingkai mentah.
• Kami mengirim bingkai mentah ( avcodec_send_frame ).
• Kami mendapatkan kompresi berdasarkan codec AVPacket kami ( avcodec_receive_packet ).
• Tetapkan stempel waktu ( av_packet_rescale_ts ).
• Kami menulis ke file output ( av_interleaved_write_frame ).

AVFrame *input_frame = av_frame_alloc();
AVPacket *input_packet = av_packet_alloc();

while (av_read_frame(decoder_avfc, input_packet) >= 0)
{
  int response = avcodec_send_packet(decoder_video_avcc, input_packet);
  while (response >= 0) {
    response = avcodec_receive_frame(decoder_video_avcc, input_frame);
    if (response == AVERROR(EAGAIN) || response == AVERROR_EOF) {
      break;
    } else if (response < 0) {
      return response;
    }
    if (response >= 0) {
      encode(encoder_avfc, decoder_video_avs, encoder_video_avs, decoder_video_avcc, input_packet->stream_index);
    }
    av_frame_unref(input_frame);
  }
  av_packet_unref(input_packet);
}
av_write_trailer(encoder_avfc);

// used function
int encode(AVFormatContext *avfc, AVStream *dec_video_avs, AVStream *enc_video_avs, AVCodecContext video_avcc int index) {
  AVPacket *output_packet = av_packet_alloc();
  int response = avcodec_send_frame(video_avcc, input_frame);

  while (response >= 0) {
    response = avcodec_receive_packet(video_avcc, output_packet);
    if (response == AVERROR(EAGAIN) || response == AVERROR_EOF) {
      break;
    } else if (response < 0) {
      return -1;
    }

    output_packet->stream_index = index;
    output_packet->duration = enc_video_avs->time_base.den / enc_video_avs->time_base.num / dec_video_avs->avg_frame_rate.num * dec_video_avs->avg_frame_rate.den;

    av_packet_rescale_ts(output_packet, dec_video_avs->time_base, enc_video_avs->time_base);
    response = av_interleaved_write_frame(avfc, output_packet);
  }
  av_packet_unref(output_packet);
  av_packet_free(&output_packet);
  return 0;
}

  /*
   * H264 -> H265
   * Audio -> remuxed (untouched)
   * MP4 - MP4
   */
  StreamingParams sp = {0};
  sp.copy_audio = 1;
  sp.copy_video = 0;
  sp.video_codec = "libx265";
  sp.codec_priv_key = "x265-params";
  sp.codec_priv_value = "keyint=60:min-keyint=60:scenecut=0";

  /*
   * H264 -> H264 (fixed gop)
   * Audio -> remuxed (untouched)
   * MP4 - MP4
   */
  StreamingParams sp = {0};
  sp.copy_audio = 1;
  sp.copy_video = 0;
  sp.video_codec = "libx264";
  sp.codec_priv_key = "x264-params";
  sp.codec_priv_value = "keyint=60:min-keyint=60:scenecut=0:force-cfr=1";

  /*
   * H264 -> H264 (fixed gop)
   * Audio -> remuxed (untouched)
   * MP4 - fragmented MP4
   */
  StreamingParams sp = {0};
  sp.copy_audio = 1;
  sp.copy_video = 0;
  sp.video_codec = "libx264";
  sp.codec_priv_key = "x264-params";
  sp.codec_priv_value = "keyint=60:min-keyint=60:scenecut=0:force-cfr=1";
  sp.muxer_opt_key = "movflags";
  sp.muxer_opt_value = "frag_keyframe+empty_moov+default_base_moof";

  /*
   * H264 -> H264 (fixed gop)
   * Audio -> AAC
   * MP4 - MPEG-TS
   */
  StreamingParams sp = {0};
  sp.copy_audio = 0;
  sp.copy_video = 0;
  sp.video_codec = "libx264";
  sp.codec_priv_key = "x264-params";
  sp.codec_priv_value = "keyint=60:min-keyint=60:scenecut=0:force-cfr=1";
  sp.audio_codec = "aac";
  sp.output_extension = ".ts";

  /* WIP :P  -> it's not playing on VLC, the final bit rate is huge
   * H264 -> VP9
   * Audio -> Vorbis
   * MP4 - WebM
   */
  //StreamingParams sp = {0};
  //sp.copy_audio = 0;
  //sp.copy_video = 0;
  //sp.video_codec = "libvpx-vp9";
  //sp.audio_codec = "libvorbis";
  //sp.output_extension = ".webm";

Terjemahan di Blog Edison:

50 waralaba game terbaik dengan lebih dari satu miliar pendapatan	Airbnb ? [: ]