Recherche avancée

Sur d’autres sites (6961)

• How to extract elementary video from mp4 using ffmpeg programmatically ?

  24 octobre 2019, par epipav

  I have started learning ffmpeg few weaks ago. At the moment I am able to transcode any video to mp4 using h264/AVC codec. The main scheme is something like that :

  -open input
  
  -demux
  
  -decode
  
  -encode
  
  -mux

  The actual code is below :

  #include <iostream>
  
  
  
  #include 
  
  
  
  extern "C" {
  
  
  
    #
  
    ifndef __STDC_CONSTANT_MACROS# undef main /* Prevents SDL from overriding main() */ # define __STDC_CONSTANT_MACROS# endif
  
  
  
    # pragma comment(lib, "avcodec.lib")# pragma comment(lib, "avformat.lib")# pragma comment(lib, "swscale.lib")# pragma comment(lib, "avutil.lib")
  
  
  
    #include 
  
    #include 
  
    #include 
  
    #include 
  
    #include <libavutil></libavutil>opt.h>
  
    #include 
  
    #include 
  
    #include 
  
    #include 
  
    #include 
  
  }
  
  
  
  using namespace std;
  
  
  
  void open_video(AVFormatContext * oc, AVCodec * codec, AVStream * st) {
  
    int ret;
  
    AVCodecContext * c;
  
    c = st - > codec;
  
  
  
    /*open codec */
  
  
  
    cout &lt;&lt; "probably starts here" &lt;&lt; endl;
  
    ret = avcodec_open2(c, codec, NULL);
  
    cout &lt;&lt; "and ends here" &lt;&lt; endl;
  
  
  
    if (ret &lt; 0) {
  
      cout &lt;&lt; ("Could not open video codec") &lt;&lt; endl;
  
    }
  
  
  
  }
  
  
  
  /*This function will add a new stream to our file.
  
  @param
  
  oc -> Format context that the new stream will be added.
  
  codec -> codec of the stream, this will be passed.
  
  codec_id -> 
  
  chWidth->
  
  chHeight->
  
  */
  
  
  
  AVStream * addStream(AVFormatContext * oc, AVCodec ** codec, enum AVCodecID codec_id, int chWidth, int chHeight, int fps) {
  
    AVCodecContext * c;
  
    AVStream * st;
  
  
  
    //find encoder of the stream, it passes this information to @codec, later on
  
    //it will be used in encoding the video @ avcodec_encode_video2 in loop.
  
    * codec = avcodec_find_encoder(AV_CODEC_ID_H264);
  
  
  
    if (( * codec) == NULL)
  
      cout &lt;&lt; "ERROR CAN NOT FIND ENCODER! ERROR! ERROR! AVCODEC_FIND_ENCODER FAILED !!!1 "
  
    "" &lt;&lt; endl;
  
  
  
    if (!( * codec))
  
      printf("Could not find encoder for ' %s ' ", avcodec_get_name(codec_id));
  
  
  
    //create a new stream with the found codec inside oc(AVFormatContext).
  
    st = avformat_new_stream(oc, * codec);
  
  
  
    if (!st)
  
      cout &lt;&lt; " Cannot allocate stream " &lt;&lt; endl;
  
  
  
    //Setting the stream id.
  
    //Since, there can be other streams in this AVFormatContext,
  
    //we should find the first non used index. And this is oc->nb_streams(number of streams) - 1
  
    st - > id = oc - > nb_streams - 1;
  
  
  
    c = st - > codec;
  
  
  
    //setting the stream's codec's properties.
  
    c - > codec_id = codec_id;
  
    c - > bit_rate = 4000000;
  
    c - > width = chWidth;
  
    c - > height = chHeight;
  
    c - > time_base.den = fps;
  
    //fps;
  
    c - > time_base.num = 1;
  
    c - > gop_size = 12;
  
    c - > pix_fmt = AV_PIX_FMT_YUV420P;
  
  
  
    if (c - > codec_id == AV_CODEC_ID_MPEG2VIDEO) {
  
      /* just for testing, we also add B frames */
  
      c - > max_b_frames = 2;
  
    }
  
  
  
    if (c - > codec_id == AV_CODEC_ID_MPEG1VIDEO) {
  
      /* Needed to avoid using macroblocks in which some coeffs overflow.
  
       * This does not happen with normal video, it just happens here as
  
       * the motion of the chroma plane does not match the luma plane. */
  
      c - > mb_decision = 2;
  
    }
  
  
  
    /* Some formats want stream headers to be separate. */
  
    if (oc - > oformat - > flags &amp; AVFMT_GLOBALHEADER)
  
      c - > flags |= CODEC_FLAG_GLOBAL_HEADER;
  
  
  
    //returning our lovely new brand stream.
  
    return st;
  
  
  
  }
  
  
  
  int changeResolution(string source, int format) {
  
    //Data members
  
    struct SwsContext * sws_ctx = NULL;
  
    AVFrame * pFrame = NULL;
  
    AVFrame * outFrame = NULL;
  
    AVPacket packet;
  
    uint8_t * buffer = NULL;
  
    uint8_t endcode[] = {
  
      0,
  
      0,
  
      1,
  
      0xb7
  
    };
  
    AVDictionary * optionsDict = NULL;
  
    AVFormatContext * pFormatCtx = NULL;
  
    AVFormatContext * outputContext = NULL;
  
    AVCodecContext * pCodecCtx;
  
    AVCodec * pCodec;
  
    AVCodec * codec;
  
    AVCodec * videoCodec;
  
    AVOutputFormat * fmt;
  
    AVStream * video_stream;
  
    int changeWidth;
  
    int changeHeight;
  
    int frameFinished;
  
    int numBytes;
  
    int fps;
  
  
  
    int lock = 0;
  
  
  
    //Register all codecs &amp; other important stuff. Vital!..
  
    av_register_all();
  
  
  
    //Selects the desired resolution.
  
    if (format == 0) {
  
      changeWidth = 320;
  
      changeHeight = 180;
  
    } else if (format == 1) {
  
      changeWidth = 640;
  
      changeHeight = 480;
  
  
  
    } else if (format == 2) {
  
      changeWidth = 960;
  
      changeHeight = 540;
  
  
  
    } else if (format == 3) {
  
      changeWidth = 1024;
  
      changeHeight = 768;
  
  
  
    } else {
  
      changeWidth = 1280;
  
      changeHeight = 720;
  
    }
  
  
  
    // Open video file
  
    int aaa;
  
    aaa = avformat_open_input( &amp; pFormatCtx, source.c_str(), NULL, NULL);
  
    if (aaa != 0) {
  
      cout &lt;&lt; " cannot open input file \n" &lt;&lt; endl;
  
      cout &lt;&lt; "aaa = " &lt;&lt; aaa &lt;&lt; endl;
  
      return -1; // Couldn't open file    
  
    }
  
  
  
    // Retrieve stream information
  
    if (av_find_stream_info(pFormatCtx) &lt; 0)
  
      return -1; // Couldn't find stream information
  
  
  
    //just checking duration casually for no reason
  
    /*int64_t duration = pFormatCtx->duration;
  
  
  
    cout &lt;&lt; "the duration is " &lt;&lt; duration &lt;&lt; " " &lt;&lt; endl;*/
  
  
  
    //this writes the info about the file
  
    av_dump_format(pFormatCtx, 0, 0, 0);
  
    cin >> lock;
  
  
  
    // Find the first video stream
  
    int videoStream = -1;
  
    int i;
  
  
  
    for (i = 0; i &lt; 3; i++)
  
      if (pFormatCtx - > streams[i] - > codec - > codec_type == AVMEDIA_TYPE_VIDEO) {
  
        videoStream = i;
  
        cout &lt;&lt; " lel \n ";
  
        break;
  
  
  
      }
  
  
  
    if (videoStream == -1)
  
      return -1; // Didn't find a video stream
  
  
  
    // Get a pointer to the codec context for the video stream
  
    pCodecCtx = pFormatCtx - > streams[videoStream] - > codec;
  
    fps = pCodecCtx - > time_base.den;
  
  
  
    //Find the decoder of the input file, for the video stream
  
    pCodec = avcodec_find_decoder(pCodecCtx - > codec_id);
  
  
  
    if (pCodec == NULL) {
  
      fprintf(stderr, "Unsupported codec!\n");
  
      return -1; // Codec not found
  
    }
  
  
  
    // Open codec, you must open it first, in order to use it.
  
    if (avcodec_open2(pCodecCtx, pCodec, &amp; optionsDict) &lt; 0)
  
      return -1; // Could not open codec
  
  
  
    // Allocate video frame ( pFrame for taking the packets into, outFrame for processed frames to packet.)
  
    pFrame = avcodec_alloc_frame();
  
    outFrame = avcodec_alloc_frame();
  
  
  
    i = 0;
  
  
  
    int ret;
  
    int video_frame_count = 0;
  
  
  
    //Initiate the outFrame set the buffer &amp; fill the properties
  
    numBytes = avpicture_get_size(PIX_FMT_YUV420P, changeWidth, changeHeight);
  
    buffer = (uint8_t * ) av_malloc(numBytes * sizeof(uint8_t));
  
    avpicture_fill((AVPicture * ) outFrame, buffer, PIX_FMT_YUV420P, changeWidth, changeHeight);
  
  
  
    int pp;
  
    int frameNo = 0;
  
  
  
    //allocate the outputContext, it will be the AVFormatContext of our output file. 
  
    //It will try to find the format by giving the file name.
  
    avformat_alloc_output_context2( &amp; outputContext, NULL, NULL, "myoutput.mp4");
  
  
  
    //Cant find the file extension, using MPEG as default.
  
    if (!outputContext) {
  
      printf("Could not deduce output format from file extension: using MPEG.\n");
  
      avformat_alloc_output_context2( &amp; outputContext, NULL, "mpeg", "myoutput.mp4");
  
    }
  
  
  
    //Still cant set file extension, exit.
  
    if (!outputContext) {
  
      return 1;
  
    }
  
  
  
    //set AVOutputFormat fmt to our outputContext's format.
  
    fmt = outputContext - > oformat;
  
    video_stream = NULL;
  
  
  
    //If fmt has a valid codec_id, create a new video stream.
  
    //This function will set the streams codec &amp; codecs desired properties.
  
    //Stream's codec will be passed to videoCodec for later usage.
  
    if (fmt - > video_codec != AV_CODEC_ID_NONE)
  
      video_stream = addStream(outputContext, &amp; videoCodec, fmt - > video_codec, changeWidth, changeHeight, fps);
  
  
  
    //open the video using videoCodec. by avcodec_open2() i.e open the codec.
  
    if (video_stream)
  
      open_video(outputContext, videoCodec, video_stream);
  
  
  
    //Creating our new output file.
  
    if (!(fmt - > flags &amp; AVFMT_NOFILE)) {
  
      ret = avio_open( &amp; outputContext - > pb, "toBeStreamed.264", AVIO_FLAG_WRITE);
  
      if (ret &lt; 0) {
  
        cout &lt;&lt; " cant open file " &lt;&lt; endl;
  
        return 1;
  
      }
  
    }
  
  
  
    //Writing the header of format context.
  
    //ret = avformat_write_header(outputContext, NULL);
  
  
  
    if (ret >= 0) {
  
      cout &lt;&lt; "writing header success !!!" &lt;&lt; endl;
  
    }
  
  
  
    //Start reading packages from input file.
  
    while (av_read_frame(pFormatCtx, &amp; packet) >= 0) {
  
  
  
      // Is this a packet from the video stream?  
  
      if (packet.stream_index == videoStream) {
  
  
  
        // Decode video package into frames
  
        ret = avcodec_decode_video2(pCodecCtx, pFrame, &amp; frameFinished, &amp; packet);
  
  
  
        if (ret &lt; 0) {
  
          printf(" Error decoding frame !!..");
  
          return ret;
  
        }
  
  
  
        if (frameFinished) {
  
          printf("video_frame n:%d    coded_n:%d\n", video_frame_count++, pFrame - > coded_picture_number);
  
        }
  
  
  
        av_free_packet( &amp; packet);
  
  
  
        //do stuff with frame, in this case we are changing the resolution.
  
        static struct SwsContext * img_convert_ctx_in = NULL;
  
        if (img_convert_ctx_in == NULL) {
  
          img_convert_ctx_in = sws_getContext(pCodecCtx - > width,
  
            pCodecCtx - > height,
  
            pCodecCtx - > pix_fmt,
  
            changeWidth,
  
            changeHeight,
  
            PIX_FMT_YUV420P,
  
            SWS_BICUBIC,
  
            NULL,
  
            NULL,
  
            NULL);
  
  
  
        }
  
        //scale the frames
  
        sws_scale(img_convert_ctx_in,
  
          pFrame - > data,
  
          pFrame - > linesize,
  
          0,
  
          pCodecCtx - > height,
  
          outFrame - > data,
  
          outFrame - > linesize);
  
  
  
        //initiate the pts value
  
        if (frameNo == 0)
  
          outFrame - > pts = 0;
  
  
  
        //calculate the pts value &amp; set it.
  
        outFrame - > pts += av_rescale_q(1, video_stream - > codec - > time_base, video_stream - > time_base);
  
  
  
        //encode frames into packages. Package passed in @packet.
  
        if (avcodec_encode_video2(outputContext - > streams[0] - > codec, &amp; packet, outFrame, &amp; pp) &lt; 0)
  
          cout &lt;&lt; "Encoding frames into packages, failed. " &lt;&lt; endl;
  
  
  
        frameNo++;
  
  
  
        //write the packages into file, resulting in creating a video file.
  
        av_interleaved_write_frame(outputContext, &amp; packet);
  
  
  
      }
  
  
  
    }
  
  
  
    av_free_packet( &amp; packet);
  
    //av_write_trailer(outputContext);
  
  
  
    avio_close(outputContext - > pb);
  
  
  
    // Free the RGB image
  
    av_free(buffer);
  
    av_free(outFrame);
  
  
  
    // Free the YUV frame
  
    av_free(pFrame);
  
  
  
    // Close the codec
  
    avcodec_close(video_stream - > codec);
  
    avcodec_close(pCodecCtx);
  
  
  
    // Close the video file
  
    avformat_close_input( &amp; pFormatCtx);
  
  
  
    return 0;
  
  }
  
  </iostream>

  at the end of the process I get my desired file with desired codec & container & resolution.

  My problem is, in a part of our project I need to get elementary video streams IN file. Such as example.264. However I can not add a stream without creating an AVFormatContext. I can not create an AVFormatContext because 264 files does not have a container,they are just raw video ?, as far as I know.

  I have tried the way in decoding_encoding.c which uses fwrite. However that example was for mpeg-2 codec and when I try to adapt that code to H264/AVC codec, I got "floating point division by zero" error from mediainfo and moreover, some of the properties of the video was not showing (such as FPS & playtime & quality factor). I think it has to do with the "endcode" the example adds at the end of the code. It is for mpeg-2. ( uint8_t endcode[] = 0, 0, 1, 0xb7  ; )

  Anyway, I would love to get a startpoint for this task. I have managed to come this far by using internet resources ( quite few & outdated for ffmpeg) but now I’m stuck a little.

• AE per frame rendering FFMPEG forming to video

  9 février 2018, par Deckard Cain

  I’m trying to setup an automated per frame rendering system using After Effects and FFMPEG. The idea here is that my slave nodes (running AE), will generate the frames and save them immediately to a Samba share (this way I can team multiple slaves together to tackle the same project file and we aren’t writing an 8GB AVI file, then compressing and deleting it when we could just render 300MB of frames and form it).

  The database and Samba share are running on FreeBSD. This machine will then take those frames and use FFMPEG to combine them into an MP4 video.

  The issue that I’m running into, is that when I render out the After Effects project file directly to an AVI file (one slave, no individual frame rendering), the video length is 1:31. When I render out the exact same project file into individual frames, then run it through FFMPEG to combine and compress them, the output is 1:49.

  I have tried a billion different things to make the length of the video the same, but can’t seem to make it so :/

  aerender.exe -mp -project %PROJECTFILE% -comp %COMPOSITION% -output [########].jpg

  ^Keep in mind, there may be 99999999 frames, or as little as 1 that needs to be rendered (if we need to re-render a specific section because of an asset change)

  ffmpeg -nostdin -i %FRAMELOCATION% -c:v libx264 -preset veryfast -an -y outputVideo.mp4

• Lossless trim and crop of MJPEG video

  28 avril 2021, par prouast

  I am working on a project where I need to trim and crop MJPEG videos without any re-encoding. I have working code that accomplishes this by exporting the relevant frames as JPEGs, cropping them individually, and then joining them back together into an MJPEG.

  


  However, this seems quite inefficient and slow. I am looking for pointers how to improve this approach. For example, would it be possible to store the JPEGs in-memory ?

  


  import ffmpeg
import os
import shutil
import subprocess

def lossless_trim_and_crop(path, output_path, start, end, x, y, width, height, fps):
  # Trim the video in time and export all individual jpeg with ffmpeg + mjpeg2jpeg
  jpeg_folder = os.path.splitext(output_path)[0]
  jpeg_path = os.path.join(jpeg_folder, "frame_%03d.jpg")
  stream = ffmpeg.input(path, ss=start/fps, t=(end-start)/fps)
  stream = ffmpeg.output(stream, jpeg_path, vcodec='copy', **{'bsf:v': 'mjpeg2jpeg'})
  stream.run(quiet=True)
  # Crop all individual jpeg with jpegtran
  for filename in os.listdir(jpeg_folder):
    filepath = os.path.join(jpeg_folder, filename)
    out_filepath = os.path.splitext(filepath)[0] + "_c.jpg"
    subprocess.call(
      "jpegtran -perfect -crop {}x{}+{}+{} -outfile {} {}".format(
        width, height, x, y, out_filepath, filepath), shell=True)
    os.remove(filepath)
  # Join individual jpg back together
  cropped_jpeg_path = os.path.join(jpeg_folder, "frame_%03d_c.jpg")
  stream = ffmpeg.input(cropped_jpeg_path, framerate=fps)
  stream = ffmpeg.output(stream, output_path, vcodec='copy')
  stream.run(quiet=True)
  # Delete jpeg directory
  shutil.rmtree(jpeg_folder)