Recherche avancée

Sur d’autres sites (12367)

• FFmpeg - MJPEG decoding - getting different values

  27 décembre 2016, par ahmadh

  I have a set of JPEG frames which I am muxing into an avi, which gives me a mjpeg video. This is the command I run on the console :

  ffmpeg -y -start_number 0 -i %06d.JPEG -codec copy vid.avi

  When I try to demux the video using ffmpeg C api, I get frames which are slightly different in values. Demuxing code looks something like this :

  AVFormatContext* fmt_ctx = NULL;
  
  AVCodecContext* cdc_ctx = NULL;
  
  AVCodec* vid_cdc = NULL;
  
  int ret;
  
  unsigned int height, width;
  
  
  
  ....
  
  // read_nframes is the number of frames to read
  
  output_arr = new unsigned char [height * width * 3 * 
  
                                  sizeof(unsigned char) * read_nframes];
  
  
  
  avcodec_open2(cdc_ctx, vid_cdc, NULL);
  
  
  
  int num_bytes;
  
  uint8_t* buffer = NULL;
  
  const AVPixelFormat out_format = AV_PIX_FMT_RGB24;
  
  
  
  num_bytes = av_image_get_buffer_size(out_format, width, height, 1);
  
  buffer = (uint8_t*)av_malloc(num_bytes * sizeof(uint8_t));
  
  
  
  AVFrame* vid_frame = NULL;
  
  vid_frame = av_frame_alloc();
  
  AVFrame* conv_frame = NULL;
  
  conv_frame = av_frame_alloc();
  
  
  
  av_image_fill_arrays(conv_frame->data, conv_frame->linesize, buffer, 
  
                       out_format, width, height, 1);
  
  
  
  struct SwsContext *sws_ctx = NULL;
  
  sws_ctx = sws_getContext(width, height, cdc_ctx->pix_fmt,
  
                           width, height, out_format,
  
                           SWS_BILINEAR, NULL,NULL,NULL);
  
  
  
  int frame_num = 0;
  
  AVPacket vid_pckt;
  
  while (av_read_frame(fmt_ctx, &vid_pckt) >=0) {
  
      ret = avcodec_send_packet(cdc_ctx, &vid_pckt);
  
      if (ret < 0)
  
          break;
  
  
  
      ret = avcodec_receive_frame(cdc_ctx, vid_frame);
  
      if (ret < 0 && ret != AVERROR(EAGAIN) && ret != AVERROR_EOF)
  
          break;
  
      if (ret >= 0) {
  
          // convert image from native format to planar GBR
  
          sws_scale(sws_ctx, vid_frame->data, 
  
                    vid_frame->linesize, 0, vid_frame->height, 
  
                    conv_frame->data, conv_frame->linesize);
  
  
  
          unsigned char* r_ptr = output_arr + 
  
              (height * width * sizeof(unsigned char) * 3 * frame_num);
  
          unsigned char* g_ptr = r_ptr + (height * width * sizeof(unsigned char));
  
          unsigned char* b_ptr = g_ptr + (height * width * sizeof(unsigned char));
  
          unsigned int pxl_i = 0;
  
  
  
          for (unsigned int r = 0; r < height; ++r) {
  
              uint8_t* avframe_r = conv_frame->data[0] + r*conv_frame->linesize[0];
  
              for (unsigned int c = 0; c < width; ++c) {
  
                  r_ptr[pxl_i] = avframe_r[0];
  
                  g_ptr[pxl_i]   = avframe_r[1];
  
                  b_ptr[pxl_i]   = avframe_r[2];
  
                  avframe_r += 3;
  
                  ++pxl_i;
  
              }
  
          }
  
  
  
          ++frame_num;
  
  
  
          if (frame_num >= read_nframes)
  
              break;
  
      }
  
  }
  
  
  
  ...

  In my experience around two-thirds of the pixel values are different, each by +-1 (in a range of [0,255]). I am wondering is it due to some decoding scheme FFmpeg uses for reading JPEG frames ? I tried encoding and decoding png frames, and it works perfectly fine.

  In short my goal is to get the same pixel by pixel values for each JPEG frame as I would I have gotten if I was reading the JPEG images directly. Here is the stand-alone code I used. It includes cmake files to build code, and a couple of jpeg frames with the converted avi file to test this problem. (give —filetype png to test the png decoding).

• How to stream H.264 bitstream to browser

  21 janvier 2019, par BobtheMagicMoose

  This is a followup to https://raspberrypi.stackexchange.com/questions/93254/stream-usb-webcam-with-audio?noredirect=1#comment150507_93254

  I, like many other brave tinkerers before me, thought it would be a simple task to take an old USB camera (c920) can pair it with a raspberry pi to make a network streaming device (e.g., baby monitor). As those that have gone before me, I have now realized (after two days of tearing my hair out), that this is an extremely complicated task.

  Problem statement : I have a raspberry pi zero and a c920 webcam. I want to use the H.264 bitstream from the webcam and serve it on the pi without transcoding it (the feeble processor would really struggle). I want to combine the video stream with its audio and send it over to a browser (phone, tablet, pc - something HTML5 without NAPI).

  My current strategy is to do the following :

  ffmpeg -re -f s16le -i /dev/zero -f v4l2 -thread_queue_size 512 -codec:v h264 -s 1920x1080 -i /dev/video0 -codec:v copy -acodec aac -ab 128k -g 50 http://localhost:8090/camera.ffm (this is with dummy audio - I figured I would add audio later)

  Followed by sudo ffserver -d -f /etc/ffserver.conf to received the feed and broadcast it as a stream. This is the ffserver.conf file :

  `HTTPPort 8090
  
  HTTPBindAddress 0.0.0.0
  
  MaxHTTPConnections 2000
  
  MaxClients 1000
  
  MaxBandwidth 100000
  
  CustomLog -
  
  <feed>
  
    File /tmp/streamwebm.ffm
  
    FileMaxSize 50M
  
    ACL allow localhost
  
    ACL allow 128.199.149.46
  
    #ACL allow 127.0.0.1
  
    ACL allow 192.168.0.0 192.168.0.255
  
  </feed>
  
  <stream stream="stream">
  
  Format webm
  
  
  
  # Video Settings
  
  VideoFrameRate 30
  
  VideoSize 1920x1080
  
  
  
  # Audio settings
  
  AudioCodec libvorbis
  
  AudioSampleRate 48000
  
  AVOptionAudio flags +global_header
  
  
  
  MaxTime 0
  
  AVOptionVideo me_range 16
  
  AVOptionVideo qdiff 4
  
  AVOptionVideo qmin 4
  
  AVOptionVideo qmax 40
  
  #AVOptionVideo good
  
  AVOptionVideo flags +global_header
  
  
  
  # Streaming settings
  
  PreRoll 10
  
  StartSendOnKey
  
  
  
  Metadata author "author"
  
  Metadata copyright "copyright"
  
  Metadata title "Web app name"
  
  Metadata comment "comment"
  
  </stream>

  My basic html is<video>  <source src="http://localhost:8090/stream"> </source></video>

  The stream however, doesn’t work (the browser won’t connect) and I get the following :
  

  And the browser on the client says (failed) NET::ERR_CONNECTION_REFUSED

  Thoughts :
   Begin stream simple mp4 with ffserver explains that ffserver can’t stream .mp4 because of headers or something. This is why I am using webm (which doesn’t support h.264 I believe and is causing the really slow performance converting to vp9). I’m not concerned about CPU usage at the moment, just want to get an image to appear on the browser !

  • I hear one issue deals with ’chunking’ - that the camera h.264 is a bitstream but h.264 streams for html5 should be chunked. Not sure how that would work.

  • I have tried VLC for some things (RTP) but haven’t have success.

  • Most resources (SE and other sites) are from 2010-2015 and it seems as thought v4l2 and other things have developed since then.

  • As my problem is most likely general ignorance of the subject matter, I would appreciate any answers that provide some general understanding as to the theory behind different techniques. I know this makes the question more of a call for opinion and less appropriate for SE, but I’m fixing to throw my computer out the window (you know the feeling).

  Thank you !

• How do I make my discord bot play music by using youtubedl's search function instead of url ? (Python)

  28 septembre 2021, par PypypieYum

  I want it to search for the video and play it, how can i change the following code to achieve that ? Every time I use the ytsearch function in ytdl, I notice that it only searches for the first word of the title and download it, however, it causes error later on and do nothing.

  


  @commands.command()
    async def play(self, ctx, url):
        if ctx.author.voice is None:
            await ctx.send("You are not in a voice channel!")
        voice_channel = ctx.author.voice.channel
        if ctx.voice_client is None:
            await voice_channel.connect()
        else:
            await ctx.voice_client.move_to(voice_channel)

        ctx.voice_client.stop()
        FFMPEG_OPTIONS = {'before_options': '-reconnect 1 -reconnect_streamed 1 -reconnect_delay_max 5', 'options': '-vn'}
        YDL_OPTIONS = {'format':"bestaudio", 'default_search':"ytsearch"}
        vc = ctx.voice_client

        with youtube_dl.YoutubeDL(YDL_OPTIONS) as ydl:
            info = ydl.extract_info(url, download=False)
            if 'entries' in info:
              url2 = info["entries"][0]["formats"][0]
            elif 'formats' in info:
              url2 = info["formats"][0]['url']
            source = await discord.FFmpegOpusAudio.from_probe(url2, **FFMPEG_OPTIONS)
            vc.play(source)


  


  And this is the error message :

  


  Ignoring exception in command play:
Traceback (most recent call last):
  File "/opt/virtualenvs/python3/lib/python3.8/site-packages/discord/ext/commands/core.py", line 85, in wrapped
    ret = await coro(*args, **kwargs)
  File "/home/runner/HandmadeLivelyLines/music.py", line 44, in play
    source = await discord.FFmpegOpusAudio.from_probe(url2, **FFMPEG_OPTIONS)
  File "/opt/virtualenvs/python3/lib/python3.8/site-packages/discord/player.py", line 387, in from_probe
    return cls(source, bitrate=bitrate, codec=codec, **kwargs)
  File "/opt/virtualenvs/python3/lib/python3.8/site-packages/discord/player.py", line 324, in __init__
    super().__init__(source, executable=executable, args=args, **subprocess_kwargs)
  File "/opt/virtualenvs/python3/lib/python3.8/site-packages/discord/player.py", line 138, in __init__
    self._process = self._spawn_process(args, **kwargs)
  File "/opt/virtualenvs/python3/lib/python3.8/site-packages/discord/player.py", line 144, in _spawn_process
    process = subprocess.Popen(args, creationflags=CREATE_NO_WINDOW, **subprocess_kwargs)
  File "/usr/lib/python3.8/subprocess.py", line 858, in __init__
    self._execute_child(args, executable, preexec_fn, close_fds,
  File "/usr/lib/python3.8/subprocess.py", line 1639, in _execute_child
    self.pid = _posixsubprocess.fork_exec(
TypeError: expected str, bytes or os.PathLike object, not dict

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/opt/virtualenvs/python3/lib/python3.8/site-packages/discord/ext/commands/bot.py", line 939, in invoke
    await ctx.command.invoke(ctx)
  File "/opt/virtualenvs/python3/lib/python3.8/site-packages/discord/ext/commands/core.py", line 863, in invoke
    await injected(*ctx.args, **ctx.kwargs)
  File "/opt/virtualenvs/python3/lib/python3.8/site-packages/discord/ext/commands/core.py", line 94, in wrapped
    raise CommandInvokeError(exc) from exc
discord.ext.commands.errors.CommandInvokeError: Command raised an exception: TypeError: expected str, bytes or os.PathLike object, not dict


  


  Thanks.