Sur d’autres sites (10212)

• FFMPEG : TS video copied to MP4, missing 3 first frames [closed]

  21 août 2023, par Vasilis Lemonidis

  Running :

  


  ffmpeg -i test.ts -fflags +genpts -c copy -y test.mp4


  


  for this test.ts, which has 30 frames, readable by opencv, I end up with 28 frames, out of which 27 are readable by opencv. More specifically :

  


  ffprobe -v error -select_streams v:0 -count_packets  -show_entries stream=nb_read_packets -of csv=p=0 tmp.ts 


  


  returns 30.

  


  ffprobe -v error -select_streams v:0 -count_packets     -show_entries stream=nb_read_packets -of csv=p=0 tmp.mp4


  


  returns 28.

  


  Using OpenCV in that manner

  


  cap = cv2.VideoCapture(tmp_path)
readMat = []
while cap.isOpened():
        ret, frame = cap.read()
        if not ret:
            break
        readMat.append(frame)


  


  I get for the ts file 30 frames, while for the mp4 27 frames.

  


  Could someone explain why the discrepancies ? I get no error during the transformation from ts to mp4 :

  


  ffmpeg version N-111746-gd53acf452f Copyright (c) 2000-2023 the FFmpeg developers
  built with gcc 11.3.0 (GCC)
  configuration: --ld=g++ --bindir=/bin --extra-libs='-lpthread -lm' --pkg-config-flags=--static --enable-static --enable-gpl --enable-libaom --enable-libass --enable-libfreetype --enable-libmp3lame --enable-libopus --enable-libsvtav1 --enable-libdav1d --enable-libvorbis --enable-libvpx --enable-libx264 --enable-libx265 --enable-nonfree --enable-cuda-nvcc --enable-cuvid --enable-nvenc --enable-libnpp 
  libavutil      58. 16.101 / 58. 16.101
  libavcodec     60. 23.100 / 60. 23.100
  libavformat    60. 10.100 / 60. 10.100
  libavdevice    60.  2.101 / 60.  2.101
  libavfilter     9. 10.100 /  9. 10.100
  libswscale      7.  3.100 /  7.  3.100
  libswresample   4. 11.100 /  4. 11.100
  libpostproc    57.  2.100 / 57.  2.100
[mpegts @ 0x4237240] DTS discontinuity in stream 0: packet 5 with DTS 306003, packet 6 with DTS 396001
Input #0, mpegts, from 'tmp.ts':
  Duration: 00:00:21.33, start: 3.400000, bitrate: 15 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), 300x300, 1 fps, 3 tbr, 90k tbn
Output #0, mp4, to 'test.mp4':
  Metadata:
    encoder         : Lavf60.10.100
  Stream #0:0: Video: h264 (High) (avc1 / 0x31637661), yuv420p(progressive), 300x300, q=2-31, 1 fps, 3 tbr, 90k tbn
Stream mapping:
  Stream #0:0 -> #0:0 (copy)
Press [q] to stop, [?] for help
[out#0/mp4 @ 0x423e280] video:25kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 4.192123%
frame=   30 fps=0.0 q=-1.0 Lsize=      26kB time=00:00:21.00 bitrate=  10.3kbits/s speed=1e+04x 


  


  Additional information

  


  The origin of the video I am processing comes from a continuous stitching operation of still images ts videos, produced by this class update method :

  


  import cv2
import os
import subprocess
from tempfile import NamedTemporaryFile
class VideoUpdater:
    def __init__(
        self, video_path: str, framerate: int, timePerFrame: Optional[int] = None
    ):
        """
        Video updater takes in a video path, and updates it using a supplied frame, based on a given framerate.
        Args:
            video_path: str: Specify the path to the video file
            framerate: int: Set the frame rate of the video
        """
        if not video_path.endswith(".mp4"):
            LOGGER.warning(
                f"File type {os.path.splitext(video_path)[1]} not supported for streaming, switching to ts"
            )
            video_path = os.path.splitext(video_path)[0] + ".mp4"

        self._ps = None
        self.env = {
            
        }
        self.ffmpeg = "/usr/bin/ffmpeg "

        self.video_path = video_path
        self.ts_path = video_path.replace(".mp4", ".ts")
        self.tfile = None
        self.framerate = framerate
        self._video = None
        self.last_frame = None
        self.curr_frame = None


    def update(self, frame: np.ndarray):
        if len(frame.shape) == 2:
            frame = cv2.cvtColor(frame, cv2.COLOR_GRAY2BGR)
        else:
            frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
        self.writeFrame(frame)

    def writeFrame(self, frame: np.ndarray):
        """
        The writeFrame function takes a frame and writes it to the video file.
        Args:
            frame: np.ndarray: Write the frame to a temporary file
        """


        tImLFrame = NamedTemporaryFile(suffix=".png")
        tVidLFrame = NamedTemporaryFile(suffix=".ts")

        cv2.imwrite(tImLFrame.name, frame)
        ps = subprocess.Popen(
            self.ffmpeg
            + rf"-loop 1 -r {self.framerate} -i {tImLFrame.name} -t {self.framerate} -vcodec libx264 -pix_fmt yuv420p -y {tVidLFrame.name}",
            env=self.env,
            shell=True,
            stdout=subprocess.PIPE,
            stderr=subprocess.PIPE,
        )
        ps.communicate()
        if os.path.isfile(self.ts_path):
            # this does not work to watch, as timestamps are not updated
            ps = subprocess.Popen(
                self.ffmpeg
                + rf'-i "concat:{self.ts_path}|{tVidLFrame.name}" -c copy -y {self.ts_path.replace(".ts", ".bak.ts")}',
                env=self.env,
                shell=True,
                stdout=subprocess.PIPE,
                stderr=subprocess.PIPE,
            )
            ps.communicate()
            shutil.move(self.ts_path.replace(".ts", ".bak.ts"), self.ts_path)

        else:
            shutil.copyfile(tVidLFrame.name, self.ts_path)
        # fixing timestamps, we dont have to wait for this operation
        ps = subprocess.Popen(
            self.ffmpeg
            + rf"-i {self.ts_path} -fflags +genpts -c copy -y {self.video_path}",
            env=self.env,
            shell=True,
            # stdout=subprocess.PIPE,
            # stderr=subprocess.PIPE,
        )
        tImLFrame.close()
        tVidLFrame.close()


  


• Android h264 decode non-existing PPS 0 referenced

  8 juin 2023, par nmxprime

  In Android JNI, using ffmpeg with libx264 use below codes to encode and decode raw rgb data !. I should use swscale to convert rgb565 to yuv420p as required by H.264. But not clear about this conversion.Please help, where i am wrong, with regard the log i get !

  



  Code for Encoding

  



  codecinit()- called once(JNI wrapper function)

  



  int Java_com_my_package_codecinit (JNIEnv *env, jobject thiz) {
avcodec_register_all();
codec = avcodec_find_encoder(AV_CODEC_ID_H264);//AV_CODEC_ID_MPEG1VIDEO);
if(codec->id == AV_CODEC_ID_H264)
    __android_log_write(ANDROID_LOG_ERROR, "set","h264_encoder");

if (!codec) {
    fprintf(stderr, "codec not found\n");
    __android_log_write(ANDROID_LOG_ERROR, "codec", "not found");

}
    __android_log_write(ANDROID_LOG_ERROR, "codec", "alloc-contest3");
c= avcodec_alloc_context3(codec);
if(c == NULL)
    __android_log_write(ANDROID_LOG_ERROR, "avcodec","context-null");

picture= av_frame_alloc();

if(picture == NULL)
    __android_log_write(ANDROID_LOG_ERROR, "picture","context-null");

c->bit_rate = 400000;
c->height = 800;
c->time_base= (AVRational){1,25};
c->gop_size = 10; 
c->max_b_frames=1;
c->pix_fmt = AV_PIX_FMT_YUV420P;
outbuf_size = 768000;
c->width = 480;

size = (c->width * c->height);

if (avcodec_open2(c, codec,NULL) < 0) {

__android_log_write(ANDROID_LOG_ERROR, "codec", "could not open");


}

ret = av_image_alloc(picture->data, picture->linesize, c->width, c->height,
                     c->pix_fmt, 32);
if (ret < 0) {
        __android_log_write(ANDROID_LOG_ERROR, "image","alloc-failed");
    fprintf(stderr, "could not alloc raw picture buffer\n");

}

picture->format = c->pix_fmt;
picture->width  = c->width;
picture->height = c->height;
return 0;

}


  



  encodeframe()-called in a while loop

  



  int Java_com_my_package_encodeframe (JNIEnv *env, jobject thiz,jbyteArray buffer) {
jbyte *temp= (*env)->GetByteArrayElements(env, buffer, 0);
Output = (char *)temp;
const uint8_t * const inData[1] = { Output }; 
const int inLinesize[1] = { 2*c->width };

//swscale should implement here

    av_init_packet(&pkt);
    pkt.data = NULL;    // packet data will be allocated by the encoder
    pkt.size = 0;

    fflush(stdout);
picture->data[0] = Output;
ret = avcodec_encode_video2(c, &pkt, picture,&got_output);

    fprintf(stderr,"ret = %d, got-out = %d \n",ret,got_output);
     if (ret < 0) {
                __android_log_write(ANDROID_LOG_ERROR, "error","encoding");
        if(got_output > 0)
        __android_log_write(ANDROID_LOG_ERROR, "got_output","is non-zero");

    }

    if (got_output) {
        fprintf(stderr,"encoding frame %3d (size=%5d): (ret=%d)\n", 1, pkt.size,ret);
        fprintf(stderr,"before caling decode");
        decode_inline(&pkt); //function that decodes right after the encode
        fprintf(stderr,"after caling decode");


        av_free_packet(&pkt);
    }


fprintf(stderr,"y val: %d \n",y);


(*env)->ReleaseByteArrayElements(env, buffer, Output, 0);
return ((ret));
}


  



  decode_inline() function

  



  decode_inline(AVPacket *avpkt){
AVCodec *codec;
AVCodecContext *c = NULL;
int frame, got_picture, len = -1,temp=0;

AVFrame *rawFrame, *rgbFrame;
uint8_t inbuf[INBUF_SIZE + FF_INPUT_BUFFER_PADDING_SIZE];
char buf[1024];
char rawBuf[768000],rgbBuf[768000];

struct SwsContext *sws_ctx;

memset(inbuf + INBUF_SIZE, 0, FF_INPUT_BUFFER_PADDING_SIZE);
avcodec_register_all();

c= avcodec_alloc_context3(codec);
if(c == NULL)
    __android_log_write(ANDROID_LOG_ERROR, "avcodec","context-null");

codec = avcodec_find_decoder(AV_CODEC_ID_H264);
if (!codec) {
    fprintf(stderr, "codec not found\n");
    fprintf(stderr, "codec = %p \n", codec);
    }
c->pix_fmt = AV_PIX_FMT_YUV420P;
c->width = 480;
c->height = 800;

rawFrame = av_frame_alloc();
rgbFrame = av_frame_alloc();

if (avcodec_open2(c, codec, NULL) < 0) {
    fprintf(stderr, "could not open codec\n");
    exit(1);
    }
sws_ctx = sws_getContext(c->width, c->height,/*PIX_FMT_RGB565BE*/
            PIX_FMT_YUV420P, c->width, c->height, AV_PIX_FMT_RGB565/*PIX_FMT_YUV420P*/,
            SWS_BILINEAR, NULL, NULL, NULL);


frame = 0;

unsigned short *decodedpixels = &rawBuf;
rawFrame->data[0] = &rawBuf;
rgbFrame->data[0] = &rgbBuf;

fprintf(stderr,"size of avpkt %d \n",avpkt->size);
temp = avpkt->size;
while (temp > 0) {
        len = avcodec_decode_video2(c, rawFrame, &got_picture, avpkt);

        if (len < 0) {
            fprintf(stderr, "Error while decoding frame %d\n", frame);
            exit(1);
            }
        temp -= len;
        avpkt->data += len;

        if (got_picture) {
            printf("saving frame %3d\n", frame);
            fflush(stdout);
        //TODO  
        //memcpy(decodedpixels,rawFrame->data[0],rawFrame->linesize[0]); 
        //  decodedpixels +=rawFrame->linesize[0];

            frame++;
            }

        }

avcodec_close(c);
av_free(c);
//free(rawBuf);
//free(rgbBuf);
av_frame_free(&rawFrame);
av_frame_free(&rgbFrame);


  



  }

  



  The log i get

  



  For the decode_inline() function :

  



  ---

  



  01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] non-existing PPS 0 referenced
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] decode_slice_header error
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] non-existing PPS 0 referenced
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] decode_slice_header error
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] non-existing PPS 0 referenced
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] decode_slice_header error
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] non-existing PPS 0 referenced
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] decode_slice_header error
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] non-existing PPS 0 referenced
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] decode_slice_header error
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] non-existing PPS 0 referenced
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] decode_slice_header error
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] non-existing PPS 0 referenced
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] decode_slice_header error
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] non-existing PPS 0 referenced
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] decode_slice_header error
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] non-existing PPS 0 referenced
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] decode_slice_header error
01-02 14:50:50.160: I/stderr(3407): [h264 @ 0x8db540] Invalid mix of idr and non-idr slices
01-02 14:50:50.160: I/stderr(3407): Error while decoding frame 0


  



  Edit : Changing GOP value :

  



  If i change c->gop_size = 3; as expected it emits one I frame every three frames. The non-existing PPS 0 referenced message is not there for in every third execution, but all other have this message

  


• How to publish selfmade stream with ffmpeg and c++ to rtmp server ?

  10 janvier 2024, par rLino

  Have a nice day to you, people !

  



  I am writing an application for Windows that will capture the screen and send the stream to Wowza server by rtmp (for broadcasting). My application use ffmpeg and Qt.
I capture the screen with WinApi, convert a buffer to YUV444(because it's simplest) and encode frame as described at the file decoding_encoding.c (from FFmpeg examples) :

  



  ///////////////////////////
//Encoder initialization
///////////////////////////
avcodec_register_all();
codec=avcodec_find_encoder(AV_CODEC_ID_H264);
c = avcodec_alloc_context3(codec);
c->width=scr_width;
c->height=scr_height;
c->bit_rate = 400000;
int base_num=1;
int base_den=1;//for one frame per second
c->time_base= (AVRational){base_num,base_den};
c->gop_size = 10;
c->max_b_frames=1;
c->pix_fmt = AV_PIX_FMT_YUV444P;
av_opt_set(c->priv_data, "preset", "slow", 0);

frame = avcodec_alloc_frame();
frame->format = c->pix_fmt;
frame->width  = c->width;
frame->height = c->height;

for(int counter=0;counter<10;counter++)
{
///////////////////////////
//Capturing Screen
///////////////////////////
    GetCapScr(shotbuf,scr_width,scr_height);//result: shotbuf is filled by screendata from HBITMAP
///////////////////////////
//Convert buffer to YUV444 (standard formula)
//It's handmade function because of problems with prepare buffer to swscale from HBITMAP
///////////////////////////
    RGBtoYUV(shotbuf,frame->linesize,frame->data,scr_width,scr_height);//result in frame->data
///////////////////////////
//Encode Screenshot
///////////////////////////
    av_init_packet(&pkt);
    pkt.data = NULL;    // packet data will be allocated by the encoder
    pkt.size = 0;
    frame->pts = counter;
    avcodec_encode_video2(c, &pkt, frame, &got_output);
    if (got_output) 
    {
        //I think that  sending packet by rtmp  must be here!
        av_free_packet(&pkt);             

    }

}
// Get the delayed frames
for (int got_output = 1,i=0; got_output; i++)
{
    ret = avcodec_encode_video2(c, &pkt, NULL, &got_output);
    if (ret < 0)
        {
            fprintf(stderr, "Error encoding frame\n");
            exit(1);
        }
        if (got_output)
        {
        //I think that  sending packet by rtmp  must be here!
        av_free_packet(&pkt);      
        }
}

///////////////////////////
//Deinitialize encoder
///////////////////////////
avcodec_close(c);
av_free(c);
av_freep(&frame->data[0]);
avcodec_free_frame(&frame);


  



  I need to send video stream generated by this code to RTMP server.
In other words, I need c++/c analog for this command :

  



  ffmpeg -re -i "sample.h264" -f flv rtmp://sample.url.com/screen/test_stream


  



  It's useful, but I don't want to save stream to file, I want to use ffmpeg libraries for realtime encoding screen capture and sending encoded frames to RTMP server inside my own application.
Please give me a little example how to initialize AVFormatContext properly and to send my encoded video AVPackets to server.

  



  Thanks.