ffmpeg sws_scale从YUV420P到RGB24的图像失真

Question

当尝试使用sws_scale将YUV420p转换为RGB24时，我得到了扭曲的图像。

码：

ret = avcodec_decode_video2(video_dec_ctx, frame, got_frame, &pkt);
if (ret < 0) {
    fprintf(stderr, "Error decoding video frame\n");
    return ret;
}
if (*got_frame) 
{
    printf("video_frame%s n:%d coded_n:%d pts:%s\n",
               cached ? "(cached)" : "",
               video_frame_count++, frame->coded_picture_number,
               "#"/*av_ts2timestr(frame->pts, &video_dec_ctx->time_base)*/);
    /* copy decoded frame to destination buffer:
     * this is required since rawvideo expects non aligned data */
    av_image_copy(video_dst_data, video_dst_linesize,
                  (const uint8_t **)(frame->data), frame->linesize,
                  video_dec_ctx->pix_fmt, video_dec_ctx->width, video_dec_ctx->height);
    /* write to rawvideo file */
    fwrite(video_dst_data[0], 1, video_dst_bufsize, video_dst_file);

    AVPicture pic;
    avpicture_alloc( &pic, AV_PIX_FMT_RGB24, frame->width, frame->height);
    SwsContext *ctxt = sws_getContext(frame->width, frame->height, static_cast<AVPixelFormat>(frame->format),
        frame->width, frame->height, AV_PIX_FMT_RGB24, SWS_BILINEAR, NULL, NULL, NULL);
    if ( NULL == ctxt )
    {
       //Log("failed to get sws context");
    }

    if ( 0 < sws_scale(ctxt, frame->data, frame->linesize, 0, frame->height, pic.data, pic.linesize))
    {
        char szPic[256] = { 0 };
        sprintf( szPic, "decoded/%d.bmp", video_frame_count );
        FILE *pf = fopen(szPic,"w");
        if ( NULL != pf )
        {
            BITMAPFILEHEADER bmpFileHeader = {0};
            bmpFileHeader.bfReserved1 = 0;
            bmpFileHeader.bfReserved2 = 0;
            bmpFileHeader.bfType = 0x4D42;
            bmpFileHeader.bfSize = sizeof(bmpFileHeader) + sizeof(BITMAPINFOHEADER) + pic.linesize[0] * frame->height;
            bmpFileHeader.bfOffBits = sizeof(bmpFileHeader) + sizeof(BITMAPINFOHEADER);
            BITMAPINFOHEADER bmiHeader = { 0 };
            bmiHeader.biSize = sizeof(BITMAPINFOHEADER);
            bmiHeader.biWidth = frame->width;
            bmiHeader.biHeight = 0 - frame->height;
            bmiHeader.biPlanes = 1;
            bmiHeader.biBitCount = 24;
            bmiHeader.biCompression = BI_RGB;
            bmiHeader.biSizeImage = pic.linesize[0] * frame->height;
            bmiHeader.biXPelsPerMeter = 0;
            bmiHeader.biYPelsPerMeter = 0;
            bmiHeader.biClrUsed = 0;
            bmiHeader.biClrImportant = 0;
            fwrite( &bmpFileHeader, 1, sizeof(bmpFileHeader), pf );
            fwrite( &bmiHeader, 1, sizeof(bmiHeader), pf );
            fwrite( pic.data[0], 1, pic.linesize[0] * frame->height, pf );
            fclose( pf );
        }
    }
    // pic.data[0] now contains the image data in RGB format (3 bytes)
    // and pic.linesize[0] is the pitch of the data (ie. size of a row in memory, which can be larger than width*sizeof(pixel))


    avpicture_free(&pic);
    sws_freeContext(ctxt);
}

上面只解码帧然后将其转换为RGB24，然后写一个位图。 像这样的原始视频帧， 但转换后的图像， 是否缺少一些代码或一些代码是错误的？

提前致谢。

Answer 1

 fwrite( pic.data[0], 1, pic.linesize[0] * frame->height, pf ); 

对于例如1280x720的图像，线条尺寸通常较大，例如1312，因此如果您编写线条尺寸*高度，则您将编写比图像尺寸更多的数据。 你想写（在一个循环中）宽度像素偏移lineize字节：

uint8_t *ptr = pic.data[0];
for (int y = 0; y < frame->height; y++) {
    fwrite(ptr, 1, frame->width, pf);
    ptr += pic.linesize[0];
}

然后它应该正常工作。

Answer 2

也许这些代码可以帮助你。 这些作品很好。

                int got_frame = 0;
                auto len = avcodec_decode_video2(m_avCodecContext
                    , m_avFrame
                    , &got_frame
                    , &avpkt);
                if (len < 0)
                {
                    return;
                }
                if (got_frame /*&& !silentMode*/)
                {
                    //if (videoRenderer != nullptr)
                    {
                        if (frameSize == NULL)
                        {
                            return;
                        }
                        uint8_t *dst_data[4];
                        int dst_linesize[4];
                        int dst_w, dst_h;

                        int ret = 0;
                        if (1)// avcodec_alloc_frame()
                        {


                            auto stride = m_avFrame->linesize;
                            auto scan0 = m_avFrame->data;

                            SwsContext *scaleContext = sws_getContext(m_avCodecContext->width
                                , m_avCodecContext->height
                                , m_avCodecContext->pix_fmt
                                , m_avCodecContext->width
                                , m_avCodecContext->height
                                , PixelFormat::PIX_FMT_BGR24
                                , SWS_FAST_BILINEAR, NULL, NULL, NULL);
                            if (scaleContext == NULL)
                            {
                                //TODO: log error
                                return;
                            }
                            try
                            {
                                //*vb->signal = 1;
                                ret = avpicture_alloc(&m_dst_picture
                                    , PixelFormat::PIX_FMT_BGR24
                                    , m_avCodecContext->width
                                    , m_avCodecContext->height);
                                //                      AVFrame *picture_RGB;
                                //                      uint8_t *bufferRGB;
                                //                      picture_RGB = avcodec_alloc_frame();
                                //                      bufferRGB = (uint8_t*)malloc(720*576*(24/8)/*avpicture_get_size(PIX_FMT_RGB24, 720, 576)*/);
                                //                      avpicture_fill((AVPicture *)picture_RGB, bufferRGB, PIX_FMT_RGB24, 720, 576);
                                if (ret < 0)
                                {
                                    return;
                                }
                                int retScale = sws_scale(scaleContext
                                    , scan0
                                    , stride
                                    , 0
                                    , m_avCodecContext->height
                                    , m_dst_picture.data //picture_RGB->data
                                    , m_dst_picture.linesize  //picture_RGB->linesize
                                    );
                                if (1)
                                {
                                    HWND hwnd = m_pParent->GetSafeHwnd();
                                    SetFocus(hwnd);
                                    CRect rc;
                                    m_pParent->GetClientRect(rc);
                                    CDC *cdc = m_pParent->GetDC();
                                    char* bitmap = (char*)m_dst_picture.data[0];
                                    //                          static unsigned int i = 0;
                                    //                          bmp_save(bitmap, m_avCodecContext->width, m_avCodecContext->height, i++);
                                    BITMAPINFO bmpinfo;
                                    bmpinfo.bmiHeader.biSize = sizeof(BITMAPINFOHEADER);
                                    bmpinfo.bmiHeader.biWidth = m_avCodecContext->width;
                                    bmpinfo.bmiHeader.biHeight = -m_avCodecContext->height;
                                    bmpinfo.bmiHeader.biPlanes = 1;
                                    bmpinfo.bmiHeader.biBitCount = 24;
                                    bmpinfo.bmiHeader.biCompression = BI_RGB;
                                    bmpinfo.bmiHeader.biSizeImage =
                                        m_avCodecContext->width * m_avCodecContext->height * (24 / 8);
                                    bmpinfo.bmiHeader.biXPelsPerMeter = 100;
                                    bmpinfo.bmiHeader.biYPelsPerMeter = 100;
                                    bmpinfo.bmiHeader.biClrUsed = 0;
                                    bmpinfo.bmiHeader.biClrImportant = 0;
                                    HBITMAP hBitmap = CreateDIBitmap(cdc->GetSafeHdc(), &bmpinfo.bmiHeader, CBM_INIT, bitmap, &bmpinfo/*bi*/, DIB_RGB_COLORS);
                                    DrawBitmap(cdc, hBitmap, m_pParent);
                                    ::DeleteObject(hBitmap);
                                    ::DeleteObject(cdc->GetSafeHdc());
                                }
                                avpicture_free(&m_dst_picture);
                                sws_freeContext(scaleContext);
                            }
                            catch (int e)
                            {
                                sws_freeContext(scaleContext);
                            }
                        }
                    }
                }





    void DrawBitmap(CDC *pDC, HBITMAP hbitmap,CWnd *wnd)
    {
        CBitmap *pBitmap = CBitmap::FromHandle(hbitmap);
        BITMAP bm;
        pBitmap -> GetBitmap(&bm);

        CDC MemDC;
        MemDC.CreateCompatibleDC(pDC);
        HGDIOBJ gob= MemDC.SelectObject(pBitmap);
        CRect rc;
        wnd->GetClientRect(rc);
        pDC->SetStretchBltMode( COLORONCOLOR);
        pDC->StretchBlt(0, 0,rc.Width(),rc.Height() , &MemDC, 0, 0, bm.bmWidth, bm.bmHeight, SRCCOPY);
        MemDC.SelectObject(gob);
        DeleteObject(pBitmap);
        DeleteObject(MemDC);
        DeleteObject(&bm);
        ReleaseDC(wnd->GetSafeHwnd(), MemDC);
    }



void initDecoder()
{
    m_avCodecContext = avcodec_alloc_context();
    if (!m_avCodecContext)
    {
        //failed to allocate codec context
        Cleanup();
        return;
    }

    m_avCodecContext->flags = 0;

    uint8_t startCode[] = { 0x00, 0x00, 0x01 };
    //////////////////////////////////////////////////////////////////////////
    //I thought for play live video you can comment these lines. 
    if (m_sProps != NULL)
    {
        //              USES_CONVERSION;
        //              ::MessageBox(NULL, A2T(sprops), TEXT("sprops"), MB_OK);
        unsigned spropCount;
        SPropRecord* spropRecords = parseSPropParameterSets(m_sProps, spropCount);
        try
        {
            for (unsigned i = 0; i < spropCount; ++i)
            {
                AddExtraData(startCode, sizeof(startCode));
                AddExtraData(spropRecords[i].sPropBytes, spropRecords[i].sPropLength);
            }
        }
        catch (void*)
        {
            //extradata exceeds size limit
            delete[] spropRecords;
            Cleanup();
            return;
        }
        delete[] spropRecords;

        m_avCodecContext->extradata = extraDataBuffer;
        m_avCodecContext->extradata_size = extraDataSize;
    }
    AddExtraData(startCode, sizeof(startCode));
    bInitEx = true;

    av_register_all();
    avcodec_register_all();
    m_codecId = CODEC_ID_H264;
    m_avCodec = avcodec_find_decoder(m_codecId);
    if (m_avCodec == NULL)
    {
        return;
    }

    if (avcodec_open(m_avCodecContext, m_avCodec) < 0)
    {
        //failed to open codec
        Cleanup();
        return;
    }


    if (m_avCodecContext->codec_id == CODEC_ID_H264)
    {
        m_avCodecContext->flags2 |= CODEC_FLAG2_CHUNKS;
        //avCodecContext->flags2 |= CODEC_FLAG2_SHOW_ALL;
    }
    m_avFrame = avcodec_alloc_frame();
    if (!m_avFrame)
    {
        //failed to allocate frame
        Cleanup();
        return;
    }
}