如何正确使用OpenH264使用代码示例进行编码？

Question

我有一个图像，想用OpenH264对其进行编码。

到目前为止，这是我从其wiki中获得的代码：

#include <fstream>
#include <iterator>

#include <iostream>
#include <codec_api.h> //standard api for openh264

//additional libaries used by sample code
#include <codec_app_def.h>
#include <codec_def.h>
#include <codec_ver.h>
#include <assert.h>
#include <vector>
#include <cstring>
int main()
{
  //parameter values
  int width = 1920;
  int height = 1080;
  int framerate = 60;
  int bitrate = 5000000;
  int total_num = 500; //what does this value do?
  //end parameter values

  //Read in the File from bmp
  std::vector<char> buf; //to store the image information

  std::basic_ifstream<char> file("/home/megamol/Git/h264_sample/build/test.bmp", std::ios::binary); //opens bitstream to source
  buf = std::vector<char>((std::istreambuf_iterator<char>(file)), std::istreambuf_iterator<char>()); // reads in data to the vector

  std::cout << "sizeof buf: " << buf.size() << std::endl;

  //Step 1: set up Encoder

  ISVCEncoder* encoder_;    //declaration of encoder pointer
  int rv = WelsCreateSVCEncoder (&encoder_);

  //Step 2: initialize with basic parameter

  SEncParamBase param;
  memset(&param, 0, sizeof (SEncParamBase));
  param.iUsageType = EUsageType::SCREEN_CONTENT_REAL_TIME;
  param.fMaxFrameRate = framerate;
  param.iPicWidth = width;
  param.iPicHeight = height;
  param.iTargetBitrate = bitrate; //default value of example
  encoder_->Initialize(&param);

  //Step 3: set video format

  int videoFormat = videoFormatI420;
  encoder_->SetOption (ENCODER_OPTION_DATAFORMAT, &videoFormat);

  //Step 4: encocode and store output bitstream
  int frameSize = width * height * 3 / 2;
  buf.resize(frameSize);  

  SFrameBSInfo info;
  std::vector<char> compressedData;

  memset (&info, 0, sizeof (SFrameBSInfo));
  SSourcePicture pic;
  memset (&pic, 0, sizeof (SSourcePicture));
  pic.iPicWidth = width;
  pic.iPicHeight = height;
  pic.iColorFormat = videoFormatI420;
  pic.iStride[0] = pic.iPicWidth;
  pic.iStride[1] = pic.iStride[2] = pic.iPicWidth >> 1;
  pic.pData[0] = reinterpret_cast<unsigned char*>(&buf[0]);
  pic.pData[1] = pic.pData[0] + width * height;
  pic.pData[2] = pic.pData[1] + (width * height >> 2);

   //encodes the frame
   rv = encoder_->EncodeFrame (&pic, &info); // encodes the Frame
   //encoding done encoded Frame should be stored in &info

   //begin decoding block
   ISVCDecoder *pSvcDecoder;
   unsigned char *pBuf= &info;

  return 0;
}

我不完全确定这是否是OpenH264的正确用法，但我也不确定如何正确测试它。

现在该代码示例的文献记载很少。

例如BufferedData buf;是什么？我知道那应该是输入，但是那是什么类型？像我如何将我的test.bmp加载为BufferedData？我认为我没有正确地做到这一点。

我很困惑的另一件事是编码后如何访问输出？在该示例中，它只说//output bitstream，与在任何地方保存此输出无关。我以为输出是info，就像它在codec_api.h头文件中所说的那样：

  /**
  * @brief Encode one frame
  * @param kpSrcPic the pointer to the source luminance plane
  *        chrominance data:
  *        CbData = kpSrc  +  m_iMaxPicWidth * m_iMaxPicHeight;
  *        CrData = CbData + (m_iMaxPicWidth * m_iMaxPicHeight)/4;
  *        the application calling this interface needs to ensure the data validation between the location
  * @param pBsInfo output bit stream
  * @return  0 - success; otherwise -failed;
  */
  virtual int EXTAPI EncodeFrame (const SSourcePicture* kpSrcPic, SFrameBSInfo* pBsInfo) = 0;

但是显然，它仅保存有关输出的信息。我只是对这一切感到困惑。

Answer 1

基于https://github.com/cisco/openh264/blob/master/codec/console/enc/src/welsenc.cpp

#include <codec_api.h>
#include <cassert>
#include <cstring>
#include <vector>
#include <fstream>
#include <iostream>

//Tested with OpenCV 3.3
#include <opencv2/core.hpp>
#include <opencv2/imgcodecs.hpp>
#include <opencv2/highgui.hpp>
#include <opencv2/imgproc.hpp>

using namespace std;
using namespace cv;

int main()
{
    ISVCEncoder *encoder_ = nullptr;
    int rv = WelsCreateSVCEncoder (&encoder_);
    assert (0==rv);
    assert (encoder_ != nullptr);

    int width = 640;
    int height = 480;
    int total_num = 100;

    SEncParamBase param;
    memset (&param, 0, sizeof (SEncParamBase));
    param.iUsageType = CAMERA_VIDEO_REAL_TIME;
    param.fMaxFrameRate = 30;
    param.iPicWidth = width;
    param.iPicHeight = height;
    param.iTargetBitrate = 5000000;
    encoder_->Initialize (&param);

    Mat image = imread("test.jpg", IMREAD_COLOR );
    Mat imageResized, imageYuv, imageYuvMini; 
    resize(image, imageResized, Size(width, height));
    Mat imageYuvCh[3], imageYuvMiniCh[3];
    cvtColor(imageResized, imageYuv, cv::COLOR_BGR2YUV);
    split(imageYuv, imageYuvCh);
    resize(imageYuv, imageYuvMini, Size(width/2, height/2));
    split(imageYuvMini, imageYuvMiniCh);

    SFrameBSInfo info;
    memset (&info, 0, sizeof (SFrameBSInfo));
    SSourcePicture pic;
    memset (&pic, 0, sizeof (SSourcePicture));
    pic.iPicWidth = width;
    pic.iPicHeight = height;
    pic.iColorFormat = videoFormatI420;
    pic.iStride[0] = imageYuvCh[0].step;
    pic.iStride[1] = imageYuvMiniCh[1].step;
    pic.iStride[2] = imageYuvMiniCh[2].step;
    pic.pData[0] = imageYuvCh[0].data;
    pic.pData[1] = imageYuvMiniCh[1].data;
    pic.pData[2] = imageYuvMiniCh[2].data;

    ofstream outFi;
    outFi.open ("test.264", ios::out | ios::binary);

    for(int num = 0; num<total_num; num++) 
    {
        //prepare input data
        rv = encoder_->EncodeFrame (&pic, &info);
        assert (rv == cmResultSuccess);
        if (info.eFrameType != videoFrameTypeSkip /*&& cbk != nullptr*/) 
        {
            //output bitstream
            for (int iLayer=0; iLayer < info.iLayerNum; iLayer++)
            {
                SLayerBSInfo* pLayerBsInfo = &info.sLayerInfo[iLayer];

                int iLayerSize = 0;
                int iNalIdx = pLayerBsInfo->iNalCount - 1;
                do {
                    iLayerSize += pLayerBsInfo->pNalLengthInByte[iNalIdx];
                    --iNalIdx;
                } while (iNalIdx >= 0);

                unsigned char *outBuf = pLayerBsInfo->pBsBuf;
                outFi.write((char *)outBuf, iLayerSize);
            }

        }
    }

    if (encoder_) {
        encoder_->Uninitialize();
        WelsDestroySVCEncoder (encoder_);
    }

    outFi.close();
}