碼率控制的各級初始化函數

碼率控制模塊初始化

void RateCtrl::init(int totalFrames, int targetBitrate, int frameRate, int GOPSize, int picWidth, int picHeight, int LCUWidth, int LCUHeight, int bitDepth, int keepHierBits, bool useLCUSeparateModel, GOPEntry  GOPList[MAX_GOP])
{
  destroy();

  bool isLowdelay = true;
  for ( int i=0; i<GOPSize-1; i++ )
  {
    if ( GOPList[i].m_POC > GOPList[i+1].m_POC )
    {
      isLowdelay = false;
      break;
    }
  }

  int numberOfLevel = 1;
  int adaptiveBit = 0;
  if ( keepHierBits > 0 )
  {
    numberOfLevel = int( log((double)GOPSize)/log(2.0) + 0.5 ) + 1;
  }
  if (!isLowdelay && (GOPSize == 16 || GOPSize == 8))
  {
    numberOfLevel = int( log((double)GOPSize)/log(2.0) + 0.5 ) + 1;
  }
  numberOfLevel++;    // intra picture
  numberOfLevel++;    // non-reference picture


  int* bitsRatio;
  bitsRatio = new int[ GOPSize ];
  for ( int i=0; i<GOPSize; i++ )
  {
    bitsRatio[i] = 10;
    if ( !GOPList[i].m_refPic )
    {
      bitsRatio[i] = 2;
    }
  }

  if ( keepHierBits > 0 )
  {
    double bpp = (double)( targetBitrate / (double)( frameRate*picWidth*picHeight ) );
    if ( GOPSize == 4 && isLowdelay )
    {
      if ( bpp > 0.2 )
      {
        bitsRatio[0] = 2;
        bitsRatio[1] = 3;
        bitsRatio[2] = 2;
        bitsRatio[3] = 6;
      }
      else if( bpp > 0.1 )
      {
        bitsRatio[0] = 2;
        bitsRatio[1] = 3;
        bitsRatio[2] = 2;
        bitsRatio[3] = 10;
      }
      else if ( bpp > 0.05 )
      {
        bitsRatio[0] = 2;
        bitsRatio[1] = 3;
        bitsRatio[2] = 2;
        bitsRatio[3] = 12;
      }
      else
      {
        bitsRatio[0] = 2;
        bitsRatio[1] = 3;
        bitsRatio[2] = 2;
        bitsRatio[3] = 14;
      }

      if ( keepHierBits == 2 )
      {
        adaptiveBit = 1;
      }
    }
    else if ( GOPSize == 8 && !isLowdelay )
    {
      if ( bpp > 0.2 )
      {
        bitsRatio[0] = 15;
        bitsRatio[1] = 5;
        bitsRatio[2] = 4;
        bitsRatio[3] = 1;
        bitsRatio[4] = 1;
        bitsRatio[5] = 4;
        bitsRatio[6] = 1;
        bitsRatio[7] = 1;
      }
      else if ( bpp > 0.1 )
      {
        bitsRatio[0] = 20;
        bitsRatio[1] = 6;
        bitsRatio[2] = 4;
        bitsRatio[3] = 1;
        bitsRatio[4] = 1;
        bitsRatio[5] = 4;
        bitsRatio[6] = 1;
        bitsRatio[7] = 1;
      }
      else if ( bpp > 0.05 )
      {
        bitsRatio[0] = 25;
        bitsRatio[1] = 7;
        bitsRatio[2] = 4;
        bitsRatio[3] = 1;
        bitsRatio[4] = 1;
        bitsRatio[5] = 4;
        bitsRatio[6] = 1;
        bitsRatio[7] = 1;
      }
      else
      {
        bitsRatio[0] = 30;
        bitsRatio[1] = 8;
        bitsRatio[2] = 4;
        bitsRatio[3] = 1;
        bitsRatio[4] = 1;
        bitsRatio[5] = 4;
        bitsRatio[6] = 1;
        bitsRatio[7] = 1;
      }

      if ( keepHierBits == 2 )
      {
        adaptiveBit = 2;
      }
    }
    else if (GOPSize == 16 && !isLowdelay)
    {
      if (bpp > 0.2)
      {
        bitsRatio[0] = 10;
        bitsRatio[1] = 8;
        bitsRatio[2] = 4;
        bitsRatio[3] = 2;
        bitsRatio[4] = 1;
        bitsRatio[5] = 1;
        bitsRatio[6] = 2;
        bitsRatio[7] = 1;
        bitsRatio[8] = 1;
        bitsRatio[9] = 4;
        bitsRatio[10] = 2;
        bitsRatio[11] = 1;
        bitsRatio[12] = 1;
        bitsRatio[13] = 2;
        bitsRatio[14] = 1;
        bitsRatio[15] = 1;
      }
      else if (bpp > 0.1)
      {
        bitsRatio[0] = 15;
        bitsRatio[1] = 9;
        bitsRatio[2] = 4;
        bitsRatio[3] = 2;
        bitsRatio[4] = 1;
        bitsRatio[5] = 1;
        bitsRatio[6] = 2;
        bitsRatio[7] = 1;
        bitsRatio[8] = 1;
        bitsRatio[9] = 4;
        bitsRatio[10] = 2;
        bitsRatio[11] = 1;
        bitsRatio[12] = 1;
        bitsRatio[13] = 2;
        bitsRatio[14] = 1;
        bitsRatio[15] = 1;
      }
      else if (bpp > 0.05)
      {
        bitsRatio[0] = 40;
        bitsRatio[1] = 17;
        bitsRatio[2] = 7;
        bitsRatio[3] = 2;
        bitsRatio[4] = 1;
        bitsRatio[5] = 1;
        bitsRatio[6] = 2;
        bitsRatio[7] = 1;
        bitsRatio[8] = 1;
        bitsRatio[9] = 7;
        bitsRatio[10] = 2;
        bitsRatio[11] = 1;
        bitsRatio[12] = 1;
        bitsRatio[13] = 2;
        bitsRatio[14] = 1;
        bitsRatio[15] = 1;
      }
      else
      {
        bitsRatio[0] = 40;
        bitsRatio[1] = 15;
        bitsRatio[2] = 6;
        bitsRatio[3] = 3;
        bitsRatio[4] = 1;
        bitsRatio[5] = 1;
        bitsRatio[6] = 3;
        bitsRatio[7] = 1;
        bitsRatio[8] = 1;
        bitsRatio[9] = 6;
        bitsRatio[10] = 3;
        bitsRatio[11] = 1;
        bitsRatio[12] = 1;
        bitsRatio[13] = 3;
        bitsRatio[14] = 1;
        bitsRatio[15] = 1;
      }

      if (keepHierBits == 2)
      {
        adaptiveBit = 3;
      }
    }
    else
    {
      msg( WARNING, "\n hierarchical bit allocation is not support for the specified coding structure currently.\n" );
    }
  }

  int* GOPID2Level = new int[ GOPSize ];
  for ( int i=0; i<GOPSize; i++ )
  {
    GOPID2Level[i] = 1;
    if ( !GOPList[i].m_refPic )
    {
      GOPID2Level[i] = 2;
    }
  }

  if ( keepHierBits > 0 )
  {
    if ( GOPSize == 4 && isLowdelay )
    {
      GOPID2Level[0] = 3;
      GOPID2Level[1] = 2;
      GOPID2Level[2] = 3;
      GOPID2Level[3] = 1;
    }
    else if ( GOPSize == 8 && !isLowdelay )
    {
      GOPID2Level[0] = 1;
      GOPID2Level[1] = 2;
      GOPID2Level[2] = 3;
      GOPID2Level[3] = 4;
      GOPID2Level[4] = 4;
      GOPID2Level[5] = 3;
      GOPID2Level[6] = 4;
      GOPID2Level[7] = 4;
    }
    else if (GOPSize == 16 && !isLowdelay)
    {
      GOPID2Level[0] = 1;
      GOPID2Level[1] = 2;
      GOPID2Level[2] = 3;
      GOPID2Level[3] = 4;
      GOPID2Level[4] = 5;
      GOPID2Level[5] = 5;
      GOPID2Level[6] = 4;
      GOPID2Level[7] = 5;
      GOPID2Level[8] = 5;
      GOPID2Level[9] = 3;
      GOPID2Level[10] = 4;
      GOPID2Level[11] = 5;
      GOPID2Level[12] = 5;
      GOPID2Level[13] = 4;
      GOPID2Level[14] = 5;
      GOPID2Level[15] = 5;
    }
  }

  if ( !isLowdelay && GOPSize == 8 )
  {
    GOPID2Level[0] = 1;
    GOPID2Level[1] = 2;
    GOPID2Level[2] = 3;
    GOPID2Level[3] = 4;
    GOPID2Level[4] = 4;
    GOPID2Level[5] = 3;
    GOPID2Level[6] = 4;
    GOPID2Level[7] = 4;
  }
  else if (GOPSize == 16 && !isLowdelay)
  {
    GOPID2Level[0] = 1;
    GOPID2Level[1] = 2;
    GOPID2Level[2] = 3;
    GOPID2Level[3] = 4;
    GOPID2Level[4] = 5;
    GOPID2Level[5] = 5;
    GOPID2Level[6] = 4;
    GOPID2Level[7] = 5;
    GOPID2Level[8] = 5;
    GOPID2Level[9] = 3;
    GOPID2Level[10] = 4;
    GOPID2Level[11] = 5;
    GOPID2Level[12] = 5;
    GOPID2Level[13] = 4;
    GOPID2Level[14] = 5;
    GOPID2Level[15] = 5;
  }

  m_encRCSeq = new EncRCSeq;
  m_encRCSeq->create( totalFrames, targetBitrate, frameRate, GOPSize, picWidth, picHeight, LCUWidth, LCUHeight, numberOfLevel, useLCUSeparateModel, adaptiveBit );
  m_encRCSeq->initBitsRatio( bitsRatio );
  m_encRCSeq->initGOPID2Level( GOPID2Level );
  m_encRCSeq->setBitDepth(bitDepth);
  m_encRCSeq->initPicPara();
  if ( useLCUSeparateModel )
  {
    m_encRCSeq->initLCUPara();
  }
#if U0132_TARGET_BITS_SATURATION
  m_CpbSaturationEnabled = false;
  m_cpbSize              = targetBitrate;
  m_cpbState             = (uint32_t)(m_cpbSize*0.5f);
  m_bufferingRate        = (int)(targetBitrate / frameRate);
#endif

  delete[] bitsRatio;
  delete[] GOPID2Level;
}

GOP碼率控制初始化

void EncRCGOP::create( EncRCSeq* encRCSeq, int numPic )
{
  destroy();
  int targetBits = xEstGOPTargetBits( encRCSeq, numPic );

  if ( encRCSeq->getAdaptiveBits() > 0 && encRCSeq->getLastLambda() > 0.1 )
  {
    double targetBpp = (double)targetBits / encRCSeq->getNumPixel();
    double basicLambda = 0.0;
    double* lambdaRatio = new double[encRCSeq->getGOPSize()];
    double* equaCoeffA = new double[encRCSeq->getGOPSize()];
    double* equaCoeffB = new double[encRCSeq->getGOPSize()];

    if ( encRCSeq->getAdaptiveBits() == 1 )   // for GOP size =4, low delay case
    {
      if ( encRCSeq->getLastLambda() < 120.0 )
      {
        lambdaRatio[1] = 0.725 * log( encRCSeq->getLastLambda() ) + 0.5793;
        lambdaRatio[0] = 1.3 * lambdaRatio[1];
        lambdaRatio[2] = 1.3 * lambdaRatio[1];
        lambdaRatio[3] = 1.0;
      }
      else
      {
        lambdaRatio[0] = 5.0;
        lambdaRatio[1] = 4.0;
        lambdaRatio[2] = 5.0;
        lambdaRatio[3] = 1.0;
      }
    }
    else if ( encRCSeq->getAdaptiveBits() == 2 )  // for GOP size = 8, random access case
    {
      if ( encRCSeq->getLastLambda() < 90.0 )
      {
        lambdaRatio[0] = 1.0;
        lambdaRatio[1] = 0.725 * log( encRCSeq->getLastLambda() ) + 0.7963;
        lambdaRatio[2] = 1.3 * lambdaRatio[1];
        lambdaRatio[3] = 3.25 * lambdaRatio[1];
        lambdaRatio[4] = 3.25 * lambdaRatio[1];
        lambdaRatio[5] = 1.3  * lambdaRatio[1];
        lambdaRatio[6] = 3.25 * lambdaRatio[1];
        lambdaRatio[7] = 3.25 * lambdaRatio[1];
      }
      else
      {
        lambdaRatio[0] = 1.0;
        lambdaRatio[1] = 4.0;
        lambdaRatio[2] = 5.0;
        lambdaRatio[3] = 12.3;
        lambdaRatio[4] = 12.3;
        lambdaRatio[5] = 5.0;
        lambdaRatio[6] = 12.3;
        lambdaRatio[7] = 12.3;
      }
    }
    else if (encRCSeq->getAdaptiveBits() == 3)  // for GOP size = 16, random access case
    {
      {
        int bitdepth_luma_scale =
          2
          * (encRCSeq->getbitDepth() - 8
            - DISTORTION_PRECISION_ADJUSTMENT(encRCSeq->getbitDepth()));

        double hierarQp = 4.2005 * log(encRCSeq->getLastLambda() / pow(2.0, bitdepth_luma_scale)) + 13.7122;  //  the qp of POC16
        double qpLev2 = (hierarQp + 0.0) + 0.2016    * (hierarQp + 0.0) - 4.8848;
        double qpLev3 = (hierarQp + 3.0) + 0.22286 * (hierarQp + 3.0) - 5.7476;
        double qpLev4 = (hierarQp + 4.0) + 0.2333    * (hierarQp + 4.0) - 5.9;
        double qpLev5 = (hierarQp + 5.0) + 0.3            * (hierarQp + 5.0) - 7.1444;

        double lambdaLev1 = exp((hierarQp - 13.7122) / 4.2005) *pow(2.0, bitdepth_luma_scale);
        double lambdaLev2 = exp((qpLev2 - 13.7122) / 4.2005) * pow(2.0, bitdepth_luma_scale);
        double lambdaLev3 = exp((qpLev3 - 13.7122) / 4.2005) * pow(2.0, bitdepth_luma_scale);
        double lambdaLev4 = exp((qpLev4 - 13.7122) / 4.2005) * pow(2.0, bitdepth_luma_scale);
        double lambdaLev5 = exp((qpLev5 - 13.7122) / 4.2005) * pow(2.0, bitdepth_luma_scale);

        lambdaRatio[0] = 1.0;
        lambdaRatio[1] = lambdaLev2 / lambdaLev1;
        lambdaRatio[2] = lambdaLev3 / lambdaLev1;
        lambdaRatio[3] = lambdaLev4 / lambdaLev1;
        lambdaRatio[4] = lambdaLev5 / lambdaLev1;
        lambdaRatio[5] = lambdaLev5 / lambdaLev1;
        lambdaRatio[6] = lambdaLev4 / lambdaLev1;
        lambdaRatio[7] = lambdaLev5 / lambdaLev1;
        lambdaRatio[8] = lambdaLev5 / lambdaLev1;
        lambdaRatio[9] = lambdaLev3 / lambdaLev1;
        lambdaRatio[10] = lambdaLev4 / lambdaLev1;
        lambdaRatio[11] = lambdaLev5 / lambdaLev1;
        lambdaRatio[12] = lambdaLev5 / lambdaLev1;
        lambdaRatio[13] = lambdaLev4 / lambdaLev1;
        lambdaRatio[14] = lambdaLev5 / lambdaLev1;
        lambdaRatio[15] = lambdaLev5 / lambdaLev1;
        const double qdfParaLev2A = 0.5847;
        const double qdfParaLev2B = -0.0782;
        const double qdfParaLev3A = 0.5468;
        const double qdfParaLev3B = -0.1364;
        const double qdfParaLev4A = 0.6539;
        const double qdfParaLev4B = -0.203;
        const double qdfParaLev5A = 0.8623;
        const double qdfParaLev5B = -0.4676;
        double qdfLev1Lev2 = Clip3(0.12, 0.9, qdfParaLev2A * encRCSeq->getPicPara(2).m_skipRatio + qdfParaLev2B);
        double qdfLev1Lev3 = Clip3(0.13, 0.9, qdfParaLev3A * encRCSeq->getPicPara(3).m_skipRatio + qdfParaLev3B);
        double qdfLev1Lev4 = Clip3(0.15, 0.9, qdfParaLev4A * encRCSeq->getPicPara(4).m_skipRatio + qdfParaLev4B);
        double qdfLev1Lev5 = Clip3(0.20, 0.9, qdfParaLev5A * encRCSeq->getPicPara(5).m_skipRatio + qdfParaLev5B);
        double qdfLev2Lev3 = Clip3(0.09, 0.9, qdfLev1Lev3 * (1 - qdfLev1Lev2));
        double qdfLev2Lev4 = Clip3(0.12, 0.9, qdfLev1Lev4 * (1 - qdfLev1Lev2));
        double qdfLev2Lev5 = Clip3(0.14, 0.9, qdfLev1Lev5 * (1 - qdfLev1Lev2));
        double qdfLev3Lev4 = Clip3(0.06, 0.9, qdfLev1Lev4 * (1 - qdfLev1Lev3));
        double qdfLev3Lev5 = Clip3(0.09, 0.9, qdfLev1Lev5 * (1 - qdfLev1Lev3));
        double qdfLev4Lev5 = Clip3(0.10, 0.9, qdfLev1Lev5 * (1 - qdfLev1Lev4));

        lambdaLev1 = 1 / (1 + 2 * (qdfLev1Lev2 + 2 * qdfLev1Lev3 + 4 * qdfLev1Lev4 + 8 * qdfLev1Lev5));
        lambdaLev2 = 1 / (1 + (3 * qdfLev2Lev3 + 5 * qdfLev2Lev4 + 8 * qdfLev2Lev5));
        lambdaLev3 = 1 / (1 + 2 * qdfLev3Lev4 + 4 * qdfLev3Lev5);
        lambdaLev4 = 1 / (1 + 2 * qdfLev4Lev5);
        lambdaLev5 = 1 / (1.0);

        lambdaRatio[0] = 1.0;
        lambdaRatio[1] = lambdaLev2 / lambdaLev1;
        lambdaRatio[2] = lambdaLev3 / lambdaLev1;
        lambdaRatio[3] = lambdaLev4 / lambdaLev1;
        lambdaRatio[4] = lambdaLev5 / lambdaLev1;
        lambdaRatio[5] = lambdaLev5 / lambdaLev1;
        lambdaRatio[6] = lambdaLev4 / lambdaLev1;
        lambdaRatio[7] = lambdaLev5 / lambdaLev1;
        lambdaRatio[8] = lambdaLev5 / lambdaLev1;
        lambdaRatio[9] = lambdaLev3 / lambdaLev1;
        lambdaRatio[10] = lambdaLev4 / lambdaLev1;
        lambdaRatio[11] = lambdaLev5 / lambdaLev1;
        lambdaRatio[12] = lambdaLev5 / lambdaLev1;
        lambdaRatio[13] = lambdaLev4 / lambdaLev1;
        lambdaRatio[14] = lambdaLev5 / lambdaLev1;
        lambdaRatio[15] = lambdaLev5 / lambdaLev1;
      }
    }

    xCalEquaCoeff( encRCSeq, lambdaRatio, equaCoeffA, equaCoeffB, encRCSeq->getGOPSize() );
    basicLambda = xSolveEqua(encRCSeq, targetBpp, equaCoeffA, equaCoeffB, encRCSeq->getGOPSize());
    encRCSeq->setAllBitRatio( basicLambda, equaCoeffA, equaCoeffB );

    delete []lambdaRatio;
    delete []equaCoeffA;
    delete []equaCoeffB;
  }

  m_picTargetBitInGOP = new int[numPic];
  int i;
  int totalPicRatio = 0;
  int currPicRatio = 0;
  for ( i=0; i<numPic; i++ )
  {
    totalPicRatio += encRCSeq->getBitRatio( i );
  }
  for ( i=0; i<numPic; i++ )
  {
    currPicRatio = encRCSeq->getBitRatio( i );
    m_picTargetBitInGOP[i] = (int)( ((double)targetBits) * currPicRatio / totalPicRatio );
  }

  m_encRCSeq    = encRCSeq;
  m_numPic       = numPic;
  m_targetBits   = targetBits;
  m_picLeft      = m_numPic;
  m_bitsLeft     = m_targetBits;
}

幀級碼率控制初始化

void EncRCPic::create( EncRCSeq* encRCSeq, EncRCGOP* encRCGOP, int frameLevel, list<EncRCPic*>& listPreviousPictures )
{
  destroy();
  m_encRCSeq = encRCSeq;
  m_encRCGOP = encRCGOP;

  int targetBits    = xEstPicTargetBits( encRCSeq, encRCGOP );
  int estHeaderBits = xEstPicHeaderBits( listPreviousPictures, frameLevel );

  if ( targetBits < estHeaderBits + 100 )
  {
    targetBits = estHeaderBits + 100;   // at least allocate 100 bits for picture data
  }

  m_frameLevel       = frameLevel;
  m_numberOfPixel    = encRCSeq->getNumPixel();
  m_numberOfLCU      = encRCSeq->getNumberOfLCU();
  m_estPicLambda     = 100.0;
  m_targetBits       = targetBits;
  m_estHeaderBits    = estHeaderBits;
  m_bitsLeft         = m_targetBits;
  int picWidth       = encRCSeq->getPicWidth();
  int picHeight      = encRCSeq->getPicHeight();
  int LCUWidth       = encRCSeq->getLCUWidth();
  int LCUHeight      = encRCSeq->getLCUHeight();
  int picWidthInLCU  = ( picWidth  % LCUWidth  ) == 0 ? picWidth  / LCUWidth  : picWidth  / LCUWidth  + 1;
  int picHeightInLCU = ( picHeight % LCUHeight ) == 0 ? picHeight / LCUHeight : picHeight / LCUHeight + 1;
#if V0078_ADAPTIVE_LOWER_BOUND
  m_lowerBound       = xEstPicLowerBound( encRCSeq, encRCGOP );
#endif

  m_LCULeft         = m_numberOfLCU;
  m_bitsLeft       -= m_estHeaderBits;
  m_pixelsLeft      = m_numberOfPixel;

  m_LCUs           = new TRCLCU[m_numberOfLCU];
  int i, j;
  int LCUIdx;
  for ( i=0; i<picWidthInLCU; i++ )
  {
    for ( j=0; j<picHeightInLCU; j++ )
    {
      LCUIdx = j*picWidthInLCU + i;
      m_LCUs[LCUIdx].m_actualBits = 0;
      m_LCUs[LCUIdx].m_actualSSE  = 0.0;
      m_LCUs[LCUIdx].m_actualMSE  = 0.0;
      m_LCUs[LCUIdx].m_QP         = 0;
      m_LCUs[LCUIdx].m_lambda     = 0.0;
      m_LCUs[LCUIdx].m_targetBits = 0;
      m_LCUs[LCUIdx].m_bitWeight  = 1.0;
      int currWidth  = ( (i == picWidthInLCU -1) ? picWidth  - LCUWidth *(picWidthInLCU -1) : LCUWidth  );
      int currHeight = ( (j == picHeightInLCU-1) ? picHeight - LCUHeight*(picHeightInLCU-1) : LCUHeight );
      m_LCUs[LCUIdx].m_numberOfPixel = currWidth * currHeight;
    }
  }
  m_picActualHeaderBits = 0;
  m_picActualBits       = 0;
  m_picQP               = 0;
  m_picLambda           = 0.0;
  m_validPixelsInPic    = 0;
  m_picMSE              = 0.0;
}

VTM碼率控制——代碼學習二

文章目錄

碼率控制的各級初始化函數

碼率控制模塊初始化

GOP碼率控制初始化

幀級碼率控制初始化

24-5-18 X

VVC學習之五：幀內預測——幀內參考像素濾波xFilterReferenceSamples()

VVC學習之五：VTM幀內預測之亮度預測——estIntraPredLumaQT()詳解

VVC學習之五：幀內預測——67個模式預測信號生成 predIntraAng()

VVC學習之五：VTM幀內預測之色度預測——estIntraPredChromaQT()

VTM中的編碼單元信息擴展：CU信息的可視化分析和統計分析

https://yachay.unat.edu.pe/blog/index.php?comment_area=format_blog&comment_component=blog&comment_co

linux以太網驅動總結