HEVC码率控制浅析——HM代码阅读之二

上一篇文章主要讨论了RC的总体框架，本文开始分析具体的代码实现细节。分析的顺序按照总体框架来，即初始化-->更新。

（1）m_cRateCtrl.init()

#if M0036_RC_IMPROVEMENT
Void TEncRateCtrl::init( Int totalFrames, Int targetBitrate, Int frameRate, Int GOPSize, Int picWidth, Int picHeight, Int LCUWidth, Int LCUHeight, Int keepHierBits, Bool useLCUSeparateModel, GOPEntry  GOPList[MAX_GOP] )
#else
Void TEncRateCtrl::init( Int totalFrames, Int targetBitrate, Int frameRate, Int GOPSize, Int picWidth, Int picHeight, Int LCUWidth, Int LCUHeight, Bool keepHierBits, Bool useLCUSeparateModel, GOPEntry  GOPList[MAX_GOP] )
#endif
{
  destroy();

  Bool isLowdelay = true;
  for ( Int i=0; i<GOPSize-1; i++ )
  {
    if ( GOPList[i].m_POC > GOPList[i+1].m_POC ) //!< 判断是否为lowdelay配置
    {
      isLowdelay = false;
      break;
    }
  }

  Int numberOfLevel = 1;
#if M0036_RC_IMPROVEMENT
  Int adaptiveBit = 0;
  if ( keepHierBits > 0 )
#else
  if ( keepHierBits )	//!< hierarchical structure
#endif
  {
    numberOfLevel = Int( log((Double)GOPSize)/log(2.0) + 0.5 ) + 1;
  }
  if ( !isLowdelay && GOPSize == 8 )
  {
    numberOfLevel = Int( log((Double)GOPSize)/log(2.0) + 0.5 ) + 1;
  }
  numberOfLevel++;    // intra picture
  numberOfLevel++;    // non-reference picture


  Int* bitsRatio;	//!< 每一幅picture的权值
  bitsRatio = new Int[ GOPSize ];
  for ( Int i=0; i<GOPSize; i++ )
  {
    bitsRatio[i] = 10;
    if ( !GOPList[i].m_refPic )
    {
      bitsRatio[i] = 2;
    }
  }

#if M0036_RC_IMPROVEMENT
  if ( keepHierBits > 0 )
#else
  if ( keepHierBits )
#endif
  {
    Double bpp = (Double)( targetBitrate / (Double)( frameRate*picWidth*picHeight ) ); //!< K0103 式子（3）
    if ( GOPSize == 4 && isLowdelay ) //!< K0103 Table 1
    {
      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 M0036_RC_IMPROVEMENT
      if ( keepHierBits == 2 )
      {
        adaptiveBit = 1;
      }
#endif
    }
    else if ( GOPSize == 8 && !isLowdelay ) //!< K0103 Table 2
    {
      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 M0036_RC_IMPROVEMENT
      if ( keepHierBits == 2 )
      {
        adaptiveBit = 2;
      }
#endif
    }
    else
    {
#if M0036_RC_IMPROVEMENT
      printf( "
 hierarchical bit allocation is not support for the specified coding structure currently.
" );
#else
      printf( "
 hierarchical bit allocation is not support for the specified coding structure currently." );
#endif
    }
  }

  Int* GOPID2Level = new int[ GOPSize ]; //!< 根据在GOP中的id确定所属的分层
  for ( int i=0; i<GOPSize; i++ )
  {
    GOPID2Level[i] = 1;
    if ( !GOPList[i].m_refPic )
    {
      GOPID2Level[i] = 2;
    }
  }
#if M0036_RC_IMPROVEMENT
  if ( keepHierBits > 0 )
#else
  if ( keepHierBits )
#endif
  {
    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;
    }
  }

  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;
  }

  m_encRCSeq = new TEncRCSeq;
#if M0036_RC_IMPROVEMENT
  m_encRCSeq->create( totalFrames, targetBitrate, frameRate, GOPSize, picWidth, picHeight, LCUWidth, LCUHeight, numberOfLevel, useLCUSeparateModel, adaptiveBit );
#else //!< 序列级RC参数的初始化
  m_encRCSeq->create( totalFrames, targetBitrate, frameRate, GOPSize, picWidth, picHeight, LCUWidth, LCUHeight, numberOfLevel, useLCUSeparateModel );
#endif
  m_encRCSeq->initBitsRatio( bitsRatio ); //!< 每幅picture的权值
  m_encRCSeq->initGOPID2Level( GOPID2Level ); 
  m_encRCSeq->initPicPara(/*TRCParameter* picPara  = NULL*/); //!< alpha, beta
  if ( useLCUSeparateModel )
  {
    m_encRCSeq->initLCUPara(); //!< alpha，beta初始化
  }

  delete[] bitsRatio;
  delete[] GOPID2Level;
}

分析该函数中调用的比较重要的若干个子函数：

m_encRCSeq->create()

#if M0036_RC_IMPROVEMENT
Void TEncRCSeq::create( Int totalFrames, Int targetBitrate, Int frameRate, Int GOPSize, Int picWidth, Int picHeight, Int LCUWidth, Int LCUHeight, Int numberOfLevel, Bool useLCUSeparateModel, Int adaptiveBit )
#else
Void TEncRCSeq::create( Int totalFrames, Int targetBitrate, Int frameRate, Int GOPSize, Int picWidth, Int picHeight, Int LCUWidth, Int LCUHeight, Int numberOfLevel, Bool useLCUSeparateModel )
#endif
{
  destroy();
  m_totalFrames         = totalFrames;
  m_targetRate          = targetBitrate;
  m_frameRate           = frameRate;
  m_GOPSize             = GOPSize;
  m_picWidth            = picWidth;
  m_picHeight           = picHeight;
  m_LCUWidth            = LCUWidth;
  m_LCUHeight           = LCUHeight;
  m_numberOfLevel       = numberOfLevel;
  m_useLCUSeparateModel = useLCUSeparateModel;

  m_numberOfPixel   = m_picWidth * m_picHeight;
  m_targetBits      = (Int64)m_totalFrames * (Int64)m_targetRate / (Int64)m_frameRate; //!< 序列总码率（输出码流总大小）
  m_seqTargetBpp = (Double)m_targetRate / (Double)m_frameRate / (Double)m_numberOfPixel; //!< m_targetRate--bps
  
  //!< m_alphaUpdata和m_betaUpdate这两个变量用于在接下来更新lamda的参数值
  if ( m_seqTargetBpp < 0.03 )	//!< (..., 0.03)
  {
    m_alphaUpdate = 0.01;
    m_betaUpdate  = 0.005;
  }
  else if ( m_seqTargetBpp < 0.08 ) //!< [0.03, 0.08)
  {
    m_alphaUpdate = 0.05;
    m_betaUpdate  = 0.025;
  }
#if M0036_RC_IMPROVEMENT
  else if ( m_seqTargetBpp < 0.2 )
  {
    m_alphaUpdate = 0.1;
    m_betaUpdate  = 0.05;
  }
  else if ( m_seqTargetBpp < 0.5 )
  {
    m_alphaUpdate = 0.2;
    m_betaUpdate  = 0.1;
  }
  else
  {
    m_alphaUpdate = 0.4;
    m_betaUpdate  = 0.2;
  }
#else
  else //!< [0.08, ...]
  {
    m_alphaUpdate = 0.1;
    m_betaUpdate  = 0.05;
  }
#endif
  m_averageBits     = (Int)(m_targetBits / totalFrames); //!< 平均每帧占用的比特数
  Int picWidthInBU  = ( m_picWidth  % m_LCUWidth  ) == 0 ? m_picWidth  / m_LCUWidth  : m_picWidth  / m_LCUWidth  + 1;
  Int picHeightInBU = ( m_picHeight % m_LCUHeight ) == 0 ? m_picHeight / m_LCUHeight : m_picHeight / m_LCUHeight + 1;
  m_numberOfLCU     = picWidthInBU * picHeightInBU; //!< 一帧picture中包含的LCU数目

  m_bitsRatio   = new Int[m_GOPSize];
  for ( Int i=0; i<m_GOPSize; i++ )
  {
    m_bitsRatio[i] = 1;
  }

  m_GOPID2Level = new Int[m_GOPSize];
  for ( Int i=0; i<m_GOPSize; i++ )
  {
    m_GOPID2Level[i] = 1;
  }

  m_picPara = new TRCParameter[m_numberOfLevel];
  for ( Int i=0; i<m_numberOfLevel; i++ )
  {
    m_picPara[i].m_alpha = 0.0;
    m_picPara[i].m_beta  = 0.0;
  }

  if ( m_useLCUSeparateModel ) //!< 每个LCU的alpha和beta都有各自的值
  {
    m_LCUPara = new TRCParameter*[m_numberOfLevel];
    for ( Int i=0; i<m_numberOfLevel; i++ )
    {
      m_LCUPara[i] = new TRCParameter[m_numberOfLCU];
      for ( Int j=0; j<m_numberOfLCU; j++)
      {
        m_LCUPara[i][j].m_alpha = 0.0;
        m_LCUPara[i][j].m_beta  = 0.0;
      }
    }
  }

  m_framesLeft = m_totalFrames; //!< 剩余的待编码帧数
  m_bitsLeft   = m_targetBits;	//!< 剩余可用的比特数
#if M0036_RC_IMPROVEMENT
  m_adaptiveBit = adaptiveBit;
  m_lastLambda = 0.0;
#endif
}

m_encRCSeq->initPicPara()

Void TEncRCSeq::initPicPara( TRCParameter* picPara )
{
  assert( m_picPara != NULL );

  if ( picPara == NULL ) //!< K0103 式子（10）
  {
    for ( Int i=0; i<m_numberOfLevel; i++ )
    {
#if RATE_CONTROL_INTRA
      if (i>0)
      {
        m_picPara[i].m_alpha = 3.2003;
        m_picPara[i].m_beta  = -1.367;
      }
      else
      {
        m_picPara[i].m_alpha = ALPHA;   
        m_picPara[i].m_beta  = BETA2;
      }
#else	//!< 第一帧图像的参数初始化
      m_picPara[i].m_alpha = 3.2003;
      m_picPara[i].m_beta  = -1.367;
#endif
    }
  }
  else
  {
    for ( Int i=0; i<m_numberOfLevel; i++ )
    {
      m_picPara[i] = picPara[i];
    }
  }
}

（2）m_cRateCtrl.initRCGOP()

Void TEncRateCtrl::initRCGOP( Int numberOfPictures )
{
  m_encRCGOP = new TEncRCGOP;
  m_encRCGOP->create( m_encRCSeq, numberOfPictures );
}

Void TEncRCGOP::create( TEncRCSeq* encRCSeq, Int numPic )
{
  destroy();
  Int targetBits = xEstGOPTargetBits( encRCSeq, numPic ); //!< GOP level bit allocation

#if M0036_RC_IMPROVEMENT
  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;
      }
    }

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

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

  m_picTargetBitInGOP = new Int[numPic]; //!< 用于保存当前GOP中每幅picture对应的目标码率
  Int i;
  Int totalPicRatio = 0;
  Int currPicRatio = 0;
  for ( i=0; i<numPic; i++ )
  {
    totalPicRatio += encRCSeq->getBitRatio( i ); //!< 总权值
  }
  for ( i=0; i<numPic; i++ )
  {
    currPicRatio = encRCSeq->getBitRatio( i ); //!< 当前picture的权值
#if M0036_RC_IMPROVEMENT
    m_picTargetBitInGOP[i] = (Int)( ((Double)targetBits) * currPicRatio / totalPicRatio );
#else
    m_picTargetBitInGOP[i] = targetBits * currPicRatio / totalPicRatio; //!< K0103 式子（9），注意：由于是初始化，式子中的CodedGOP等于0
#endif
  }

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

Int TEncRCGOP::xEstGOPTargetBits( TEncRCSeq* encRCSeq, Int GOPSize )
{
  Int realInfluencePicture = min( g_RCSmoothWindowSize, encRCSeq->getFramesLeft() ); //!< 获得实际的平滑窗口大小
  Int averageTargetBitsPerPic = (Int)( encRCSeq->getTargetBits() / encRCSeq->getTotalFrames() ); //!< RPicArg
  Int currentTargetBitsPerPic = (Int)( ( encRCSeq->getBitsLeft() - averageTargetBitsPerPic * (encRCSeq->getFramesLeft() - realInfluencePicture) ) / realInfluencePicture ); //!< TAvgPic，计算方法跟K0103不同，这里利用left的思路计算，而K0103利用coded的思路计算，但结果是一样的
  Int targetBits = currentTargetBitsPerPic * GOPSize; //!< TGOP

  if ( targetBits < 200 )
  {
    targetBits = 200;   // at least allocate 200 bits for one GOP
  }

  return targetBits;
}

（未完待续...）