1. 程式人生 > >如何在JM8.6程式碼的編碼端提取殘差(為簡便起見,僅以I4x4巨集塊為例)

如何在JM8.6程式碼的編碼端提取殘差(為簡便起見,僅以I4x4巨集塊為例)

        要在JM8.6程式碼中找出某一資料,不能瞎撞,不能用蠻力,而是要根據H.264的流程來找.比如,要在編碼端找到畫素殘差,就可以按照下面的思路來找. (為簡便起見,僅以I4x4巨集塊為例)

       提前說一句:有時候對於同一個量,有好幾個地方多可以提取,所以思路不要太侷限,重要的是知道該量過去從何而來,將來又何去何從. 下面的思路是提取I4x4巨集塊中殘差的思路.(囉嗦一句:如何要提取所有型別巨集塊的殘差,那麼僅在下面這個地方提取則是不夠的)

       前面說過,原始的YUV畫素儲存在imgY_org中,而編碼端要對殘差進行變換編碼,而encode_one_macroblock就是編碼一個巨集塊的關鍵函式,所以,如果要在編碼端提取殘差,就可以嘗試在encode_one_macroblock所在的檔案搜尋imgY_org, 一搜索,還真有,但很多,回想一下,殘差是怎麼形成的?很顯然殘差的形成必然涉及到相減,也就是要在程式碼中找“imgY_org[][] - ...”這樣形式的程式碼. 找找,還真有,但是我們需要的“imgY_org[][] - ...”形式的程式碼卻在Mode_Decision_for_4x4IntraBlocks函式中,沒關係的,因為encode_one_macroblock呼叫了Mode_Decision_for_4x4IntraBlocks函式.

      提取殘差的程式碼如下:(其中只有部分程式碼用於提取殘差,以I4x4巨集塊為例))

int Mode_Decision_for_4x4IntraBlocks (int  b8,  int  b4,  double  lambda,  int*  min_cost)
{
  int     ipmode, best_ipmode = 0, i, j, k, x, y, cost, dummy;
  int     c_nz, nonzero = 0, rec4x4[4][4], diff[16];
  double  rdcost;
  int     block_x     = 8*(b8%2)+4*(b4%2);
  int     block_y     = 8*(b8/2)+4*(b4/2);
  int     pic_pix_x   = img->pix_x+block_x;
  int     pic_pix_y   = img->pix_y+block_y;
  int     pic_opix_x   = img->opix_x+block_x;
  int     pic_opix_y   = img->opix_y+block_y;
  int     pic_block_x = pic_pix_x/4;
  int     pic_block_y = pic_pix_y/4;
  double  min_rdcost  = 1e30;

  int left_available, up_available, all_available;

  int     upMode;
  int     leftMode;
  int     mostProbableMode;

  static int controlFlag = 0;

  PixelPos left_block;
  PixelPos top_block;

  getLuma4x4Neighbour(img->current_mb_nr, block_x/4, block_y/4, -1,  0, &left_block);
  getLuma4x4Neighbour(img->current_mb_nr, block_x/4, block_y/4,  0, -1, &top_block);


  // constrained intra pred
  if (input->UseConstrainedIntraPred)
  {
    left_block.available = left_block.available ? img->intra_block[left_block.mb_addr] : 0;
    top_block.available  = top_block.available  ? img->intra_block[top_block.mb_addr]  : 0;
  }
  
  upMode            = top_block.available ? img->ipredmode[top_block.pos_x ][top_block.pos_y ] : -1;
  leftMode          = left_block.available ? img->ipredmode[left_block.pos_x][left_block.pos_y] : -1;
  
  mostProbableMode  = (upMode < 0 || leftMode < 0) ? DC_PRED : upMode < leftMode ? upMode : leftMode;

  *min_cost = (1<<20);

  //===== INTRA PREDICTION FOR 4x4 BLOCK =====
  intrapred_luma (pic_pix_x, pic_pix_y, &left_available, &up_available, &all_available);

  //===== LOOP OVER ALL 4x4 INTRA PREDICTION MODES =====
  for (ipmode=0; ipmode<NO_INTRA_PMODE; ipmode++)
  {
    int available_mode =  (ipmode==DC_PRED) ||
        ((ipmode==VERT_PRED||ipmode==VERT_LEFT_PRED||ipmode==DIAG_DOWN_LEFT_PRED) && up_available ) ||
        ((ipmode==HOR_PRED||ipmode==HOR_UP_PRED) && left_available ) ||(all_available);
    if( available_mode)
    {
      if (!input->rdopt)
      {
        for (k=j=0; j<4; j++)
          for (i=0; i<4; i++, k++)
          {
            diff[k] = imgY_org[pic_opix_y+j][pic_opix_x+i] - img->mprr[ipmode][j][i];
          }
        cost  = (ipmode == mostProbableMode) ? 0 : (int)floor(4 * lambda );
        cost += SATD (diff, input->hadamard);
        if (cost < *min_cost)
        {
          best_ipmode = ipmode;
          *min_cost   = cost;
        }
      }
      else
      {
        // get prediction and prediction error
        for (j=0; j<4; j++)
        for (i=0; i<4; i++)
        {
          img->mpr[block_x+i][block_y+j]  = img->mprr[ipmode][j][i];
          img->m7[i][j]                   = imgY_org[pic_opix_y+j][pic_opix_x+i] - img->mprr[ipmode][j][i];
        }


//**************************************************************

		// 下面是提取殘差的程式碼(原始值,預測值和殘差都打印出來)

		// controlFlag是static int 型別的變數,用於表示巨集塊中的小塊
		// 比如controlFlag為2,則表示第一巨集塊的第二個4*4小塊
		controlFlag++;
		if(2 == controlFlag)
		{
			printf("****************************\n");
			for (j = 0; j < 4; j++)
			{
				for (i = 0; i < 4; i++)
				{
					printf("%d\t",imgY_org[pic_opix_y+j][pic_opix_x+i]);
				}
				printf("\n");
			}

			
			printf("****************************\n");
			for (j = 0; j < 4; j++)
			{
				for (i = 0; i < 4; i++)
				{
					printf("%d\t",img->mprr[ipmode][j][i]);
				}
				printf("\n");
			}

			printf("****************************\n");
			for (j=0; j<4; j++)
			{
				for (i=0; i<4; i++)
				{
					printf("%d\t",img->m7[i][j]);
				}
				printf("\n");
			}
		}
		
//**************************************************************


        //===== store the coding state =====
        store_coding_state (cs_cm);
        // get and check rate-distortion cost
        if ((rdcost = RDCost_for_4x4IntraBlocks (&c_nz, b8, b4, ipmode, lambda, min_rdcost, mostProbableMode)) < min_rdcost)
        {
          //--- set coefficients ---
          for (j=0; j<2; j++)
          for (i=0; i<18;i++)  cofAC4x4[j][i]=img->cofAC[b8][b4][j][i];

          //--- set reconstruction ---
          for (y=0; y<4; y++)
          for (x=0; x<4; x++)  rec4x4[y][x] = enc_picture->imgY[pic_pix_y+y][pic_pix_x+x];

          //--- flag if dct-coefficients must be coded ---
          nonzero = c_nz;

          //--- set best mode update minimum cost ---
          min_rdcost  = rdcost;
          best_ipmode = ipmode;
        }
        reset_coding_state (cs_cm);
      }
    }
  }

  //===== set intra mode prediction =====
  img->ipredmode[pic_block_x][pic_block_y] = best_ipmode;
  img->mb_data[img->current_mb_nr].intra_pred_modes[4*b8+b4] = mostProbableMode == best_ipmode ? -1 : best_ipmode < mostProbableMode ? best_ipmode : best_ipmode-1;

  if (!input->rdopt)
  {
    // get prediction and prediction error
    for (j=0; j<4; j++)
      for (i=0; i<4; i++)
      {
        img->mpr[block_x+i][block_y+j]  = img->mprr[best_ipmode][j][i];
        img->m7[i][j]                   = imgY_org[pic_opix_y+j][pic_opix_x+i] - img->mprr[best_ipmode][j][i];
      }
    nonzero = dct_luma (block_x, block_y, &dummy, 1);
  }
  else
  {
    //===== restore coefficients =====
    for (j=0; j<2; j++)
    for (i=0; i<18;i++)  img->cofAC[b8][b4][j][i]=cofAC4x4[j][i];
  
    //===== restore reconstruction and prediction (needed if single coeffs are removed) =====
    for (y=0; y<4; y++)
    for (x=0; x<4; x++)
    {
      enc_picture->imgY[pic_pix_y+y][pic_pix_x+x] = rec4x4[y][x];
      img->mpr[block_x+x][block_y+y] = img->mprr[best_ipmode][y][x];
    }
  }

  return nonzero;
}

      結果為:

****************************
251     254     254     253
228     205     213     185
197     173     185     136
177     189     198     160
****************************
238     238     238     238
205     205     205     205
167     167     167     167
160     160     160     160
****************************
13      16      16      15
23      0       8       -20
30      6       18      -31
17      29      38      0

      三個矩陣分別對應第一幀第一巨集塊的第二個4*4塊的原始值、預測值和殘差,為了驗證上述結果的正確性,可以用H.264visa分析一下,結果如下:

      原始值為:(注意: H.264visa也可以讀取原始的YUV資料)
====================== Y Data ======================
+----------------+----------------+----------------+----------------+
| 43,216,254,249,|251,254,254,253,|251,252,254,254,|254,254,254,253,|
| 49,198,193,211,|228,205,213,185,|211,207,186,248,|198,203,208,183,|
| 48,194,177,171,|197,173,185,136,|191,195,138,179,|142,176,177,135,|
| 46,214,225,169,|177,189,198,160,|203,208,177,165,|173,196,191,156,|
+----------------+----------------+----------------+----------------+
| 41,185,208,180,|203,228,226,200,|214,226,225,227,|228,225,224,210,|
| 31,130,173,178,|215,230,221,212,|220,229,227,228,|229,227,226,226,|
| 29,119,194,216,|211,213,219,222,|225,223,220,219,|218,218,218,218,|
| 25,126,219,224,|217,224,227,227,|227,226,225,224,|220,220,221,222,|
+----------------+----------------+----------------+----------------+
| 26,131,215,223,|226,225,225,225,|225,226,223,219,|221,221,219,220,|
| 30,136,216,226,|223,224,225,225,|224,221,217,221,|222,219,220,226,|
| 30,136,216,227,|224,224,225,223,|221,218,221,216,|211,224,224,211,|
| 29,135,217,225,|222,221,222,222,|221,209,181,155,|186,210,186,164,|
+----------------+----------------+----------------+----------------+
| 29,134,216,224,|226,230,230,227,|206,177,146,113,|149,162,147,150,|
| 29,135,219,231,|225,201,190,185,|163,144,153,140,|127,143,165,184,|
| 30,139,210,192,|165,142,134,133,|143,141,129,138,|150,178,201,207,|
| 30,125,166,145,|144,154,132,111,|118,161,175,180,|204,214,213,209,|
+----------------+----------------+----------------+----------------+

       預測值為:(注意:H.264visa相當於一個解碼器,解碼端的殘差和編碼端的殘差必定相等)

====================== Y Data ======================
+----------------+----------------+----------------+----------------+
|128,128,128,128,|238,238,238,238,|255,255,255,255,|245,228,210,192,|
|128,128,128,128,|205,205,205,205,|180,180,180,180,|210,192,174,170,|
|128,128,128,128,|167,167,167,167,|137,137,137,137,|174,170,166,166,|
|128,128,128,128,|160,160,160,160,|169,169,169,169,|166,166,166,166,|
+----------------+----------------+----------------+----------------+
|161,161,161,161,|179,189,182,169,|201,201,201,201,|219,219,219,219,|
|161,161,161,161,|184,185,175,169,|214,214,214,214,|227,227,227,227,|
|161,161,161,161,|189,182,169,169,|216,216,216,216,|219,219,219,219,|
|161,161,161,161,|185,175,169,169,|229,229,229,229,|227,227,227,227,|
+----------------+----------------+----------------+----------------+
| 28,127,218,229,|224,224,224,224,|227,227,228,227,|224,224,224,224,|
| 28,127,218,229,|224,224,224,224,|224,225,227,227,|214,214,214,214,|
| 28,127,218,229,|224,224,224,224,|224,224,224,225,|212,212,212,212,|
| 28,127,218,229,|224,224,224,224,|224,224,224,224,|165,165,165,165,|
+----------------+----------------+----------------+----------------+
| 33,130,216,224,|231,223,215,194,|204,182,160,142,|127,133,139,147,|
| 33,130,216,224,|215,194,173,162,|160,142,125,120,|139,147,154,165,|
| 33,130,216,224,|173,162,150,150,|125,120,116,116,|154,165,176,176,|
| 33,130,216,224,|150,150,150,150,|116,116,116,116,|176,176,176,176,|
+----------------+----------------+----------------+----------------+

      殘差為:(注意:H.264visa相當於一個解碼器,而解碼端的殘差與編碼端的殘差只是近似,並不相等)

====================== Y Data ======================
+------------------------+------------------------+------------------------+------------------------+
|  -78,   88,  132,  110,|   24,   14,   24,   19,|   -8,    7,   -3,   -4,|   16,   31,   48,   51,|
|  -81,   63,   67,   77,|   30,    1,   11,  -25,|   19,   24,    6,   59,|  -12,   20,   32,   10,|
|  -83,   62,   48,   39,|   25,    6,   16,  -30,|   54,   46,    4,   44,|  -30,    7,    5,  -32,|
|  -80,   87,   93,   32,|   14,   24,   34,    9,|   31,   37,    7,   -3,|    6,   28,   21,   -9,|
+------------------------+------------------------+------------------------+------------------------+
| -117,   22,   51,   22,|   25,   35,   38,   32,|   18,   18,   18,   18,|    5,    5,    5,    5,|
| -135,  -22,   22,   19,|   32,   43,   50,   45,|   13,   13,   13,   13,|    3,    3,    3,    3,|
| -131,  -38,   38,   55,|   20,   35,   48,   47,|    3,    3,    3,    3,|   -2,   -2,   -2,   -2,|
| -133,  -34,   57,   68,|   27,   43,   60,   60,|   -2,   -2,   -2,   -2,|   -5,   -5,   -5,   -5,|
+------------------------+------------------------+------------------------+------------------------+
|    5,    3,   -2,   -5,|    0,    0,    0,    0,|   -4,   -4,   -3,   -3,|   -5,   -6,   -5,   -2,|
|    5,    3,   -2,   -5,|    0,    0,    0,    0,|   -3,   -5,  -10,  -13,|   -2,    5,   14,   15,|
|    5,    3,   -2,   -5,|    0,    0,    0,    0,|   -3,   -5,  -10,  -13,|    0,   14,   15,    3,|
|    5,    3,   -2,   -5,|    0,    0,    0,    0,|    2,  -13,  -44,  -59,|   23,   35,   24,    0,|
+------------------------+------------------------+------------------------+------------------------+
|   -4,   -4,    0,    4,|    1,    5,   18,   26,|    0,    0,   -2,  -34,|   25,   20,    8,    3,|
|    2,    7,   11,   10,|   13,    3,    9,   25,|    6,    7,   25,   26,|   -9,   -3,    9,   15,|
|    0,    6,   -8,  -28,|   -5,  -11,  -17,  -17,|   16,   20,   12,   16,|   -5,    4,   22,   31,|
|   -6,   -5,  -39,  -74,|   -9,    3,  -10,  -34,|    6,   43,   55,   60,|   33,   33,   35,   35,|
+------------------------+------------------------+------------------------+------------------------+

       最後,如果上面程式碼中的if(2 == controlFlag)改為if(1 == controlFlag),那麼結果為:

****************************
43      216     254     249
49      198     193     211
48      194     177     171
46      214     225     169
****************************
128     128     128     128
128     128     128     128
128     128     128     128
128     128     128     128
****************************
-85     88      126     121
-79     70      65      83
-80     66      49      43
-82     86      97      41

       與上面的H.264visa的結果進行對比,一切都一目瞭然,便不再贅述了.

       P.S. 後來,我發現,上面的過程是有瑕疵的,因為對於一個巨集塊來說,Mode_Decision_for_4x4IntraBlocks函式不止被呼叫16次,所以並不對應16個4*4塊,為什麼會有這種情況呢?跟蹤程式碼後發現,原來對於一個4*4塊而言,要選出最終最合理的幀內預測模式,所要進行的DCT變換次數遠不止16次. 所以如果要真正在編碼端提取畫素殘差,就應該對這麼多次有所選擇, 而JM8.6程式碼必然要作出了這樣的選擇,找找就可以了.