[x265] [PATCH] slicetype: Modify Scenecut algorithm to detect scene transition points

[aarthi at multicorewareinc.com]

# HG changeset patch
# User Aarthi Thirumalai
# Date 1437505166 -19800
#      Wed Jul 22 00:29:26 2015 +0530
# Node ID f134920ac855af45f052ccd6d3c239d39940a100
# Parent  46152345eb6ff261fd90272f7a0712300d6324c0
slicetype: Modify Scenecut algorithm to detect scene transition points
to improve Rate Control.

identify scene trasitions, fade-ins, fadeouts, sceneCuts and signal the flag bSceneChange
in Lowres structure. This flag will be used by RateControl to adjust the wps during scene cuts.
No changes in sliceType decisions or I frame placement.

diff -r 46152345eb6f -r f134920ac855 source/common/lowres.cpp
--- a/source/common/lowres.cpp	Mon Jul 20 17:18:54 2015 -0700
+++ b/source/common/lowres.cpp	Wed Jul 22 00:29:26 2015 +0530
@@ -127,6 +127,7 @@
 {
     bLastMiniGopBFrame = false;
     bScenecut = true;  // could be a scene-cut, until ruled out by flash detection
+    bSceneChange = true;
     bKeyframe = false; // Not a keyframe unless identified by lookahead
     frameNum = poc;
     leadingBframes = 0;
diff -r 46152345eb6f -r f134920ac855 source/common/lowres.h
--- a/source/common/lowres.h	Mon Jul 20 17:18:54 2015 -0700
+++ b/source/common/lowres.h	Wed Jul 22 00:29:26 2015 +0530
@@ -115,6 +115,7 @@
     int    leadingBframes;   // number of leading B frames for P or I
 
     bool   bScenecut;        // Set to false if the frame cannot possibly be part of a real scenecut.
+    bool   bSceneChange;
     bool   bKeyframe;
     bool   bLastMiniGopBFrame;
 
diff -r 46152345eb6f -r f134920ac855 source/encoder/slicetype.cpp
--- a/source/encoder/slicetype.cpp	Mon Jul 20 17:18:54 2015 -0700
+++ b/source/encoder/slicetype.cpp	Wed Jul 22 00:29:26 2015 +0530
@@ -462,6 +462,7 @@
     m_pool  = pool;
 
     m_lastNonB = NULL;
+    m_isSceneTransition = false;
     m_scratch  = NULL;
     m_tld      = NULL;
     m_filled   = false;
@@ -1375,6 +1376,8 @@
 bool Lookahead::scenecut(Lowres **frames, int p0, int p1, bool bRealScenecut, int numFrames, int maxSearch)
 {
     /* Only do analysis during a normal scenecut check. */
+    int64_t avgSatdCost = 0;
+    int cnt = 0;
     if (bRealScenecut && m_param->bframes)
     {
         int origmaxp1 = p0 + 1;
@@ -1392,11 +1395,45 @@
         for (int cp1 = p1; cp1 <= maxp1; cp1++)
         {
             if (!scenecutInternal(frames, p0, cp1, false))
+            {
                 /* Any frame in between p0 and cur_p1 cannot be a real scenecut. */
                 for (int i = cp1; i > p0; i--)
+                {
                     frames[i]->bScenecut = false;
+                    frames[i]->bSceneChange = false;
+                }
+            }
+            else if (!scenecutInternal(frames,cp1 - 1, cp1, false))
+            {
+                /* Prevent false flashes. */
+                frames[cp1]->bSceneChange = false;
+            }
+            else
+            {
+                /* compute average satdcost of flashes of scenecuts to confirm 
+                 * bwhether a scene transition is possible within the segment. */
+                avgSatdCost += frames[cp1]->costEst[1][0];
+                cnt++;
+            }
         }
-
+        /* Identify possible scene fluctuations by comparing the satd cost of the flashes.
+         * This could denote the beginning or ending of scene transitions.
+         * During a scene transition(fade in/fade outs), if fluctuate remains false,
+         * then the scene had completed its transition or stabilized. 
+         */
+        bool fluctuate = false;
+        if (avgSatdCost > 0)
+        {
+            avgSatdCost /= cnt;
+            for (int i= p0 ; i <= maxp1; i++)
+            {
+                if (abs(frames[i]->costEst[1][0] - avgSatdCost)  > 0.1 * avgSatdCost)
+                {
+                    fluctuate = true;
+                    break;
+                }
+            }
+        }
         /* Where A-F are scenes: AAAAABBCCDDEEFFFFFF
          * If each of BB ... EE are shorter than (maxp1-p0), they are
          * detected as flashes and not considered scenecuts.
@@ -1405,8 +1442,23 @@
         for (int cp0 = p0; cp0 <= maxp1; cp0++)
         {
             if (origmaxp1 > maxSearch || (cp0 < maxp1 && scenecutInternal(frames, cp0, maxp1, false)))
+            {
                 /* If cur_p0 is the p0 of a scenecut, it cannot be the p1 of a scenecut. */
                 frames[cp0]->bScenecut = false;
+                /* Check for start of flash sequence for a new scene transition segment. */
+                if (frames[cp0]->bSceneChange && !m_isSceneTransition && scenecutInternal(frames, cp0, cp0 + 1, false) && fluctuate)
+                {
+                    m_isSceneTransition = true;
+                }
+                else
+                    frames[cp0]->bSceneChange = false;
+             }
+        }
+
+        if (avgSatdCost == 0 || !fluctuate)
+        {
+            /* Signal end of scene transitioning */
+            m_isSceneTransition = false;
         }
     }
 
diff -r 46152345eb6f -r f134920ac855 source/encoder/slicetype.h
--- a/source/encoder/slicetype.h	Mon Jul 20 17:18:54 2015 -0700
+++ b/source/encoder/slicetype.h	Wed Jul 22 00:29:26 2015 +0530
@@ -127,7 +127,7 @@
     int           m_numCoopSlices;
     int           m_numRowsPerSlice;
     bool          m_filled;
-
+    bool          m_isSceneTransition;
     Lookahead(x265_param *param, ThreadPool *pool);
 
 #if DETAILED_CU_STATS