2-nd level of parallelization + detector remake

1. Added 2-nd level of parallelization of NN on OpenCL
2. Restructured detector - now all filters work independently:
Variance Filter->Ensemble->NN,  through "buffers"

Author: Auron-X

modules/tracking/samples/tld_test.cpp

@@ -48,8 +48,8 @@
 using namespace std;
 using namespace cv;
 
-#define NUM_TEST_FRAMES 500
-#define TEST_VIDEO_INDEX 1		//TLD Dataset Video Index from 1-10
+#define NUM_TEST_FRAMES 100
+#define TEST_VIDEO_INDEX 7		//TLD Dataset Video Index from 1-10
 //#define RECORD_VIDEO_FLG
 
 static Mat image;

modules/tracking/src/opencl/tldDetector.cl

@@ -31,12 +31,11 @@ __kernel void NCC(__global const uchar *patch,
 	int s1 = 0, s2 = 0, n1 = 0, n2 = 0, prod = 0;
 	float sq1 = 0, sq2 = 0, ares = 0;
 	int N = 225;
-	//NCC with positive patch
+	//NCC with positive sample
 	if (posFlg && id < posNum)
 	{
 		for (int i = 0; i < N; i++)
 		{
-			
 			s1 += positiveSamples[id * N + i];
 			s2 += patch[i];
 			n1 += positiveSamples[id * N + i] * positiveSamples[id * N + i];
@@ -46,10 +45,10 @@ __kernel void NCC(__global const uchar *patch,
 		sq1 = sqrt(max(0.0, n1 - 1.0 * s1 * s1 / N));
 		sq2 = sqrt(max(0.0, n2 - 1.0 * s2 * s2 / N));
 		ares = (sq2 == 0) ? sq1 / fabs(sq1) : (prod - s1 * s2 / N) / sq1 / sq2;
-		ncc[id] = ares;		
+		ncc[id] = ares;
 	}
 
-	//NCC with negative patch
+	//NCC with negative sample
 	if (!posFlg && id < negNum)
 	{
 		for (int i = 0; i < N; i++)
@@ -67,3 +66,68 @@ __kernel void NCC(__global const uchar *patch,
 		ncc[id+500] = ares;
 	}
 }
+
+__kernel void batchNCC(__global const uchar *patches,
+	__global const uchar *positiveSamples,
+	__global const uchar *negativeSamples,
+	__global float *posNcc,
+	__global float *negNcc,
+	int posNum,
+	int negNum,
+	int patchNum)
+{
+	int id = get_global_id(0);
+	bool posFlg;
+
+	if (id < 500*patchNum)
+		posFlg = true;
+	if (id >= 500*patchNum)
+	{
+		//Negative index
+		id = id - 500*patchNum;
+		posFlg = false;
+	}
+
+	int modelSampleID = id % 500;
+	int patchID = id / 500;
+
+	//Variables
+	int s1 = 0, s2 = 0, n1 = 0, n2 = 0, prod = 0;
+	float sq1 = 0, sq2 = 0, ares = 0;
+	int N = 225;
+
+	//NCC with positive sample
+	if (posFlg && modelSampleID < posNum)
+	{
+		for (int i = 0; i < N; i++)
+		{
+			s1 += positiveSamples[modelSampleID * N + i];
+			s2 += patches[patchID*N + i];
+			n1 += positiveSamples[modelSampleID * N + i] * positiveSamples[modelSampleID * N + i];
+			n2 += patches[patchID*N + i] * patches[patchID*N + i];
+			prod += positiveSamples[modelSampleID * N + i] * patches[patchID*N + i];
+		}
+		sq1 = sqrt(max(0.0, n1 - 1.0 * s1 * s1 / N));
+		sq2 = sqrt(max(0.0, n2 - 1.0 * s2 * s2 / N));
+		ares = (sq2 == 0) ? sq1 / fabs(sq1) : (prod - s1 * s2 / N) / sq1 / sq2;
+		posNcc[id] = ares;
+	}
+
+	//NCC with negative sample
+	if (!posFlg && modelSampleID < negNum)
+	{
+		for (int i = 0; i < N; i++)
+		{
+
+			s1 += negativeSamples[modelSampleID * N + i];
+			s2 += patches[patchID*N + i];
+			n1 += negativeSamples[modelSampleID * N + i] * negativeSamples[modelSampleID * N + i];
+			n2 += patches[patchID*N + i] * patches[patchID*N + i];
+			prod += negativeSamples[modelSampleID * N + i] * patches[patchID*N + i];
+		}
+		sq1 = sqrt(max(0.0, n1 - 1.0 * s1 * s1 / N));
+		sq2 = sqrt(max(0.0, n2 - 1.0 * s2 * s2 / N));
+		ares = (sq2 == 0) ? sq1 / fabs(sq1) : (prod - s1 * s2 / N) / sq1 / sq2;
+		negNcc[id] = ares;
+	}
+}