Merge remote-tracking branch 'origin/2.4'

Pull requests:
	#943 from jet47:cuda-5.5-support
	#944 from jet47:cmake-2.8.11-cuda-fix
	#912 from SpecLad:contributing
	#934 from SpecLad:parallel-for
	#931 from jet47:gpu-test-fixes
	#932 from bitwangyaoyao:2.4_fixBFM
	#918 from bitwangyaoyao:2.4_samples
	#924 from pengx17:2.4_arithm_fix
	#925 from pengx17:2.4_canny_tmp_fix
	#927 from bitwangyaoyao:2.4_perf
	#930 from pengx17:2.4_haar_ext
	#928 from apavlenko:bugfix_3027
	#920 from asmorkalov:android_move
	#910 from pengx17:2.4_oclgfft
	#913 from janm399:2.4
	#916 from bitwangyaoyao:2.4_fixPyrLK
	#919 from abidrahmank:2.4
	#923 from pengx17:2.4_macfix

Conflicts:
	modules/calib3d/src/stereobm.cpp
	modules/features2d/src/detectors.cpp
	modules/gpu/src/error.cpp
	modules/gpu/src/precomp.hpp
	modules/imgproc/src/distransform.cpp
	modules/imgproc/src/morph.cpp
	modules/ocl/include/opencv2/ocl/ocl.hpp
	modules/ocl/perf/perf_color.cpp
	modules/ocl/perf/perf_imgproc.cpp
	modules/ocl/perf/perf_match_template.cpp
	modules/ocl/perf/precomp.cpp
	modules/ocl/perf/precomp.hpp
	modules/ocl/src/arithm.cpp
	modules/ocl/src/canny.cpp
	modules/ocl/src/filtering.cpp
	modules/ocl/src/haar.cpp
	modules/ocl/src/hog.cpp
	modules/ocl/src/imgproc.cpp
	modules/ocl/src/opencl/haarobjectdetect.cl
	modules/ocl/src/pyrlk.cpp
	modules/video/src/bgfg_gaussmix2.cpp
	modules/video/src/lkpyramid.cpp
	platforms/linux/scripts/cmake_arm_gnueabi_hardfp.sh
	platforms/linux/scripts/cmake_arm_gnueabi_softfp.sh
	platforms/scripts/ABI_compat_generator.py
	samples/ocl/facedetect.cpp

samples/ocl/hog.cpp

@@ -46,7 +46,6 @@ public:
     bool gamma_corr;
 };
 
-
 class App
 {
 public:
@@ -65,6 +64,13 @@ public:
 
     string message() const;
 
+// This function test if gpu_rst matches cpu_rst.
+// If the two vectors are not equal, it will return the difference in vector size
+// Else if will return 
+// (total diff of each cpu and gpu rects covered pixels)/(total cpu rects covered pixels)
+    double checkRectSimilarity(Size sz, 
+                               std::vector<Rect>& cpu_rst, 
+                               std::vector<Rect>& gpu_rst);
 private:
     App operator=(App&);
 
@@ -291,6 +297,7 @@ void App::run()
         ocl::oclMat gpu_img;
 
         // Iterate over all frames
+        bool verify = false;
         while (running && !frame.empty())
         {
             workBegin();
@@ -317,7 +324,18 @@ void App::run()
                 gpu_img.upload(img);
                 gpu_hog.detectMultiScale(gpu_img, found, hit_threshold, win_stride,
                                          Size(0, 0), scale, gr_threshold);
-            }
+                if (!verify)
+                {
+                    // verify if GPU output same objects with CPU at 1st run
+                    verify = true;
+                    vector<Rect> ref_rst;
+                    cvtColor(img, img, COLOR_BGRA2BGR);
+                    cpu_hog.detectMultiScale(img, ref_rst, hit_threshold, win_stride,
+                                              Size(0, 0), scale, gr_threshold-2);
+                    double accuracy = checkRectSimilarity(img.size(), ref_rst, found);
+                    cout << "\naccuracy value: " << accuracy << endl;           
+                } 
+           }
             else cpu_hog.detectMultiScale(img, found, hit_threshold, win_stride,
                                           Size(0, 0), scale, gr_threshold);
             hogWorkEnd();
@@ -458,3 +476,45 @@ inline string App::workFps() const
     return ss.str();
 }
 
+double App::checkRectSimilarity(Size sz, 
+                                std::vector<Rect>& ob1, 
+                                std::vector<Rect>& ob2)
+{
+    double final_test_result = 0.0;
+    size_t sz1 = ob1.size();
+    size_t sz2 = ob2.size();
+
+    if(sz1 != sz2)
+        return sz1 > sz2 ? (double)(sz1 - sz2) : (double)(sz2 - sz1);
+    else
+    {
+        cv::Mat cpu_result(sz, CV_8UC1);
+        cpu_result.setTo(0);
+
+        for(vector<Rect>::const_iterator r = ob1.begin(); r != ob1.end(); r++)
+        {      
+            cv::Mat cpu_result_roi(cpu_result, *r);
+            cpu_result_roi.setTo(1);
+            cpu_result.copyTo(cpu_result);
+        }
+        int cpu_area = cv::countNonZero(cpu_result > 0);
+
+        cv::Mat gpu_result(sz, CV_8UC1);
+        gpu_result.setTo(0);
+        for(vector<Rect>::const_iterator r2 = ob2.begin(); r2 != ob2.end(); r2++)
+        {
+            cv::Mat gpu_result_roi(gpu_result, *r2);
+            gpu_result_roi.setTo(1);
+            gpu_result.copyTo(gpu_result);
+        }
+
+        cv::Mat result_;
+        multiply(cpu_result, gpu_result, result_);
+        int result = cv::countNonZero(result_ > 0);
+
+        final_test_result = 1.0 - (double)result/(double)cpu_area;
+    }
+    return final_test_result;
+
+}
+