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

modules/features2d/src/detectors.cpp

@@ -212,7 +212,7 @@ static void keepStrongest( int N, std::vector<KeyPoint>& keypoints )
 }
 
 namespace {
-class GridAdaptedFeatureDetectorInvoker
+class GridAdaptedFeatureDetectorInvoker : public ParallelLoopBody
 {
 private:
     int gridRows_, gridCols_;
@@ -221,29 +221,24 @@ private:
     const Mat& image_;
     const Mat& mask_;
     const Ptr<FeatureDetector>& detector_;
-#ifdef HAVE_TBB
-    tbb::mutex* kptLock_;
-#endif
+    Mutex* kptLock_;
 
     GridAdaptedFeatureDetectorInvoker& operator=(const GridAdaptedFeatureDetectorInvoker&); // to quiet MSVC
 
 public:
 
-    GridAdaptedFeatureDetectorInvoker(const Ptr<FeatureDetector>& detector, const Mat& image, const Mat& mask, std::vector<KeyPoint>& keypoints, int maxPerCell, int gridRows, int gridCols
-#ifdef HAVE_TBB
-        , tbb::mutex* kptLock
-#endif
-        ) : gridRows_(gridRows), gridCols_(gridCols), maxPerCell_(maxPerCell),
-            keypoints_(keypoints), image_(image), mask_(mask), detector_(detector)
-#ifdef HAVE_TBB
-            , kptLock_(kptLock)
-#endif
+    GridAdaptedFeatureDetectorInvoker(const Ptr<FeatureDetector>& detector, const Mat& image, const Mat& mask,
+                                      std::vector<KeyPoint>& keypoints, int maxPerCell, int gridRows, int gridCols,
+                                      cv::Mutex* kptLock)
+        : gridRows_(gridRows), gridCols_(gridCols), maxPerCell_(maxPerCell),
+          keypoints_(keypoints), image_(image), mask_(mask), detector_(detector),
+          kptLock_(kptLock)
     {
     }
 
-    void operator() (const BlockedRange& range) const
+    void operator() (const Range& range) const
     {
-        for (int i = range.begin(); i < range.end(); ++i)
+        for (int i = range.start; i < range.end; ++i)
         {
             int celly = i / gridCols_;
             int cellx = i - celly * gridCols_;
@@ -268,9 +263,8 @@ public:
                 it->pt.x += col_range.start;
                 it->pt.y += row_range.start;
             }
-#ifdef HAVE_TBB
-            tbb::mutex::scoped_lock join_keypoints(*kptLock_);
-#endif
+
+            cv::AutoLock join_keypoints(*kptLock_);
             keypoints_.insert( keypoints_.end(), sub_keypoints.begin(), sub_keypoints.end() );
         }
     }
@@ -287,13 +281,9 @@ void GridAdaptedFeatureDetector::detectImpl( const Mat& image, std::vector<KeyPo
     keypoints.reserve(maxTotalKeypoints);
     int maxPerCell = maxTotalKeypoints / (gridRows * gridCols);
 
-#ifdef HAVE_TBB
-    tbb::mutex kptLock;
-    cv::parallel_for(cv::BlockedRange(0, gridRows * gridCols),
+    cv::Mutex kptLock;
+    cv::parallel_for_(cv::Range(0, gridRows * gridCols),
         GridAdaptedFeatureDetectorInvoker(detector, image, mask, keypoints, maxPerCell, gridRows, gridCols, &kptLock));
-#else
-    GridAdaptedFeatureDetectorInvoker(detector, image, mask, keypoints, maxPerCell, gridRows, gridCols)(cv::BlockedRange(0, gridRows * gridCols));
-#endif
 }
 
 /*