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/ml/src/gbt.cpp

@@ -884,7 +884,7 @@ float CvGBTrees::predict_serial( const CvMat* _sample, const CvMat* _missing,
 }
 
 
-class Tree_predictor
+class Tree_predictor : public cv::ParallelLoopBody
 {
 private:
     pCvSeq* weak;
@@ -894,9 +894,7 @@ private:
     const CvMat* missing;
     const float shrinkage;
 
-#ifdef HAVE_TBB
-    static tbb::spin_mutex SumMutex;
-#endif
+    static cv::Mutex SumMutex;
 
 
 public:
@@ -915,14 +913,11 @@ public:
     Tree_predictor& operator=( const Tree_predictor& )
     { return *this; }
 
-    virtual void operator()(const cv::BlockedRange& range) const
+    virtual void operator()(const cv::Range& range) const
     {
-#ifdef HAVE_TBB
-        tbb::spin_mutex::scoped_lock lock;
-#endif
         CvSeqReader reader;
-        int begin = range.begin();
-        int end = range.end();
+        int begin = range.start;
+        int end = range.end;
 
         int weak_count = end - begin;
         CvDTree* tree;
@@ -940,13 +935,11 @@ public:
                     tmp_sum += shrinkage*(float)(tree->predict(sample, missing)->value);
                 }
             }
-#ifdef HAVE_TBB
-            lock.acquire(SumMutex);
-            sum[i] += tmp_sum;
-            lock.release();
-#else
-            sum[i] += tmp_sum;
-#endif
+
+            {
+                cv::AutoLock lock(SumMutex);
+                sum[i] += tmp_sum;
+            }
         }
     } // Tree_predictor::operator()
 
@@ -954,11 +947,7 @@ public:
 
 }; // class Tree_predictor
 
-
-#ifdef HAVE_TBB
-tbb::spin_mutex Tree_predictor::SumMutex;
-#endif
-
+cv::Mutex Tree_predictor::SumMutex;
 
 
 float CvGBTrees::predict( const CvMat* _sample, const CvMat* _missing,
@@ -976,12 +965,7 @@ float CvGBTrees::predict( const CvMat* _sample, const CvMat* _missing,
         Tree_predictor predictor = Tree_predictor(weak_seq, class_count,
                                     params.shrinkage, _sample, _missing, sum);
 
-//#ifdef HAVE_TBB
-//      tbb::parallel_for(cv::BlockedRange(begin, end), predictor,
-//                          tbb::auto_partitioner());
-//#else
-        cv::parallel_for(cv::BlockedRange(begin, end), predictor);
-//#endif
+        cv::parallel_for_(cv::Range(begin, end), predictor);
 
         for (int i=0; i<class_count; ++i)
             sum[i] = sum[i] /** params.shrinkage*/ + base_value;
@@ -1210,7 +1194,7 @@ void CvGBTrees::read( CvFileStorage* fs, CvFileNode* node )
 
 //===========================================================================
 
-class Sample_predictor
+class Sample_predictor : public cv::ParallelLoopBody
 {
 private:
     const CvGBTrees* gbt;
@@ -1240,10 +1224,10 @@ public:
     {}
 
 
-    virtual void operator()(const cv::BlockedRange& range) const
+    virtual void operator()(const cv::Range& range) const
     {
-        int begin = range.begin();
-        int end = range.end();
+        int begin = range.start;
+        int end = range.end;
 
         CvMat x;
         CvMat miss;
@@ -1299,11 +1283,7 @@ CvGBTrees::calc_error( CvMLData* _data, int type, std::vector<float> *resp )
     Sample_predictor predictor = Sample_predictor(this, pred_resp, _data->get_values(),
             _data->get_missing(), _sample_idx);
 
-//#ifdef HAVE_TBB
-//    tbb::parallel_for(cv::BlockedRange(0,n), predictor, tbb::auto_partitioner());
-//#else
-    cv::parallel_for(cv::BlockedRange(0,n), predictor);
-//#endif
+    cv::parallel_for_(cv::Range(0,n), predictor);
 
     int* sidx = _sample_idx ? _sample_idx->data.i : 0;
     int r_step = CV_IS_MAT_CONT(response->type) ?