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

apps/traincascade/boost.cpp

@@ -815,7 +815,7 @@ float CvCascadeBoostTrainData::getVarValue( int vi, int si )
 }
 
 
-struct FeatureIdxOnlyPrecalc
+struct FeatureIdxOnlyPrecalc : ParallelLoopBody
 {
     FeatureIdxOnlyPrecalc( const CvFeatureEvaluator* _featureEvaluator, CvMat* _buf, int _sample_count, bool _is_buf_16u )
     {
@@ -825,11 +825,11 @@ struct FeatureIdxOnlyPrecalc
         idst = _buf->data.i;
         is_buf_16u = _is_buf_16u;
     }
-    void operator()( const BlockedRange& range ) const
+    void operator()( const Range& range ) const
     {
         cv::AutoBuffer<float> valCache(sample_count);
         float* valCachePtr = (float*)valCache;
-        for ( int fi = range.begin(); fi < range.end(); fi++)
+        for ( int fi = range.start; fi < range.end; fi++)
         {
             for( int si = 0; si < sample_count; si++ )
             {
@@ -852,7 +852,7 @@ struct FeatureIdxOnlyPrecalc
     bool is_buf_16u;
 };
 
-struct FeatureValAndIdxPrecalc
+struct FeatureValAndIdxPrecalc : ParallelLoopBody
 {
     FeatureValAndIdxPrecalc( const CvFeatureEvaluator* _featureEvaluator, CvMat* _buf, Mat* _valCache, int _sample_count, bool _is_buf_16u )
     {
@@ -863,9 +863,9 @@ struct FeatureValAndIdxPrecalc
         idst = _buf->data.i;
         is_buf_16u = _is_buf_16u;
     }
-    void operator()( const BlockedRange& range ) const
+    void operator()( const Range& range ) const
     {
-        for ( int fi = range.begin(); fi < range.end(); fi++)
+        for ( int fi = range.start; fi < range.end; fi++)
         {
             for( int si = 0; si < sample_count; si++ )
             {
@@ -889,7 +889,7 @@ struct FeatureValAndIdxPrecalc
     bool is_buf_16u;
 };
 
-struct FeatureValOnlyPrecalc
+struct FeatureValOnlyPrecalc : ParallelLoopBody
 {
     FeatureValOnlyPrecalc( const CvFeatureEvaluator* _featureEvaluator, Mat* _valCache, int _sample_count )
     {
@@ -897,9 +897,9 @@ struct FeatureValOnlyPrecalc
         valCache = _valCache;
         sample_count = _sample_count;
     }
-    void operator()( const BlockedRange& range ) const
+    void operator()( const Range& range ) const
     {
-        for ( int fi = range.begin(); fi < range.end(); fi++)
+        for ( int fi = range.start; fi < range.end; fi++)
             for( int si = 0; si < sample_count; si++ )
                 valCache->at<float>(fi,si) = (*featureEvaluator)( fi, si );
     }
@@ -913,12 +913,12 @@ void CvCascadeBoostTrainData::precalculate()
     int minNum = MIN( numPrecalcVal, numPrecalcIdx);
 
     double proctime = -TIME( 0 );
-    parallel_for( BlockedRange(numPrecalcVal, numPrecalcIdx),
-                  FeatureIdxOnlyPrecalc(featureEvaluator, buf, sample_count, is_buf_16u!=0) );
-    parallel_for( BlockedRange(0, minNum),
-                  FeatureValAndIdxPrecalc(featureEvaluator, buf, &valCache, sample_count, is_buf_16u!=0) );
-    parallel_for( BlockedRange(minNum, numPrecalcVal),
-                  FeatureValOnlyPrecalc(featureEvaluator, &valCache, sample_count) );
+    parallel_for_( Range(numPrecalcVal, numPrecalcIdx),
+                   FeatureIdxOnlyPrecalc(featureEvaluator, buf, sample_count, is_buf_16u!=0) );
+    parallel_for_( Range(0, minNum),
+                   FeatureValAndIdxPrecalc(featureEvaluator, buf, &valCache, sample_count, is_buf_16u!=0) );
+    parallel_for_( Range(minNum, numPrecalcVal),
+                   FeatureValOnlyPrecalc(featureEvaluator, &valCache, sample_count) );
     cout << "Precalculation time: " << (proctime + TIME( 0 )) << endl;
 }