Fix opencv/opencv#4685. Fix #433.

Enable SURF OCL. Fix incorrect calling sequence for two kernels.
Fix compiler warnings in surf.cl.
Enable SURF OCL test. Test runs with no failures.

Author: Albert

modules/xfeatures2d/src/opencl/surf.cl

@@ -1102,10 +1102,10 @@ void SURF_computeDescriptors128(
     descriptors_step /= sizeof(*descriptors);
     keypoints_step   /= sizeof(*keypoints);
 
-    __global float * featureX   = keypoints + X_ROW * keypoints_step;
-    __global float * featureY   = keypoints + Y_ROW * keypoints_step;
-    __global float* featureSize = keypoints + SIZE_ROW * keypoints_step;
-    __global float* featureDir  = keypoints + ANGLE_ROW * keypoints_step;
+    __global const float * featureX   = keypoints + X_ROW * keypoints_step;
+    __global const float * featureY   = keypoints + Y_ROW * keypoints_step;
+    __global const float* featureSize = keypoints + SIZE_ROW * keypoints_step;
+    __global const float* featureDir  = keypoints + ANGLE_ROW * keypoints_step;
 
     // 2 floats (dx,dy) for each thread (5x5 sample points in each sub-region)
     volatile __local  float sdx[25];

modules/xfeatures2d/src/surf.ocl.cpp

@@ -91,11 +91,13 @@ bool SURF_OCL::init(const SURF_Impl* p)
         if(ocl::haveOpenCL())
         {
             const ocl::Device& dev = ocl::Device::getDefault();
-            if( dev.type() == ocl::Device::TYPE_CPU || dev.doubleFPConfig() == 0 )
+            if( dev.type() == ocl::Device::TYPE_CPU )
                 return false;
-            haveImageSupport = false;//dev.imageSupport();
-            kerOpts = haveImageSupport ? "-D HAVE_IMAGE2D -D DOUBLE_SUPPORT" : "";
-//            status = 1;
+            haveImageSupport = dev.imageSupport();
+            kerOpts = format("%s%s",
+				haveImageSupport ? "-D HAVE_IMAGE2D" : "",
+				dev.doubleFPConfig() > 0? " -D DOUBLE_SUPPORT": "");
+            status = 1;
         }
     }
     return status > 0;
@@ -243,7 +245,7 @@ bool SURF_OCL::computeDescriptors(const UMat &keypoints, OutputArray _descriptor
     }
 
     size_t localThreads[] = {6, 6};
-    size_t globalThreads[] = {nFeatures*localThreads[0], localThreads[1]};
+    size_t globalThreads[] = {nFeatures*localThreads[0], 16 * localThreads[1]};
 
     if(haveImageSupport)
     {
@@ -420,7 +422,7 @@ bool SURF_OCL::findMaximaInLayer(int counterOffset, int octave,
                               ocl::KernelArg::PtrReadWrite(maxPosBuffer),
                               ocl::KernelArg::PtrReadWrite(counters),
                               counterOffset, img_rows, img_cols,
-                              octave, nOctaveLayers,
+                              nOctaveLayers, octave,
                               layer_rows, layer_cols,
                               maxCandidates,
                               (float)params->hessianThreshold).run(2, globalThreads, localThreads, true);

modules/xfeatures2d/test/test_precomp.hpp

@@ -21,8 +21,8 @@
 #include "opencv2/opencv_modules.hpp"
 #include "cvconfig.h"
 
-#ifdef HAVE_OPENCV_OCL
-#  include "opencv2/ocl.hpp"
+#ifdef HAVE_OPENCL
+#  include "opencv2/core/ocl.hpp"
 #endif
 
 #ifdef HAVE_CUDA

modules/xfeatures2d/test/test_surf.ocl.cpp

@@ -45,11 +45,13 @@
 
 #include "test_precomp.hpp"
 
-#ifdef HAVE_OPENCV_OCL
+#ifdef HAVE_OPENCL
+
+namespace cvtest {
+namespace ocl {
 
 using namespace std;
 using std::tr1::get;
-
 static bool keyPointsEquals(const cv::KeyPoint& p1, const cv::KeyPoint& p2)
 {
     const double maxPtDif = 0.1;
@@ -133,31 +135,20 @@ PARAM_TEST_CASE(SURF, HessianThreshold, Octaves, OctaveLayers, Extended, Upright
     }
 };
 
-TEST_P(SURF, DISABLED_Detector)
+TEST_P(SURF, Detector)
 {
-    cv::Mat image  = cv::imread(string(cvtest::TS::ptr()->get_data_path()) + "shared/fruits.png", cv::IMREAD_GRAYSCALE);
+	cv::UMat image;
+	cv::ocl::setUseOpenCL(true);
+	cv::imread(string(cvtest::TS::ptr()->get_data_path()) + "shared/fruits.png", cv::IMREAD_GRAYSCALE).copyTo(image);
     ASSERT_FALSE(image.empty());
 
-    cv::ocl::SURF_OCL surf;
-    surf.hessianThreshold = static_cast<float>(hessianThreshold);
-    surf.nOctaves = nOctaves;
-    surf.nOctaveLayers = nOctaveLayers;
-    surf.extended = extended;
-    surf.upright = upright;
-    surf.keypointsRatio = 0.05f;
-
+    cv::Ptr<cv::xfeatures2d::SURF> surf = cv::xfeatures2d::SURF::create(hessianThreshold, nOctaves, nOctaveLayers, extended, upright);
     std::vector<cv::KeyPoint> keypoints;
-    surf(cv::ocl::oclMat(image), cv::ocl::oclMat(), keypoints);
-
-    cv::SURF surf_gold;
-    surf_gold.hessianThreshold = hessianThreshold;
-    surf_gold.nOctaves = nOctaves;
-    surf_gold.nOctaveLayers = nOctaveLayers;
-    surf_gold.extended = extended;
-    surf_gold.upright = upright;
+    surf->detect(image, keypoints, cv::noArray());
 
+	cv::ocl::setUseOpenCL(false);
     std::vector<cv::KeyPoint> keypoints_gold;
-    surf_gold(image, cv::noArray(), keypoints_gold);
+	surf->detect(image, keypoints_gold, cv::noArray());
 
     ASSERT_EQ(keypoints_gold.size(), keypoints.size());
     int matchedCount = getMatchedPointsCount(keypoints_gold, keypoints);
@@ -166,38 +157,29 @@ TEST_P(SURF, DISABLED_Detector)
     EXPECT_GT(matchedRatio, 0.99);
 }
 
-TEST_P(SURF, DISABLED_Descriptor)
+TEST_P(SURF, Descriptor)
 {
-    cv::Mat image  = cv::imread(string(cvtest::TS::ptr()->get_data_path()) + "shared/fruits.png", cv::IMREAD_GRAYSCALE);
+	cv::UMat image;
+	cv::ocl::setUseOpenCL(true);
+	cv::imread(string(cvtest::TS::ptr()->get_data_path()) + "shared/fruits.png", cv::IMREAD_GRAYSCALE).copyTo(image);
     ASSERT_FALSE(image.empty());
 
-    cv::ocl::SURF_OCL surf;
-    surf.hessianThreshold = static_cast<float>(hessianThreshold);
-    surf.nOctaves = nOctaves;
-    surf.nOctaveLayers = nOctaveLayers;
-    surf.extended = extended;
-    surf.upright = upright;
-    surf.keypointsRatio = 0.05f;
-
-    cv::SURF surf_gold;
-    surf_gold.hessianThreshold = hessianThreshold;
-    surf_gold.nOctaves = nOctaves;
-    surf_gold.nOctaveLayers = nOctaveLayers;
-    surf_gold.extended = extended;
-    surf_gold.upright = upright;
+	cv::Ptr<cv::xfeatures2d::SURF> surf = cv::xfeatures2d::SURF::create(hessianThreshold, nOctaves, nOctaveLayers, extended, upright);
 
     std::vector<cv::KeyPoint> keypoints;
-    surf_gold(image, cv::noArray(), keypoints);
+	surf->detect(image, keypoints, cv::noArray());
+
+    cv::UMat descriptors;
 
-    cv::ocl::oclMat descriptors;
-    surf(cv::ocl::oclMat(image), cv::ocl::oclMat(), keypoints, descriptors, true);
+    surf->detectAndCompute(image, cv::noArray(), keypoints, descriptors, true);
 
+	cv::ocl::setUseOpenCL(false);
     cv::Mat descriptors_gold;
-    surf_gold(image, cv::noArray(), keypoints, descriptors_gold, true);
+	surf->detectAndCompute(image, cv::noArray(), keypoints, descriptors_gold, true);
 
-    cv::BFMatcher matcher(surf.defaultNorm());
+    cv::BFMatcher matcher(surf->defaultNorm());
     std::vector<cv::DMatch> matches;
-    matcher.match(descriptors_gold, cv::Mat(descriptors), matches);
+    matcher.match(descriptors_gold, descriptors, matches);
 
     int matchedCount = getMatchedPointsCount(keypoints, keypoints, matches);
     double matchedRatio = static_cast<double>(matchedCount) / keypoints.size();
@@ -212,4 +194,6 @@ INSTANTIATE_TEST_CASE_P(OCL_Features2D, SURF, testing::Combine(
     testing::Values(Extended(false), Extended(true)),
     testing::Values(Upright(false), Upright(true))));
 
-#endif // HAVE_OPENCV_OCL
+} } // namespace cvtest::ocl
+
+#endif // HAVE_OPENCL