Merge cuda-geek/soft-cascade-gpu into cuda-dev

modules/gpu/include/opencv2/gpu/gpu.hpp

@@ -1532,6 +1532,76 @@ public:
     int detectMultiScale(const GpuMat& image, GpuMat& objectsBuf, Size maxObjectSize, Size minSize = Size(), double scaleFactor = 1.1, int minNeighbors = 4);
 };
 
+// ======================== GPU version for soft cascade ===================== //
+
+// Implementation of soft (stageless) cascaded detector.
+class CV_EXPORTS SCascade : public Algorithm
+{
+public:
+
+    // Representation of detectors result.
+    struct CV_EXPORTS Detection
+    {
+        ushort x;
+        ushort y;
+        ushort w;
+        ushort h;
+        float confidence;
+        int kind;
+
+        enum {PEDESTRIAN = 0};
+    };
+
+    enum { NO_REJECT = 1, DOLLAR = 2, /*PASCAL = 4,*/ DEFAULT = NO_REJECT};
+
+    // An empty cascade will be created.
+    // Param minScale is a minimum scale relative to the original size of the image on which cascade will be applyed.
+    // Param minScale is a maximum scale relative to the original size of the image on which cascade will be applyed.
+    // Param scales is a number of scales from minScale to maxScale.
+    // Param rejfactor is used for NMS.
+    SCascade(const double minScale = 0.4, const double maxScale = 5., const int scales = 55, const int rejCriteria = 1);
+
+    virtual ~SCascade();
+
+    cv::AlgorithmInfo* info() const;
+
+    // Load cascade from FileNode.
+    // Param fn is a root node for cascade. Should be <cascade>.
+    virtual bool load(const FileNode& fn);
+
+    // Load cascade config.
+    virtual void read(const FileNode& fn);
+
+    // Return the matrix of of detectioned objects.
+    // Param image is a frame on which detector will be applied.
+    // Param rois is a regions of interests mask generated by genRoi.
+    //    Only the objects that fall into one of the regions will be returned.
+    // Param objects is an output array of Detections represented as GpuMat of detections (SCascade::Detection)
+    //    The first element of the matrix is  actually a count of detections.
+    // Param stream is stream is a high-level CUDA stream abstraction used for asynchronous execution
+    virtual void detect(InputArray image, InputArray rois, OutputArray objects, Stream& stream = Stream::Null()) const;
+
+    // Convert ROI matrix into the suitable for detect method.
+    // Param roi is an input matrix of the same size as the image.
+    //    There non zero value mean that detector should be executed in this point.
+    // Param mask is an output mask
+    // Param stream is stream is a high-level CUDA stream abstraction used for asynchronous execution
+    virtual void genRoi(InputArray roi, OutputArray mask, Stream& stream = Stream::Null()) const;
+
+private:
+
+    struct Fields;
+    Fields* fields;
+
+    double minScale;
+    double maxScale;
+
+    int scales;
+    int rejCriteria;
+};
+
+CV_EXPORTS bool initModule_gpu(void);
+
 ////////////////////////////////// SURF //////////////////////////////////////////
 
 class CV_EXPORTS SURF_GPU