almost finished opencl-ization of cascade classifier

modules/core/include/opencv2/core/ocl.hpp

@@ -402,6 +402,61 @@ public:
         int i = set(0, a0); i = set(i, a1); i = set(i, a2); i = set(i, a3); i = set(i, a4); i = set(i, a5);
         i = set(i, a6); i = set(i, a7); i = set(i, a8); i = set(i, a9); i = set(i, a10); set(i, a11); return *this;
     }
+    
+    template<typename _Tp0, typename _Tp1, typename _Tp2, typename _Tp3,
+             typename _Tp4, typename _Tp5, typename _Tp6, typename _Tp7,
+             typename _Tp8, typename _Tp9, typename _Tp10, typename _Tp11, typename _Tp12>
+    Kernel& args(const _Tp0& a0, const _Tp1& a1, const _Tp2& a2, const _Tp3& a3,
+                 const _Tp4& a4, const _Tp5& a5, const _Tp6& a6, const _Tp7& a7,
+                 const _Tp8& a8, const _Tp9& a9, const _Tp10& a10, const _Tp11& a11,
+                 const _Tp12& a12)
+    {
+        int i = set(0, a0); i = set(i, a1); i = set(i, a2); i = set(i, a3); i = set(i, a4); i = set(i, a5);
+        i = set(i, a6); i = set(i, a7); i = set(i, a8); i = set(i, a9); i = set(i, a10); i = set(i, a11);
+        set(i, a12); return *this;
+    }
+    
+    template<typename _Tp0, typename _Tp1, typename _Tp2, typename _Tp3,
+             typename _Tp4, typename _Tp5, typename _Tp6, typename _Tp7,
+             typename _Tp8, typename _Tp9, typename _Tp10, typename _Tp11, typename _Tp12,
+             typename _Tp13>
+    Kernel& args(const _Tp0& a0, const _Tp1& a1, const _Tp2& a2, const _Tp3& a3,
+                 const _Tp4& a4, const _Tp5& a5, const _Tp6& a6, const _Tp7& a7,
+                 const _Tp8& a8, const _Tp9& a9, const _Tp10& a10, const _Tp11& a11,
+                 const _Tp12& a12, const _Tp13& a13)
+    {
+        int i = set(0, a0); i = set(i, a1); i = set(i, a2); i = set(i, a3); i = set(i, a4); i = set(i, a5);
+        i = set(i, a6); i = set(i, a7); i = set(i, a8); i = set(i, a9); i = set(i, a10); i = set(i, a11);
+        i = set(i, a12); set(i, a13); return *this;
+    }
+    
+    template<typename _Tp0, typename _Tp1, typename _Tp2, typename _Tp3,
+             typename _Tp4, typename _Tp5, typename _Tp6, typename _Tp7,
+             typename _Tp8, typename _Tp9, typename _Tp10, typename _Tp11, typename _Tp12,
+             typename _Tp13, typename _Tp14>
+    Kernel& args(const _Tp0& a0, const _Tp1& a1, const _Tp2& a2, const _Tp3& a3,
+                 const _Tp4& a4, const _Tp5& a5, const _Tp6& a6, const _Tp7& a7,
+                 const _Tp8& a8, const _Tp9& a9, const _Tp10& a10, const _Tp11& a11,
+                 const _Tp12& a12, const _Tp13& a13, const _Tp14& a14)
+    {
+        int i = set(0, a0); i = set(i, a1); i = set(i, a2); i = set(i, a3); i = set(i, a4); i = set(i, a5);
+        i = set(i, a6); i = set(i, a7); i = set(i, a8); i = set(i, a9); i = set(i, a10); i = set(i, a11);
+        i = set(i, a12); i = set(i, a13); set(i, a14); return *this;
+    }
+    
+    template<typename _Tp0, typename _Tp1, typename _Tp2, typename _Tp3,
+             typename _Tp4, typename _Tp5, typename _Tp6, typename _Tp7,
+             typename _Tp8, typename _Tp9, typename _Tp10, typename _Tp11, typename _Tp12,
+             typename _Tp13, typename _Tp14, typename _Tp15>
+    Kernel& args(const _Tp0& a0, const _Tp1& a1, const _Tp2& a2, const _Tp3& a3,
+                 const _Tp4& a4, const _Tp5& a5, const _Tp6& a6, const _Tp7& a7,
+                 const _Tp8& a8, const _Tp9& a9, const _Tp10& a10, const _Tp11& a11,
+                 const _Tp12& a12, const _Tp13& a13, const _Tp14& a14, const _Tp15& a15)
+    {
+        int i = set(0, a0); i = set(i, a1); i = set(i, a2); i = set(i, a3); i = set(i, a4); i = set(i, a5);
+        i = set(i, a6); i = set(i, a7); i = set(i, a8); i = set(i, a9); i = set(i, a10); i = set(i, a11);
+        i = set(i, a12); i = set(i, a13); i = set(i, a14); set(i, a15); return *this;
+    }
 
     bool run(int dims, size_t globalsize[],
              size_t localsize[], bool sync, const Queue& q=Queue());

modules/imgproc/include/opencv2/imgproc.hpp

@@ -1075,6 +1075,11 @@ CV_EXPORTS_W void boxFilter( InputArray src, OutputArray dst, int ddepth,
                              Size ksize, Point anchor = Point(-1,-1),
                              bool normalize = true,
                              int borderType = BORDER_DEFAULT );
+    
+CV_EXPORTS_W void sqrBoxFilter( InputArray _src, OutputArray _dst, int ddepth,
+                                Size ksize, Point anchor = Point(-1, -1),
+                                bool normalize = true,
+                                int borderType = BORDER_DEFAULT );
 
 //! a synonym for normalized box filter
 CV_EXPORTS_W void blur( InputArray src, OutputArray dst,

modules/imgproc/src/smooth.cpp

@@ -741,6 +741,114 @@ void cv::blur( InputArray src, OutputArray dst,
     boxFilter( src, dst, -1, ksize, anchor, true, borderType );
 }
 
+
+/****************************************************************************************\
+                                    Squared Box Filter
+\****************************************************************************************/
+
+namespace cv
+{
+
+template<typename T, typename ST> struct SqrRowSum : public BaseRowFilter
+{
+    SqrRowSum( int _ksize, int _anchor )
+    {
+        ksize = _ksize;
+        anchor = _anchor;
+    }
+    
+    void operator()(const uchar* src, uchar* dst, int width, int cn)
+    {
+        const T* S = (const T*)src;
+        ST* D = (ST*)dst;
+        int i = 0, k, ksz_cn = ksize*cn;
+        
+        width = (width - 1)*cn;
+        for( k = 0; k < cn; k++, S++, D++ )
+        {
+            ST s = 0;
+            for( i = 0; i < ksz_cn; i += cn )
+            {
+                ST val = (ST)S[i];
+                s += val*val;
+            }
+            D[0] = s;
+            for( i = 0; i < width; i += cn )
+            {
+                ST val0 = (ST)S[i], val1 = (ST)S[i + ksz_cn];
+                s += val1*val1 - val0*val0;
+                D[i+cn] = s;
+            }
+        }
+    }
+};
+
+static Ptr<BaseRowFilter> getSqrRowSumFilter(int srcType, int sumType, int ksize, int anchor)
+{
+    int sdepth = CV_MAT_DEPTH(srcType), ddepth = CV_MAT_DEPTH(sumType);
+    CV_Assert( CV_MAT_CN(sumType) == CV_MAT_CN(srcType) );
+    
+    if( anchor < 0 )
+        anchor = ksize/2;
+    
+    if( sdepth == CV_8U && ddepth == CV_32S )
+        return makePtr<SqrRowSum<uchar, int> >(ksize, anchor);
+    if( sdepth == CV_8U && ddepth == CV_64F )
+        return makePtr<SqrRowSum<uchar, double> >(ksize, anchor);
+    if( sdepth == CV_16U && ddepth == CV_64F )
+        return makePtr<SqrRowSum<ushort, double> >(ksize, anchor);
+    if( sdepth == CV_16S && ddepth == CV_64F )
+        return makePtr<SqrRowSum<short, double> >(ksize, anchor);
+    if( sdepth == CV_32F && ddepth == CV_64F )
+        return makePtr<SqrRowSum<float, double> >(ksize, anchor);
+    if( sdepth == CV_64F && ddepth == CV_64F )
+        return makePtr<SqrRowSum<double, double> >(ksize, anchor);
+    
+    CV_Error_( CV_StsNotImplemented,
+              ("Unsupported combination of source format (=%d), and buffer format (=%d)",
+               srcType, sumType));
+    
+    return Ptr<BaseRowFilter>();
+}
+
+}
+
+void cv::sqrBoxFilter( InputArray _src, OutputArray _dst, int ddepth,
+                       Size ksize, Point anchor,
+                       bool normalize, int borderType )
+{
+    Mat src = _src.getMat();
+    int sdepth = src.depth(), cn = src.channels();
+    if( ddepth < 0 )
+        ddepth = sdepth < CV_32F ? CV_32F : CV_64F;
+    _dst.create( src.size(), CV_MAKETYPE(ddepth, cn) );
+    Mat dst = _dst.getMat();
+    if( borderType != BORDER_CONSTANT && normalize )
+    {
+        if( src.rows == 1 )
+            ksize.height = 1;
+        if( src.cols == 1 )
+            ksize.width = 1;
+    }
+    
+    int sumType = CV_64F;
+    if( sdepth == CV_8U )
+        sumType = CV_32S;
+    sumType = CV_MAKETYPE( sumType, cn );
+    int srcType = CV_MAKETYPE(sdepth, cn);
+    int dstType = CV_MAKETYPE(ddepth, cn);
+    
+    Ptr<BaseRowFilter> rowFilter = getSqrRowSumFilter(srcType, sumType, ksize.width, anchor.x );
+    Ptr<BaseColumnFilter> columnFilter = getColumnSumFilter(sumType,
+                                                            dstType, ksize.height, anchor.y,
+                                                            normalize ? 1./(ksize.width*ksize.height) : 1);
+    
+    Ptr<FilterEngine> f = makePtr<FilterEngine>(Ptr<BaseFilter>(), rowFilter, columnFilter,
+                                                srcType, dstType, sumType, borderType );
+    f->apply( src, dst );
+}
+
+
 /****************************************************************************************\
                                      Gaussian Blur
 \****************************************************************************************/

modules/objdetect/include/opencv2/objdetect.hpp

@@ -135,7 +135,7 @@ public:
     virtual Ptr<FeatureEvaluator> clone() const;
     virtual int getFeatureType() const;
 
-    virtual bool setImage(InputArray img, Size origWinSize);
+    virtual bool setImage(InputArray img, Size origWinSize, Size sumSize);
     virtual bool setWindow(Point p);
 
     virtual double calcOrd(int featureIdx) const;

modules/objdetect/src/cascadedetect.hpp

@@ -42,21 +42,20 @@ public:
     bool isOldFormatCascade() const;
     Size getOriginalWindowSize() const;
     int getFeatureType() const;
-    bool setImage( InputArray );
     void* getOldCascade();
 
     void setMaskGenerator(const Ptr<MaskGenerator>& maskGenerator);
     Ptr<MaskGenerator> getMaskGenerator();
 
 protected:
+    enum { SUM_ALIGN = 16 };
+    
     bool detectSingleScale( InputArray image, Size processingRectSize,
                             int yStep, double factor, std::vector<Rect>& candidates,
                             std::vector<int>& rejectLevels, std::vector<double>& levelWeights,
-                            bool outputRejectLevels = false );
+                            Size sumSize0, bool outputRejectLevels = false );
     bool ocl_detectSingleScale( InputArray image, Size processingRectSize,
-                           int yStep, double factor, std::vector<Rect>& candidates,
-                           std::vector<int>& rejectLevels, std::vector<double>& levelWeights,
-                           bool outputRejectLevels = false );
+                                int yStep, double factor, Size sumSize0 );
     
 
     void detectMultiScaleNoGrouping( InputArray image, std::vector<Rect>& candidates,
@@ -86,7 +85,6 @@ protected:
     template<class FEval>
     friend int predictCategoricalStump( CascadeClassifierImpl& cascade, Ptr<FeatureEvaluator> &featureEvaluator, double& weight);
 
-    bool setImage( Ptr<FeatureEvaluator>& feval, const Mat& image);
     int runAt( Ptr<FeatureEvaluator>& feval, Point pt, double& weight );
 
     class Data
@@ -134,7 +132,7 @@ protected:
 
     Ptr<MaskGenerator> maskGenerator;
     UMat ugrayImage, uimageBuffer;
-    UMat ufacepos, ustages, uclassifiers, unodes, uleaves, usubsets;
+    UMat ufacepos, ustages, uclassifiers, unodes, uleaves, usubsets, uparams;
     ocl::Kernel cascadeKernel;
     bool tryOpenCL;
     
@@ -270,10 +268,9 @@ public:
     virtual Ptr<FeatureEvaluator> clone() const;
     virtual int getFeatureType() const { return FeatureEvaluator::HAAR; }
 
-    virtual bool setImage(InputArray, Size origWinSize);
+    virtual bool setImage(InputArray, Size origWinSize, Size sumSize);
     virtual bool setWindow(Point pt);
-    
-    virtual bool setUMat(InputArray, Size origWinSize, Size origImgSize);
+    virtual Rect getNormRect() const;
     virtual void getUMats(std::vector<UMat>& bufs);
 
     double operator()(int featureIdx) const
@@ -282,22 +279,19 @@ public:
     { return (*this)(featureIdx); }
 
 protected:
-    Size origWinSize, origImgSize;
+    Size origWinSize, sumSize0;
     Ptr<std::vector<Feature> > features;
     Ptr<std::vector<OptFeature> > optfeatures;
     OptFeature* optfeaturesPtr; // optimization
     bool hasTiltedFeatures;
 
-    Mat sum0, sqsum0;
-    Mat sum, sqsum, tilted;
-    UMat usum, usqsum, fbuf;
+    Mat sum0, sum, sqsum0, sqsum;
+    UMat usum0, usum, usqsum0, usqsum, ufbuf;
 
     Rect normrect;
     int nofs[4];
-    int nqofs[4];
 
     const int* pwin;
-    const double* pqwin;
     double varianceNormFactor;
 };
 
@@ -376,7 +370,7 @@ public:
     virtual Ptr<FeatureEvaluator> clone() const;
     virtual int getFeatureType() const { return FeatureEvaluator::LBP; }
 
-    virtual bool setImage(InputArray image, Size _origWinSize);
+    virtual bool setImage(InputArray image, Size _origWinSize, Size);
     virtual bool setWindow(Point pt);
 
     int operator()(int featureIdx) const
@@ -453,7 +447,7 @@ public:
     virtual bool read( const FileNode& node );
     virtual Ptr<FeatureEvaluator> clone() const;
     virtual int getFeatureType() const { return FeatureEvaluator::HOG; }
-    virtual bool setImage( InputArray image, Size winSize );
+    virtual bool setImage( InputArray image, Size winSize, Size );
     virtual bool setWindow( Point pt );
     double operator()(int featureIdx) const
     {