opencv/doc/gpu_object_detection.tex

\section{Object Detection}


\cvclass{gpu::HOGDescriptor}
Histogram of Oriented Gradients descriptor and detector.

\begin{lstlisting}
struct CV_EXPORTS HOGDescriptor
{
    enum { DEFAULT_WIN_SIGMA = -1 };
    enum { DEFAULT_NLEVELS = 64 };
    enum { DESCR_FORMAT_ROW_BY_ROW, DESCR_FORMAT_COL_BY_COL };

    HOGDescriptor(Size win_size=Size(64, 128), Size block_size=Size(16, 16),
                  Size block_stride=Size(8, 8), Size cell_size=Size(8, 8),
                  int nbins=9, double win_sigma=DEFAULT_WIN_SIGMA,
                  double threshold_L2hys=0.2, bool gamma_correction=true,
                  int nlevels=DEFAULT_NLEVELS);

    size_t getDescriptorSize() const;
    size_t getBlockHistogramSize() const;

    void setSVMDetector(const vector<float>& detector);

    static vector<float> getDefaultPeopleDetector();
    static vector<float> getPeopleDetector48x96();
    static vector<float> getPeopleDetector64x128();

    void detect(const GpuMat& img, vector<Point>& found_locations, 
                double hit_threshold=0, Size win_stride=Size(), 
                Size padding=Size());

    void detectMultiScale(const GpuMat& img, vector<Rect>& found_locations,
                          double hit_threshold=0, Size win_stride=Size(), 
                          Size padding=Size(), double scale0=1.05, 
                          int group_threshold=2);

    void getDescriptors(const GpuMat& img, Size win_stride, 
                        GpuMat& descriptors,
                        int descr_format=DESCR_FORMAT_COL_BY_COL);

    Size win_size;
    Size block_size;
    Size block_stride;
    Size cell_size;
    int nbins;
    double win_sigma;
    double threshold_L2hys;
    bool gamma_correction;
    int nlevels;

private:
    // Hidden
}
\end{lstlisting}

Interfaces of all methods are kept similar to CPU HOG descriptor and detector analogues as much as possible.


\cvCppFunc{gpu::HOGDescriptor::HOGDescriptor}
Creates HOG descriptor and detector.

\cvdefCpp{HOGDescriptor(Size win\_size=Size(64, 128), Size block\_size=Size(16, 16),\par
          Size block\_stride=Size(8, 8), Size cell\_size=Size(8, 8),\par
          int nbins=9, double win\_sigma=DEFAULT\_WIN\_SIGMA,\par
          double threshold\_L2hys=0.2, bool gamma\_correction=true,\par
          int nlevels=DEFAULT\_NLEVELS);}

\begin{description}
\cvarg{win\_size}{Detection window size. Must be aligned to block size and block stride.}
\cvarg{block\_size}{Block size in pixels. Must be aligned to cell size. Only (16,16) is supported for now.}
\cvarg{block\_stride}{Block stride. Must be a multiple of cell size.}
\cvarg{cell\_size}{Cell size. Only (8, 8) is supported for now.}
\cvarg{nbins}{Number of bins. Only 9 bins per cell is supported for now.}
\cvarg{win\_sigma}{Gaussian smoothing window parameter.}
\cvarg{threshold\_L2Hys}{L2-Hys normalization method shrinkage.}
\cvarg{gamma\_correction}{Do gamma correction preprocessing or not.}
\cvarg{nlevels}{Maximum number of detection window increases.}
\end{description}


\cvCppFunc{gpu::HOGDescriptor::getDescriptorSize}
Returns number of coefficients required for the classification.

\cvdefCpp{size\_t getDescriptorSize() const;}


\cvCppFunc{gpu::HOGDescriptor::getBlockHistogramSize}
Returns block histogram size.

\cvdefCpp{size\_t getBlockHistogramSize() const;}


\cvCppFunc{gpu::HOGDescriptor::setSVMDetector}
Sets coefficients for the linear SVM classifier. 

\cvdefCpp{void setSVMDetector(const vector<float>\& detector);}


\cvCppFunc{gpu::HOGDescriptor::getDefaultPeopleDetector}
Returns coefficients of the classifier trained for people detection (for default window size).

\cvdefCpp{static vector<float> getDefaultPeopleDetector();}


\cvCppFunc{gpu::HOGDescriptor::getPeopleDetector48x96}
Returns coefficients of the classifier trained for people detection (for 48x96 windows).

\cvdefCpp{static vector<float> getPeopleDetector48x96();}


\cvCppFunc{gpu::HOGDescriptor::getPeopleDetector64x128}
Returns coefficients of the classifier trained for people detection (for 64x128 windows).

\cvdefCpp{static vector<float> getPeopleDetector64x128();}


\cvCppFunc{gpu::HOGDescriptor::detect}
Perfroms object detection without multiscale window.

\cvdefCpp{void detect(const GpuMat\& img, vector<Point>\& found\_locations,\par
             double hit\_threshold=0, Size win\_stride=Size(),\par
             Size padding=Size());}

\begin{description}
\cvarg{img}{Source image. \texttt{CV\_8UC1} and \texttt{CV\_8UC4}types are supported for now.}
\cvarg{found\_locations}{Will contain left-top corner points of detected objects boundaries.}
\cvarg{hit\_threshold}{Threshold for the distance between features and SVM classifying plane. Usually it's 0 and should be specfied in the detector coefficients (as the last free coefficient), but if the free coefficient is omitted (it's allowed) you can specify it manually here.}
\cvarg{win\_stride}{Window stride. Must be a multiple of block stride.}
\cvarg{padding}{Mock parameter to keep CPU interface compatibility. Must be (0,0).}
\end{description}


\cvCppFunc{gpu::HOGDescriptor::detectMultiScale}
Perfroms object detection with multiscale window.

\cvdefCpp{void detectMultiScale(const GpuMat\& img, vector<Rect>\& found\_locations,\par
                      double hit\_threshold=0, Size win\_stride=Size(),\par
                      Size padding=Size(), double scale0=1.05,\par
                      int group\_threshold=2);}

\begin{description}
\cvarg{img}{Source image. See \cvCppCross{gpu::HOGDescriptor::detect} for type limitations.}
\cvarg{found\_locations}{Will contain detected objects boundaries.}
\cvarg{hit\_threshold}{The threshold for the distance between features and SVM classifying plane. See \cvCppCross{gpu::HOGDescriptor::detect} for details.}
\cvarg{win\_stride}{Window stride. Must be a multiple of block stride.}
\cvarg{padding}{Mock parameter to keep CPU interface compatibility. Must be (0,0).}
\cvarg{scale0}{Coefficient of the detection window increase.}
\cvarg{group\_threshold}{After detection some objects could be covered by many rectangles. This coefficient regulates similarity threshold. 0 means don't perform grouping.\newline
See \cvCppCross{groupRectangles}.}
\end{description}


\cvCppFunc{gpu::HOGDescriptor::getDescriptors}
Returns block descriptors computed for the whole image. It's mainly used for classifier learning purposes.

\cvdefCpp{void getDescriptors(const GpuMat\& img, Size win\_stride,\par
                    GpuMat\& descriptors,\par
                    int descr\_format=DESCR\_FORMAT\_COL\_BY\_COL);}

\begin{description}
\cvarg{img}{Source image. See \cvCppCross{gpu::HOGDescriptor::detect} for type limitations.}
\cvarg{win\_stride}{Window stride. Must be a multiple of block stride.}
\cvarg{descriptors}{2D array of descriptors.}
\cvarg{descr\_format}{Descriptor storage format: 
\begin{description}
    \cvarg{DESCR\_FORMAT\_ROW\_BY\_ROW}{Row-major order.}
    \cvarg{DESCR\_FORMAT\_COL\_BY\_COL}{Column-major order.}
\end{description}}
\end{description}