/*M/////////////////////////////////////////////////////////////////////////////////////// // // IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING. // // By downloading, copying, installing or using the software you agree to this license. // If you do not agree to this license, do not download, install, // copy or use the software. // // // License Agreement // For Open Source Computer Vision Library // // Copyright (C) 2000-2008, Intel Corporation, all rights reserved. // Copyright (C) 2009, Willow Garage Inc., all rights reserved. // Copyright (C) 2013, OpenCV Foundation, all rights reserved. // Third party copyrights are property of their respective owners. // // Redistribution and use in source and binary forms, with or without modification, // are permitted provided that the following conditions are met: // // * Redistribution's of source code must retain the above copyright notice, // this list of conditions and the following disclaimer. // // * Redistribution's in binary form must reproduce the above copyright notice, // this list of conditions and the following disclaimer in the documentation // and/or other materials provided with the distribution. // // * The name of the copyright holders may not be used to endorse or promote products // derived from this software without specific prior written permission. // // This software is provided by the copyright holders and contributors "as is" and // any express or implied warranties, including, but not limited to, the implied // warranties of merchantability and fitness for a particular purpose are disclaimed. // In no event shall the Intel Corporation or contributors be liable for any direct, // indirect, incidental, special, exemplary, or consequential damages // (including, but not limited to, procurement of substitute goods or services; // loss of use, data, or profits; or business interruption) however caused // and on any theory of liability, whether in contract, strict liability, // or tort (including negligence or otherwise) arising in any way out of // the use of this software, even if advised of the possibility of such damage. // //M*/ #ifndef OPENCV_OBJDETECT_HPP #define OPENCV_OBJDETECT_HPP #include "opencv2/core.hpp" /** @defgroup objdetect Object Detection Haar Feature-based Cascade Classifier for Object Detection ---------------------------------------------------------- The object detector described below has been initially proposed by Paul Viola @cite Viola01 and improved by Rainer Lienhart @cite Lienhart02 . First, a classifier (namely a *cascade of boosted classifiers working with haar-like features*) is trained with a few hundred sample views of a particular object (i.e., a face or a car), called positive examples, that are scaled to the same size (say, 20x20), and negative examples - arbitrary images of the same size. After a classifier is trained, it can be applied to a region of interest (of the same size as used during the training) in an input image. The classifier outputs a "1" if the region is likely to show the object (i.e., face/car), and "0" otherwise. To search for the object in the whole image one can move the search window across the image and check every location using the classifier. The classifier is designed so that it can be easily "resized" in order to be able to find the objects of interest at different sizes, which is more efficient than resizing the image itself. So, to find an object of an unknown size in the image the scan procedure should be done several times at different scales. The word "cascade" in the classifier name means that the resultant classifier consists of several simpler classifiers (*stages*) that are applied subsequently to a region of interest until at some stage the candidate is rejected or all the stages are passed. The word "boosted" means that the classifiers at every stage of the cascade are complex themselves and they are built out of basic classifiers using one of four different boosting techniques (weighted voting). Currently Discrete Adaboost, Real Adaboost, Gentle Adaboost and Logitboost are supported. The basic classifiers are decision-tree classifiers with at least 2 leaves. Haar-like features are the input to the basic classifiers, and are calculated as described below. The current algorithm uses the following Haar-like features: ![image](pics/haarfeatures.png) The feature used in a particular classifier is specified by its shape (1a, 2b etc.), position within the region of interest and the scale (this scale is not the same as the scale used at the detection stage, though these two scales are multiplied). For example, in the case of the third line feature (2c) the response is calculated as the difference between the sum of image pixels under the rectangle covering the whole feature (including the two white stripes and the black stripe in the middle) and the sum of the image pixels under the black stripe multiplied by 3 in order to compensate for the differences in the size of areas. The sums of pixel values over a rectangular regions are calculated rapidly using integral images (see below and the integral description). To see the object detector at work, have a look at the facedetect demo: The following reference is for the detection part only. There is a separate application called opencv_traincascade that can train a cascade of boosted classifiers from a set of samples. @note In the new C++ interface it is also possible to use LBP (local binary pattern) features in addition to Haar-like features. .. [Viola01] Paul Viola and Michael J. Jones. Rapid Object Detection using a Boosted Cascade of Simple Features. IEEE CVPR, 2001. The paper is available online at @{ @defgroup objdetect_c C API @} */ typedef struct CvHaarClassifierCascade CvHaarClassifierCascade; namespace cv { //! @addtogroup objdetect //! @{ ///////////////////////////// Object Detection //////////////////////////// //! class for grouping object candidates, detected by Cascade Classifier, HOG etc. //! instance of the class is to be passed to cv::partition (see cxoperations.hpp) class CV_EXPORTS SimilarRects { public: SimilarRects(double _eps) : eps(_eps) {} inline bool operator()(const Rect& r1, const Rect& r2) const { double delta = eps * ((std::min)(r1.width, r2.width) + (std::min)(r1.height, r2.height)) * 0.5; return std::abs(r1.x - r2.x) <= delta && std::abs(r1.y - r2.y) <= delta && std::abs(r1.x + r1.width - r2.x - r2.width) <= delta && std::abs(r1.y + r1.height - r2.y - r2.height) <= delta; } double eps; }; /** @brief Groups the object candidate rectangles. @param rectList Input/output vector of rectangles. Output vector includes retained and grouped rectangles. (The Python list is not modified in place.) @param groupThreshold Minimum possible number of rectangles minus 1. The threshold is used in a group of rectangles to retain it. @param eps Relative difference between sides of the rectangles to merge them into a group. The function is a wrapper for the generic function partition . It clusters all the input rectangles using the rectangle equivalence criteria that combines rectangles with similar sizes and similar locations. The similarity is defined by eps. When eps=0 , no clustering is done at all. If \f$\texttt{eps}\rightarrow +\inf\f$ , all the rectangles are put in one cluster. Then, the small clusters containing less than or equal to groupThreshold rectangles are rejected. In each other cluster, the average rectangle is computed and put into the output rectangle list. */ CV_EXPORTS void groupRectangles(std::vector& rectList, int groupThreshold, double eps = 0.2); /** @overload */ CV_EXPORTS_W void groupRectangles(CV_IN_OUT std::vector& rectList, CV_OUT std::vector& weights, int groupThreshold, double eps = 0.2); /** @overload */ CV_EXPORTS void groupRectangles(std::vector& rectList, int groupThreshold, double eps, std::vector* weights, std::vector* levelWeights ); /** @overload */ CV_EXPORTS void groupRectangles(std::vector& rectList, std::vector& rejectLevels, std::vector& levelWeights, int groupThreshold, double eps = 0.2); /** @overload */ CV_EXPORTS void groupRectangles_meanshift(std::vector& rectList, std::vector& foundWeights, std::vector& foundScales, double detectThreshold = 0.0, Size winDetSize = Size(64, 128)); template<> CV_EXPORTS void DefaultDeleter::operator ()(CvHaarClassifierCascade* obj) const; enum { CASCADE_DO_CANNY_PRUNING = 1, CASCADE_SCALE_IMAGE = 2, CASCADE_FIND_BIGGEST_OBJECT = 4, CASCADE_DO_ROUGH_SEARCH = 8 }; class CV_EXPORTS_W BaseCascadeClassifier : public Algorithm { public: virtual ~BaseCascadeClassifier(); virtual bool empty() const = 0; virtual bool load( const String& filename ) = 0; virtual void detectMultiScale( InputArray image, CV_OUT std::vector& objects, double scaleFactor, int minNeighbors, int flags, Size minSize, Size maxSize ) = 0; virtual void detectMultiScale( InputArray image, CV_OUT std::vector& objects, CV_OUT std::vector& numDetections, double scaleFactor, int minNeighbors, int flags, Size minSize, Size maxSize ) = 0; virtual void detectMultiScale( InputArray image, CV_OUT std::vector& objects, CV_OUT std::vector& rejectLevels, CV_OUT std::vector& levelWeights, double scaleFactor, int minNeighbors, int flags, Size minSize, Size maxSize, bool outputRejectLevels ) = 0; virtual bool isOldFormatCascade() const = 0; virtual Size getOriginalWindowSize() const = 0; virtual int getFeatureType() const = 0; virtual void* getOldCascade() = 0; class CV_EXPORTS MaskGenerator { public: virtual ~MaskGenerator() {} virtual Mat generateMask(const Mat& src)=0; virtual void initializeMask(const Mat& /*src*/) { } }; virtual void setMaskGenerator(const Ptr& maskGenerator) = 0; virtual Ptr getMaskGenerator() = 0; }; /** @brief Cascade classifier class for object detection. */ class CV_EXPORTS_W CascadeClassifier { public: CV_WRAP CascadeClassifier(); /** @brief Loads a classifier from a file. @param filename Name of the file from which the classifier is loaded. */ CV_WRAP CascadeClassifier(const String& filename); ~CascadeClassifier(); /** @brief Checks whether the classifier has been loaded. */ CV_WRAP bool empty() const; /** @brief Loads a classifier from a file. @param filename Name of the file from which the classifier is loaded. The file may contain an old HAAR classifier trained by the haartraining application or a new cascade classifier trained by the traincascade application. */ CV_WRAP bool load( const String& filename ); /** @brief Reads a classifier from a FileStorage node. @note The file may contain a new cascade classifier (trained traincascade application) only. */ CV_WRAP bool read( const FileNode& node ); /** @brief Detects objects of different sizes in the input image. The detected objects are returned as a list of rectangles. @param image Matrix of the type CV_8U containing an image where objects are detected. @param objects Vector of rectangles where each rectangle contains the detected object, the rectangles may be partially outside the original image. @param scaleFactor Parameter specifying how much the image size is reduced at each image scale. @param minNeighbors Parameter specifying how many neighbors each candidate rectangle should have to retain it. @param flags Parameter with the same meaning for an old cascade as in the function cvHaarDetectObjects. It is not used for a new cascade. @param minSize Minimum possible object size. Objects smaller than that are ignored. @param maxSize Maximum possible object size. Objects larger than that are ignored. If `maxSize == minSize` model is evaluated on single scale. The function is parallelized with the TBB library. @note - (Python) A face detection example using cascade classifiers can be found at opencv_source_code/samples/python/facedetect.py */ CV_WRAP void detectMultiScale( InputArray image, CV_OUT std::vector& objects, double scaleFactor = 1.1, int minNeighbors = 3, int flags = 0, Size minSize = Size(), Size maxSize = Size() ); /** @overload @param image Matrix of the type CV_8U containing an image where objects are detected. @param objects Vector of rectangles where each rectangle contains the detected object, the rectangles may be partially outside the original image. @param numDetections Vector of detection numbers for the corresponding objects. An object's number of detections is the number of neighboring positively classified rectangles that were joined together to form the object. @param scaleFactor Parameter specifying how much the image size is reduced at each image scale. @param minNeighbors Parameter specifying how many neighbors each candidate rectangle should have to retain it. @param flags Parameter with the same meaning for an old cascade as in the function cvHaarDetectObjects. It is not used for a new cascade. @param minSize Minimum possible object size. Objects smaller than that are ignored. @param maxSize Maximum possible object size. Objects larger than that are ignored. If `maxSize == minSize` model is evaluated on single scale. */ CV_WRAP_AS(detectMultiScale2) void detectMultiScale( InputArray image, CV_OUT std::vector& objects, CV_OUT std::vector& numDetections, double scaleFactor=1.1, int minNeighbors=3, int flags=0, Size minSize=Size(), Size maxSize=Size() ); /** @overload This function allows you to retrieve the final stage decision certainty of classification. For this, one needs to set `outputRejectLevels` on true and provide the `rejectLevels` and `levelWeights` parameter. For each resulting detection, `levelWeights` will then contain the certainty of classification at the final stage. This value can then be used to separate strong from weaker classifications. A code sample on how to use it efficiently can be found below: @code Mat img; vector weights; vector levels; vector detections; CascadeClassifier model("/path/to/your/model.xml"); model.detectMultiScale(img, detections, levels, weights, 1.1, 3, 0, Size(), Size(), true); cerr << "Detection " << detections[0] << " with weight " << weights[0] << endl; @endcode */ CV_WRAP_AS(detectMultiScale3) void detectMultiScale( InputArray image, CV_OUT std::vector& objects, CV_OUT std::vector& rejectLevels, CV_OUT std::vector& levelWeights, double scaleFactor = 1.1, int minNeighbors = 3, int flags = 0, Size minSize = Size(), Size maxSize = Size(), bool outputRejectLevels = false ); CV_WRAP bool isOldFormatCascade() const; CV_WRAP Size getOriginalWindowSize() const; CV_WRAP int getFeatureType() const; void* getOldCascade(); CV_WRAP static bool convert(const String& oldcascade, const String& newcascade); void setMaskGenerator(const Ptr& maskGenerator); Ptr getMaskGenerator(); Ptr cc; }; CV_EXPORTS Ptr createFaceDetectionMaskGenerator(); //////////////// HOG (Histogram-of-Oriented-Gradients) Descriptor and Object Detector ////////////// //! struct for detection region of interest (ROI) struct DetectionROI { //! scale(size) of the bounding box double scale; //! set of requrested locations to be evaluated std::vector locations; //! vector that will contain confidence values for each location std::vector confidences; }; struct CV_EXPORTS_W HOGDescriptor { public: enum { L2Hys = 0 }; enum { DEFAULT_NLEVELS = 64 }; CV_WRAP HOGDescriptor() : winSize(64,128), blockSize(16,16), blockStride(8,8), cellSize(8,8), nbins(9), derivAperture(1), winSigma(-1), histogramNormType(HOGDescriptor::L2Hys), L2HysThreshold(0.2), gammaCorrection(true), free_coef(-1.f), nlevels(HOGDescriptor::DEFAULT_NLEVELS), signedGradient(false) {} CV_WRAP HOGDescriptor(Size _winSize, Size _blockSize, Size _blockStride, Size _cellSize, int _nbins, int _derivAperture=1, double _winSigma=-1, int _histogramNormType=HOGDescriptor::L2Hys, double _L2HysThreshold=0.2, bool _gammaCorrection=false, int _nlevels=HOGDescriptor::DEFAULT_NLEVELS, bool _signedGradient=false) : winSize(_winSize), blockSize(_blockSize), blockStride(_blockStride), cellSize(_cellSize), nbins(_nbins), derivAperture(_derivAperture), winSigma(_winSigma), histogramNormType(_histogramNormType), L2HysThreshold(_L2HysThreshold), gammaCorrection(_gammaCorrection), free_coef(-1.f), nlevels(_nlevels), signedGradient(_signedGradient) {} CV_WRAP HOGDescriptor(const String& filename) { load(filename); } HOGDescriptor(const HOGDescriptor& d) { d.copyTo(*this); } virtual ~HOGDescriptor() {} CV_WRAP size_t getDescriptorSize() const; CV_WRAP bool checkDetectorSize() const; CV_WRAP double getWinSigma() const; CV_WRAP virtual void setSVMDetector(InputArray _svmdetector); virtual bool read(FileNode& fn); virtual void write(FileStorage& fs, const String& objname) const; CV_WRAP virtual bool load(const String& filename, const String& objname = String()); CV_WRAP virtual void save(const String& filename, const String& objname = String()) const; virtual void copyTo(HOGDescriptor& c) const; CV_WRAP virtual void compute(InputArray img, CV_OUT std::vector& descriptors, Size winStride = Size(), Size padding = Size(), const std::vector& locations = std::vector()) const; //! with found weights output CV_WRAP virtual void detect(const Mat& img, CV_OUT std::vector& foundLocations, CV_OUT std::vector& weights, double hitThreshold = 0, Size winStride = Size(), Size padding = Size(), const std::vector& searchLocations = std::vector()) const; //! without found weights output virtual void detect(const Mat& img, CV_OUT std::vector& foundLocations, double hitThreshold = 0, Size winStride = Size(), Size padding = Size(), const std::vector& searchLocations=std::vector()) const; //! with result weights output CV_WRAP virtual void detectMultiScale(InputArray img, CV_OUT std::vector& foundLocations, CV_OUT std::vector& foundWeights, double hitThreshold = 0, Size winStride = Size(), Size padding = Size(), double scale = 1.05, double finalThreshold = 2.0,bool useMeanshiftGrouping = false) const; //! without found weights output virtual void detectMultiScale(InputArray img, CV_OUT std::vector& foundLocations, double hitThreshold = 0, Size winStride = Size(), Size padding = Size(), double scale = 1.05, double finalThreshold = 2.0, bool useMeanshiftGrouping = false) const; CV_WRAP virtual void computeGradient(const Mat& img, CV_OUT Mat& grad, CV_OUT Mat& angleOfs, Size paddingTL = Size(), Size paddingBR = Size()) const; CV_WRAP static std::vector getDefaultPeopleDetector(); CV_WRAP static std::vector getDaimlerPeopleDetector(); CV_PROP Size winSize; CV_PROP Size blockSize; CV_PROP Size blockStride; CV_PROP Size cellSize; CV_PROP int nbins; CV_PROP int derivAperture; CV_PROP double winSigma; CV_PROP int histogramNormType; CV_PROP double L2HysThreshold; CV_PROP bool gammaCorrection; CV_PROP std::vector svmDetector; UMat oclSvmDetector; float free_coef; CV_PROP int nlevels; CV_PROP bool signedGradient; //! evaluate specified ROI and return confidence value for each location virtual void detectROI(const cv::Mat& img, const std::vector &locations, CV_OUT std::vector& foundLocations, CV_OUT std::vector& confidences, double hitThreshold = 0, cv::Size winStride = Size(), cv::Size padding = Size()) const; //! evaluate specified ROI and return confidence value for each location in multiple scales virtual void detectMultiScaleROI(const cv::Mat& img, CV_OUT std::vector& foundLocations, std::vector& locations, double hitThreshold = 0, int groupThreshold = 0) const; //! read/parse Dalal's alt model file void readALTModel(String modelfile); void groupRectangles(std::vector& rectList, std::vector& weights, int groupThreshold, double eps) const; }; //! @} objdetect } #include "opencv2/objdetect/detection_based_tracker.hpp" #ifndef DISABLE_OPENCV_24_COMPATIBILITY #include "opencv2/objdetect/objdetect_c.h" #endif #endif