Merge branch 4.x

modules/objdetect/CMakeLists.txt

@@ -1,5 +1,16 @@
 set(the_description "Object Detection")
-ocv_define_module(objdetect opencv_core opencv_imgproc opencv_3d opencv_dnn WRAP java objc python js)
+ocv_define_module(objdetect
+    opencv_core
+    opencv_imgproc
+    opencv_3d
+    OPTIONAL
+        opencv_dnn
+    WRAP
+        python
+        java
+        objc
+        js
+)
 
 if(HAVE_QUIRC)
     get_property(QUIRC_INCLUDE GLOBAL PROPERTY QUIRC_INCLUDE_DIR)

modules/objdetect/include/opencv2/objdetect.hpp

@@ -49,8 +49,8 @@
 /**
 @defgroup objdetect Object Detection
 
-Haar Feature-based Cascade Classifier for Object Detection
-----------------------------------------------------------
+@{
+    @defgroup objdetect_cascade_classifier 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 .
@@ -90,8 +90,7 @@ middle) and the sum of the image pixels under the black stripe multiplied by 3 i
 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:
-<https://github.com/opencv/opencv/tree/5.x/samples/cpp/dbt_face_detection.cpp>
+Check @ref tutorial_cascade_classifier "the corresponding tutorial" for more details.
 
 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.
@@ -99,10 +98,13 @@ opencv_traincascade that can train a cascade of boosted classifiers from a set o
 @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
-<http://research.microsoft.com/en-us/um/people/viola/Pubs/Detect/violaJones_CVPR2001.pdf>
+<https://github.com/SvHey/thesis/blob/master/Literature/ObjectDetection/violaJones_CVPR2001.pdf>
 
-@{
-    @defgroup objdetect_c C API
+    @defgroup objdetect_hog HOG (Histogram of Oriented Gradients) descriptor and object detector
+    @defgroup objdetect_qrcode QRCode detection and encoding
+    @defgroup objdetect_dnn_face DNN-based face detection and recognition
+Check @ref tutorial_dnn_face "the corresponding tutorial" for more details.
+    @defgroup objdetect_common Common functions and classes
 @}
  */
 
@@ -111,13 +113,15 @@ typedef struct CvHaarClassifierCascade CvHaarClassifierCascade;
 namespace cv
 {
 
-//! @addtogroup objdetect
+//! @addtogroup objdetect_common
 //! @{
 
 ///////////////////////////// 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)
+/** @brief This class is used for grouping object candidates detected by Cascade Classifier, HOG etc.
+
+instance of the class is to be passed to cv::partition
+ */
 class CV_EXPORTS SimilarRects
 {
 public:
@@ -162,6 +166,10 @@ CV_EXPORTS   void groupRectangles(std::vector<Rect>& rectList, std::vector<int>&
 CV_EXPORTS   void groupRectangles_meanshift(std::vector<Rect>& rectList, std::vector<double>& foundWeights,
                                             std::vector<double>& foundScales,
                                             double detectThreshold = 0.0, Size winDetSize = Size(64, 128));
+//! @}
+
+//! @addtogroup objdetect_cascade_classifier
+//! @{
 
 template<> struct DefaultDeleter<CvHaarClassifierCascade>{ CV_EXPORTS void operator ()(CvHaarClassifierCascade* obj) const; };
 
@@ -243,7 +251,7 @@ public:
     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.
+    @note The file may contain a new cascade classifier (trained by the traincascade application) only.
      */
     CV_WRAP bool read( const FileNode& node );
 
@@ -260,12 +268,6 @@ public:
     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<Rect>& objects,
@@ -338,7 +340,10 @@ public:
 };
 
 CV_EXPORTS Ptr<BaseCascadeClassifier::MaskGenerator> createFaceDetectionMaskGenerator();
+//! @}
 
+//! @addtogroup objdetect_hog
+//! @{
 //////////////// HOG (Histogram-of-Oriented-Gradients) Descriptor and Object Detector //////////////
 
 //! struct for detection region of interest (ROI)
@@ -378,7 +383,7 @@ public:
          };
     enum DescriptorStorageFormat { DESCR_FORMAT_COL_BY_COL, DESCR_FORMAT_ROW_BY_ROW };
 
-    /**@brief Creates the HOG descriptor and detector with default params.
+    /**@brief Creates the HOG descriptor and detector with default parameters.
 
     aqual to HOGDescriptor(Size(64,128), Size(16,16), Size(8,8), Size(8,8), 9 )
     */
@@ -414,6 +419,8 @@ public:
     {}
 
     /** @overload
+
+    Creates the HOG descriptor and detector and loads HOGDescriptor parameters and coefficients for the linear SVM classifier from a file.
     @param filename The file name containing HOGDescriptor properties and coefficients for the linear SVM classifier.
     */
     CV_WRAP HOGDescriptor(const String& filename)
@@ -452,19 +459,19 @@ public:
     */
     CV_WRAP virtual void setSVMDetector(InputArray svmdetector);
 
-    /** @brief Reads HOGDescriptor parameters from a cv::FileNode.
+    /** @brief Reads HOGDescriptor parameters and coefficients for the linear SVM classifier from a file node.
     @param fn File node
     */
     virtual bool read(FileNode& fn);
 
-    /** @brief Stores HOGDescriptor parameters in a cv::FileStorage.
+    /** @brief Stores HOGDescriptor parameters and coefficients for the linear SVM classifier in a file storage.
     @param fs File storage
     @param objname Object name
     */
     virtual void write(FileStorage& fs, const String& objname) const;
 
-    /** @brief loads HOGDescriptor parameters and coefficients for the linear SVM classifier from a file.
-    @param filename Path of the file to read.
+    /** @brief loads HOGDescriptor parameters and coefficients for the linear SVM classifier from a file
+    @param filename Name of the file to read.
     @param objname The optional name of the node to read (if empty, the first top-level node will be used).
     */
     CV_WRAP virtual bool load(const String& filename, const String& objname = String());
@@ -537,13 +544,14 @@ public:
     @param winStride Window stride. It must be a multiple of block stride.
     @param padding Padding
     @param scale Coefficient of the detection window increase.
-    @param finalThreshold Final threshold
+    @param groupThreshold Coefficient to regulate the similarity threshold. When detected, some objects can be covered
+    by many rectangles. 0 means not to perform grouping.
     @param useMeanshiftGrouping indicates grouping algorithm
     */
     CV_WRAP virtual void detectMultiScale(InputArray img, CV_OUT std::vector<Rect>& foundLocations,
                                   CV_OUT std::vector<double>& foundWeights, double hitThreshold = 0,
                                   Size winStride = Size(), Size padding = Size(), double scale = 1.05,
-                                  double finalThreshold = 2.0,bool useMeanshiftGrouping = false) const;
+                                  double groupThreshold = 2.0, bool useMeanshiftGrouping = false) const;
 
     /** @brief Detects objects of different sizes in the input image. The detected objects are returned as a list
     of rectangles.
@@ -555,13 +563,14 @@ public:
     @param winStride Window stride. It must be a multiple of block stride.
     @param padding Padding
     @param scale Coefficient of the detection window increase.
-    @param finalThreshold Final threshold
+    @param groupThreshold Coefficient to regulate the similarity threshold. When detected, some objects can be covered
+    by many rectangles. 0 means not to perform grouping.
     @param useMeanshiftGrouping indicates grouping algorithm
     */
     virtual void detectMultiScale(InputArray img, CV_OUT std::vector<Rect>& foundLocations,
                                   double hitThreshold = 0, Size winStride = Size(),
                                   Size padding = Size(), double scale = 1.05,
-                                  double finalThreshold = 2.0, bool useMeanshiftGrouping = false) const;
+                                  double groupThreshold = 2.0, bool useMeanshiftGrouping = false) const;
 
     /** @brief  Computes gradients and quantized gradient orientations.
     @param img Matrix contains the image to be computed
@@ -666,6 +675,10 @@ public:
     */
     void groupRectangles(std::vector<cv::Rect>& rectList, std::vector<double>& weights, int groupThreshold, double eps) const;
 };
+//! @}
+
+//! @addtogroup objdetect_qrcode
+//! @{
 
 class CV_EXPORTS_W QRCodeEncoder {
 protected:
@@ -827,7 +840,7 @@ protected:
     Ptr<Impl> p;
 };
 
-//! @} objdetect
+//! @}
 }
 
 #include "opencv2/objdetect/detection_based_tracker.hpp"

modules/objdetect/include/opencv2/objdetect/detection_based_tracker.hpp

@@ -51,7 +51,7 @@
 namespace cv
 {
 
-//! @addtogroup objdetect
+//! @addtogroup objdetect_cascade_classifier
 //! @{
 
 class CV_EXPORTS DetectionBasedTracker
@@ -215,7 +215,7 @@ class CV_EXPORTS DetectionBasedTracker
         void detectInRegion(const cv::Mat& img, const cv::Rect& r, std::vector<cv::Rect>& detectedObjectsInRegions);
 };
 
-//! @} objdetect
+//! @}
 
 } //end of cv namespace
 

modules/objdetect/include/opencv2/objdetect/face.hpp

@@ -7,13 +7,15 @@
 
 #include <opencv2/core.hpp>
 
-/** @defgroup dnn_face DNN-based face detection and recognition
- */
-
 namespace cv
 {
 
-/** @brief DNN-based face detector, model download link: https://github.com/ShiqiYu/libfacedetection.train/tree/master/tasks/task1/onnx.
+//! @addtogroup objdetect_dnn_face
+//! @{
+
+/** @brief DNN-based face detector
+
+model download link: https://github.com/opencv/opencv_zoo/tree/master/models/face_detection_yunet
  */
 class CV_EXPORTS_W FaceDetectorYN
 {
@@ -80,7 +82,9 @@ public:
                                               int target_id = 0);
 };
 
-/** @brief DNN-based face recognizer, model download link: https://drive.google.com/file/d/1ClK9WiB492c5OZFKveF3XiHCejoOxINW/view.
+/** @brief DNN-based face recognizer
+
+model download link: https://github.com/opencv/opencv_zoo/tree/master/models/face_recognition_sface
  */
 class CV_EXPORTS_W FaceRecognizerSF
 {
@@ -105,11 +109,11 @@ public:
     CV_WRAP virtual void feature(InputArray aligned_img, OutputArray face_feature) = 0;
 
     /** @brief Calculating the distance between two face features
-     *  @param _face_feature1 the first input feature
-     *  @param _face_feature2 the second input feature of the same size and the same type as _face_feature1
+     *  @param face_feature1 the first input feature
+     *  @param face_feature2 the second input feature of the same size and the same type as face_feature1
      *  @param dis_type defining the similarity with optional values "FR_OSINE" or "FR_NORM_L2"
      */
-    CV_WRAP virtual double match(InputArray _face_feature1, InputArray _face_feature2, int dis_type = FaceRecognizerSF::FR_COSINE) const = 0;
+    CV_WRAP virtual double match(InputArray face_feature1, InputArray face_feature2, int dis_type = FaceRecognizerSF::FR_COSINE) const = 0;
 
     /** @brief Creates an instance of this class with given parameters
      *  @param model the path of the onnx model used for face recognition
@@ -120,6 +124,7 @@ public:
     CV_WRAP static Ptr<FaceRecognizerSF> create(const String& model, const String& config, int backend_id = 0, int target_id = 0);
 };
 
+//! @}
 } // namespace cv
 
 #endif

modules/objdetect/src/face_detect.cpp

@@ -6,13 +6,16 @@
 
 #include "opencv2/imgproc.hpp"
 #include "opencv2/core.hpp"
+#ifdef HAVE_OPENCV_DNN
 #include "opencv2/dnn.hpp"
+#endif
 
 #include <algorithm>
 
 namespace cv
 {
 
+#ifdef HAVE_OPENCV_DNN
 class FaceDetectorYNImpl : public FaceDetectorYN
 {
 public:
@@ -273,6 +276,7 @@ private:
 
     std::vector<Rect2f> priors;
 };
+#endif
 
 Ptr<FaceDetectorYN> FaceDetectorYN::create(const String& model,
                                            const String& config,
@@ -283,7 +287,12 @@ Ptr<FaceDetectorYN> FaceDetectorYN::create(const String& model,
                                            const int backend_id,
                                            const int target_id)
 {
+#ifdef HAVE_OPENCV_DNN
     return makePtr<FaceDetectorYNImpl>(model, config, input_size, score_threshold, nms_threshold, top_k, backend_id, target_id);
+#else
+    CV_UNUSED(model); CV_UNUSED(config); CV_UNUSED(input_size); CV_UNUSED(score_threshold); CV_UNUSED(nms_threshold); CV_UNUSED(top_k); CV_UNUSED(backend_id); CV_UNUSED(target_id);
+    CV_Error(cv::Error::StsNotImplemented, "cv::FaceDetectorYN requires enabled 'dnn' module.");
+#endif
 }
 
 } // namespace cv

modules/objdetect/src/face_recognize.cpp

@@ -4,13 +4,17 @@
 
 #include "precomp.hpp"
 
+#include "opencv2/core.hpp"
+#ifdef HAVE_OPENCV_DNN
 #include "opencv2/dnn.hpp"
+#endif
 
 #include <algorithm>
 
 namespace cv
 {
 
+#ifdef HAVE_OPENCV_DNN
 class FaceRecognizerSFImpl : public FaceRecognizerSF
 {
 public:
@@ -173,10 +177,16 @@ private:
 private:
     dnn::Net net;
 };
+#endif
 
 Ptr<FaceRecognizerSF> FaceRecognizerSF::create(const String& model, const String& config, int backend_id, int target_id)
 {
+#ifdef HAVE_OPENCV_DNN
     return makePtr<FaceRecognizerSFImpl>(model, config, backend_id, target_id);
+#else
+    CV_UNUSED(model); CV_UNUSED(config); CV_UNUSED(backend_id); CV_UNUSED(target_id);
+    CV_Error(cv::Error::StsNotImplemented, "cv::FaceRecognizerSF requires enabled 'dnn' module");
+#endif
 }
 
 } // namespace cv

modules/objdetect/src/hog.cpp

@@ -42,7 +42,6 @@
 
 #include "precomp.hpp"
 #include "cascadedetect.hpp"
-#include "opencv2/core/core_c.h"
 #include "opencv2/core/hal/intrin.hpp"
 #include "opencl_kernels_objdetect.hpp"
 
@@ -1887,7 +1886,7 @@ static bool ocl_detectMultiScale(InputArray _img, std::vector<Rect> &found_locat
 void HOGDescriptor::detectMultiScale(
     InputArray _img, std::vector<Rect>& foundLocations, std::vector<double>& foundWeights,
     double hitThreshold, Size winStride, Size padding,
-    double scale0, double finalThreshold, bool useMeanshiftGrouping) const
+    double scale0, double groupThreshold, bool useMeanshiftGrouping) const
 {
     CV_INSTRUMENT_REGION();
 
@@ -1913,7 +1912,7 @@ void HOGDescriptor::detectMultiScale(
 
     CV_OCL_RUN(_img.dims() <= 2 && _img.type() == CV_8UC1 && scale0 > 1 && winStride.width % blockStride.width == 0 &&
         winStride.height % blockStride.height == 0 && padding == Size(0,0) && _img.isUMat(),
-        ocl_detectMultiScale(_img, foundLocations, levelScale, hitThreshold, winStride, finalThreshold, oclSvmDetector,
+        ocl_detectMultiScale(_img, foundLocations, levelScale, hitThreshold, winStride, groupThreshold, oclSvmDetector,
         blockSize, cellSize, nbins, blockStride, winSize, gammaCorrection, L2HysThreshold, (float)getWinSigma(), free_coef, signedGradient));
 
     std::vector<Rect> allCandidates;
@@ -1934,21 +1933,21 @@ void HOGDescriptor::detectMultiScale(
     std::copy(tempWeights.begin(), tempWeights.end(), back_inserter(foundWeights));
 
     if ( useMeanshiftGrouping )
-        groupRectangles_meanshift(foundLocations, foundWeights, foundScales, finalThreshold, winSize);
+        groupRectangles_meanshift(foundLocations, foundWeights, foundScales, groupThreshold, winSize);
     else
-        groupRectangles(foundLocations, foundWeights, (int)finalThreshold, 0.2);
+        groupRectangles(foundLocations, foundWeights, (int)groupThreshold, 0.2);
     clipObjects(imgSize, foundLocations, 0, &foundWeights);
 }
 
 void HOGDescriptor::detectMultiScale(InputArray img, std::vector<Rect>& foundLocations,
     double hitThreshold, Size winStride, Size padding,
-    double scale0, double finalThreshold, bool useMeanshiftGrouping) const
+    double scale0, double groupThreshold, bool useMeanshiftGrouping) const
 {
     CV_INSTRUMENT_REGION();
 
     std::vector<double> foundWeights;
     detectMultiScale(img, foundLocations, foundWeights, hitThreshold, winStride,
-                padding, scale0, finalThreshold, useMeanshiftGrouping);
+                padding, scale0, groupThreshold, useMeanshiftGrouping);
 }
 
 std::vector<float> HOGDescriptor::getDefaultPeopleDetector()

modules/objdetect/test/test_face.cpp

@@ -78,7 +78,7 @@ TEST(Objdetect_face_detection, regression)
     // }
 
     // Initialize detector
-    std::string model = findDataFile("dnn/onnx/models/yunet-202109.onnx", false);
+    std::string model = findDataFile("dnn/onnx/models/yunet-202202.onnx", false);
     Ptr<FaceDetectorYN> faceDetector = FaceDetectorYN::create(model, "", Size(300, 300));
     faceDetector->setScoreThreshold(0.7f);
 
@@ -178,7 +178,7 @@ TEST(Objdetect_face_recognition, regression)
     }
 
     // Initialize detector
-    std::string detect_model = findDataFile("dnn/onnx/models/yunet-202109.onnx", false);
+    std::string detect_model = findDataFile("dnn/onnx/models/yunet-202202.onnx", false);
     Ptr<FaceDetectorYN> faceDetector = FaceDetectorYN::create(detect_model, "", Size(150, 150), score_thresh, nms_thresh);
 
     std::string recog_model = findDataFile("dnn/onnx/models/face_recognizer_fast.onnx", false);