Merge pull request #127 from BKNio/lsvm_develop

latentsvm caskade

Author: vpisarev

modules/latentsvm/CMakeLists.txt

@@ -0,0 +1,2 @@
+set(the_description "Object Detection")
+ocv_define_module(latentsvm opencv_core opencv_imgproc opencv_objdetect opencv_ts OPTIONAL opencv_highgui)

modules/latentsvm/doc/latent_svm_cascade.rst

@@ -0,0 +1,113 @@
+Latent SVM
+===============================================================
+
+Discriminatively Trained Part Based Models for Object Detection
+---------------------------------------------------------------
+
+The object detector described below has been initially proposed by
+P.F. Felzenszwalb in [Felzenszwalb2010a]_.  It is based on a
+Dalal-Triggs detector that uses a single filter on histogram of
+oriented gradients (HOG) features to represent an object category.
+This detector uses a sliding window approach, where a filter is
+applied at all positions and scales of an image. The first
+innovation is enriching the Dalal-Triggs model using a
+star-structured part-based model defined by a "root" filter
+(analogous to the Dalal-Triggs filter) plus a set of parts filters
+and associated deformation models. The score of one of star models
+at a particular position and scale within an image is the score of
+the root filter at the given location plus the sum over parts of the
+maximum, over placements of that part, of the part filter score on
+its location minus a deformation cost easuring the deviation of the
+part from its ideal location relative to the root. Both root and
+part filter scores are defined by the dot product between a filter
+(a set of weights) and a subwindow of a feature pyramid computed
+from the input image. Another improvement is a representation of the
+class of models by a mixture of star models. The score of a mixture
+model at a particular position and scale is the maximum over
+components, of the score of that component model at the given
+location. 
+
+The detector was dramatically speeded-up with cascade algorithm
+proposed by P.F. Felzenszwalb in [Felzenszwalb2010b]_. The algorithm
+prunes partial hypotheses using thresholds on their scores.The basic
+idea of the algorithm is to use a hierarchy of models defined by an
+ordering of the original model's parts. For a model with (n+1)
+parts, including the root, a sequence of (n+1) models is obtained.
+The i-th model in this sequence is defined by the first i parts from
+the original model. Using this hierarchy, low scoring hypotheses can be
+pruned after looking at the best configuration of a subset of the parts.
+Hypotheses that score high under a weak model are evaluated further using
+a richer model.
+
+In OpenCV there is an C++ implementation of Latent SVM.
+
+.. highlight:: cpp
+
+LSVMDetector
+-----------------
+.. ocv:class:: LSVMDetector
+
+This is a C++ abstract class, it provides external user API to work with Latent SVM.
+
+LSVMDetector::ObjectDetection
+----------------------------------
+.. ocv:struct:: LSVMDetector::ObjectDetection
+
+  Structure contains the detection information.
+
+  .. ocv:member:: Rect rect
+
+     bounding box for a detected object
+
+  .. ocv:member:: float score
+
+     confidence level
+
+  .. ocv:member:: int classID
+
+     class (model or detector) ID that detect an object
+
+LSVMDetector::~LSVMDetector
+-------------------------------------
+Destructor.
+
+.. ocv:function:: LSVMDetector::~LSVMDetector()
+
+LSVMDetector::create
+-----------------------
+Load the trained models from given ``.xml`` files and return ``cv::Ptr<LSVMDetector>``.
+
+.. ocv:function:: static cv::Ptr<LSVMDetector> LSVMDetector::create( const vector<string>& filenames, const vector<string>& classNames=vector<string>() )
+
+    :param filenames: A set of filenames storing the trained detectors (models). Each file contains one model. See examples of such files here /opencv_extra/testdata/cv/LSVMDetector/models_VOC2007/.
+
+    :param classNames: A set of trained models names. If it's empty then the name of each model will be constructed from the name of file containing the model. E.g. the model stored in "/home/user/cat.xml" will get the name "cat".
+
+LSVMDetector::detect
+-------------------------
+Find rectangular regions in the given image that are likely to contain objects of loaded classes (models)
+and corresponding confidence levels.
+
+.. ocv:function:: void LSVMDetector::detect( const Mat& image, vector<ObjectDetection>& objectDetections, float overlapThreshold=0.5f, int numThreads=-1 )
+
+    :param image: An image.
+    :param objectDetections: The detections: rectangulars, scores and class IDs.
+    :param overlapThreshold: Threshold for the non-maximum suppression algorithm.
+    :param numThreads: Number of threads used in parallel version of the algorithm.
+
+LSVMDetector::getClassNames
+--------------------------------
+Return the class (model) names that were passed in constructor or method ``load`` or extracted from models filenames in those methods.
+
+.. ocv:function:: const vector<string>& LSVMDetector::getClassNames() const
+
+LSVMDetector::getClassCount
+--------------------------------
+Return a count of loaded models (classes).
+
+.. ocv:function:: size_t LSVMDetector::getClassCount() const
+
+
+.. [Felzenszwalb2010a] Felzenszwalb, P. F. and Girshick, R. B. and McAllester, D. and Ramanan, D. *Object Detection with Discriminatively Trained Part Based Models*. PAMI, vol. 32, no. 9, pp. 1627-1645, September 2010
+.. [Felzenszwalb2010b] Felzenszwalb, P. F. and Girshick, R. B. and McAllester, D. *Cascade Object Detection with Deformable Part Models*. CVPR 2010, pp. 2241-2248
+

modules/latentsvm/include/opencv2/latentsvm.hpp

@@ -0,0 +1,93 @@
+/*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) 2010-2013, University of Nizhny Novgorod, 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.
+//
+// SVM implementation authors:
+// Evgeniy Kozinov - [email protected]
+// Valentina Kustikova - [email protected]
+// Nikolai Zolotykh - [email protected]
+// Iosif Meyerov - [email protected]
+// Alexey Polovinkin - [email protected]
+//
+//M*/
+
+#ifndef __OPENCV_LATENTSVM_HPP__
+#define __OPENCV_LATENTSVM_HPP__
+
+#include "opencv2/core.hpp"
+
+#include <map>
+#include <vector>
+#include <string>
+
+namespace cv
+{
+
+namespace lsvm
+{
+
+class CV_EXPORTS_W LSVMDetector
+{
+public:
+
+    struct CV_EXPORTS_W ObjectDetection
+    {
+        ObjectDetection();
+        ObjectDetection( const Rect& rect, float score, int classID=-1 );
+        Rect rect;
+        float score;
+        int classID;
+    };
+
+    virtual bool isEmpty() const = 0;
+    virtual void detect(cv::Mat const &image, CV_OUT std::vector<ObjectDetection> &objects,
+                         float overlapThreshold=0.5f ) = 0;
+
+    virtual std::vector<std::string> const& getClassNames() const = 0;
+    virtual size_t getClassCount() const = 0;
+
+    static cv::Ptr<LSVMDetector> create(std::vector<std::string> const &filenames,
+                                        std::vector<std::string> const &classNames = std::vector<std::string>());
+
+    virtual ~LSVMDetector(){}
+};
+
+} // namespace lsvm
+} // namespace cv
+
+#endif

modules/latentsvm/perf/perf_cascadeclassifier.cpp

@@ -0,0 +1,50 @@
+#include "perf_precomp.hpp"
+#include <opencv2/imgproc.hpp>
+
+using namespace std;
+using namespace cv;
+using namespace perf;
+using std::tr1::make_tuple;
+using std::tr1::get;
+
+typedef std::tr1::tuple<std::string, int> ImageName_MinSize_t;
+typedef perf::TestBaseWithParam<ImageName_MinSize_t> ImageName_MinSize;
+
+PERF_TEST_P(ImageName_MinSize, CascadeClassifierLBPFrontalFace,
+            testing::Combine(testing::Values( std::string("cv/shared/lena.png"),
+                                              std::string("cv/shared/1_itseez-0000289.png"),
+                                              std::string("cv/shared/1_itseez-0000492.png"),
+                                              std::string("cv/shared/1_itseez-0000573.png")),
+                             testing::Values(24, 30, 40, 50, 60, 70, 80, 90)
+                             )
+            )
+{
+    const string filename = get<0>(GetParam());
+    int min_size = get<1>(GetParam());
+    Size minSize(min_size, min_size);
+
+    CascadeClassifier cc(getDataPath("cv/cascadeandhog/cascades/lbpcascade_frontalface.xml"));
+    if (cc.empty())
+        FAIL() << "Can't load cascade file";
+
+    Mat img = imread(getDataPath(filename), 0);
+    if (img.empty())
+        FAIL() << "Can't load source image";
+
+    vector<Rect> faces;
+
+    equalizeHist(img, img);
+    declare.in(img);
+
+    while(next())
+    {
+        faces.clear();
+
+        startTimer();
+        cc.detectMultiScale(img, faces, 1.1, 3, 0, minSize);
+        stopTimer();
+    }
+
+    std::sort(faces.begin(), faces.end(), comparators::RectLess());
+    SANITY_CHECK(faces, 3.001 * faces.size());
+}

modules/latentsvm/perf/perf_main.cpp

@@ -0,0 +1,3 @@
+#include "perf_precomp.hpp"
+
+CV_PERF_TEST_MAIN(objdetect)

modules/latentsvm/perf/perf_precomp.cpp

@@ -0,0 +1 @@
+#include "perf_precomp.hpp"

modules/latentsvm/perf/perf_precomp.hpp

@@ -0,0 +1,20 @@
+#ifdef __GNUC__
+#  pragma GCC diagnostic ignored "-Wmissing-declarations"
+#  if defined __clang__ || defined __APPLE__
+#    pragma GCC diagnostic ignored "-Wmissing-prototypes"
+#    pragma GCC diagnostic ignored "-Wextra"
+#  endif
+#endif
+
+#ifndef __OPENCV_PERF_PRECOMP_HPP__
+#define __OPENCV_PERF_PRECOMP_HPP__
+
+#include "opencv2/ts.hpp"
+#include "opencv2/objdetect.hpp"
+#include "opencv2/highgui.hpp"
+
+#ifdef GTEST_CREATE_SHARED_LIBRARY
+#error no modules except ts should have GTEST_CREATE_SHARED_LIBRARY defined
+#endif
+
+#endif

modules/latentsvm/src/_lsvmc_error.h

@@ -0,0 +1,61 @@
+/*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) 2010-2013, University of Nizhny Novgorod, 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 LSVM_ERROR
+#define LSVM_ERROR
+
+#define LATENT_SVM_OK 0
+#define LATENT_SVM_MEM_NULL 2
+#define DISTANCE_TRANSFORM_OK 1
+#define DISTANCE_TRANSFORM_GET_INTERSECTION_ERROR -1
+#define DISTANCE_TRANSFORM_ERROR -2
+#define DISTANCE_TRANSFORM_EQUAL_POINTS -3
+#define LATENT_SVM_GET_FEATURE_PYRAMID_FAILED -4
+#define LATENT_SVM_SEARCH_OBJECT_FAILED -5
+#define LATENT_SVM_FAILED_SUPERPOSITION -6
+#define FILTER_OUT_OF_BOUNDARIES -7
+#define LATENT_SVM_TBB_SCHEDULE_CREATION_FAILED -8
+#define LATENT_SVM_TBB_NUMTHREADS_NOT_CORRECT -9
+#define FFT_OK 2
+#define FFT_ERROR -10
+#define LSVM_PARSER_FILE_NOT_FOUND -11
+
+#endif