1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
/*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"
typedef struct CvHaarClassifierCascade CvHaarClassifierCascade;
namespace cv
{
///////////////////////////// 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;
};
CV_EXPORTS void groupRectangles(std::vector<Rect>& rectList, int groupThreshold, double eps = 0.2);
CV_EXPORTS_W void groupRectangles(CV_IN_OUT std::vector<Rect>& rectList, CV_OUT std::vector<int>& weights,
int groupThreshold, double eps = 0.2);
CV_EXPORTS void groupRectangles(std::vector<Rect>& rectList, int groupThreshold,
double eps, std::vector<int>* weights, std::vector<double>* levelWeights );
CV_EXPORTS void groupRectangles(std::vector<Rect>& rectList, std::vector<int>& rejectLevels,
std::vector<double>& levelWeights, int groupThreshold, double eps = 0.2);
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));
template<> CV_EXPORTS void DefaultDeleter<CvHaarClassifierCascade>::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<Rect>& objects,
double scaleFactor,
int minNeighbors, int flags,
Size minSize, Size maxSize ) = 0;
virtual void detectMultiScale( InputArray image,
CV_OUT std::vector<Rect>& objects,
CV_OUT std::vector<int>& numDetections,
double scaleFactor,
int minNeighbors, int flags,
Size minSize, Size maxSize ) = 0;
virtual void detectMultiScale( InputArray image,
CV_OUT std::vector<Rect>& objects,
CV_OUT std::vector<int>& rejectLevels,
CV_OUT std::vector<double>& 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>& maskGenerator) = 0;
virtual Ptr<MaskGenerator> getMaskGenerator() = 0;
};
class CV_EXPORTS_W CascadeClassifier
{
public:
CV_WRAP CascadeClassifier();
CV_WRAP CascadeClassifier(const String& filename);
~CascadeClassifier();
CV_WRAP bool empty() const;
CV_WRAP bool load( const String& filename );
CV_WRAP bool read( const FileNode& node );
CV_WRAP void detectMultiScale( InputArray image,
CV_OUT std::vector<Rect>& objects,
double scaleFactor = 1.1,
int minNeighbors = 3, int flags = 0,
Size minSize = Size(),
Size maxSize = Size() );
CV_WRAP_AS(detectMultiScale2) void detectMultiScale( InputArray image,
CV_OUT std::vector<Rect>& objects,
CV_OUT std::vector<int>& numDetections,
double scaleFactor=1.1,
int minNeighbors=3, int flags=0,
Size minSize=Size(),
Size maxSize=Size() );
CV_WRAP_AS(detectMultiScale3) void detectMultiScale( InputArray image,
CV_OUT std::vector<Rect>& objects,
CV_OUT std::vector<int>& rejectLevels,
CV_OUT std::vector<double>& 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<BaseCascadeClassifier::MaskGenerator>& maskGenerator);
Ptr<BaseCascadeClassifier::MaskGenerator> getMaskGenerator();
Ptr<BaseCascadeClassifier> cc;
};
CV_EXPORTS Ptr<BaseCascadeClassifier::MaskGenerator> 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<cv::Point> locations;
// vector that will contain confidence values for each location
std::vector<double> 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)
{}
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)
: 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)
{}
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<float>& descriptors,
Size winStride = Size(), Size padding = Size(),
const std::vector<Point>& locations = std::vector<Point>()) const;
//with found weights output
CV_WRAP virtual void detect(const Mat& img, CV_OUT std::vector<Point>& foundLocations,
CV_OUT std::vector<double>& weights,
double hitThreshold = 0, Size winStride = Size(),
Size padding = Size(),
const std::vector<Point>& searchLocations = std::vector<Point>()) const;
//without found weights output
virtual void detect(const Mat& img, CV_OUT std::vector<Point>& foundLocations,
double hitThreshold = 0, Size winStride = Size(),
Size padding = Size(),
const std::vector<Point>& searchLocations=std::vector<Point>()) const;
//with result weights output
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;
//without found weights output
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;
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<float> getDefaultPeopleDetector();
CV_WRAP static std::vector<float> 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<float> svmDetector;
UMat oclSvmDetector;
float free_coef;
CV_PROP int nlevels;
// evaluate specified ROI and return confidence value for each location
virtual void detectROI(const cv::Mat& img, const std::vector<cv::Point> &locations,
CV_OUT std::vector<cv::Point>& foundLocations, CV_OUT std::vector<double>& 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<cv::Rect>& foundLocations,
std::vector<DetectionROI>& locations,
double hitThreshold = 0,
int groupThreshold = 0) const;
// read/parse Dalal's alt model file
void readALTModel(String modelfile);
void groupRectangles(std::vector<cv::Rect>& rectList, std::vector<double>& weights, int groupThreshold, double eps) const;
};
}
#include "opencv2/objdetect/detection_based_tracker.hpp"
#endif