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
// Copyright (C) 2014 Davis E. King (davis@dlib.net)
// License: Boost Software License See LICENSE.txt for the full license.
#ifndef DLIB_SIMPLE_OBJECT_DETECTOR_PY_H__
#define DLIB_SIMPLE_OBJECT_DETECTOR_PY_H__
#include <dlib/python.h>
#include <dlib/matrix.h>
#include <boost/python/args.hpp>
#include <dlib/geometry.h>
#include <dlib/image_processing/frontal_face_detector.h>
namespace dlib
{
typedef object_detector<scan_fhog_pyramid<pyramid_down<6> > > simple_object_detector;
inline void split_rect_detections (
std::vector<rect_detection>& rect_detections,
std::vector<rectangle>& rectangles,
std::vector<double>& detection_confidences,
std::vector<double>& weight_indices
)
{
rectangles.clear();
detection_confidences.clear();
weight_indices.clear();
for (unsigned long i = 0; i < rect_detections.size(); ++i)
{
rectangles.push_back(rect_detections[i].rect);
detection_confidences.push_back(rect_detections[i].detection_confidence);
weight_indices.push_back(rect_detections[i].weight_index);
}
}
inline std::vector<dlib::rectangle> run_detector_with_upscale1 (
dlib::simple_object_detector& detector,
boost::python::object img,
const unsigned int upsampling_amount,
const double adjust_threshold,
std::vector<double>& detection_confidences,
std::vector<double>& weight_indices
)
{
pyramid_down<2> pyr;
std::vector<rectangle> rectangles;
std::vector<rect_detection> rect_detections;
if (is_gray_python_image(img))
{
array2d<unsigned char> temp;
if (upsampling_amount == 0)
{
detector(numpy_gray_image(img), rect_detections, adjust_threshold);
split_rect_detections(rect_detections, rectangles,
detection_confidences, weight_indices);
return rectangles;
}
else
{
pyramid_up(numpy_gray_image(img), temp, pyr);
unsigned int levels = upsampling_amount-1;
while (levels > 0)
{
levels--;
pyramid_up(temp);
}
detector(temp, rect_detections, adjust_threshold);
for (unsigned long i = 0; i < rect_detections.size(); ++i)
rect_detections[i].rect = pyr.rect_down(rect_detections[i].rect,
upsampling_amount);
split_rect_detections(rect_detections, rectangles,
detection_confidences, weight_indices);
return rectangles;
}
}
else if (is_rgb_python_image(img))
{
array2d<rgb_pixel> temp;
if (upsampling_amount == 0)
{
detector(numpy_rgb_image(img), rect_detections, adjust_threshold);
split_rect_detections(rect_detections, rectangles,
detection_confidences, weight_indices);
return rectangles;
}
else
{
pyramid_up(numpy_rgb_image(img), temp, pyr);
unsigned int levels = upsampling_amount-1;
while (levels > 0)
{
levels--;
pyramid_up(temp);
}
detector(temp, rect_detections, adjust_threshold);
for (unsigned long i = 0; i < rect_detections.size(); ++i)
rect_detections[i].rect = pyr.rect_down(rect_detections[i].rect,
upsampling_amount);
split_rect_detections(rect_detections, rectangles,
detection_confidences, weight_indices);
return rectangles;
}
}
else
{
throw dlib::error("Unsupported image type, must be 8bit gray or RGB image.");
}
}
inline std::vector<dlib::rectangle> run_detectors_with_upscale1 (
std::vector<simple_object_detector >& detectors,
boost::python::object img,
const unsigned int upsampling_amount,
const double adjust_threshold,
std::vector<double>& detection_confidences,
std::vector<double>& weight_indices
)
{
pyramid_down<2> pyr;
std::vector<rectangle> rectangles;
std::vector<rect_detection> rect_detections;
if (is_gray_python_image(img))
{
array2d<unsigned char> temp;
if (upsampling_amount == 0)
{
evaluate_detectors(detectors, numpy_gray_image(img), rect_detections, adjust_threshold);
split_rect_detections(rect_detections, rectangles,
detection_confidences, weight_indices);
return rectangles;
}
else
{
pyramid_up(numpy_gray_image(img), temp, pyr);
unsigned int levels = upsampling_amount-1;
while (levels > 0)
{
levels--;
pyramid_up(temp);
}
evaluate_detectors(detectors, temp, rect_detections, adjust_threshold);
for (unsigned long i = 0; i < rect_detections.size(); ++i)
rect_detections[i].rect = pyr.rect_down(rect_detections[i].rect,
upsampling_amount);
split_rect_detections(rect_detections, rectangles,
detection_confidences, weight_indices);
return rectangles;
}
}
else if (is_rgb_python_image(img))
{
array2d<rgb_pixel> temp;
if (upsampling_amount == 0)
{
evaluate_detectors(detectors, numpy_rgb_image(img), rect_detections, adjust_threshold);
split_rect_detections(rect_detections, rectangles,
detection_confidences, weight_indices);
return rectangles;
}
else
{
pyramid_up(numpy_rgb_image(img), temp, pyr);
unsigned int levels = upsampling_amount-1;
while (levels > 0)
{
levels--;
pyramid_up(temp);
}
evaluate_detectors(detectors, temp, rect_detections, adjust_threshold);
for (unsigned long i = 0; i < rect_detections.size(); ++i)
rect_detections[i].rect = pyr.rect_down(rect_detections[i].rect,
upsampling_amount);
split_rect_detections(rect_detections, rectangles,
detection_confidences, weight_indices);
return rectangles;
}
}
else
{
throw dlib::error("Unsupported image type, must be 8bit gray or RGB image.");
}
}
inline std::vector<dlib::rectangle> run_detector_with_upscale2 (
dlib::simple_object_detector& detector,
boost::python::object img,
const unsigned int upsampling_amount
)
{
std::vector<double> detection_confidences;
std::vector<double> weight_indices;
const double adjust_threshold = 0.0;
return run_detector_with_upscale1(detector, img, upsampling_amount,
adjust_threshold,
detection_confidences, weight_indices);
}
inline boost::python::tuple run_rect_detector (
dlib::simple_object_detector& detector,
boost::python::object img,
const unsigned int upsampling_amount,
const double adjust_threshold)
{
boost::python::tuple t;
std::vector<double> detection_confidences;
std::vector<double> weight_indices;
std::vector<rectangle> rectangles;
rectangles = run_detector_with_upscale1(detector, img, upsampling_amount,
adjust_threshold,
detection_confidences, weight_indices);
return boost::python::make_tuple(rectangles,
detection_confidences, weight_indices);
}
inline boost::python::tuple run_multiple_rect_detectors (
boost::python::list& detectors,
boost::python::object img,
const unsigned int upsampling_amount,
const double adjust_threshold)
{
boost::python::tuple t;
std::vector<simple_object_detector > vector_detectors;
const unsigned long num_detectors = len(detectors);
// Now copy the data into dlib based objects.
for (unsigned long i = 0; i < num_detectors; ++i)
{
vector_detectors.push_back(boost::python::extract<simple_object_detector >(detectors[i]));
}
std::vector<double> detection_confidences;
std::vector<double> weight_indices;
std::vector<rectangle> rectangles;
rectangles = run_detectors_with_upscale1(vector_detectors, img, upsampling_amount,
adjust_threshold,
detection_confidences, weight_indices);
return boost::python::make_tuple(rectangles,
detection_confidences, weight_indices);
}
struct simple_object_detector_py
{
simple_object_detector detector;
unsigned int upsampling_amount;
simple_object_detector_py() {}
simple_object_detector_py(simple_object_detector& _detector, unsigned int _upsampling_amount) :
detector(_detector), upsampling_amount(_upsampling_amount) {}
std::vector<dlib::rectangle> run_detector1 (boost::python::object img,
const unsigned int upsampling_amount_)
{
return run_detector_with_upscale2(detector, img, upsampling_amount_);
}
std::vector<dlib::rectangle> run_detector2 (boost::python::object img)
{
return run_detector_with_upscale2(detector, img, upsampling_amount);
}
};
}
#endif // DLIB_SIMPLE_OBJECT_DETECTOR_PY_H__