File: scan_image_pyramid.h

package info (click to toggle)
mldemos 0.5.1-3
  • links: PTS, VCS
  • area: main
  • in suites: jessie-kfreebsd
  • size: 32,224 kB
  • ctags: 46,525
  • sloc: cpp: 306,887; ansic: 167,718; ml: 126; sh: 109; makefile: 2
file content (1086 lines) | stat: -rw-r--r-- 41,012 bytes parent folder | download | duplicates (2)
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
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
// Copyright (C) 2011  Davis E. King (davis@dlib.net)
// License: Boost Software License   See LICENSE.txt for the full license.
#ifndef DLIB_SCAN_IMaGE_PYRAMID_H__
#define DLIB_SCAN_IMaGE_PYRAMID_H__

#include "scan_image_pyramid_abstract.h"
#include "../matrix.h"
#include "../geometry.h"
#include "../image_processing.h"
#include "../array2d.h"
#include <vector>
#include "full_object_detection.h"

namespace dlib
{

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    class scan_image_pyramid : noncopyable
    {

    public:

        typedef matrix<double,0,1> feature_vector_type;

        typedef Pyramid_type pyramid_type;
        typedef Feature_extractor_type feature_extractor_type;

        scan_image_pyramid (
        );  

        template <
            typename image_type
            >
        void load (
            const image_type& img
        );

        inline bool is_loaded_with_image (
        ) const;

        inline void copy_configuration(
            const feature_extractor_type& fe
        );

        inline void copy_configuration (
            const scan_image_pyramid& item
        );

        void add_detection_template (
            const rectangle& object_box,
            const std::vector<rectangle>& stationary_feature_extraction_regions,
            const std::vector<rectangle>& movable_feature_extraction_regions
        );

        void add_detection_template (
            const rectangle& object_box,
            const std::vector<rectangle>& stationary_feature_extraction_regions
        );

        inline unsigned long get_num_detection_templates (
        ) const;

        inline unsigned long get_num_movable_components_per_detection_template (
        ) const;

        inline unsigned long get_num_stationary_components_per_detection_template (
        ) const;

        inline unsigned long get_num_components_per_detection_template (
        ) const;

        inline long get_num_dimensions (
        ) const;

        unsigned long get_max_pyramid_levels (
        ) const;

        void set_max_pyramid_levels (
            unsigned long max_levels
        );

        inline unsigned long get_max_detections_per_template (
        ) const;

        void set_min_pyramid_layer_size (
            unsigned long width,
            unsigned long height 
        );

        inline unsigned long get_min_pyramid_layer_width (
        ) const;

        inline unsigned long get_min_pyramid_layer_height (
        ) const;

        void set_max_detections_per_template (
            unsigned long max_dets
        );

        void detect (
            const feature_vector_type& w,
            std::vector<std::pair<double, rectangle> >& dets,
            const double thresh
        ) const;

        void get_feature_vector (
            const full_object_detection& obj,
            feature_vector_type& psi
        ) const;

        full_object_detection get_full_object_detection (
            const rectangle& rect,
            const feature_vector_type& w
        ) const;

        const rectangle get_best_matching_rect (
            const rectangle& rect
        ) const;

        template <typename T, typename U>
        friend void serialize (
            const scan_image_pyramid<T,U>& item,
            std::ostream& out
        );

        template <typename T, typename U>
        friend void deserialize (
            scan_image_pyramid<T,U>& item,
            std::istream& in 
        );

    private:
        static bool compare_pair_rect (
            const std::pair<double, rectangle>& a,
            const std::pair<double, rectangle>& b
        )
        {
            return a.first < b.first;
        }

        struct detection_template
        {
            rectangle object_box; // always centered at (0,0)
            std::vector<rectangle> rects; // template with respect to (0,0)
            std::vector<rectangle> movable_rects; 
        };

        friend void serialize(const detection_template& item, std::ostream& out)
        {
            int version = 1;
            serialize(version, out);
            serialize(item.object_box, out);
            serialize(item.rects, out);
            serialize(item.movable_rects, out);
        }
        friend void deserialize(detection_template& item, std::istream& in)
        {
            int version = 0;
            deserialize(version, in);
            if (version != 1)
                throw serialization_error("Unexpected version found while deserializing a dlib::scan_image_pyramid::detection_template object.");

            deserialize(item.object_box, in);
            deserialize(item.rects, in);
            deserialize(item.movable_rects, in);
        }

        void get_mapped_rect_and_metadata (
            const unsigned long number_pyramid_levels,
            rectangle rect,
            rectangle& mapped_rect,
            detection_template& best_template,
            rectangle& object_box,
            unsigned long& best_level
        ) const;

        double get_match_score (
            rectangle r1,
            rectangle r2
        ) const
        {
            // make the rectangles overlap as much as possible before computing the match score.
            r1 = move_rect(r1, r2.tl_corner());
            return (r1.intersect(r2).area())/(double)(r1 + r2).area();
        }

        void test_coordinate_transforms()
        {
            for (long x = -10; x <= 10; x += 10)
            {
                for (long y = -10; y <= 10; y += 10)
                {
                    const rectangle rect = centered_rect(x,y,5,6);
                    rectangle a;

                    a = feats_config.image_to_feat_space(rect);
                    if (a.width()  > 10000000 || a.height() > 10000000 )
                    {
                        DLIB_CASSERT(false, "The image_to_feat_space() routine is outputting rectangles of an implausibly "
                                     << "\nlarge size.  This means there is probably a bug in your feature extractor.");
                    }
                    a = feats_config.feat_to_image_space(rect);
                    if (a.width()  > 10000000 || a.height() > 10000000 )
                    {
                        DLIB_CASSERT(false, "The feat_to_image_space() routine is outputting rectangles of an implausibly "
                                     << "\nlarge size.  This means there is probably a bug in your feature extractor.");
                    }
                }
            }
            
        }

        feature_extractor_type feats_config; // just here to hold configuration.  use it to populate the feats elements.
        array<feature_extractor_type> feats;
        std::vector<detection_template> det_templates;
        unsigned long max_dets_per_template;
        unsigned long max_pyramid_levels;
        unsigned long min_pyramid_layer_width;
        unsigned long min_pyramid_layer_height;

    };

// ----------------------------------------------------------------------------------------

    template <typename T, typename U>
    void serialize (
        const scan_image_pyramid<T,U>& item,
        std::ostream& out
    )
    {
        int version = 2;
        serialize(version, out);
        serialize(item.feats_config, out);
        serialize(item.feats, out);
        serialize(item.det_templates, out);
        serialize(item.max_dets_per_template, out);
        serialize(item.max_pyramid_levels, out);
        serialize(item.min_pyramid_layer_width, out);
        serialize(item.min_pyramid_layer_height, out);
    }

// ----------------------------------------------------------------------------------------

    template <typename T, typename U>
    void deserialize (
        scan_image_pyramid<T,U>& item,
        std::istream& in 
    )
    {
        int version = 0;
        deserialize(version, in);
        if (version != 2)
            throw serialization_error("Unsupported version found when deserializing a scan_image_pyramid object.");

        deserialize(item.feats_config, in);
        deserialize(item.feats, in);
        deserialize(item.det_templates, in);
        deserialize(item.max_dets_per_template, in);
        deserialize(item.max_pyramid_levels, in);
        deserialize(item.min_pyramid_layer_width, in);
        deserialize(item.min_pyramid_layer_height, in);
    }

// ----------------------------------------------------------------------------------------
// ----------------------------------------------------------------------------------------
//                         scan_image_pyramid member functions
// ----------------------------------------------------------------------------------------
// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    scan_image_pyramid (
    ) : 
        max_dets_per_template(10000),
        max_pyramid_levels(1000),
        min_pyramid_layer_width(20),
        min_pyramid_layer_height(20)
    {
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    template <
        typename image_type
        >
    void scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    load (
        const image_type& img
    )
    {
        unsigned long levels = 0;
        rectangle rect = get_rect(img);

        // figure out how many pyramid levels we should be using based on the image size
        pyramid_type pyr;
        do
        {
            rect = pyr.rect_down(rect);
            ++levels;
        } while (rect.width() >= min_pyramid_layer_width && rect.height() >= min_pyramid_layer_height &&
                 levels < max_pyramid_levels);

        if (feats.max_size() < levels)
            feats.set_max_size(levels);
        feats.set_size(levels);

        for (unsigned long i = 0; i < feats.size(); ++i)
            feats[i].copy_configuration(feats_config);

        // build our feature pyramid
        feats[0].load(img);
        if (feats.size() > 1)
        {
            image_type temp1, temp2;
            pyr(img, temp1);
            feats[1].load(temp1);
            swap(temp1,temp2);

            for (unsigned long i = 2; i < feats.size(); ++i)
            {
                pyr(temp2, temp1);
                feats[i].load(temp1);
                swap(temp1,temp2);
            }
        }


    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    unsigned long scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_max_detections_per_template (
    ) const
    {
        return max_dets_per_template;
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    void scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    set_max_detections_per_template (
        unsigned long max_dets
    )
    {
        // make sure requires clause is not broken
        DLIB_ASSERT(max_dets > 0 ,
            "\t void scan_image_pyramid::set_max_detections_per_template()"
            << "\n\t The max number of possible detections can't be zero. "
            << "\n\t max_dets: " << max_dets
            << "\n\t this: " << this
            );

        max_dets_per_template = max_dets;
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    bool scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    is_loaded_with_image (
    ) const
    {
        return feats.size() != 0;
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    void scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    copy_configuration(
        const feature_extractor_type& fe
    )
    {
        test_coordinate_transforms();
        feats_config.copy_configuration(fe);
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    void scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    copy_configuration (
        const scan_image_pyramid& item
    )
    {
        feats_config.copy_configuration(item.feats_config);
        det_templates = item.det_templates;
        max_dets_per_template = item.max_dets_per_template;
        max_pyramid_levels = item.max_pyramid_levels;
        min_pyramid_layer_width = item.min_pyramid_layer_width;
        min_pyramid_layer_height = item.min_pyramid_layer_height;
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    void scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    add_detection_template (
        const rectangle& object_box,
        const std::vector<rectangle>& stationary_feature_extraction_regions,
        const std::vector<rectangle>& movable_feature_extraction_regions
    )
    {
#ifdef ENABLE_ASSERTS
        // make sure requires clause is not broken
        DLIB_ASSERT((get_num_detection_templates() == 0 || 
                        (get_num_stationary_components_per_detection_template() == stationary_feature_extraction_regions.size() &&
                        get_num_movable_components_per_detection_template() == movable_feature_extraction_regions.size())) &&
                        center(object_box) == point(0,0),
            "\t void scan_image_pyramid::add_detection_template()"
            << "\n\t The number of rects in this new detection template doesn't match "
            << "\n\t the number in previous detection templates."
            << "\n\t get_num_stationary_components_per_detection_template(): " << get_num_stationary_components_per_detection_template()
            << "\n\t stationary_feature_extraction_regions.size():           " << stationary_feature_extraction_regions.size()
            << "\n\t get_num_movable_components_per_detection_template():    " << get_num_movable_components_per_detection_template()
            << "\n\t movable_feature_extraction_regions.size():              " << movable_feature_extraction_regions.size()
            << "\n\t this: " << this
            );

        for (unsigned long i = 0; i < movable_feature_extraction_regions.size(); ++i)
        {
            DLIB_ASSERT(center(movable_feature_extraction_regions[i]) == point(0,0),
                        "Invalid inputs were given to this function."
                        << "\n\t center(movable_feature_extraction_regions["<<i<<"]): " << center(movable_feature_extraction_regions[i]) 
                        << "\n\t this: " << this
            );
        }
#endif

        detection_template temp;
        temp.object_box = object_box;
        temp.rects = stationary_feature_extraction_regions;
        temp.movable_rects = movable_feature_extraction_regions;
        det_templates.push_back(temp);
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    void scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    add_detection_template (
        const rectangle& object_box,
        const std::vector<rectangle>& stationary_feature_extraction_regions
    )
    {
        // an empty set of movable feature regions
        const std::vector<rectangle> movable_feature_extraction_regions;
        add_detection_template(object_box, stationary_feature_extraction_regions,
                               movable_feature_extraction_regions);
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    unsigned long scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_num_detection_templates (
    ) const
    {
        return det_templates.size();
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    unsigned long scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_num_stationary_components_per_detection_template (
    ) const
    {
        // make sure requires clause is not broken
        DLIB_ASSERT(get_num_detection_templates() > 0 ,
            "\t unsigned long scan_image_pyramid::get_num_stationary_components_per_detection_template()"
            << "\n\t You need to give some detection templates before calling this function. "
            << "\n\t get_num_detection_templates(): " << get_num_detection_templates()
            << "\n\t this: " << this
            );

        return det_templates[0].rects.size();
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    unsigned long scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_num_movable_components_per_detection_template (
    ) const
    {
        // make sure requires clause is not broken
        DLIB_ASSERT(get_num_detection_templates() > 0 ,
            "\t unsigned long scan_image_pyramid::get_num_movable_components_per_detection_template()"
            << "\n\t You need to give some detection templates before calling this function. "
            << "\n\t get_num_detection_templates(): " << get_num_detection_templates()
            << "\n\t this: " << this
            );

        return det_templates[0].movable_rects.size();
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    unsigned long scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_num_components_per_detection_template (
    ) const
    {
        // make sure requires clause is not broken
        DLIB_ASSERT(get_num_detection_templates() > 0 ,
            "\t unsigned long scan_image_pyramid::get_num_components_per_detection_template()"
            << "\n\t You need to give some detection templates before calling this function. "
            << "\n\t get_num_detection_templates(): " << get_num_detection_templates()
            << "\n\t this: " << this
            );

        return get_num_movable_components_per_detection_template() +
               get_num_stationary_components_per_detection_template();
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    long scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_num_dimensions (
    ) const
    {
        // make sure requires clause is not broken
        DLIB_ASSERT(get_num_detection_templates() > 0 ,
            "\t long scan_image_pyramid::get_num_dimensions()"
            << "\n\t You need to give some detection templates before calling this function. "
            << "\n\t get_num_detection_templates(): " << get_num_detection_templates()
            << "\n\t this: " << this
            );

        return feats_config.get_num_dimensions()*get_num_components_per_detection_template();
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    unsigned long scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_max_pyramid_levels (
    ) const
    {
        return max_pyramid_levels;
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    void scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    set_max_pyramid_levels (
        unsigned long max_levels
    )
    {
        // make sure requires clause is not broken
        DLIB_ASSERT(max_levels > 0 ,
            "\t void scan_image_pyramid::set_max_pyramid_levels()"
            << "\n\t You can't have zero levels. "
            << "\n\t max_levels: " << max_levels 
            << "\n\t this: " << this
            );

        max_pyramid_levels = max_levels;

    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    void scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    detect (
        const feature_vector_type& w,
        std::vector<std::pair<double, rectangle> >& dets,
        const double thresh
    ) const
    {
        // make sure requires clause is not broken
        DLIB_ASSERT(get_num_detection_templates() > 0 &&
                    is_loaded_with_image() &&
                    w.size() >= get_num_dimensions(), 
            "\t void scan_image_pyramid::detect()"
            << "\n\t Invalid inputs were given to this function "
            << "\n\t get_num_detection_templates(): " << get_num_detection_templates()
            << "\n\t is_loaded_with_image(): " << is_loaded_with_image()
            << "\n\t w.size():               " << w.size()
            << "\n\t get_num_dimensions():   " << get_num_dimensions()
            << "\n\t this: " << this
            );

        dets.clear();

        array<array2d<double> > saliency_images;
        saliency_images.set_max_size(get_num_components_per_detection_template());
        saliency_images.set_size(get_num_components_per_detection_template());
        std::vector<std::pair<unsigned int,rectangle> > stationary_region_rects(get_num_stationary_components_per_detection_template()); 
        std::vector<std::pair<unsigned int,rectangle> > movable_region_rects(get_num_movable_components_per_detection_template()); 
        pyramid_type pyr;
        std::vector<std::pair<double, point> > point_dets;

        // for all pyramid levels
        for (unsigned long l = 0; l < feats.size(); ++l)
        {
            for (unsigned long i = 0; i < saliency_images.size(); ++i)
            {
                saliency_images[i].set_size(feats[l].nr(), feats[l].nc());
                const unsigned long offset = feats_config.get_num_dimensions()*i;

                // build saliency images for pyramid level l 
                for (long r = 0; r < feats[l].nr(); ++r)
                {
                    for (long c = 0; c < feats[l].nc(); ++c)
                    {
                        const typename feature_extractor_type::descriptor_type& descriptor = feats[l](r,c);

                        double sum = 0;
                        for (unsigned long k = 0; k < descriptor.size(); ++k)
                        {
                            sum += w(descriptor[k].first + offset)*descriptor[k].second;
                        }
                        saliency_images[i][r][c] = sum;
                    }
                }
            }

            // now search the saliency images
            for (unsigned long i = 0; i < det_templates.size(); ++i)
            {
                const point offset = -feats[l].image_to_feat_space(point(0,0));
                for (unsigned long j = 0; j < stationary_region_rects.size(); ++j)
                {
                    stationary_region_rects[j] = std::make_pair(j, translate_rect(feats[l].image_to_feat_space(det_templates[i].rects[j]),offset)); 
                }
                for (unsigned long j = 0; j < movable_region_rects.size(); ++j)
                {
                    // Scale the size of the movable rectangle but make sure its center
                    // stays at point(0,0).
                    const rectangle temp = feats[l].image_to_feat_space(det_templates[i].movable_rects[j]);
                    movable_region_rects[j] = std::make_pair(j+stationary_region_rects.size(),
                                                             centered_rect(point(0,0),temp.width(), temp.height())); 
                }

                // Scale the object box into the feature extraction image, but keeping it
                // centered at point(0,0).
                rectangle scaled_object_box = feats[l].image_to_feat_space(det_templates[i].object_box);
                scaled_object_box = centered_rect(point(0,0),scaled_object_box.width(), scaled_object_box.height());

                scan_image_movable_parts(point_dets, saliency_images, scaled_object_box,
                                         stationary_region_rects, movable_region_rects,
                                         thresh, max_dets_per_template); 

                // convert all the point detections into rectangles at the original image scale and coordinate system
                for (unsigned long j = 0; j < point_dets.size(); ++j)
                {
                    const double score = point_dets[j].first;
                    point p = point_dets[j].second;
                    p = feats[l].feat_to_image_space(p);
                    rectangle rect = translate_rect(det_templates[i].object_box, p);
                    rect = pyr.rect_up(rect, l);

                    dets.push_back(std::make_pair(score, rect));
                }
            }
        }

        std::sort(dets.rbegin(), dets.rend(), compare_pair_rect);
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    const rectangle scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_best_matching_rect (
        const rectangle& rect
    ) const
    {
        // make sure requires clause is not broken
        DLIB_ASSERT(get_num_detection_templates() > 0 ,
            "\t const rectangle scan_image_pyramid::get_best_matching_rect()"
            << "\n\t Invalid inputs were given to this function "
            << "\n\t get_num_detection_templates(): " << get_num_detection_templates()
            << "\n\t this: " << this
            );

        rectangle mapped_rect, object_box;
        detection_template best_template;
        unsigned long best_level;
        get_mapped_rect_and_metadata(max_pyramid_levels, rect, mapped_rect, best_template, object_box, best_level);
        return mapped_rect;
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    void scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_mapped_rect_and_metadata (
        const unsigned long number_pyramid_levels,
        rectangle rect,
        rectangle& mapped_rect,
        detection_template& best_template,
        rectangle& object_box,
        unsigned long& best_level
    ) const
    {
        pyramid_type pyr;
        // Figure out the pyramid level which best matches rect against one of our 
        // detection template object boxes.
        best_level = 0;
        double best_match_score = -1;


        // for all the levels
        for (unsigned long l = 0; l < number_pyramid_levels; ++l)
        {
            // Run the center point through the feature/image space transformation just to make
            // sure we exactly replicate the procedure for shifting an object_box used elsewhere 
            // in this file.
            const rectangle temp = pyr.rect_down(rect,l);
            if (temp.area() <= 1) 
                break;
            const point origin = feats_config.feat_to_image_space(feats_config.image_to_feat_space(center(temp)));

            for (unsigned long t = 0; t < det_templates.size(); ++t)
            {
                // Map this detection template into the normal image space and see how
                // close it is to the rect we are looking for.  We do the translation here
                // because the rect_up() routine takes place using integer arithmetic and
                // could potentially give slightly different results with and without the
                // translation.
                rectangle temp2 = translate_rect(det_templates[t].object_box, origin);
                temp2 = pyr.rect_up(temp2, l);

                const double match_score = get_match_score(temp2, rect);
                if (match_score > best_match_score)
                {
                    best_match_score = match_score;
                    best_level = l;
                    best_template = det_templates[t];
                }
            }
        }


        // Now we translate best_template into the right spot (it should be centered at the location 
        // determined by rect) and convert it into the feature image coordinate system.
        rect = pyr.rect_down(rect,best_level);
        const point offset = -feats_config.image_to_feat_space(point(0,0));
        const point origin = feats_config.image_to_feat_space(center(rect)) + offset;
        for (unsigned long k = 0; k < best_template.rects.size(); ++k)
        {
            rectangle temp = best_template.rects[k];
            temp = feats_config.image_to_feat_space(temp);
            temp = translate_rect(temp, origin);
            best_template.rects[k] = temp;
        }
        for (unsigned long k = 0; k < best_template.movable_rects.size(); ++k)
        {
            rectangle temp = best_template.movable_rects[k];
            temp = feats_config.image_to_feat_space(temp);
            temp = centered_rect(point(0,0), temp.width(), temp.height());
            best_template.movable_rects[k] = temp;
        }

        const rectangle scaled_object_box = feats_config.image_to_feat_space(best_template.object_box);
        object_box = centered_rect(origin-offset, scaled_object_box.width(), scaled_object_box.height());

        // The input rectangle was mapped to one of the detection templates.  Reverse the process
        // to figure out what the mapped rectangle is in the original input space.
        mapped_rect = translate_rect(best_template.object_box, feats_config.feat_to_image_space(origin-offset));
        mapped_rect = pyr.rect_up(mapped_rect, best_level);
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    full_object_detection scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_full_object_detection (
        const rectangle& rect,
        const feature_vector_type& w
    ) const
    {
        // fill in movable part positions.  

        rectangle mapped_rect;
        detection_template best_template;
        unsigned long best_level;
        rectangle object_box;
        get_mapped_rect_and_metadata(feats.size(), rect, mapped_rect, best_template, object_box, best_level);

        Pyramid_type pyr;

        array2d<double> saliency_image, sum_img;

        double total_temp_score = 0;
        // convert into feature space.
        object_box = object_box.intersect(get_rect(feats[best_level]));

        std::vector<point> movable_parts;
        movable_parts.reserve(get_num_movable_components_per_detection_template());
        for (unsigned long i = 0; i < get_num_movable_components_per_detection_template(); ++i)
        {
            // make the saliency_image for the ith movable part.

            const rectangle part_rect = best_template.movable_rects[i];
            const rectangle area = grow_rect(object_box, 
                                             part_rect.width()/2, 
                                             part_rect.height()/2).intersect(get_rect(feats[best_level]));

            saliency_image.set_size(area.height(), area.width());
            const unsigned long offset = feats_config.get_num_dimensions()*(i+get_num_stationary_components_per_detection_template());

            // build saliency image for pyramid level best_level 
            for (long r = area.top(); r <= area.bottom(); ++r)
            {
                for (long c = area.left(); c <= area.right(); ++c)
                {
                    const typename feature_extractor_type::descriptor_type& descriptor = feats[best_level](r,c);

                    double sum = 0;
                    for (unsigned long k = 0; k < descriptor.size(); ++k)
                    {
                        sum += w(descriptor[k].first + offset)*descriptor[k].second;
                    }
                    saliency_image[r-area.top()][c-area.left()] = sum;
                }
            }

            sum_img.set_size(saliency_image.nr(), saliency_image.nc());
            sum_filter_assign(saliency_image, sum_img, part_rect);
            // Figure out where the maximizer is in sum_img.  Note that we
            // only look in the part of sum_img that corresponds to a location inside
            // object_box.
            rectangle valid_area = get_rect(sum_img);
            valid_area.left()   += object_box.left()   - area.left();
            valid_area.top()    += object_box.top()    - area.top();
            valid_area.right()  += object_box.right()  - area.right();
            valid_area.bottom() += object_box.bottom() - area.bottom();
            double max_val = 0;
            point max_loc;
            for (long r = valid_area.top(); r <= valid_area.bottom(); ++r)
            {
                for (long c = valid_area.left(); c <= valid_area.right(); ++c)
                {
                    if (sum_img[r][c] > max_val)
                    {
                        //if (object_box.contains(point(c,r) + area.tl_corner()))
                        {
                            max_loc = point(c,r);
                            max_val = sum_img[r][c];
                        }
                    }
                }
            }

            if (max_val <= 0)
            {
                max_loc = OBJECT_PART_NOT_PRESENT;
            }
            else
            {
                total_temp_score += max_val;
                // convert max_loc back into feature image space from our cropped image.
                max_loc += area.tl_corner();

                // now convert from feature space to image space.
                max_loc = feats[best_level].feat_to_image_space(max_loc);
                max_loc = pyr.point_up(max_loc, best_level);
                max_loc = nearest_point(rect, max_loc);
            }

            movable_parts.push_back(max_loc);
        }

        return full_object_detection(rect, movable_parts);
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    void scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_feature_vector (
        const full_object_detection& obj,
        feature_vector_type& psi
    ) const
    {
        // make sure requires clause is not broken
        DLIB_ASSERT(get_num_detection_templates() > 0 &&
                    is_loaded_with_image() &&
                    psi.size() >= get_num_dimensions() &&
                    obj.num_parts() == get_num_movable_components_per_detection_template(),
            "\t void scan_image_pyramid::get_feature_vector()"
            << "\n\t Invalid inputs were given to this function "
            << "\n\t get_num_detection_templates(): " << get_num_detection_templates()
            << "\n\t is_loaded_with_image(): " << is_loaded_with_image()
            << "\n\t psi.size():             " << psi.size()
            << "\n\t get_num_dimensions():   " << get_num_dimensions()
            << "\n\t get_num_movable_components_per_detection_template(): " << get_num_movable_components_per_detection_template()
            << "\n\t obj.num_parts():                            " << obj.num_parts()
            << "\n\t this: " << this
            );
        DLIB_ASSERT(all_parts_in_rect(obj), 
            "\t void scan_image_pyramid::get_feature_vector()"
            << "\n\t Invalid inputs were given to this function "
            << "\n\t obj.get_rect(): " << obj.get_rect()
            << "\n\t this: " << this
        );



        rectangle mapped_rect;
        detection_template best_template;
        unsigned long best_level;
        rectangle object_box;
        get_mapped_rect_and_metadata (feats.size(), obj.get_rect(), mapped_rect, best_template, object_box, best_level);

        Pyramid_type pyr;

        // put the movable rects at the places indicated by obj.
        std::vector<rectangle> rects = best_template.rects;
        for (unsigned long i = 0; i < obj.num_parts(); ++i)
        {
            if (obj.part(i) != OBJECT_PART_NOT_PRESENT)
            {
                // map from the original image to scaled feature space.
                point loc = feats[best_level].image_to_feat_space(pyr.point_down(obj.part(i), best_level));
                // Make sure the movable part always stays within the object_box.
                // Otherwise it would be at a place that the detect() function can never
                // look.  
                loc = nearest_point(object_box, loc);
                rects.push_back(translate_rect(best_template.movable_rects[i], loc));
            }
            else
            {
                // add an empty rectangle since this part wasn't observed.
                rects.push_back(rectangle());
            }
        }

        // pull features out of all the boxes in rects.
        for (unsigned long j = 0; j < rects.size(); ++j)
        {
            const rectangle rect = rects[j].intersect(get_rect(feats[best_level]));
            const unsigned long template_region_id = j;
            const unsigned long offset = feats_config.get_num_dimensions()*template_region_id;
            for (long r = rect.top(); r <= rect.bottom(); ++r)
            {
                for (long c = rect.left(); c <= rect.right(); ++c)
                {
                    const typename feature_extractor_type::descriptor_type& descriptor = feats[best_level](r,c);
                    for (unsigned long k = 0; k < descriptor.size(); ++k)
                    {
                        psi(descriptor[k].first + offset) += descriptor[k].second;
                    }
                }
            }
        }

    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    void scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    set_min_pyramid_layer_size (
        unsigned long width,
        unsigned long height 
    )
    {
        // make sure requires clause is not broken
        DLIB_ASSERT(width > 0 && height > 0 ,
            "\t void scan_image_pyramid::set_min_pyramid_layer_size()"
            << "\n\t These sizes can't be zero. "
            << "\n\t width:  " << width 
            << "\n\t height: " << height 
            << "\n\t this:   " << this
            );

        min_pyramid_layer_width = width;
        min_pyramid_layer_height = height;
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    unsigned long scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_min_pyramid_layer_width (
    ) const
    {
        return min_pyramid_layer_width;
    }

// ----------------------------------------------------------------------------------------

    template <
        typename Pyramid_type,
        typename Feature_extractor_type
        >
    unsigned long scan_image_pyramid<Pyramid_type,Feature_extractor_type>::
    get_min_pyramid_layer_height (
    ) const
    {
        return min_pyramid_layer_height;
    }

// ----------------------------------------------------------------------------------------

}

#endif // DLIB_SCAN_IMaGE_PYRAMID_H__