lluis
dba336c0e3
fixed a bug in the non-max-suppression filter procedure
2013-09-06 12:27:19 +02:00
Roman Donchenko
a50d75d362
Made Filestorage able to not own its CvFileStorage instance.
...
This allows to get rid of the last remaining Ptr<T>::addref calls.
2013-09-05 19:03:00 +04:00
Roman Donchenko
b12894d95a
Boring changes - objdetect.
2013-09-05 19:02:58 +04:00
Roman Donchenko
dd25f416a6
War on Whitespace, master edition: tabs.
2013-08-27 17:13:53 +04:00
Roman Donchenko
9ed475cf52
War on Whitespace, master edition: file endings.
2013-08-27 14:23:26 +04:00
Roman Donchenko
9b92545ce6
War on Whitespace, master edition: trailing spaces.
2013-08-27 13:57:24 +04:00
Roman Donchenko
2c4bbb313c
Merge commit '43aec5ad' into merge-2.4
...
Conflicts:
cmake/OpenCVConfig.cmake
cmake/OpenCVLegacyOptions.cmake
modules/contrib/src/retina.cpp
modules/gpu/doc/camera_calibration_and_3d_reconstruction.rst
modules/gpu/doc/video.rst
modules/gpu/src/speckle_filtering.cpp
modules/python/src2/cv2.cv.hpp
modules/python/test/test2.py
samples/python/watershed.py
2013-08-27 13:26:44 +04:00
Roman Donchenko
e9a28f66ee
Normalized file endings.
2013-08-21 18:59:25 +04:00
Roman Donchenko
f55740da70
Deleted all trailing whitespace.
2013-08-21 18:59:24 +04:00
Roman Donchenko
893e8b4371
Merge pull request #942 from achalddave:patch-1
2013-08-21 16:06:31 +04:00
Roman Donchenko
f76dd99299
Merge remote-tracking branch 'origin/2.4' into merge-2.4
...
Conflicts:
cmake/OpenCVModule.cmake
doc/tutorials/calib3d/camera_calibration/camera_calibration.rst
doc/tutorials/features2d/feature_detection/feature_detection.rst
doc/tutorials/features2d/feature_flann_matcher/feature_flann_matcher.rst
doc/tutorials/features2d/feature_homography/feature_homography.rst
modules/core/include/opencv2/core/operations.hpp
modules/core/src/arithm.cpp
modules/gpu/perf/perf_video.cpp
modules/imgproc/include/opencv2/imgproc/imgproc.hpp
modules/java/generator/gen_java.py
modules/java/generator/src/cpp/VideoCapture.cpp
modules/nonfree/src/opencl/surf.cl
modules/ocl/include/opencv2/ocl/ocl.hpp
modules/ocl/perf/perf_haar.cpp
modules/ocl/perf/perf_precomp.hpp
modules/ocl/src/color.cpp
modules/ocl/src/filtering.cpp
modules/ocl/test/test_color.cpp
modules/ocl/test/test_objdetect.cpp
modules/python/src2/cv2.cpp
samples/gpu/CMakeLists.txt
samples/gpu/super_resolution.cpp
2013-08-19 19:02:36 +04:00
Achal Dave
0bc609257d
Comparing rejected stage index with minimum required neighbors does not make sense
...
As described here, http://code.opencv.org/issues/3064 , the test before
led to a case where we compared the index of the latest stage at which a
rectangle was rejected with the minimum number of neighbors required as
specified in `detectMultiScale`. Please see the issue for more
information.
2013-08-13 20:42:04 -07:00
Roman Donchenko
d9f71b762f
Deleted almost all of the precomp.cpp files.
...
Looks like we don't actually use them; when creating precompiled headers
with Visual C++, a dummy .cpp is created at build time.
2013-08-08 12:43:07 +04:00
Roman Donchenko
dcaf923517
Merge remote-tracking branch 'origin/2.4'
...
Conflicts:
3rdparty/ffmpeg/ffmpeg_version.cmake
cmake/OpenCVFindLibsGrfmt.cmake
cmake/templates/cvconfig.h.cmake
modules/bioinspired/doc/retina/index.rst
modules/calib3d/doc/camera_calibration_and_3d_reconstruction.rst
modules/calib3d/src/precomp.hpp
modules/contrib/src/inputoutput.cpp
modules/contrib/src/precomp.hpp
modules/core/include/opencv2/core/internal.hpp
modules/core/include/opencv2/core/types_c.h
modules/core/src/drawing.cpp
modules/core/src/precomp.hpp
modules/core/src/system.cpp
modules/features2d/doc/common_interfaces_of_descriptor_matchers.rst
modules/features2d/doc/common_interfaces_of_feature_detectors.rst
modules/features2d/include/opencv2/features2d/features2d.hpp
modules/features2d/src/precomp.hpp
modules/flann/src/precomp.hpp
modules/gpu/doc/camera_calibration_and_3d_reconstruction.rst
modules/gpu/doc/image_filtering.rst
modules/gpu/doc/image_processing.rst
modules/gpu/doc/video.rst
modules/gpu/perf/perf_imgproc.cpp
modules/gpu/perf4au/main.cpp
modules/gpu/src/imgproc.cpp
modules/gpu/src/precomp.hpp
modules/gpu/test/test_imgproc.cpp
modules/highgui/CMakeLists.txt
modules/highgui/test/test_precomp.hpp
modules/imgproc/doc/structural_analysis_and_shape_descriptors.rst
modules/imgproc/src/precomp.hpp
modules/java/generator/src/cpp/Mat.cpp
modules/legacy/src/precomp.hpp
modules/ml/doc/k_nearest_neighbors.rst
modules/ml/src/precomp.hpp
modules/nonfree/doc/feature_detection.rst
modules/nonfree/src/precomp.hpp
modules/objdetect/include/opencv2/objdetect/objdetect.hpp
modules/objdetect/src/cascadedetect.cpp
modules/objdetect/src/hog.cpp
modules/objdetect/src/precomp.hpp
modules/objdetect/test/test_latentsvmdetector.cpp
modules/ocl/src/hog.cpp
modules/ocl/src/opencl/objdetect_hog.cl
modules/ocl/src/precomp.hpp
modules/photo/src/precomp.hpp
modules/stitching/src/precomp.hpp
modules/superres/perf/perf_precomp.hpp
modules/superres/src/optical_flow.cpp
modules/superres/src/precomp.hpp
modules/superres/test/test_precomp.hpp
modules/ts/include/opencv2/ts.hpp
modules/video/src/precomp.hpp
modules/videostab/src/precomp.hpp
modules/world/src/precomp.hpp
2013-08-06 13:56:49 +04:00
Andrey Pavlenko
9b5d1596dc
Merge pull request #891 from NCBee:2.4
2013-07-31 16:38:16 +04:00
Roman Donchenko
8afb7a40c6
Merge pull request #1159 from lluisgomez:scene_text_detection_NM
2013-07-25 12:13:49 +04:00
lluis
c4f88b0687
removed some unnecessary ERStat members as they are easily computable from others
2013-07-23 15:04:01 +02:00
lluis
43e7e6e475
removed extra cv:: scope qualifiers for better readability
2013-07-23 14:37:45 +02:00
lluis
2087d4602b
using Rect for storing the bounding box instead of an integer array
2013-07-23 13:58:52 +02:00
lluis
9fbff009e9
fixed compilation errors and warnings on builds 3298 and 4384
2013-07-20 11:35:56 +02:00
lluis
6adba09463
fixed some warnings on build 4285
2013-07-20 11:13:38 +02:00
lluis
1d8e80aa3b
add opencv_ml headers to precomp
2013-07-20 10:33:42 +02:00
lluis
5abe3b59f5
Class-specific Extremal Region Filter algorithm as proposed in :
...
Neumann L., Matas J.: Real-Time Scene Text Localization and Recognition, CVPR 2012.
High-level C++ interface and implementation of algorithm is in the objdetect module.
C++ example, a test image, and the default classifiers in xml files.
2013-07-20 01:10:05 +02:00
Roman Donchenko
ac39bfb4cc
Remove HAVE_CVCONFIG_H - it's always defined.
2013-07-10 16:02:07 +04:00
Peter Minin
7d70399d72
Add a new variant of detectMultiScale with output arguments 'objects' and 'numDetections'; factor most of detectMultiScale's code into 2 protected methods
2013-06-14 04:25:17 +04:00
Roman Donchenko
d583a79869
Revert "Add a variant of detectMultiScale with an argument 'weights'"
...
It was merged by mistake.
This reverts commit ab6be9b7b7
.
2013-06-10 17:06:34 +04:00
Peter Minin
ab6be9b7b7
Add a variant of detectMultiScale with an argument 'weights' that
...
receives the number of neighbors joined into each detected object
2013-06-06 19:00:55 +04:00
Roman Donchenko
bae85660da
Merge remote-tracking branch 'origin/2.4'
...
Pull requests:
#943 from jet47:cuda-5.5-support
#944 from jet47:cmake-2.8.11-cuda-fix
#912 from SpecLad:contributing
#934 from SpecLad:parallel-for
#931 from jet47:gpu-test-fixes
#932 from bitwangyaoyao:2.4_fixBFM
#918 from bitwangyaoyao:2.4_samples
#924 from pengx17:2.4_arithm_fix
#925 from pengx17:2.4_canny_tmp_fix
#927 from bitwangyaoyao:2.4_perf
#930 from pengx17:2.4_haar_ext
#928 from apavlenko:bugfix_3027
#920 from asmorkalov:android_move
#910 from pengx17:2.4_oclgfft
#913 from janm399:2.4
#916 from bitwangyaoyao:2.4_fixPyrLK
#919 from abidrahmank:2.4
#923 from pengx17:2.4_macfix
Conflicts:
modules/calib3d/src/stereobm.cpp
modules/features2d/src/detectors.cpp
modules/gpu/src/error.cpp
modules/gpu/src/precomp.hpp
modules/imgproc/src/distransform.cpp
modules/imgproc/src/morph.cpp
modules/ocl/include/opencv2/ocl/ocl.hpp
modules/ocl/perf/perf_color.cpp
modules/ocl/perf/perf_imgproc.cpp
modules/ocl/perf/perf_match_template.cpp
modules/ocl/perf/precomp.cpp
modules/ocl/perf/precomp.hpp
modules/ocl/src/arithm.cpp
modules/ocl/src/canny.cpp
modules/ocl/src/filtering.cpp
modules/ocl/src/haar.cpp
modules/ocl/src/hog.cpp
modules/ocl/src/imgproc.cpp
modules/ocl/src/opencl/haarobjectdetect.cl
modules/ocl/src/pyrlk.cpp
modules/video/src/bgfg_gaussmix2.cpp
modules/video/src/lkpyramid.cpp
platforms/linux/scripts/cmake_arm_gnueabi_hardfp.sh
platforms/linux/scripts/cmake_arm_gnueabi_softfp.sh
platforms/scripts/ABI_compat_generator.py
samples/ocl/facedetect.cpp
2013-06-05 15:42:07 +04:00
Roman Donchenko
29b13ec1de
Replaced most of the usages of parallel_for with that of parallel_for_.
...
This should allow many algorithms to take advantage of more parallelization
technologies.
2013-05-31 12:22:04 +04:00
Bahram Dahi
e2d6a3abe5
Added spacing in a nested template argument list.
2013-05-24 18:44:03 -04:00
Bahram Dahi
dcad6ce65a
Reverted back to the previous method where a public method groupRectangles was added to HOGDescriptor to take care of ROI and weight grouping
2013-05-24 18:25:23 -04:00
Roman Donchenko
029fce10c9
Merge remote-tracking branch 'origin/2.4'
...
Conflicts:
3rdparty/libjasper/CMakeLists.txt
cmake/OpenCVDetectOpenCL.cmake
modules/calib3d/doc/camera_calibration_and_3d_reconstruction.rst
modules/imgproc/src/floodfill.cpp
modules/ocl/include/opencv2/ocl/ocl.hpp
modules/ocl/src/arithm.cpp
modules/ocl/src/haar.cpp
modules/ocl/src/imgproc.cpp
modules/ocl/src/initialization.cpp
modules/ocl/src/matrix_operations.cpp
modules/ocl/src/mcwutil.cpp
modules/ocl/src/opencl/arithm_bitwise_and_mask.cl
modules/ocl/src/opencl/arithm_bitwise_and_scalar_mask.cl
modules/ocl/src/opencl/arithm_bitwise_binary_mask.cl
modules/ocl/src/opencl/arithm_bitwise_binary_scalar.cl
modules/ocl/src/opencl/arithm_bitwise_binary_scalar_mask.cl
modules/ocl/src/opencl/arithm_bitwise_or.cl
modules/ocl/src/opencl/arithm_bitwise_or_scalar.cl
modules/ocl/src/opencl/arithm_bitwise_or_scalar_mask.cl
modules/ocl/src/opencl/arithm_bitwise_xor.cl
modules/ocl/src/opencl/arithm_bitwise_xor_mask.cl
modules/ocl/src/opencl/arithm_bitwise_xor_scalar.cl
modules/ocl/src/stereobm.cpp
modules/ocl/test/precomp.hpp
modules/python/src2/api
modules/ts/src/ts_func.cpp
samples/gpu/bgfg_segm.cpp
2013-05-21 17:19:23 +04:00
Bahram Dahi
8c25f9f28a
[3rd attempt] fixed HOGDescriptor::detectMultiScale() to group weights as well as ROIs
2013-05-20 13:20:57 -04:00
ShengyinWu
ef5578a7ce
Fixs: After scaling back to original image, some detected ROI will outside the original image ROI
2013-04-29 12:16:42 +08:00
Andrey Kamaev
5e048d1fa5
Move C API of opencv_objdetect to separate file
...
Also move cv::linemod to own header
2013-04-12 14:37:01 +04:00
Andrey Kamaev
c98c246fc2
Move border type constants and Moments class to core module
2013-04-10 19:14:24 +04:00
Andrey Kamaev
0738ea7d0f
Make highgui.hpp independent from C API
2013-04-08 15:47:29 +04:00
Andrey Kamaev
517062039e
Make core/internal.hpp a private header
2013-04-01 17:29:10 +04:00
Andrey Kamaev
3890a74565
Drop outdated definitions from internal.hpp
...
This also fixes few clang build errors
2013-04-01 15:24:35 +04:00
Andrey Kamaev
4ab650d15b
Remove gcd function from core headers
2013-04-01 15:24:34 +04:00
Andrey Kamaev
715fa3303e
Move cv::Mat out of core.hpp
2013-04-01 15:24:34 +04:00
Andrey Kamaev
62adc01980
Move cv::Rect_
2013-04-01 15:24:33 +04:00
Andrey Kamaev
addf0309ec
Move cv::Size_
2013-04-01 15:24:32 +04:00
Andrey Kamaev
13b31b0804
Move C++ basic structures to separate header and inverse dependency from C API
...
cv::Complex, cv::Point_ and cv::Point3_ are moved.
2013-04-01 15:24:32 +04:00
Andrey Kamaev
19f8f85c51
Move C structures wrappers from core.hpp to core_c.h
...
Also move RTTIImpl class to the only usage
2013-04-01 15:24:32 +04:00
Vladislav Vinogradov
b62cf65b91
fixed inconsistent new/delete operators
2013-04-01 11:55:02 +04:00
Andrey Kamaev
04eabf8d9f
Merge pull request #699 from jacob-baines/patch-1
...
Mismatching new[] / delete
2013-03-25 03:26:18 -07:00
Jacob Baines
1e1645e214
Mismatching new[] / delete
2013-03-24 22:45:31 -03:00
Andrey Kamaev
be7bbe3aa9
Drop cv:: prefix from cv::String used inside the cv namespace
2013-03-22 22:14:50 +04:00
Andrey Kamaev
75513a46dc
Remove all include directives for <string>
2013-03-22 22:14:47 +04:00
Andrey Kamaev
2ad7b97f1c
All modules (except ocl and gpu) compiles and pass tests
2013-03-22 22:14:26 +04:00
Andrey Kamaev
89356ff16d
Move non-CV functionality from core.hpp to separate utility.hpp header
2013-03-20 17:56:06 +04:00
Andrey Kamaev
0b0c9be771
Merge pull request #636 from ilya-lavrenov:SSE2_HOG
2013-03-18 15:56:16 +04:00
Andrey Kamaev
ad5cddc007
Main module headers are moved 1 level up
...
e.g. <opencv2/core/core.hpp> become <opencv2/core.hpp>
Also renamed <opencv2/core/opengl_interop.hpp> to <opencv2/core/opengl.hpp>
2013-03-13 17:26:56 +04:00
Ilya Lavrenov
8b510ad8dc
sse2 hog
2013-03-11 20:21:48 +04:00
Andrey Kamaev
2a6fb2867e
Remove all using directives for STL namespace and members
...
Made all STL usages explicit to be able automatically find all usages of
particular class or function.
2013-02-25 15:04:17 +04:00
Andrey Kamaev
c527340cb6
Merge branch 2.4
2013-02-04 17:15:55 +04:00
Andy Maloney
b79e8053c1
Check memory allocation
...
Declare vars as locally as possible
2013-02-02 08:44:25 -05:00
Andy Maloney
bc68dfb4e8
Remove unused vars
2013-02-01 18:09:58 -05:00
cuda-geek
f52ce6529b
Merge pull request #322 from cuda-geek:training
2013-02-01 18:45:12 +04:00
Andrey Kamaev
61079547f0
Merge branch '2.4'
2013-02-01 14:59:40 +04:00
marina.kolpakova
1b43b0e2df
move soft cascade functionality into dedicated module
2013-02-01 14:36:05 +04:00
marina.kolpakova
a28f5a89b3
move preprocessor to objdetect
2013-02-01 14:35:27 +04:00
Vadim Pisarevsky
50299c1d5e
disabled the use of SSE4 instructions as well to make the code compatible with the old Intel and AMD chips
2013-01-31 22:57:46 +04:00
Vadim Pisarevsky
18039d7829
added test for the old cvHaarDetectObjects. disabled AVX optimization in haar.cpp. it should cover tickets #2534 , #2591 , #2669
2013-01-31 22:55:04 +04:00
cuda-geek
d874d93e24
Merge pull request #372 from cuda-geek:gpu-cascade-fixes
2013-01-31 20:13:31 +04:00
Andrey Kamaev
57d3152cd0
Merge branch '2.4'
2013-01-31 14:35:27 +04:00
Evgeny Talanin
50c2f87add
Fix and test for #2607
2013-01-31 12:23:08 +04:00
marina.kolpakova
8d9c9c2690
integrate new cascade format to GPU soft cascade implementation
2013-01-30 15:55:04 +04:00
Andrey Kamaev
78a338159d
Merge branch '2.4'
2013-01-29 14:17:13 +04:00
Andy Maloney
5bd56e7464
Fix mem leak and mismatched new/delete
2013-01-28 17:57:19 -05:00
Andrey Kamaev
f4e27bcbbc
Merge branch '2.4'
2013-01-25 16:30:36 +04:00
Siegfried Hochdorfer
195d501b43
fixed broken indentation
2013-01-24 11:40:35 +01:00
marina.kolpakova
53433884ee
fix python wrapping
2013-01-18 15:58:48 +04:00
marina.kolpakova
f9649a029b
fix typo
2013-01-18 15:58:47 +04:00
marina.kolpakova
0a40bbd0d0
add two types of feature boxes support:
...
- (left, top, width, height)
- (left, top, right, bottom)
2013-01-18 15:58:47 +04:00
marina.kolpakova
9efd668a57
a bit refactored soft cascade
2013-01-18 15:58:47 +04:00
marina.kolpakova
0c6c78d149
integrate 128x256 scale; remove log
2013-01-18 15:58:47 +04:00
marina.kolpakova
e09694bde8
integrated 128x256 scale
2013-01-18 15:58:47 +04:00
marina.kolpakova
3e7965a5a5
first debug integration of newly trained cascade
2013-01-18 15:58:46 +04:00
Siegfried Hochdorfer
82a9f9a5a9
MeanshiftGrouping Bugfix (Bug #2685 )
2013-01-17 11:46:24 +01:00
Andrey Kamaev
084b1c7969
Merge branch 2.4
2013-01-11 15:45:23 +04:00
Andrey Kamaev
399c20a928
Merge pull request #272 from 5kg:fix_haar
2013-01-09 16:53:11 +04:00
marina.kolpakova
e53d57664d
fix precompiled headers usage in gpu module
2012-12-30 16:58:41 +04:00
Zifei Tong
260bdc057c
Changed parallel_for to parallel_for_ in haar.cpp
2012-12-28 22:56:47 +08:00
Zifei Tong
e331787645
Fix race condition for Cascade Classifier when TBB enabled.
2012-12-28 20:51:02 +08:00
marina.kolpakova
2d45af790e
fix according to pull requests comments
2012-12-12 05:07:39 +04:00
marina.kolpakova
88c71d1b7d
add NMS according to Dollar's paper.
2012-12-12 04:31:44 +04:00
Andrey Kamaev
e10ee89ec4
Merge branch 2.4
2012-11-30 19:54:24 +04:00
Maria Dimashova
97e36b9375
fix a compile error in case of building without highgui
2012-11-24 18:10:29 +04:00
marina.kolpakova
6ccd7aca4c
fix tests for arm
2012-11-22 13:26:13 +04:00
marina.kolpakova
1edab12068
fix for negative confidence
2012-11-13 23:08:19 +04:00
marina.kolpakova
bd9ca48fab
export to python/java
2012-11-13 02:49:35 +04:00
marina.kolpakova
665bf430d5
fix warnings under win
2012-11-09 00:07:32 +04:00
marina.kolpakova
8a3e897999
min and max params become double
2012-11-08 02:34:49 +04:00
marina.kolpakova
f93cffaa0d
fix compilation under win
2012-11-08 02:34:49 +04:00
marina.kolpakova
1022094dc0
fix levels computing
2012-11-08 02:34:49 +04:00
marina.kolpakova
f1e36043e6
clean code
2012-11-08 02:34:49 +04:00
marina.kolpakova
4656872161
fixed typo
2012-11-08 02:34:49 +04:00
marina.kolpakova
5fb9f48360
fix angle scaling
2012-11-08 02:34:49 +04:00
marina.kolpakova
4207552e19
add object init
2012-11-08 02:34:49 +04:00
marina.kolpakova
157ab66ab9
add ROI support
2012-11-08 02:34:49 +04:00
marina.kolpakova
6a3a723938
refactor integral channels
2012-11-08 02:34:48 +04:00
marina.kolpakova
4a1c4a9862
soft cascade become Algorithm
2012-11-08 02:34:48 +04:00
marina.kolpakova
ff8417db00
remove input frame size constraints
2012-11-07 03:19:07 +04:00
marina.kolpakova
a84334cfc2
brief soft cascade interface description
2012-11-07 03:19:07 +04:00
marina.kolpakova
2e8ed77383
get rid of hard-coded values
2012-11-07 03:19:07 +04:00
marina.kolpakova
16dd09ccfc
move scale related parameters to SoftCascade constructor
2012-11-07 03:19:07 +04:00
marina.kolpakova
017d970b9a
load SoftCascade from FileStorage
2012-11-07 03:19:06 +04:00
marina.kolpakova
a22ee13620
rename markDetection to addDetection
2012-11-07 03:19:06 +04:00
marina.kolpakova
40c0c60e2b
remove unused struct
2012-11-07 03:19:06 +04:00
marina.kolpakova
7b6da394f0
rename Stage to Weak because there is no such term for Soft Cascades
2012-11-07 03:19:06 +04:00
marina.kolpakova
2d0fc80c95
use IntegralChannels class
2012-11-07 03:19:06 +04:00
marina.kolpakova
3d41846c39
move frame processing into separate class
2012-11-07 03:19:06 +04:00
marina.kolpakova
5651743784
remove debug imshow from code
2012-11-07 03:19:06 +04:00
marina.kolpakova
8e092f8b5d
add Detection struct to interface
2012-11-07 03:19:06 +04:00
marina.kolpakova
754fd7311b
improve pointer usage
2012-11-07 03:19:06 +04:00
marina.kolpakova
2914f24521
improve cpu version of SoftCascade:
...
- remove division
- remove cvRound
- cache feature area
2012-11-07 03:19:06 +04:00
marina.kolpakova
2d2c46e717
add const qualifier to detectMultiScale method
2012-11-07 03:19:06 +04:00
marina.kolpakova
9771c3c7ec
remove Mat copying
2012-11-07 03:19:05 +04:00
marina.kolpakova
0ff8a4633d
remove pow calculations
2012-11-07 03:19:05 +04:00
marina.kolpakova
26af7d7389
refactor logs
2012-11-07 03:19:05 +04:00
marina.kolpakova
b6081438fa
clean code
2012-11-07 03:19:05 +04:00
marina.kolpakova
296aa8854c
fix hog channels
2012-11-07 03:19:05 +04:00
marina.kolpakova
efd2615844
fix floating point bug
2012-11-07 03:19:05 +04:00
marina.kolpakova
765dea9ddf
fix bugs in the soft cascade detect method; add options for debug logging
...
- WITH_DEBUG_OUT for logging cascade scales
- DEBUG_STORE_IMAGES for xml matrix serialization
- DEBUG_SHOW_RESULT to see detection result
2012-11-07 03:19:05 +04:00
marina.kolpakova
ba27d89173
add feature rescaling according to Dollal's paper FPDW
2012-11-07 03:19:05 +04:00
marina.kolpakova
8d90b973b0
add detectAt to soft cascade
2012-11-07 03:19:05 +04:00
marina.kolpakova
801368ee82
refactoring
2012-11-07 03:19:05 +04:00
marina.kolpakova
6f53be4102
shrinking before integral calculation
2012-11-07 03:19:04 +04:00
marina.kolpakova
dc74ce20ab
OpenCV friendly xml format for soft cascade
2012-11-07 03:19:04 +04:00
marina.kolpakova
c04725b681
add apply cascade method
2012-11-07 03:19:04 +04:00
marina.kolpakova
695827050f
Integral images for ICF
2012-11-07 03:19:04 +04:00
marina.kolpakova
b0b85f36f6
add test for soft cascade detect method
2012-11-07 03:19:04 +04:00
marina.kolpakova
f01c5d9033
compute scales pyramid
2012-11-07 03:19:04 +04:00
marina.kolpakova
a54d456ad0
parse soft cascade from xml
2012-11-07 03:19:04 +04:00
marina.kolpakova
fe2c38be80
add method to fill soft cascade
2012-11-07 03:19:04 +04:00
marina.kolpakova
7290d8576d
add ICF feature
2012-11-07 03:19:04 +04:00
marina.kolpakova
fb113e5ce4
scale pyramid calculations
2012-11-07 03:19:04 +04:00
marina.kolpakova
9966d7feba
add structures for cascade representation
2012-11-07 03:19:04 +04:00
Andrey Kamaev
673aa91bac
Fix remaining windows build warnings
2012-10-24 20:27:20 +04:00
Andrey Kamaev
9751014067
Fix warnings from MSVC 10 64-bit
2012-10-23 18:20:07 +04:00
Andrey Kamaev
9900f8deb2
Remove russian comments
2012-10-22 17:24:43 +04:00
OpenCV Buildbot
04384a71e4
Normalize line endings and whitespace
2012-10-17 15:32:23 +04:00
Andrey Kamaev
2abb67cc92
Merge pull request #29 from thorikawa/feature-523
2012-10-12 13:16:17 +04:00
Vadim Pisarevsky
a8c5e35619
some more fixes towards binary compatibility
2012-10-09 15:56:16 +04:00
Evgeny Talanin
6308be2c3e
Changed parallel_for to parallel_for_ in hog.cpp and cascadedetect.cpp
2012-09-25 12:18:33 +04:00
Andrey Kamaev
089de14ed7
Fix copy-paste bug in AVX optimization of haar
2012-09-17 13:30:28 +04:00
Andrey Kamaev
bcd0aefbca
Fix gcc build errors and warnings
2012-09-05 15:51:51 +04:00
Takahiro Horikawa
ec45453baa
#523 Fix the problem where the MaxSize parameter in cvHaarDetectObjects does not work when the flag CV_HAAR_SCALE_IMAGE is not set.
2012-09-04 20:46:42 -07:00
Andrey Kamaev
07d92d9e5a
Fix android build warnings
2012-09-04 17:44:23 +04:00
Vadim Pisarevsky
959674618f
restored SSE2 and added AVX optimization of the old haar face detector
2012-09-04 14:59:38 +04:00
Vadim Pisarevsky
67ff95083d
added openfabmap code, contributed by Arren Glover. fixed several warnings in the new versions of retina filters
2012-09-03 17:03:31 +04:00
Vadim Pisarevsky
633a8bfacc
fixed many warnings (modified pull request 13)
2012-08-28 18:15:14 +04:00
Andrey Kamaev
4a1ef53deb
Fixed gcc build warning
2012-08-20 19:53:03 +04:00
Andrey Kamaev
1a621c2916
Fix build warnings
2012-08-19 19:36:43 +04:00
Andrey Kamaev
1852cb7eab
Fix tegra build warnings
2012-08-07 14:29:51 +04:00
Vadim Pisarevsky
fac3d9994c
integrated another portion of SSE optimizations from Grigory Frolov
2012-07-31 19:07:55 +04:00
marina.kolpakova
e1e0c46639
integrated patch: HOG confidence calculation. Thanks, Wongun.
2012-07-25 15:26:26 +04:00
Marina Kolpakova
336dcbcff7
fixed brocken tests by classifier loger from r9027
2012-07-15 04:11:46 +00:00
Anatoly Baksheev
9706079ace
a bit refactoring in LBP face detection on GPU
2012-07-13 15:47:09 +00:00
Marina Kolpakova
1365e28a54
initial support of GPU LBP classifier: added new style xml format loading
2012-06-22 15:00:36 +00:00
Andrey Kamaev
d48d7b2b46
Updated warning options for GCC; fixed new warnings.
2012-06-20 12:27:02 +00:00
Andrey Kamaev
7cccc93bdf
Fixed Android build warnings and few warnings in specific cnfigurations
2012-06-13 13:19:43 +00:00
Andrey Kamaev
c5aba337e9
Fixed number of warnings. Fixed mingw64 build.
2012-06-12 14:46:12 +00:00
Andrey Kamaev
f2d3b9b4a1
Warning fixes continued
2012-06-09 15:00:04 +00:00
Andrey Kamaev
89e3c461ec
Fixed build with TBB
2012-06-08 06:23:28 +00:00
Andrey Kamaev
f62028dc16
Fixed mingw build.
2012-06-08 03:15:08 +00:00
Andrey Kamaev
49a1ba6038
Set stricter warning rules for gcc
2012-06-07 17:21:29 +00:00
Vadim Pisarevsky
d5a0088bbe
merged 2.4 into trunk
2012-04-30 14:33:52 +00:00
Gary Bradski
54f92013b0
fix to Detector::write so that it doesn't abort on read
2012-04-27 04:05:33 +00:00
Vadim Pisarevsky
2fd1e2ea57
merged all the latest changes from 2.4 to trunk
2012-04-13 21:50:59 +00:00
Vadim Pisarevsky
beb7fc3c92
a LOT of obsolete stuff has been moved to the legacy module.
2012-03-30 12:19:25 +00:00
Vadim Pisarevsky
806aab164b
save, load & copy HOGDescriptor::nlevels (ticket #1533 )
2012-03-28 14:31:03 +00:00
Andrey Kamaev
67838a7a66
Made dependency of opencv_objdetect from opencv_highgui optional.
2012-03-27 20:17:31 +00:00
Vadim Pisarevsky
afd9523ff2
possibly fixed bug #1453
2012-03-26 09:40:49 +00:00
Marina Kolpakova
2ca6a50546
Fixed bug #1663
2012-03-18 16:53:00 +00:00
Vadim Pisarevsky
846e37ded5
fixed many warnings from GCC 4.6.1
2012-03-17 09:22:31 +00:00
Vadim Pisarevsky
4985c1b632
fixed hundreds of warnings from MSVC 2010.
2012-03-16 21:21:04 +00:00
Vadim Pisarevsky
957e80abbd
lot's of changes; nonfree & photo modules added; SIFT & SURF -> nonfree module; Inpainting -> photo; refactored features2d (ORB is still failing tests), optimized brute-force matcher and made it non-template.
2012-03-15 14:36:01 +00:00
Andrey Kamaev
e4307d05f3
Made dependency of features2d and calib3d from highgui optional
2012-03-13 12:33:16 +00:00
Alexander Shishkov
0279ba953e
fixed warnings in linemod on Windows
2012-02-27 11:42:33 +00:00
Patrick Mihelich
f483272d09
No longer expose internal LINE-MOD methods like response map computation, linearizing similarities, etc in public header.
2012-02-27 00:07:52 +00:00
Patrick Mihelich
f174b001f3
Initial commit of LINE-MOD source code to objdetect module.
2012-02-26 23:55:18 +00:00
Andrey Kamaev
9a88aea697
Eliminated all compiler warnings on Android
2012-02-21 14:07:44 +00:00
Vadim Pisarevsky
716a5d04ab
fixed a few problems detected by Xcode 4.2.1
2012-02-15 19:48:04 +00:00
Andrey Kamaev
8cab65c173
Started top-level CMakeLists.txt file reorganization: cmake scripts are moved to separate folder; refactored BUILD_*, INSTALL_*, ENABLE_*, USE_*, WITH_* options.
2012-01-03 13:48:12 +00:00
Leonid Beynenson
9f837d3486
Made changes concerning inserting prefiltering modes into CascadeClassifier class.
...
Now developers should call the method setFaceDetectionMaskGenerator() to use prefiltering mask generator
implemented for face detection.
2011-10-21 14:56:37 +00:00
Leonid Beynenson
da3a60a5a7
Made changes in the method of inserting prefilters into the CascadeClassifier class.
2011-10-12 11:32:01 +00:00
Leonid Beynenson
630288fdef
Added possibility of prefiltering into CascadeClassifier. Now OpenCV users can implement their own mask generators and insert them into CascadeClassifier.
2011-10-05 13:21:28 +00:00
Maria Dimashova
36967575be
Added doc on c++ version of latent svm
2011-10-04 12:10:57 +00:00
Maria Dimashova
a4bc940a50
fixed method clear()
2011-10-04 11:35:39 +00:00
Maria Dimashova
4d85ee7de1
added c++ wrapper of latent svm
2011-10-03 16:45:46 +00:00
Leonid Beynenson
87a21016d8
Implemented the first variant of working with masks in CascadeClassifier. Probably, will be rewritten soon.
2011-09-28 21:14:20 +00:00
Vadim Pisarevsky
86882e5dd1
fixed bug #1381
2011-09-27 15:50:17 +00:00
Vadim Pisarevsky
1c738820de
fixed resource leak in lsvmparser (ticket #1390 )
2011-09-27 15:43:13 +00:00
Vadim Pisarevsky
3535aacc23
fixed bug #1389
2011-09-27 15:17:00 +00:00
Anatoly Baksheev
25cadb1abd
fixed compilation under ubuntu
2011-09-21 18:25:22 +00:00
Alexey Kazakov
50543d627f
Added HOG features to cascade detection algorithm.
...
Added pedestrian detection trained model for HOG cascade detection algorithm.
2011-09-21 18:03:53 +00:00
Vadim Pisarevsky
d3d55f3234
fixed crashes in parallel HOG detector; avoid use of new POPCNT instruction in ORB (to make it compatible with older CPUs).
2011-08-16 13:52:02 +00:00
Vadim Pisarevsky
a51a8ad577
fixed tickets #1301 , #1303 , #1305
2011-08-14 19:46:39 +00:00
Vadim Pisarevsky
d58459ccdd
fixed default maxSize case in cvHaarDetectObjects (ticket #1296 )
2011-08-11 13:16:00 +00:00
Leonid Beynenson
aa78754720
Changed tabulation.
2011-08-10 14:21:20 +00:00
Leonid Beynenson
dc13ec205d
Made additional internal header modules/objdetect/src/cascadedetect.hpp, and moved
...
some internal classes and template functions from cascadedetect.cpp to this header.
This will allow to make a child class for such classes as LBPEvaluator, etc.
Also made all "private" fields in LBPEvaluator and HaarEvaluator to be "protected".
2011-07-29 14:18:45 +00:00
Vadim Pisarevsky
ff5e97c8e4
added COVAR_ and SORT_ enums to core.hpp; fixed many, many VS2005, VS2010 and MinGW (GCC 4.5.2) warnings
2011-07-19 12:27:07 +00:00
Vadim Pisarevsky
8f41b2b23b
commented off print (due to the report from the mailing list)
2011-07-15 19:43:34 +00:00
Evgeniy Kozinov
c3e9d0dd7e
fixed parser bug.
...
fixed TBB version in LatentSVM.
example works ok.
2011-07-15 06:35:12 +00:00
Vadim Pisarevsky
08f1f5769a
ok. enabled TBB in LatentSVM, but need to check if it works
2011-07-14 12:11:18 +00:00
Vadim Pisarevsky
36ba3d691e
temporarily switch off TBB
2011-07-14 11:51:43 +00:00
Andrey Kamaev
87cfcc8ee2
Fixed Android build
2011-07-14 07:04:36 +00:00
Evgeniy Kozinov
07eed8c489
refactoring latentSVM
2011-07-12 18:43:41 +00:00
Vadim Pisarevsky
b0aae19fb4
probably fixed parallel face detector (i.e. built with TBB), ticket #1185 . Thanks to mengw for the patch
2011-07-07 22:52:54 +00:00
Vadim Pisarevsky
5649f35757
some more bugfixed in 2.3 propagated to trunk
2011-07-07 11:43:21 +00:00
James Bowman
1d335bddfc
Fix for SSE swapping bug
2011-06-28 23:29:15 +00:00
Maria Dimashova
1580806730
removed DOT implementation
2011-06-14 12:28:44 +00:00
Vadim Pisarevsky
9df999154c
fixed a few warnings and bugs, including ticket #1079
2011-06-12 20:29:50 +00:00
Anatoly Baksheev
8f4c7db3f6
~40 warnings under VS2008
...
HAVE_CONFIG_H -> HAVE_CVCONFIG_H
2011-06-11 17:24:09 +00:00
Maria Dimashova
eace415f57
fixed cascade detection on images of size equal to feature size ( #1070 )
2011-06-10 12:19:23 +00:00
Leonid Beynenson
1299941622
Made small optimization: for some processors using float accumulator gives speedup.
2011-05-31 13:44:13 +00:00
Vadim Pisarevsky
c0ec0e05c5
made datamatrix build on Windows; fixed unresolved symbols
2011-05-25 14:49:09 +00:00
Ethan Rublee
355ad2993a
adding c++ interface to the datamtrix codes of j.
2011-05-25 00:23:50 +00:00
Maria Dimashova
a360a19c56
added TBB optimization to DOT
2011-05-24 13:20:32 +00:00
Vadim Pisarevsky
23768b1826
replaced #include <some_opencv_hdr> with #include "some_opencv_hdr" (ticket #719 )
2011-05-21 18:32:34 +00:00
Vadim Pisarevsky
51c6842384
alter the read stage.threshold to match traincascade behavior (ticket #1071 )
2011-05-19 12:41:48 +00:00
Maria Dimashova
0f6b8002dc
fixed save/load of dot; added data for the sample
2011-05-10 13:30:58 +00:00
Maria Dimashova
f4c74eb532
changed the dot
2011-05-10 12:01:42 +00:00
Anatoly Baksheev
927dccb463
fixed compilation WITH_TBB
2011-05-07 11:37:56 +00:00
Anatoly Baksheev
1c18e5fef9
fixed ~300 warnings under windows (had to hack gtest a bit)
2011-05-06 21:45:48 +00:00
Vadim Pisarevsky
0c9e5f6c9c
removed comments in Russian
2011-05-03 13:03:48 +00:00
Vadim Pisarevsky
23a9b7bb9c
fixed several warnings from Xcode 4 LLVM compiler; fixed bug #920
2011-04-30 19:29:26 +00:00
Leonid Beynenson
2806db93d8
Merged the branch /branches/opencv_pthread_framework/opencv into the trunk.
...
The branch contains changes, concerning adding ThreadingFramework -- temporary lightweight decision for ARM instead of Intel TBB.
Also some changes in Android highgui camera class were made.
2011-04-29 14:20:24 +00:00
Vadim Pisarevsky
9ca45daba3
fixed couple of integral-related bugs
2011-04-29 11:55:33 +00:00
Vadim Pisarevsky
0e0929af15
fixed compile errors on Ubuntu
2011-04-26 15:38:32 +00:00
Maria Dimashova
cd981f4d13
started to integrate DOT detector
2011-04-26 13:57:55 +00:00
James Bowman
6f82c0d662
simple mean for decode
2011-04-26 00:02:09 +00:00
Alexey Kazakov
1e69bd5118
class MeanshiftGrouping replaced from objdetect.hpp to cascadedetect.cpp
2011-04-22 16:11:35 +00:00
Alexey Kazakov
fb0b25692e
A little fix in haar cascade
2011-04-22 11:21:40 +00:00
Vadim Pisarevsky
5c1fafdd6f
moved precomp.hpp before all other headers (to repair PCH mechanism). moved tables from the header to datamatrix.cpp
2011-04-22 10:35:51 +00:00
Alexey Kazakov
e9aa6fa012
Added ROC-curve calculating to the cascade detection algorithm
2011-04-22 10:03:05 +00:00
Vadim Pisarevsky
a4924cf52d
some more minor fixes in datamatrix: warnings eliminated, replaced MMX intrinsics (which are not recommended to use on x64) with SSE2.
2011-04-22 07:25:09 +00:00
James Bowman
2c05ddd565
#1018 : predicate on SSE2
2011-04-21 17:29:21 +00:00
Andrey Morozov
efd368f432
temporary fix for problem with compilation sse intrinsics on Windows
2011-04-21 14:47:57 +00:00
James Bowman
f385bb97eb
datamatrix
2011-04-21 00:47:37 +00:00
James Bowman
324e89ab3a
datamatrix
2011-04-21 00:21:42 +00:00
Vadim Pisarevsky
17a2480a21
integrated parallel SVM prediction; fixed warnings after meanshift integration
2011-04-19 16:20:44 +00:00
Alexey Kazakov
537a36115f
The bug was fixed
2011-04-19 12:31:35 +00:00
Alexey Kazakov
e863c3d5f6
Added to objdetect module: meanshift grouping (groupRectangles_meanshift(...) for input rectangles); new pedestrian detection model, trained on the Daimler base (getDaimlerPeopleDetector(...) ).
...
Some changes in the HOGDescriptor class interface(objdetect.hpp) (added useMeanShiftGrouping parameter to the detectMultiScale(...) function)
2011-04-19 09:05:15 +00:00
Vladimir Dudnik
8e7768379f
minor changes: removed trailing spaces in some files
2011-04-18 19:34:51 +00:00
Vadim Pisarevsky
abeeb40d46
a big patch; use special proxy types (Input/OutputArray, Input/OutputArrayOfArrays) for passing in vectors, matrices etc.
2011-04-17 13:14:45 +00:00
Valentina Kustikova
110351d3de
Bugs in the test for LatentSVM were fixed.
2011-04-08 03:51:40 +00:00