Vadim Pisarevsky
|
bc730292bb
|
workaround for some strange bug on old Mac.
|
2013-12-23 21:29:31 +04:00 |
|
Vadim Pisarevsky
|
8998186ce4
|
removed extra whitespaces and hopefully fixed the test failures
|
2013-12-23 18:41:54 +04:00 |
|
Vadim Pisarevsky
|
d084d19779
|
added OpenCL optimization for LBP-based face detector
|
2013-12-23 15:28:50 +04:00 |
|
Vadim Pisarevsky
|
1540910542
|
started adding OpenCL acceleration of LBP-based object detectors
|
2013-12-20 18:39:35 +04:00 |
|
Vadim Pisarevsky
|
242a3d1f19
|
2 more fixes to calm down the doc builder
|
2013-12-19 16:57:02 +04:00 |
|
Vadim Pisarevsky
|
f41f633d2d
|
fixed various warnings from the “doc” and other builders
|
2013-12-19 16:31:30 +04:00 |
|
Vadim Pisarevsky
|
a1784b7320
|
converted old haar cascades to the new format; added the conversion function; added OpenCL optimization into CascadeClassfier; optimized the data structures and CPU code for the stump case.
|
2013-12-19 14:48:42 +04:00 |
|
Vadim Pisarevsky
|
ec3f22cee2
|
renamed OpenCL kernel filename; made some final changes
|
2013-12-19 14:29:28 +04:00 |
|
Vadim Pisarevsky
|
b7553d4e2e
|
some attempts to tune the performance
|
2013-12-19 14:09:44 +04:00 |
|
Vadim Pisarevsky
|
02fb3f0a77
|
it finally works!!!
|
2013-12-17 20:55:49 +04:00 |
|
Vadim Pisarevsky
|
ef509ace43
|
trying to debug the new cascade
|
2013-12-17 14:51:22 +04:00 |
|
Vadim Pisarevsky
|
9d3e7e027a
|
almost finished opencl-ization of cascade classifier
|
2013-12-17 14:29:30 +04:00 |
|
Vadim Pisarevsky
|
d8513d627d
|
continue adding OpenCL optimization to cascade classifier
|
2013-12-12 21:58:42 +04:00 |
|
Vadim Pisarevsky
|
302a5adcc2
|
converted Haar cascades to the new format; now they are handled with C++ code.
|
2013-12-10 22:54:37 +04:00 |
|
Vadim Pisarevsky
|
fdf1996e2e
|
added old=>new cascade conversion function
|
2013-12-07 01:51:35 +04:00 |
|
Vadim Pisarevsky
|
828b0b151b
|
another attempt to fix compile errors
|
2013-12-04 22:22:36 +04:00 |
|
Vadim Pisarevsky
|
fe11ca886a
|
trying to eliminate compile problems
|
2013-12-04 21:56:35 +04:00 |
|
Vadim Pisarevsky
|
ff87385201
|
refactored CascadeClassifier to hide implementation details (take 2)
|
2013-12-04 19:00:39 +04:00 |
|
Roman Donchenko
|
d58cd9851f
|
Merge remote-tracking branch 'origin/2.4' into merge-2.4
Conflicts:
CMakeLists.txt
cmake/OpenCVDetectCUDA.cmake
doc/tutorials/features2d/feature_flann_matcher/feature_flann_matcher.rst
modules/core/src/cmdparser.cpp
modules/gpu/CMakeLists.txt
modules/gpu/doc/introduction.rst
modules/gpu/perf/perf_video.cpp
modules/highgui/doc/reading_and_writing_images_and_video.rst
modules/ocl/src/cl_context.cpp
modules/video/include/opencv2/video/background_segm.hpp
samples/cpp/image_sequence.cpp
samples/cpp/tutorial_code/ImgTrans/HoughCircle_Demo.cpp
samples/python/chessboard.py
samples/python/cvutils.py
samples/python/demhist.py
samples/python/dft.py
samples/python/distrans.py
samples/python/edge.py
samples/python/ffilldemo.py
samples/python/fitellipse.py
samples/python/houghlines.py
samples/python/inpaint.py
samples/python/logpolar.py
samples/python/morphology.py
samples/python/numpy_array.py
samples/python/watershed.py
|
2013-12-03 17:35:21 +04:00 |
|
Roman Donchenko
|
10aec14a4d
|
Merge pull request #1849 from StevenPuttemans:feature_3375_documentation
|
2013-11-27 13:22:31 +04:00 |
|
Roman Donchenko
|
9c2272d520
|
Merge remote-tracking branch 'origin/2.4' into merge-2.4
Conflicts:
.gitignore
CMakeLists.txt
doc/CMakeLists.txt
modules/calib3d/src/stereosgbm.cpp
modules/core/include/opencv2/core/mat.hpp
modules/highgui/src/cap_openni.cpp
modules/ml/include/opencv2/ml/ml.hpp
modules/objdetect/src/hog.cpp
modules/ocl/perf/perf_color.cpp
modules/ocl/src/arithm.cpp
modules/ocl/src/filtering.cpp
modules/ocl/src/imgproc.cpp
modules/ocl/src/optical_flow_farneback.cpp
platforms/scripts/camera_build.conf
platforms/scripts/cmake_android_all_cameras.py
samples/cpp/Qt_sample/main.cpp
samples/cpp/tutorial_code/introduction/windows_visual_studio_Opencv/Test.cpp
|
2013-11-26 15:05:26 +04:00 |
|
StevenPuttemans
|
6f892b10ff
|
Applied feature #3375 and fix of pull 1842 to avoid merging problems later
|
2013-11-25 10:53:03 +01:00 |
|
Piotr Miecielica
|
a19cc6cb64
|
Added pointer initialization
|
2013-11-22 13:33:33 +01:00 |
|
Piotr Miecielica
|
923698d700
|
Fixes of some memory leaks
|
2013-11-21 18:55:09 +01:00 |
|
Vadim Pisarevsky
|
e2bbe7597b
|
fixed few compile errors and doc build errors
|
2013-11-18 13:48:04 -05:00 |
|
Vadim Pisarevsky
|
8762ee3f6f
|
removed unnecessary opencl kernels
|
2013-11-18 12:02:10 -05:00 |
|
Vadim Pisarevsky
|
d914f20a4c
|
updated patch to bring in the first functions with "transparent API"
|
2013-11-18 11:48:00 -05:00 |
|
Anatoly Baksheev
|
e154bce259
|
fixed compilation for vs2008
|
2013-11-17 14:13:13 +04:00 |
|
Roman Donchenko
|
334292083e
|
Merge pull request #1629 from lluisgomez:er_tree_clean_bug_fix
|
2013-10-29 16:03:51 +04:00 |
|
lluis
|
b50185e160
|
Fix a bug in the er tree clean-up process (see discussion in https://github.com/Itseez/opencv/pull/1520). It's not necessary to walk the er tree in order to clean up the memory since it's possible to cleanup the regions in the stack just by iterating over the er_stack vector instead of walking the tree structure. This turns out to be safer because the tree structure of those regions may have been modified previously in er_save function.
|
2013-10-15 19:44:08 +02:00 |
|
Ilya Lavrenov
|
35d9ce0c0c
|
fixed warnings
|
2013-10-08 12:46:43 +04:00 |
|
lluis
|
047b568f6d
|
erGrouping now uses a classifier for group validation instead of a set of heuristical ifos.
Updated documentation and sample to use the new function API
|
2013-09-27 19:19:45 +02:00 |
|
Alexander Smorkalov
|
0d49206a98
|
Merge pull request #1485 from vpisarev:ipp_fixes
|
2013-09-26 11:09:59 +04:00 |
|
lluis
|
5670e4f6cd
|
fixed typos
|
2013-09-23 10:17:47 +02:00 |
|
lluis
|
5556f051f1
|
added rst documentation for the Class-specific Extremal Regions for Scene Text Detection
|
2013-09-20 21:39:11 +02:00 |
|
Vadim Pisarevsky
|
8e7eb79f6e
|
fixed compile errors and warnings when building master branch with IPP enabled
|
2013-09-20 16:02:15 +04:00 |
|
lluis
|
2837bfd9fa
|
Added erGrouping function: Find groups of Extremal Regions that are organized as text blocks. Updated sample/cpp to use the complete text detection pipeline
|
2013-09-19 10:30:25 +02:00 |
|
lluis
|
d25309f82e
|
first parameter of createERFilterNM1/createERFilterNM2 is now mandatory. changed the sample program to use the new prototypes
|
2013-09-13 16:29:21 +02:00 |
|
lluis
|
75fdfba281
|
renamed getDefaultClassifierNM{1,2}() to loadClassifierNM{1,2}() and added "const std::string& filename" parameter (mandatory).
|
2013-09-13 16:19:52 +02:00 |
|
lluis
|
95d92c099c
|
functions getDefaultClassifierNM1() and getDefaultClassifierNM2() allow to implicitly load the default classifiers when creating a ERFilter object
|
2013-09-13 12:54:23 +02:00 |
|
lluis
|
ad94628038
|
Using cv::magnitude instead of custom loop and Mat<float> instead of Mat<double> to compute gradient magnitude channel.
|
2013-09-09 18:37:55 +02:00 |
|
lluis
|
e8d3732aaf
|
added computeNMChannels helper function to compute the diferent channels to be processed independently in the N&M algorithm.
|
2013-09-09 11:37:58 +02:00 |
|
lluis
|
cd33ca0009
|
changed default parameters in CreateERFiltersNM{1,2} functions. They are not needed now in the sample example.
|
2013-09-06 19:10:53 +02:00 |
|
lluis
|
6ef1d456dd
|
fixed rebase conflicts
|
2013-09-06 14:00:11 +02:00 |
|
lluis
|
512111af9c
|
removed blank line at EOF
|
2013-09-06 12:32:10 +02:00 |
|
lluis
|
1cc6502db3
|
removed unnecessary commented block
|
2013-09-06 12:32:10 +02:00 |
|
lluis
|
04913f5af7
|
removed trailing whitespaces
|
2013-09-06 12:32:10 +02:00 |
|
lluis
|
f4d01175b8
|
fixed a bug in the calculation of the number of inflexion points feature
|
2013-09-06 12:31:49 +02:00 |
|
lluis
|
765921cc25
|
fixed a typo error in the default min_Probability param of CreateERFilterNM2
|
2013-09-06 12:30:22 +02:00 |
|
lluis
|
dba336c0e3
|
fixed a bug in the non-max-suppression filter procedure
|
2013-09-06 12:27:19 +02:00 |
|