56 Commits

Author SHA1 Message Date
Vladislav Vinogradov
281d036fcf optimizations:
- new reduce implementation (with kepler optimizations)
- saturate_cast via asm command
- video SIMD instructions in element operations
- float arithmetics instead of double
- new deviceSupports function
2013-01-23 21:05:07 +04:00
Vladislav Vinogradov
ae6266e101 fixes for gpu module:
- fixed printCudaDeviceInfo for new CC
- fixed some compilation errors and warnings
- removed unset command from CMake script
- removed unused std imports
2013-01-23 21:05:06 +04:00
OpenCV Buildbot
04384a71e4 Normalize line endings and whitespace 2012-10-17 15:32:23 +04:00
Anatoly Baksheev
4b5bbb7752 fast_nlm initial version 2012-10-08 19:57:19 +04:00
Anatoly Baksheev
55b1d7c097 added CUDA_DISABLER preprocessor commands 2012-10-01 23:57:38 +04:00
Anatoly Baksheev
70204a8e68 Removed PtrElemStep, Marked DevMem1D as deprecated, now should use PtrStepSz now 2012-08-24 02:02:42 +04:00
marina.kolpakova
c8a54f67d4 minor warning fix 2012-08-23 13:43:42 +04:00
marina.kolpakova
ede3781e3e fixed -Wstrict_alliasing warning for GCC 2012-08-20 02:27:54 +04:00
Marina Kolpakova
1365e28a54 initial support of GPU LBP classifier: added new style xml format loading 2012-06-22 15:00:36 +00:00
Marina Kolpakova
b065c7a296 fixes for the newly added gcc warning keys 2012-06-21 03:48:36 +00:00
Marina Kolpakova
e7f6c4b7ef scan operations are moved in separate header 2012-06-20 05:41:16 +00:00
Marina Kolpakova
c17bd8c11b fixed "shadow" warnings in nvidia folder 2012-06-15 13:16:43 +00:00
Marina Kolpakova
9dac223039 fixed part of shadow warnings 2012-06-13 13:12:21 +00:00
Marina Kolpakova
e86f0aaea1 fixed hundreds of "anonymous" warnings for gpu module. 2012-06-08 17:09:38 +00:00
Vadim Pisarevsky
d5a0088bbe merged 2.4 into trunk 2012-04-30 14:33:52 +00:00
Vladislav Vinogradov
917063b7f7 reverted r8003 (CascadeClassifier_GPU) 2012-04-28 08:41:10 +00:00
Vladislav Vinogradov
f65d841d6f fixed several warnings (VS2010, Win64)
added getParams method to VideoWriter_GPU
2012-04-23 14:22:02 +00:00
Vadim Pisarevsky
2fd1e2ea57 merged all the latest changes from 2.4 to trunk 2012-04-13 21:50:59 +00:00
Vladislav Vinogradov
4a41107b01 applied patch #1734 2012-03-31 17:05:33 +00:00
Vladislav Vinogradov
5aae21c037 fixed bug #1640 2012-03-28 14:25:41 +00:00
Vladislav Vinogradov
63b5cf6dea temporary disabled optimized version of CascadeClassifier (bug #1640)
fixed HaarCascadeLoader test (incorrect behavior due to macros usage)
2012-03-05 13:49:42 +00:00
Vladislav Vinogradov
9304d32b82 disabled unnecessary code (it can't be compiled with VS 2008 Ticket #1561) 2012-01-26 12:52:32 +00:00
Vladislav Vinogradov
ddf56fa629 added additional error check 2012-01-25 07:32:35 +00:00
Vladislav Vinogradov
4fee5ef818 fixed build under linux 2011-12-27 10:30:54 +00:00
Vladislav Vinogradov
b398ac7a96 added ImagePyramid class to gpu module 2011-12-27 06:24:31 +00:00
Anton Obukhov
ebc3043c86 [*] Fixed two bugs in reduction functor: out of shared memory bounds access and missing volatile on GF100 and further 2011-11-21 17:46:55 +00:00
Vladislav Vinogradov
d926541311 fixed compilation error 2011-11-14 06:22:42 +00:00
Anton Obukhov
54337fd513 [+] CUDA path for NCVImagePyramid 2011-11-13 20:52:48 +00:00
Anton Obukhov
2cb9192604 [*] Fixed #1464
[~] NCVPyramid uses tr1 and thus can be compiled with CL, commented out on linux
[+] Moved reduction functors to NCVAlg
[*] Warnings in NCV
2011-11-06 09:43:17 +00:00
Anton Obukhov
3396a2ec1a [~] Refactored device reduction for better reuse (now with functor semantics) 2011-11-04 13:49:05 +00:00
Anton Obukhov
56531c6161 [*] Fixed #1461 2011-11-04 12:41:54 +00:00
Anton Obukhov
5afb445283 [+] Pixel types via templates
[+] Color conversions stub via pixel types
[+] Pyramid calculation (required for mipmaps in CUDA 4.1)
[~] Changed C strings to C++ throughout NCV
[~] Fixed a couple of bugs in NCV
2011-10-27 10:13:28 +00:00
Vladislav Vinogradov
b0536279eb added wrappers for BroxOpticalFlow and interpolateFrames 2011-10-17 13:12:39 +00:00
Anatoly Baksheev
ee768d4605 fixed bug in ptr in optflow.cu 2011-10-10 09:37:08 +00:00
Anatoly Baksheev
f444f9b43e optflow gpu compilation fix under vs2010 2011-10-04 17:37:05 +00:00
Anatoly Baksheev
923f771cfc warnings
optical flow gpu cosmetics
2011-10-03 09:26:00 +00:00
Anatoly Baksheev
0fc8fc77c0 eliminated shread_ptr dependency from optical flow gpu. It caused compilation errors. 2011-09-30 11:27:30 +00:00
Anatoly Baksheev
b9ea3ef741 compilation under ubuntu 2011-09-30 09:02:03 +00:00
Anton Obukhov
42c7aece36 [+] Added Brox optical flow (implementation courtesy of Michael Smirnov) 2011-09-29 14:46:39 +00:00
Vladislav Vinogradov
42ced17c2c fixed some warnings under win64 2011-08-08 11:28:14 +00:00
Alexey Spizhevoy
5d703abdc2 fix for GPU module compile time (VS2010) error (from 2.3 branch) 2011-06-30 14:47:20 +00:00
Alexander Shishkov
f010539aaf Fixed MacOS GPU Compilation for i386 2011-06-16 15:02:58 +00:00
Anton Obukhov
c6a7432e92 [*] Approach to the bug with integral image calculation on SM_2.0 (Fermi) 2011-06-14 17:34:00 +00:00
Alexey Spizhevoy
7d350280c0 compilation under mac 2011-05-18 13:02:27 +00:00
Anton Obukhov
b28c33f5dc [~] Added nppStSetActiveCUDAstream and nppStGetActiveCUDAstream to the export table 2011-04-25 15:35:33 +00:00
Alexey Spizhevoy
c9894f9655 fixed compile-time bug under Ubuntu 2011-04-25 08:38:54 +00:00
Anton Obukhov
0c325cace3 [~] Minor refactoring, clean-up
[+] Added 128-bit transpose
2011-04-24 21:39:08 +00:00
Anton Obukhov
58476b64a6 [*] Fixed #974 ("GPU CascadeClassifier fails with some training files"): Moved IsNodeLeaf bit from NodeDescriptor to FeatureDescriptor for both left and right nodes, therefore from now on max number of rects in a feature is 31 2011-04-04 11:47:21 +00:00
Anatoly Baksheev
047c7e0fd6 *applied patch from NVidia (nppstTraspose bug)
*fixed some warnings
*finished gpu test port to gtest framework
2011-02-18 12:23:18 +00:00
Anatoly Baksheev
6b34532901 minor + warnings 2011-02-15 15:09:54 +00:00