文件列表:

benchmark_gpu_convolution.m (6148, 2014-01-04)
changelog.txt (1434, 2014-01-04)
example-images\psychological\popout_whiteInBlack.png (9028, 2014-01-04)
example-images\psychological\popout_camouflage.png (34989, 2014-01-04)
example-images\psychological\popout_yellowInBlue.png (9454, 2014-01-04)
example-images\psychological\popout_redInGreen.png (9530, 2014-01-04)
example-images\psychological\orientation_popout.png (13746, 2014-01-04)
example-images\psychological\popout_local.png (15291, 2014-01-04)
example-images\golden_retriever.jpg (33125, 2014-01-04)
example.m (4364, 2014-01-04)
get_additional_files.m (3055, 2014-01-04)
imconvert.m (8482, 2014-01-04)
process_folder.m (4066, 2014-01-04)
qdct_impl\dct_48_64.cpp (11519, 2014-01-04)
qdct_impl\dct_type3_64.cpp (31294, 2014-01-04)
qdct_impl\dct_type2_64.cpp (31445, 2014-01-04)
qdct_impl\hamilton_product.hpp (11227, 2014-01-04)
qdct_impl\dct_type3_48.cpp (19945, 2014-01-04)
qdct_impl\signum.hpp (6700, 2014-01-04)
qdct_impl\build.m (1296, 2014-01-04)
qdct_impl\qdct_saliency_48_64_nofilter.cpp (7345, 2014-01-04)
qdct_impl\hamilton_product.cpp (5250, 2014-01-04)
qdct_impl\dct_48_64.hpp (2946, 2014-01-04)
qdct_impl\dct_type2.hpp (3450, 2014-01-04)
qdct_impl\dct_type2_48.cpp (19866, 2014-01-04)
qdct_impl\signum.cpp (4347, 2014-01-04)
qtfm\@quaternion\iqdct2.m (1824, 2014-01-04)
qtfm\@quaternion\qdct2.m (1901, 2014-01-04)
reshape_spectral_image.m (2947, 2014-01-04)
rgb2icopp.m (2137, 2014-01-04)
rgb2icopp2.m (2117, 2014-01-04)
spectral_dct_saliency.m (2914, 2014-01-04)
spectral_dct_saliency_quaternion.m (3386, 2014-01-04)
spectral_saliency.m (4917, 2014-01-04)
spectral_saliency_multichannel.m (67859, 2014-01-04)
spectral_saliency_quaternion.m (4451, 2014-01-04)
spectral_saliency_quaternion_eigenpqft.m (3341, 2014-01-04)
spectral_saliency_quaternion_eigensr.m (4016, 2014-01-04)
... ...

1. GENERAL Not much to say at the moment. If you are interested in the topic, then please visit my website (http://cvhci.anthropomatik.kit.edu/~bschauer/). If you use any of this work in scientific research or as part of a larger software system, you are kindly requested to cite the use in any related publications or technical documentation. The work is based upon: [1] B. Schauerte, and R. Stiefelhagen, "Quaternion-based Spectral Saliency Detection for Eye Fixation Prediction," in European Conference on Computer Vision (ECCV), 2012 [2] B. Schauerte, and R. Stiefelhagen, "Predicting Human Gaze using Quaternion DCT Image Signature Saliency and Face Detection," in IEEE Workshop on the Applications of Computer Vision (WACV), 2012. 2. INSTALLATION 2.1. QUATERNION METHODS AND THE QTFM If you want to use the Quaternion spectral saliency methods, then you need the "Quaternion Toolbox for Matlab" (QTFM). Most importantly, for the .m-file implementation of the quaternion dct spectral saliency you need to patch the implementation by adding the .m-files in qtfm/@quaternion to the corresponding folder of the QTFM. A patched version of the QTFM that already contains the QDCT/iQDCT routines can be downloaded at: http://cvhci.anthropomatik.kit.edu/~bschauer/code/qdct-qtfm/ You can also use the get_additional_files.m to download the library. 2.2. OPTIMIZED C/C++ IMPLEMENTATION (.MEX) The necessary .mex files for the optimized implementations can be generated by running build.m. However, this should also be done automatically when calling spectral_saliency_multichannel, if needed. 2.3 OPTIMIZED C/C++ IMPLEMENTATION (PRE-COMPILED .MEX BINARIES) If you have trouble compiling, you can download pre-compiled .mex files for some platforms at: http://cvhci.anthropomatik.kit.edu/~bschauer/code/qdct-mex-binaries/ You can also use the get_additional_files.m to download the binaries. 2.4 LOCALLY DEBIASED REGION CONTRAST SALIENCY You can download, compile, and install the C/C++ code for locally debiased region contrast saliency [3]. To this end, simply execute get_additional_files.m, which should download the latest code version from the github repository at: https://github.com/bschauerte/region_contrast_saliency [3] B. Schauerte, R. Stiefelhagen, "How the Distribution of Salient Objects in Images Influences Salient Object Detection". In Proceedings of the 20th International Conference on Image Processing (ICIP), 2013. 3. AUTHORS AND CONTACT INFORMATION Boris Schauerte 4. ACKNOWLEDGEMENTS 4.1 INSTITUTIONS Part of this work was/is supported by the German Research Foundation (DFG) within the Collaborative Research Program SFB 588 "Humanoid Robots" and the Quaero Programme, funded by OSEO, French State agency for innovation. 4.2 PEOPLE Thanks for reporting bugs go to ... Lahouari Ghouti Hadi Hadizadeh

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：