Motion_Video_Segmentation
所属分类：模式识别(视觉/语音等)
开发工具：C
文件大小：110045KB
下载次数：0
上传日期：2015-02-14 16:08:35
上 传 者：
sh-1993
说明： 基于运动的自我中心视频分割。
(Segmentation based on motion for egocentric videos.)
文件列表:
GCMex (0, 2015-02-15)
GCMex\GCMex.cpp (5275, 2015-02-15)
GCMex\GCMex.m (1942, 2015-02-15)
GCMex\GCMex.mexa64 (169414, 2015-02-15)
GCMex\GCMex.mexglx (141594, 2015-02-15)
GCMex\GCMex.mexmaci (64024, 2015-02-15)
GCMex\GCMex.mexmaci64 (70040, 2015-02-15)
GCMex\GCMex.mexw32 (51712, 2015-02-15)
GCMex\GCMex.mexw64 (44544, 2015-02-15)
GCMex\GCMex_compile.m (309, 2015-02-15)
GCMex\GCMex_test.m (861, 2015-02-15)
GCMex\GCoptimization.cpp (23641, 2015-02-15)
GCMex\GCoptimization.h (24747, 2015-02-15)
GCMex\LICENSE.TXT (18009, 2015-02-15)
GCMex\LinkedBlockList.cpp (1386, 2015-02-15)
GCMex\LinkedBlockList.h (1715, 2015-02-15)
GCMex\block.h (7909, 2015-02-15)
GCMex\energy.h (8773, 2015-02-15)
GCMex\example.cpp (13262, 2015-02-15)
GCMex\graph.cpp (2197, 2015-02-15)
GCMex\graph.h (5616, 2015-02-15)
GCMex\maxflow.cpp (10773, 2015-02-15)
K_Means (0, 2015-02-15)
K_Means\data.mat (31215, 2015-02-15)
K_Means\license.txt (1312, 2015-02-15)
K_Means\litekmeans.m (645, 2015-02-15)
K_Means\spread.m (879, 2015-02-15)
LICENSE.txt (18026, 2015-02-15)
MeanShift (0, 2015-02-15)
MeanShift\MeanShiftCluster.m (5691, 2015-02-15)
MeanShift\testMeanShift.m (958, 2015-02-15)
OpticalFlow (0, 2015-02-15)
OpticalFlow\car1.jpg (132186, 2015-02-15)
OpticalFlow\car2.jpg (128038, 2015-02-15)
OpticalFlow\computeColor.m (3142, 2015-02-15)
... ...
Using the Caltech 101 splits provided on the web and an SVM Classifier you should have the following results:
Shape 180 Shape180 Shape360 Shape360
(whole image) (roi) (whole image) (roi)
l=0 13.20 14.70 16.20 17.57
l=1 33.07 38.56 36.14 44.37
l=2 46.99 58.76 47.25 61.69
l=3 48.43 61.04 49.28 61.63
merge
(exhaustive
search) 51.76 ***.31 54.33 66.27
merge
(varma
method) 49.21 60.19 50.00 61.04
NOTE: SVM 1-vs-all has been used to learn the level weights when merging all the pyramid levels.
------------------------------------------------
Using the Caltech 256 splits provided on the web and an SVM Classifier you should have the following results:
Shape 180 Shape180 Shape360 Shape360
(whole image) (roi) (whole image) (roi)
merge
(exhaustive
search) 16.81 24.28 19.31 27.17
NOTE: again, SVM 1-vs-all has been used to learn the level weights when merging all the pyramid levels.
近期下载者：
相关文件：
收藏者：