Abstract Due to the single feature space used in standard mean-shift algorithm, the confusion caused by the similarity object in its vicinity is hard to deal with. A variety of local pixel-level features are summarized, and a method for measuring the discrimination of various features is presented to make feature selection adaptive. Based on the analysis of deriving the weights during the iteration, an improved mean shift algorithm is proposed based on the discrimination measurement of various features through multi-feature space. It monitors the saliency of each feature effectively to compensate each other and improves the robustness to the confusion caused by the outlier. Experimental results indicate the proposed algorithm is real-time and robust and it has good tracking performance on object tracking.
[1] Pavlovie V I, Sharma R, Huang T S. Visual Interpretation of Hand Gestures for Human-Computer Interaction: A Review. IEEE Trans on Pattern Analysis and Machine Intelligence, 1997, 19(7): 677-695 [2] Lien C C, Huang C L. Model-Based Articulated Hand Motion Tracking for Gesture Recognition. Image and Vision Computing, 1998, 16(2): 121-134 [3] Haritaoglu I, Harwood D, Davis L S. W4: Real-Time Surveillance of People and Their Activities. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830 [4] Wren C R, Azarbayejani A, Darrell T, et al. Pfinder: Real-Time Tracking of the Human Body. IEEE Trans on Pattern Analysis and Machine Intelligence, 1997, 19(7): 780-785 [5] Stricker D, Kettenbach T. Real-Time and Markerless Vision-Based Tracking for Outdoor Augmented Reality Application // Proc of the IEEE and ACM International Symposium on Augmented Reality. New York, USA, 2001: 189-190 [6] Wang Liang, Hu Weimin, Tan Tieniu. A Survey of Visual Analysis of Human Motion. Chinese Journal of Computers, 2002, 25(3): 225-237 (in Chinese) (王 亮,胡卫明,谭铁牛.人运动的视觉分析综述.计算机学报, 2002, 25(3): 225-237) [7] Cheng Yizong. Mean Shift, Mode Seeking and Clustering. IEEE Trans on Pattern Analysis and Machine Intelligence, 1995, 17(8): 790-799 [8] Comaniciu D, Ramesh V, Meer P. Real-Time Tracking of Non-Rigid Objects Using Mean Shift // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Hilton Head Island, USA, 2000, Ⅱ: 142-149 [9] Engelson S P, McDermott D V. Image Signatures for Place Recognition and Map Construction. Proc of SPIE, 1992, 1611: 282-293 [10] Ojala T, Pietikainen M, Menp T. Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 24(7): 971-987 [11] Manjunath B S, Ohm J R, Vasudevan W, et al. Color and Texture Descriptors. IEEE Trans on Circuit and Systems for Video Technology, 2001, 11(6): 703-715 [12]Huang Chaobing, Yu Shengsheng, Zhou Jingli, et al. Combining Neighbor Fuzzy Entropy, Gradient Unit Feature with Color-Spatial Feature for Image Retrieval // Proc of the International Conference on Machine Learning and Cybernetics. Shanghai, China, 2004, 7(7): 4319-4324 [13] Pass G, Zabih R. Comparing Image Using Joint Histograms. Multimedia Systems, 1999, 7(3): 234-240
2009, Vol. 22 
