Building Regionally Spatial Appearance Model by Topological Color Histogram

Color histogram is widely used in the appearance modeling. However the lack of spatial information makes the features less distinctive. In this paper, we propose to detect local region relationship based on segmentation in the color space. After efficiently computing the region's spatial information, a novel topological color histograms is used to represent the spatial context. Through the experimental observation, we find the region based spatial appearance model make the object's feature more discriminative.

[1]  Lily Lee,et al.  Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Ehud Rivlin,et al.  Robust Fragments-based Tracking using the Integral Histogram , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[3]  Emilio Maggio,et al.  Multi-part target representation for color tracking , 2005, IEEE International Conference on Image Processing 2005.

[4]  Dorin Comaniciu,et al.  Kernel-Based Object Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Irene Y. H. Gu,et al.  Joint Random Sample Consensus and Multiple Motion Models for Robust Video Tracking , 2009, SCIA.

[6]  David A. Forsyth,et al.  Tracking People by Learning Their Appearance , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Daniel P. Huttenlocher,et al.  Pictorial Structures for Object Recognition , 2004, International Journal of Computer Vision.

[8]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[9]  Christopher Hunt,et al.  Notes on the OpenSURF Library , 2009 .

[10]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[11]  Pierre Vandergheynst,et al.  Cascade of descriptors to detect and track objects across any network of cameras , 2010, Comput. Vis. Image Underst..