Object tracking with dynamic feature graph

Two major problems for model-based object tracking are: 1) how to represent an object so that it can effectively be discriminated with background and other objects; 2) how to dynamically update the model to accommodate the object appearance and structure changes. Traditional appearance based representations (like color histogram) fails when the object has rich texture. In this paper, we present a novel feature based object representation attributed relational graph (ARG) for reliable object tracking. The object is modeled with invariant features (SIFT) and their relationship is encoded in the form of an ARG that can effectively distinguish itself from background and other objects. We adopt a competitive and efficient dynamic model to adoptively update the object model by adding new stable features as well as deleting inactive features. A relaxation labeling method is used to match the model graph with the observation to gel the best object position. Experiments show that our method can get reliable track even under dramatic appearance changes, occlusions, etc.

[1]  King-Sun Fu,et al.  An Image Understanding System Using Attributed Symbolic Representation and Inexact Graph-Matching , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Cordelia Schmid,et al.  Shape recognition with edge-based features , 2003, BMVC.

[3]  Michael Isard,et al.  Contour Tracking by Stochastic Propagation of Conditional Density , 1996, ECCV.

[4]  Michael Brady,et al.  Saliency, Scale and Image Description , 2001, International Journal of Computer Vision.

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

[6]  R. Collins,et al.  On-line selection of discriminative tracking features , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[7]  Horst Bunke,et al.  Efficient Attributed Graph Matching and Its Application to Image Analysis , 1995, ICIAP.

[8]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  C. Schmid,et al.  Scale-invariant shape features for recognition of object categories , 2004, CVPR 2004.

[10]  Rachid Deriche,et al.  Tracking line segments , 1990, Image Vis. Comput..

[11]  Stefan Schaal,et al.  Graph matching vs mutual information maximization for object detection , 2001, Neural Networks.

[12]  Takahiro Ishikawa,et al.  The template update problem , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Cordelia Schmid,et al.  Affine-invariant local descriptors and neighborhood statistics for texture recognition , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[14]  Hai Tao,et al.  Object Tracking with Bayesian Estimation of Dynamic Layer Representations , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

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

[16]  Martial Hebert,et al.  Shape-based recognition of wiry objects , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..