Hierarchical feature grouping for multiple object segmentation and tracking

ABSTRACT

In this paper, we propose a hierarchical feature grouping method for multiple object segmentation and tracking. The proposed method aims to segment and track objects in the object-level without prior knowledge about the scene and object. We firstly group the motion feature into region-level with the proposed region features which represent a homogeneous region in an object. Object-level groups are achieved by clustering the region-level groups based on foreground information and motion similarity. To find optimal object-level groups, we formulate energy minimization problem, design its objective functions and solve it using simulated annealing(SA). By this hiearchical feature grouping, the proposed method efficiently segments and tracks various kinds of objects without object detector, 3D model and geometry information. Experimental results on several video clips show that our approach robustly segments and tracks multiple object regardness of camera position and object-class.

References

1. M. Breitenstein, F. Reichlin, B. Leibe, E. Koller-Meier, and L. Van Gool. Robust tracking-by-detection using a detector confidence particle filter. In Computer Vision, 2009 IEEE 12th International Conference on, pages 1515--1522, 29 2009-oct. 2 2009.
2. N. Kanhere, S. Pundlik, and S. Birchfield. Vehicle segmentation and tracking from a low-angle off-axis camera. In Computer Vision and Pattern Recognition, 2005. IEEE Computer Society Conference on, volume 2, pages 1152--1157 vol. 2, june 2005.
3. Z. Kim. Real time object tracking based on dynamic feature grouping with background subtraction. In Computer Vision and Pattern Recognition, 2008. IEEE Conference on, pages 1--8, june 2008.
4. S. Kirkpatrick, C. D. Gelatt, and M. P. Vecchi. Optimization by simulated annealing. Science, 220(4598): 671--680, 1983.
5. J. Matas, O. Chum, M. Urban, and T. Pajdla. Robust wide-baseline stereo from maximally stable extremal regions. Image and Vision Computing, 22(10): 761--767, 2004.
6. D. Nister and H. Stewenius. Linear time maximally stable extremal regions. In Computer Vision ECCV 2008, volume 5303, pages 183--196, 2008.
7. J. Shewchuk. Triangle: Engineering a 2d quality mesh generator and delaunay triangulator. In M. Lin and D. Manocha, editors, Applied Computational Geometry Towards Geometric Engineering, volume 1148 of Lecture Notes in Computer Science, pages 203--222. Springer Berlin / Heidelberg, 1996.
8. J. Shi and J. Malik. Normalized cuts and image segmentation. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 22(8): 888--905, aug 2000.
9. J. Shi and C. Tomasi. Good features to track. In Computer Vision and Pattern Recognition, 1994. IEEE Computer Society Conference on, pages 593--600, jun 1994.
10. X. Song and R. Nevatia. Detection and tracking of moving vehicles in crowded scenes. In Motion and Video Computing, 2007. WMVC '07. IEEE Workshop on, page 4, feb. 2007.
11. C. Stauffer and W. Grimson. Adaptive background mixture models for real-time tracking. In Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., volume 2, pages 2 vol. (xxiii+637+663), 1999.
12. B. Yang and R. Nevatia. An online learned crf model for multi-target tracking. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pages 2034--2041, june 2012.
13. J. Yang, Y. Wang, G. Ye, A. Sowmya, B. Zhang, and J. Xu. Feature clustering for vehicle detection and tracking in road traffic surveillance. In Image Processing (ICIP), 2009 16th IEEE International Conference on, pages 1145--1148, nov. 2009.
14. J. Yu, D. Farin, and H. Loos. Multi-cue based visual tracking in clutter scenes with occlusions. In Advanced Video and Signal Based Surveillance, 2009. Sixth IEEE International Conference on, pages 158--163, sept. 2009.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Computer vision

      • Computer vision problems

      • Computer vision tasks

        • Scene understanding