Callaborative Visual Analysis of Complex Motions

Supported in part by NSF IIS-0347877 (CAREER)

It turns out that most vision tasks that are intuitive to humans are extremely difficult for computers. One of them is visual motion analysis, which ranges from motion tracking/capturing to action recognition, from analyzing image pixels and geometric primitives to complex objects and dynamic scenes.

Since the 1970s, great efforts have been made to successfully address low-dimensional motion (or LD-Motion), e.g., 3D planar motion and rigid motion, which then made possible research in the 1990s, such as structure from motion and 3D scene reconstruction. Different from LD-Motion, high-dimensional motion (HD-Motion) or complx motion refers to complex motions with high degrees of freedom, which include:

articulation of linked structures, e.g., the motion of human body and hand;
deformation of elastic contours or surfaces, e.g., the motion of the face and organ contours;
multi-motion of multiple occluding targets, e.g., the motion of multiple moving people or cars.

The studies of complex motions can be tracked back to mid-1980s on deformable contours and multiple motions. There has been an upsurge in non-rigid motion and human motion in recent decades. However, the exploration has been confronted by the curse of dimensionality induced by the complexity in HD-Motion analysis, which plagues the accuracy, efficiency and robustness of existing methods.

The goal of our research to overcome the curse of dimensionality in computer vision by systematically and rigorously pursuing a new collaborative and distributed approach to HD-Motion analysis. In addition, we also study the manifold learning-based approach. Noticing that the collaborative approach is completely different from the centralized and manifold learning-based approach, we investigate the bridge between them..

Research Issues

[1]	Theoretical Foundation of the Collaborative Approach
[2]	Analyzing Articulated Motion
[3]	Decentralized Visual Tracking of Multiple Targets
[4]	Analyzing Deformable Motion

Publication:

Jornal Papers

Gang Hua and Ying Wu, "Variational Maximum a Posteriori by Annealed Mean Field Analysis", IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.27, No.11, pp.1747-1781, Nov., 2005. [PDF]
Gang Hua and Ying Wu, "Sequential Mean Field Variational Analysis of Structured Deformable Shapes", Computer Vision and Image Understanding, Vol.101, No.2., pp.87-99, Feb., 2006. [PDF]
Ying Wu, John Lin and Thomas S. Huang, "Analyzing and Capturing Articulated Hand Motion in Image Sequences", IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.27, No.12, pp.1910-1922, Dec., 2005. [PDF]

Conference Papers

Ming Yang, Ting Yu and Ying Wu, "Game-Theoretic Multiple Target Tracking", in Proc. IEEE Int'l Conf. on Computer Vision (ICCV'07), Rio de Janeiro, Brazil, Oct. 2007 [PDF]
Gang Hua, Ying Wu and Zhimin Fan, "Measurement Integration Under Inconsistency for Robust Tracking", in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR 06), New York City, NY, June 17-22, 2006. [PDF]
Zhimin Fan and Ying Wu, "Multiple Collaborative Kernel Tracking", in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'05), San Diego, CA, June 20-26, 2005. [PDF]
Ting Yu and Ying Wu, "Decentralized Multiple Target Tracking using Netted Collaborative Autonomous Trackers", in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'05), San Diego, CA, June 20-26, 2005. [PDF]
Gang Hua, Ming-Hsuan Yang and Ying Wu, "Learning to Estimate Human Poses with Data Driven Belief Propagation", in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'05), San Diego, CA, June 20-26, 2005. [PDF]
Gang Hua and Ying Wu, "Capturing Human Body Motion from Video for Perceptual Interfaces by Sequential Variational MAP", invited, in Proc.11th Int'l Conf. on Human-Computer Interaction (HCII'05), Las Vegas, Nevada, July 2005. [PDF]
Ting Yu and Ying Wu, "Collaborative Tracking of Multiple Targets", in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'04), vol.I, pp. 834-841, Washington, DC, June, 2004. [PDF]
Gang Hua and Ying Wu, "Multi-scale Visual Tracking by Sequential Belief Propagation", in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'04), vol.I, pp. 826-833, Washington, DC, June, 2004. [PDF]
Gang Hua, Ying Wu and Ting Yu, "Analyzing Structured Deformable Shapes Via Mean Field Monte Carlo", in Proc. IEEE Asia Conference on Computer Vision ( ACCV'2004), Jeju Island, Korea, Jan., 2004. [PDF]
Ying Wu, Gang Hua and Ting Yu, "Tracking Articulated Body by Dynamic Markov Network", in Proc. IEEE Int'l Conf. on Computer Vision (ICCV'03), pp.1094-1101, Nice, France, Oct., 2003. [PDF]

Return to Research