Coarse-to-fine  

Optical Flow Estimation on Coarse-to-Fine Region-Trees using Discrete Optimization

In this paper, we propose a new region-based method for accurate motion estimation using discrete optimization. In particular, the input image is represented as a tree of over-segmented regions and the optical flow is estimated by optimizing an energy function defined on such a region-tree using dynamic programming. To accommodate the sampling-inefficiency problem intrinsic to discrete optimization compared to the continuous optimization based methods, both spatial and solution domain coarse-to-fine (C2F) strategies are used. That is, multiple region-trees are built by using different over-segmentation granularities. Starting from a global displacement label discretization, optical flow estimation on the coarser level region-tree is used for defining region-wise finer displacement samplings for finer level region-trees. Furthermore, cross-checking based occlusion detection and correction and continuous optimization are also used to improve accuracy. Extensive experiments on the Middlebury benchmark datasets have shown that our proposed method can produce top-ranking results.

Reference

C. Lei and Y.H. Yang, "Optical Flow Estimation on Coarse-to-Fine Region-Trees using Discrete Optimization," International Conference on Computer Vision, Kyoto, Japan, September 27-October 2, 2009.

 

   

Estimate Large Motions Using Reliability-based Motion Estimation Algorithm

Detecting and estimating motions of fast moving objects has many important applications. However, most existing motion estimation techniques have difficulties in handling large motions in the scene. In this paper, we extend our recently proposed reliability-based stereo vision technique to solving large motion estimation problem. Compared with our stereo vision approach, the new algorithm removes the constant penalty assumption and explicitly enforces the inter-scanline consistency constraint. The resulting algorithm can handle sequences that contain large motions and can produce optical flows with 100% density over the entire image domain. The experimental results indicate that it can generate more accurate optical flows than existing approaches.

Reference

M. Gong and Y.H. Yang, “Estimate Large Motions Using the Reliability-based Motion Estimation Algorithm,” International Journal of Computer Vision, Vol. 68, No. 3, 2006, pp. 319-330.

 

   

Some early work on motion analysis

M.K. Leung and Y.H. Yang, "First Sight: A human body outline labeling system,'' IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 17, No. 4, 1995, pp. 359-377.

Y.H. Yang and M.D. Levine, “The Background Primal Sketch: An Approach for Tracking Moving Objects,” Machine Vision and Applications, Vol. 5, 1992, pp. 17-34.

W. Long and Y.H. Yang, “Stationary Background Generation: An Alternative to the Difference of Two Images,” Pattern Recognition, Vol. 23, 1990, pp. 1351-1359.

M.K. Leung and Y.H. Yang, “Human Body Motion Segmentation in a Complex Scene,” Pattern Recognition, Vol. 20, No. 1, 1987, pp. 55-64.

M.K. Leung and Y.H. Yang, “A Region-Based Approach for Human Body Motion Analysis,” Pattern Recognition, Vol. 20, No. 3, 1987, pp. 321-339.