Motion analysis by translational decomposition

Abstract The Local Translational Decomposition (LTD) is a low-level description of image motion, constructed by applying procedures for processing translational motion to small image areas. This yields a 3D vector for local areas which approximates the direction of motion of the corresponding area in the environment. The LTD profoundly simplifies processing for motion constrained to an unknown plane, and simplifies the rigidity constraint to a quadratic equation with a single unknown.

[1]  J. Gibson.  The perception of the visual world , 1951 .

[2]  David J. Fleet,et al.  Performance of optical flow techniques , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Daryl T. Lawton,et al.  Processing translational motion sequences , 1983, Comput. Vis. Graph. Image Process..

[4]  Daryl T. Lawton,et al.  Constraint-Based Inference from Image Motion , 1980, AAAI.

[5]  Daryl T. Lawton,et al.  Interactive Model-Based Vehicle Tracking , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Ramesh C. Jain,et al.  Direct Computation of the Focus of Expansion , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  W. Burger,et al.  On computing a 'fuzzy' focus of expansion for autonomous navigation , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Gilad Adiv,et al.  Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.