Motion detection and analysis of matching graphs of intermediate-level primitives

Introduces a new primitive, the half-chunk, for encoding boundary, region, and surface information in graph form. General graph matching is discussed and a specific graph matching system based on half-chunk graphs is presented. Following matching, bindings are interpreted as object component motion or depth. The half-chunk graph allows scale and coordinate system independent object models to be represented. Half-chunk graphs may encode 2-D or 3-D structure equally well.

[1]  Clarence L. Coates,et al.  Visual Learning from Multiple Views , 1975, IEEE Transactions on Computers.

[2]  D Marr,et al.  Cooperative computation of stereo disparity. , 1976, Science.

[3]  Donald B. Gennery,et al.  A Stereo Vision System for an Autonomous Vehicle , 1977, IJCAI.

[4]  Robert T. Chien,et al.  A System for Stereo Computer Vision with Geometric Models , 1977, IJCAI.

[5]  J. Potter.  Scene segmentation using motion information , 1977 .

[6]  H. Baker,et al.  Three-Dimensional Modeling , 2019, IJCAI.

[7]  D. Marr,et al.  Representation and recognition of the spatial organization of three-dimensional shapes , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.