Motion and Structure From Two Perspective Views: Algorithms, Error Analysis, and Error Estimation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Matching Two Perspective Views
IEEE Transactions on Pattern Analysis and Machine Intelligence
Matching Point Features with Ordered Geometric, Rigidity, and Disparity Constraints
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.15 |
We present a novel approach for finding corresponding points between two line drawings extracted from perspective views of a moving object whose surface is composed of planar polygons. In our approach, each circuit of the drawings is encoded with a boundary shape code which we call the RLCC code (run length code of convex and concave strings), then a clustering technique is used to obtain the matching result recursively. A series of measures are taken to make the algorithm tolerate considerable dissimilarities which may exist between the two drawings, such as missing lines, scale differences, rotation, perspective shape distortions, etc. Experimental results are presented.