Three-dimensional object recognition
ACM Computing Surveys (CSUR) - Annals of discrete mathematics, 24
Regularization of inverse visual problems involving discontinuities
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Scaling Theorems for Zero Crossings
IEEE Transactions on Pattern Analysis and Machine Intelligence
Scale-Based Description and Recognition of Planar Curves and Two-Dimensional Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Using Polygons to Recognize and Locate Partially Occluded Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
Least-Squares Fitting of Two 3-D Point Sets
IEEE Transactions on Pattern Analysis and Machine Intelligence
New forms of shape invariants from elliptic Fourier descriptors
Pattern Recognition
International Journal of Robotics Research
A 3-D Contour Segmentation Scheme Based on Curvature and Torsion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Optimal Estimation of Contour Properties by Cross-Validated Regularization
IEEE Transactions on Pattern Analysis and Machine Intelligence
3-D Moment Forms: Their Construction and Application to Object Identification and Positioning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer Vision
Hi-index | 0.00 |
Space curves are highly descriptive features for 3-D objects. Two invariant representations for space curves are discussed in this paper. One represents space curves by complex waveforms. The other represents space curves using the 3-D moment invariants of the data points on the curves. Space curve matching using invariant global features is discussed. An algorithm for matching partially occluded 3-D curves is also presented, in which rigidity constraints on pairwise curve segments are used to determine the globally consistent matching. An association graph can be constructed from the local matches. The maximal cliques of the graph will determine the visible part of the model curves in the scene. Experimental results using 3-D curves obtained from stereo matching and edges detected from the range data are also presented.