论文信息 - Model matching using multiple data sources

Model matching using multiple data sources

We describe an industrial inspection system with multiple data sources for object location and inspection. Within the context of this system, we present an approach for extraction of reliable and full object features consisting of both surfaces and space curves from registered range and intensity data. For matching, a homogeneous representation is adopted, which is applicable to a wide classes of object features. However, initial results are demonstrated on line and plane data only.

[1] Olivier D. Faugeras,et al. Building, Registrating, and Fusing Noisy Visual Maps , 1988, Int. J. Robotics Res..

[2] Joshua Z. Levin. Mathematical models for determining the intersections of quadric surfaces , 1979 .

[3] Andrew M. Wallace,et al. Compilation and sufficient representation of object models for visual recognition , 1992, Pattern Recognit. Lett..

[4] A. H. Etemadi. Robust segmentation of edge data , 1992 .

[5] Andrew M. Wallace,et al. Semantic boundary description from range and intensity images , 1992 .

[6] Andrew M. Wallace,et al. Message based control of parallel high level depth and intensity matching , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[7] D. Hutber. Active stereo vision and its application to industrial inspection , 1991 .

[8] Ramesh C. Jain,et al. Invariant surface characteristics for 3D object recognition in range images , 1985, Comput. Vis. Graph. Image Process..

[9] Andrew M. Wallace,et al. Edge Classification and Depth Reconstruction by Fusion of Range and Intensity Edge Data , 1992, ECCV.

[10] G. T. Reid,et al. Absolute and comparative measurements of three-dimensional shape by phase measuring moiré topography , 1984 .

[11] W. Eric L. Grimson,et al. Localizing Overlapping Parts by Searching the Interpretation Tree , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.