ML Anthology

Indexing to 3D Model Aspects Using 2D Contour Features

Jin-Long Chen, George C. Stockman
CVPR 1996 pp. 913-920
doi:10.1109/CVPR.1996.517180 /cvpr/1996/chen1996cvpr-indexing/

Abstract

We present a shape-based method of indexing to model aspects from a single intensity image. Objects are assumed to be rigid. A model aspect is represented by a 2 1/2 D edgemap and the parts of the object silhouette. Part decomposition is derived from a codon representation of the object silhouette. Invariant features extracted from each part are then used to index into a hash table to generate model-aspect hypotheses. Knowledge about parts is incorporated in voting schemes to order hypotheses for efficient verification of candidate models. Verification of model-aspect hypotheses is carried out by an alignment algorithm that is robust to partial occlusion. Results of tests using 658 model aspects from 100 objects demonstrate that accurate recognition can be achieved with very few verification attempts.

CVPR Semantic Scholar

Cite

Text

Chen and Stockman. "Indexing to 3D Model Aspects Using 2D Contour Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996. doi:10.1109/CVPR.1996.517180

Markdown

[Chen and Stockman. "Indexing to 3D Model Aspects Using 2D Contour Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996.](https://mlanthology.org/cvpr/1996/chen1996cvpr-indexing/) doi:10.1109/CVPR.1996.517180

BibTeX

@inproceedings{chen1996cvpr-indexing,
  title     = {{Indexing to 3D Model Aspects Using 2D Contour Features}},
  author    = {Chen, Jin-Long and Stockman, George C.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1996},
  pages     = {913-920},
  doi       = {10.1109/CVPR.1996.517180},
  url       = {https://mlanthology.org/cvpr/1996/chen1996cvpr-indexing/}
}