Recognizing Objects in Range Data Using Regional Point Descriptors
Abstract
Recognition of three dimensional (3D) objects in noisy and cluttered scenes is a challenging problem in 3D computer vision. One approach that has been successful in past research is the regional shape descriptor. In this paper, we introduce two new regional shape descriptors: 3D shape contexts and harmonic shape contexts. We evaluate the performance of these descriptors on the task of recognizing vehicles in range scans of scenes using a database of 56 cars. We compare the two novel descriptors to an existing descriptor, the spin image, showing that the shape context based descriptors have a higher recognition rate on noisy scenes and that 3D shape contexts outperform the others on cluttered scenes.
Cite
Text
Frome et al. "Recognizing Objects in Range Data Using Regional Point Descriptors." European Conference on Computer Vision, 2004. doi:10.1007/978-3-540-24672-5_18Markdown
[Frome et al. "Recognizing Objects in Range Data Using Regional Point Descriptors." European Conference on Computer Vision, 2004.](https://mlanthology.org/eccv/2004/frome2004eccv-recognizing/) doi:10.1007/978-3-540-24672-5_18BibTeX
@inproceedings{frome2004eccv-recognizing,
title = {{Recognizing Objects in Range Data Using Regional Point Descriptors}},
author = {Frome, Andrea and Huber, Daniel and Kolluri, Ravi and Bülow, Thomas and Malik, Jitendra},
booktitle = {European Conference on Computer Vision},
year = {2004},
pages = {224-237},
doi = {10.1007/978-3-540-24672-5_18},
url = {https://mlanthology.org/eccv/2004/frome2004eccv-recognizing/}
}