Active 3D Object Recognition Using 3D Affine Invariants
Abstract
We evaluate the power of 3D affine invariants in an object recognition scheme. These invariants are actively estimated by Kalman filtering the data obtained from real-time tracking of image features through a sequence of images. Object information is stored and retrieved in a hash table using the invariants as stable indices. Recognition takes place when significant evidence for a particular shape has been found from the table. Results with real data are presented, and the noise problems arising due to the weak perspective approximation and corner localisation errors are discussed. Preliminary results for extending this method to multiple object recognition in cluttered scenes are also presented.
Cite
Text
Vinther and Cipolla. "Active 3D Object Recognition Using 3D Affine Invariants." European Conference on Computer Vision, 1994. doi:10.1007/BFB0028331Markdown
[Vinther and Cipolla. "Active 3D Object Recognition Using 3D Affine Invariants." European Conference on Computer Vision, 1994.](https://mlanthology.org/eccv/1994/vinther1994eccv-active/) doi:10.1007/BFB0028331BibTeX
@inproceedings{vinther1994eccv-active,
title = {{Active 3D Object Recognition Using 3D Affine Invariants}},
author = {Vinther, Sven and Cipolla, Roberto},
booktitle = {European Conference on Computer Vision},
year = {1994},
pages = {15-24},
doi = {10.1007/BFB0028331},
url = {https://mlanthology.org/eccv/1994/vinther1994eccv-active/}
}