Navigation Using Affine Structure from Motion
Abstract
A structure from motion algorithm is described which recovers structure and camera position, modulo a projective ambiguity. Camera calibration is not required, and camera parameters such as focal length can be altered freely during motion. Unlike recent schemes which compute projective or affine structure using a batch process, the structure is updated sequentially over an image sequence. A specialisation of the algorithm to recover structure modulo an affine transformation is described. We demonstrate how the affine coordinate frame can be periodically updated to prevent drift over time. Structure is recovered from image corners detected and matched automatically and reliably in image sequences. Results are shown for reference objects and indoor environments. Finally, the affine structure is used to construct free space maps enabling navigation through unstructured environments and avoidance of obstacles. The path planning involves only affine constructions. Examples are provided for real image sequences.
Cite
Text
Beardsley et al. "Navigation Using Affine Structure from Motion." European Conference on Computer Vision, 1994. doi:10.1007/BFB0028337Markdown
[Beardsley et al. "Navigation Using Affine Structure from Motion." European Conference on Computer Vision, 1994.](https://mlanthology.org/eccv/1994/beardsley1994eccv-navigation/) doi:10.1007/BFB0028337BibTeX
@inproceedings{beardsley1994eccv-navigation,
title = {{Navigation Using Affine Structure from Motion}},
author = {Beardsley, Paul A. and Zisserman, Andrew and Murray, David William},
booktitle = {European Conference on Computer Vision},
year = {1994},
pages = {85-96},
doi = {10.1007/BFB0028337},
url = {https://mlanthology.org/eccv/1994/beardsley1994eccv-navigation/}
}