ML Anthology

On a Spectral Attentional Mechanism

Philippe Burlina, Bruce Lin, Rama Chellappa
CVPR 1996 pp. 120-127
doi:10.1109/CVPR.1996.517063 /cvpr/1996/burlina1996cvpr-spectral/

Abstract

This paper describes an attentional mechanism based on the interpretation of spectral signatures for detecting regular object configurations in areas of an image delineated using context information. The proposed global operator relies on the spectral analyse's of edge structure and exploits spatial as well as frequency domain constraints derived from known geometrical models of monitored objects. A decision theoretic method for learning decision regions is presented. Applications of this mechanism are demonstrated for several aerial image interpretation tasks. Specific examples are described for detecting vehicle formations (such as convoys), qualifying the geometry of detected formations, or monitoring the occupancy of regions of interest (such as parking areas, roads, or open areas). Experiments and sensitivity analysis results are reported.

CVPR Semantic Scholar

Cite

Text

Burlina et al. "On a Spectral Attentional Mechanism." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996. doi:10.1109/CVPR.1996.517063

Markdown

[Burlina et al. "On a Spectral Attentional Mechanism." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996.](https://mlanthology.org/cvpr/1996/burlina1996cvpr-spectral/) doi:10.1109/CVPR.1996.517063

BibTeX

@inproceedings{burlina1996cvpr-spectral,
  title     = {{On a Spectral Attentional Mechanism}},
  author    = {Burlina, Philippe and Lin, Bruce and Chellappa, Rama},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1996},
  pages     = {120-127},
  doi       = {10.1109/CVPR.1996.517063},
  url       = {https://mlanthology.org/cvpr/1996/burlina1996cvpr-spectral/}
}