ML Anthology

Background Subtraction Based on Cooccurrence of Image Variations

Makito Seki, Toshikazu Wada, Hideto Fujiwara, Kazuhiko Sumi
CVPR 2003 pp. 65-72
doi:10.1109/CVPR.2003.1211453 /cvpr/2003/seki2003cvpr-background/

Abstract

This paper presents a novel background subtraction method for detecting foreground objects in dynamic scenes involving swaying trees and fluttering flags. Most methods proposed so far adjust the permissible range of the background image variations according to the training samples of background images. Thus, the detection sensitivity decreases at those pixels having wide permissible ranges. If we can narrow the ranges by analyzing input images, the detection sensitivity can be improved. For this narrowing, we employ the property that image variations at neighboring image blocks have strong correlation, also known as "cooccurrence". This approach is essentially different from chronological background image updating or morphological postprocessing. Experimental results for real images demonstrate the effectiveness of our method.

CVPR Semantic Scholar

Cite

Text

Seki et al. "Background Subtraction Based on Cooccurrence of Image Variations." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211453

Markdown

[Seki et al. "Background Subtraction Based on Cooccurrence of Image Variations." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/seki2003cvpr-background/) doi:10.1109/CVPR.2003.1211453

BibTeX

@inproceedings{seki2003cvpr-background,
  title     = {{Background Subtraction Based on Cooccurrence of Image Variations}},
  author    = {Seki, Makito and Wada, Toshikazu and Fujiwara, Hideto and Sumi, Kazuhiko},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {65-72},
  doi       = {10.1109/CVPR.2003.1211453},
  url       = {https://mlanthology.org/cvpr/2003/seki2003cvpr-background/}
}