Background segmentation with feedback: The Pixel-Based Adaptive Segmenter

In this paper we present a novel method for foreground segmentation. Our proposed approach follows a nonparametric background modeling paradigm, thus the background is modeled by a history of recently observed pixel values. The foreground decision depends on a decision threshold. The background update is based on a learning parameter. We extend both of these parameters to dynamic per-pixel state variables and introduce dynamic controllers for each of them. Furthermore, both controllers are steered by an estimate of the background dynamics. In our experiments, the proposed Pixel-Based Adaptive Segmenter (PBAS) outperforms most state-of-the-art methods.

• Type: Journal
• Year: 2012
• Where: CVPR
• Authors: Martin Hofmann 0011, Philipp Tiefenbacher, Gerhard Rigoll
• Keywords: Computer Vision, Cvpr 2012, Decision Threshold, Dynamic Controllers, State Variables