Title :
Background segmentation with feedback: The Pixel-Based Adaptive Segmenter
Author :
Hofmann, Martin ; Tiefenbacher, Philipp ; Rigoll, Gerhard
Author_Institution :
Inst. for Human-Machine Commun., Tech. Univ. Munchen, Munich, Germany
Abstract :
In this paper we present a novel method for foreground segmentation. Our proposed approach follows a non-parametric 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.
Keywords :
adaptive control; control engineering computing; feedback; image segmentation; learning (artificial intelligence); PBAS; background dynamics estimation; background segmentation; background update; dynamic controllers; dynamic per-pixel state variables; feedback; foreground decision threshold; foreground segmentation; learning parameter; nonparametric background modeling paradigm; pixel values; pixel-based adaptive segmenter; Adaptation models; Arrays; Databases; History; Image segmentation; Jitter; Performance evaluation;
Conference_Titel :
Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4673-1611-8
Electronic_ISBN :
2160-7508
DOI :
10.1109/CVPRW.2012.6238925