Unusual Motion Detection for Vision-Based Driver Assistance


by L-H Fu, W-D Wu, Y Zhang, R Klette
Abstract:
For a vision-based driver assistance system, unusual motion detection is one of the importantmeans of preventing accidents. In this paper, we propose a real-time unusual-motion-detectionmodel, which contains two stages: salient region detection and unusual motion detection.In the salient-region-detection stage, we present an improved temporal attention model. Inthe unusual-motion-detection stage, three kinds of factors, the speed, the motion direction,and the distance, are extracted for detecting unusual motion. A series of experimental results demonstrates the proposed method and shows the feasibility of the proposed model. Keywords:Vision-based driver assistance, Salient regions, Unusual motion, Video analysis
Reference:
Unusual Motion Detection for Vision-Based Driver Assistance (L-H Fu, W-D Wu, Y Zhang, R Klette), In International Journal of Fuzzy Logic and Intelligent Systems, volume 15, 2015.
Bibtex Entry:
@article{fu2015unusualassistance,
author = "Fu, L-H and Wu, W-D and Zhang, Y and Klette, R",
journal = "International Journal of Fuzzy Logic and Intelligent Systems",
number = "1",
pages = "27--34",
title = "Unusual Motion Detection for Vision-Based Driver Assistance",
volume = "15",
year = "2015",
abstract = "For a vision-based driver assistance system, unusual motion detection is one of the importantmeans of preventing accidents. In this paper, we propose a real-time unusual-motion-detectionmodel, which contains two stages:  salient region detection and unusual motion detection.In the salient-region-detection stage, we present an improved temporal attention model. Inthe unusual-motion-detection stage, three kinds of factors, the speed, the motion direction,and the distance, are extracted for detecting unusual motion. A series of experimental results demonstrates the proposed method and shows the feasibility of the proposed model.

Keywords:Vision-based driver assistance, Salient regions, Unusual motion, Video analysis",
doi = "10.5391/IJFIS.2015.15.1.27",
issn = "1598-2645",
eissn = "2093-744X",
issue = "1",
}