Self-detection of optical contamination or occlusion in vehicle vision systems

被引:6
作者
Zhang, Yi [1 ]
Yang, Jie [1 ]
Liu, Kun [1 ]
Zhang, Xiang [1 ]
机构
[1] Shanghai Jiao Tong Univ, Inst Image Proc & Pattern Recognit, Shanghai 200240, Peoples R China
关键词
lens contamination detection; lens occlusion detection; cumulative difference; blured edge detection;
D O I
10.1117/1.2947578
中图分类号
O43 [光学];
学科分类号
070207 ; 0803 ;
摘要
We present a novel and practical algorithm for the self-detection problem of contamination or occlusions on the lens of a camera mounted on a vehicle. First, we analyze the intrinsic characteristics of such contamination on the video image. Based on this, cumulative differences are used to segment the static region in the image. A blurred edge detection algorithm based on wavelet decomposition is introduced to confirm if the static region belongs to contamination or an occlusion. Through the combination of these algorithms, contamination or occlusions can be detected. Experimental data are analyzed to show the detection performance of our algorithm and the effect of different contamination or occlusion material. (C) 2008 Society of Photo-Optical Instrumentation Engineers.
引用
收藏
页数:6
相关论文
共 8 条
[1]  
Collins R., 2000, VSAM FINAL REP, V5, P1
[2]   A new wavelet-based measure of image focus [J].
Kautsky, J ;
Flusser, J ;
Zitová, B ;
Simberová, S .
PATTERN RECOGNITION LETTERS, 2002, 23 (14) :1785-1794
[3]   Moving target classification and tracking from real-time video [J].
Lipton, AJ ;
Fujiyoshi, H ;
Patil, RS .
FOURTH IEEE WORKSHOP ON APPLICATIONS OF COMPUTER VISION - WACV'98, PROCEEDINGS, 1998, :8-14
[4]  
MARICHAL X, P IEEE ICIP99, P386
[5]  
ROBINS MN, 2005, Patent No. 6940554
[6]  
TANG YY, 1999, 2 INT C MULT INT, pV7
[7]   Blur detection for digital images using wavelet transform [J].
Tong, HH ;
Li, MJ ;
Zhang, HJ ;
Zhang, CS .
2004 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXP (ICME), VOLS 1-3, 2004, :17-20
[8]  
WRIGHT DB, ENCY STAT BEHAV SCI, V4, P1718