Moving Object Refining in Traffic Monitoring Applications

CASIA OpenIR > 中科院工业视觉智能装备工程实验室 > 先进制造与自动化

	Moving Object Refining in Traffic Monitoring Applications
	Kunfeng Wang; Qingming Yao; Xin Qiao; Shuming Tang; Fei-Yue Wang
	2007-09-01
会议名称	The Proceedings of the 10th IEEE International Conference on Intelligent Transportation Systems
会议录名称	Intelligent Transportation Systems Conference
会议日期	30 Sept.-3 Oct. 2007
会议地点	Seattle, WA, USA
摘要	Moving object segmentation is an important task in vision-based traﬃc monitoring applications. In traﬃc scenes, various outliers such as sudden illumination changes, moving cast shadows, camera jitter, etc., often cause serious errors in image analysis due to misclassiﬁcation of moving objects. An eﬃcient moving object reﬁning approach is thus expected. In this paper, we address the problem of moving object reﬁning by processing the background subtraction results. In an analytical multi-stage procedure, we remove sudden illumination changesandlocalreﬂectedregionsemployingphotometriccolor invariants, remove moving cast shadows based on a single Gaussian shadow model, uniform-region classiﬁcation, and spatial analysis, and further remove other types of outliers in a postprocessing stage of area ﬁltering and area-to-perimeter test. Experimental results on actual video sequences representative of diﬀerent traﬃc scenes and illuminations are presented. The results illustrate that our approach is eﬃcient when handling widely diﬀerent conditions that can occur.
关键词	Gaussian Processes Computerised Monitoring Filtering Theory Image Classification Image Colour Analysis Image Segmentation Image Sequences Lighting Object Detection Photometry
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/41422
专题	中科院工业视觉智能装备工程实验室_先进制造与自动化
通讯作者	Shuming Tang
推荐引用方式 GB/T 7714	Kunfeng Wang,Qingming Yao,Xin Qiao,et al. Moving Object Refining in Traffic Monitoring Applications[C],2007.