Moving Object Extraction in Video Sequences with Low Illumination Condition
Imaging under low illumination exists outstanding problems, so moving objects detecting and extracting in video sequences with low illumination becomes a rather difficult study subject. This paper describes a method of moving objects extraction in video sequences with low illumination condition. This method integrates image gradient information with motion information. Basing on two consecutive frames, we construct an extracting function to extract moving regions. The value of the function stresses the small gray level difference between two frames under low illumination. Comparing to inter-frame subtraction, this method is more effective to extract moving objects with low gray level. At the same time, we use multi-scale morphological gradient operator to detect edge, this operator has a very good effect to the detail of the edge location. The result is superior to the traditional method in edge continuity and isotropy. Past approaches have built detection based on motion information and edge information, but ours is the first to use extracting function and multi-scale morphological gradient operator. The implementation described can operate on lower resolution images under low illumination conditions. Novel contributions of this paper include: 1) the method can operate on lower resolution images under low illumination conditions. 2) Using extracting function and only the first two frames, this detection has small computation, so it is suitable for real-time application. 3) Basing on multi-scale morphological gradient operator, this algorithm is robust to noise, objects shadow and illumination.
moving object detection images egmentation object recognition
Ou Yang
Department of Electronic Engineering, University of Science and Technology of Suzhou, Suzhou ,China NO 1701 Binhe Road, 215011
国际会议
北京
英文
2007-08-05（万方平台首次上网日期，不代表论文的发表时间）