Depth-Adaptive Motion Detection in Dark Scenes

摘要：

Motion detection approaches can detect the foreground and object from the video sequence for many computer vision applications, including traffic security, human-machine interaction, object recognition, and so on. In general, many motion detection approaches cannot detect moving objects in dark scenes due to the insufficient illumination. This paper proposes a depth-adaptive motion detection approach to detect moving objects in dark scenes. Based on the use of depth information, the binary mask of moving objects can be generated by the proposed method. Experimental results demonstrate the effectiveness of the proposed approach in providing a promising detection outcome and low computational cost.

关键词： Video surveillance motion detection background subtraction depth generation

作者: Hao-Chan Ting Yen-Hsiang Chen Fan-Chieh Cheng Shanq-Jang Ruan

作者单位: Department of Electronic Engineering National Taiwan University of Science and Technology Taipei 106, Taiwan

会议类型: 国际会议

会议名称: The 13th IEEE Joint International Computer Science and Information Technology Conference(2011年第13届IEEE联合国际计算机科学与信息技术会议 JICSIT 2011)

会议地点: 重庆

会议语种:英文

页码: 1863-1865

在线出版日期: 2011-08-20（万方平台首次上网日期，不代表论文的发表时间）