Comparison background modeling methods on moving object detection in video sequences for Thailand

• Main Authors: Kitti Puritat, Suepphong Chernbumroong, Pradorn Sureephong
• Format: Journal
• Published: 2018
• Subjects: Agricultural and Biological Sciences
• Online Access: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85020883626&origin=inward; http://cmuir.cmu.ac.th/jspui/handle/6653943832/46872
• Institution: Chiang Mai University

© Research India Publications. The research reported drivers in Thailand spent time on car an average of 61 hours stuck in traffic last year, followed by motorists in Colombia and Indonesia with an average 47 hours and the second in the world (behind Libya) for number of road accident deaths. Thus, manual traffic count is time consuming in order to identify which routes are used most, and to either improve or solve the problem that road or provide an alternative if there is an excessive amount of traffic with vehicle counting systems. For the first step of analysis the road accident in Thailand, real time segmentation algorithms of moving regions in image sequences is an important step in counting systems including automated video surveillance. Background subtraction of video sequences is mainly regards as a solved problem. In this paper not only helps better understand to which type of videos each method suits best for video surveillance of Thailand but also compared of basic background subtraction methods.