期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2018
卷号：170
期号：4
页码：042139
DOI：10.1088/1755-1315/170/4/042139
语种：English
出版社：IOP Publishing
摘要：Aiming at the problem in accident vehicle tracking system and the flaws of low detection precision and slow speed in the traditional algorithm designed a vehicle that based on hybrid intelligent algorithm. First getting moving objects by using frame differential method and picking up accurate target image by using differential background image, then abstracting the light stream of the target and marking object the area of interested to overcome the problem of empty, duplicate detection and illumination influence, reduce the time complexity to improve the reliability of target tracking and reduce the test time. According to the result of the experiment, compared with the traditional algorithms, the system can quickly and accurately track the vehicle, with strong validity and practicality.
