Author(s): Shuxia Li; Lukai Xu; Baosen Zhang
Linked Author(s):
Keywords: No Keywords
Abstract: In recent years, Melting ice flood situation of the Yellow River were grim under the influence of extreme weather. Therefor the ice flood prevention work become very important. Flood control departments could obtain real-time video stream about the Yellow River ice through remote video surveillance system. And on this basis, the use of Target tracking technology and subsequent Video measurement technology can get the parameter of ice velocity which is needed by ice flood hazard prediction model of early warning. However, this paper found that there will be the phenomenon of false targets& loss targets in the practical application by using traditional methods of target detection and tracking. Also it will directly impacts on the calculation precision of Ice velocity. The reasons for this problem is the characteristics of the Yellow River ice images as well as the problems of lost frames in the process of the remote wireless video streaming transmission. The article considers that introduced the pyramid structure of L-K optical flow method which is based on strong angular point feature point set can solve this problem. In this article, through experiment further verifies the effectiveness and robustness of the algorithm.
Year: 2014