Research on river surface velocimetry monitoring method Based on video surveillance
作者单位：State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University
会议名称：《第35届中国过程控制会议》
会议日期：1000年
学科分类：08[工学] 080203[工学-机械设计及理论] 081501[工学-水文学及水资源] 0815[工学-水利工程] 0802[工学-机械工程]
关 键 词：River Surface Velocity Optical Flow Estimation Adaptive Histogram Equalization Gaussian Mixture Model Pixel-Based Adaptive Segmenter
摘 要：The allocation and utilization of water resources have always been the focus of social development concerns. River flow velocity is the basis for flow rate estimation and is very important hydrological information. The most widely used contact flowmeters require manual wading to place the instrument in water, making them difficult to deploy over large areas. In this paper, an optical flow estimation method of river surface velocity detection based on RAFT is constructed to obtain flow velocity and direction information. To solve the interference problem caused by flying insects and birds, a flow velocity and direction outlier identification method based on Gaussian Mixture Model is investigated. Results demonstrate that the method can effectively and accurately realize real-time monitoring of river surface velocity, providing important information for water allocation, flood prevention and control.