A Real-time Monitoring Method for Power Transmission Corridor Integrated with Laser Point Clouds
Junjie Huang, Li Huang · 2024
Ensuring the reliable operation of overhead transmission lines is paramount, and video surveillance of transmission line corridors is a key strategy. Traditional image processing methods are commonly used to gauge distances between transmission lines and surrounding objects in surveillance imagery. In this paper, a monocular image ranging method integrated with laser point cloud is proposed for the problem of lack of depth information in monocular video images. The method employs an intelligent algorithm to extract the edge information of the potential hazards, and obtains the localization points for distance evaluation. The correlation between two-dimensional (2D) image space and three-dimensional (3D) corridor space was mapped through the features matching relationship between the 3D laser point cloud and the monocular image, which enables the measurement of the distance between transmission lines and hazardous target. Field tests have demonstrated that the measurement results base on the method are highly accurate, with an error of less than 5%, which meets the requirements of on-site transmission corridor monitoring. Furthermore, this method can be deployed on monitoring terminals with edge computing capabilities.