On-line Monitoring Method of Transmission Tower Tilt Based on Remote Sensing Satellite Optical Image and Neural Network

Transmission tower is the infrastructure to ensure the operation of the power grid. For long-term monitoring the tilt of transmission towers, an online monitoring method of tower tilt based on remote sensing satellite optical image and neural network is proposed. Firstly, The K-means clustering algorithm is used to segment shadows of towers, and the Hough line detection algorithm is used to extract the contours of tower shadows. Then, according to the results of image processing and the actual tilt, a data set is made to train the Back Propagation (BP) neural network. Finally, the trained neural network is used to determine the tilt of the image to be discriminated. The neural network is capable of achieving over 90% accuracy with a small training set. The correct rate of the tilt discrimination result of the actual selected sample is 100%, and the discrimination accuracy rate of the simulated sample is 87.5%. Compared with other methods, this method is fast in calculation, low in cost, and has engineering application value.