In order to further alleviate the tasks of regular inspections and patrols of transmission lines, the article proposes an intelligent drone inspection technology to extract and track aerial images. Firstly, the aerial image is preprocessed by using histogram equalization and image filtering to solve the interference of the aerial image light intensity and background on the extraction of transmission line elements; secondly, the LSD algorithm is used to achieve the extraction of the line edge, and the image background signal is removed. On the basis of the Hough transform mathematical algorithm, the accurate connection of the transmission line is realized; finally, the particle filter and the extended Kalman filter are used to track the aerial video line by the two image tracking methods. To identify them, the detection accuracy of the two methods are 95.34% and 94.72%, respectively, confirming that the article processing algorithm can realize the extraction and tracking of transmission lines.
