In recent years, with the continuous progress of the west to East power transmission project, the scale of the transmission line network in the plateau region continues to expand, but due to the influence of the plateau climate conditions, the difficulty of the inspection of the transmission channel in the plateau region gradually increases. In order to improve the inspection accuracy and efficiency of the plateau transmission channel, the worldview-3 high-resolution satellite image data is used in this paper. The multi-scale segmentation technology and object-oriented classification algorithm are adopted to study and analyze the extraction method of key ground feature information of the transmission channel on the plateau. The result shows that the object-oriented algorithm is applicable to the information extraction of high-resolution image data, and the inspection of transmission channel based on high-resolution satellite image technology is feasible. The accuracy of shed information extraction can reach 95% by multi-scale segmentation technology coupled with object-oriented classification algorithm, which can replace manual interpretation work. The accuracy of road information is relatively low, but it can still replace most of manual interpretation work. Compared with traditional field inspection and manual visual interpretation, multi-scale segmentation technology coupled with object-oriented classification algorithm has the advantages of high boundary precision and high efficiency.