Research on Defect Recognition Method for Unmanned Aerial Vehicle Inspection Images of Overhead Transmission Lines
Traditional manual defect image interpretation has problems such as low efficiency,excessive reliance on personal experience,and low recognition rate.A deep learning based object detection algorithm is used to simulate and train inspection photos to achieve recognition and positioning of transmission equipment components.The super-resolution algorithm(SRCNN)is used to autonomously identify specific defects,which is of great significance for improving the efficiency of drone inspection data photo processing.
万方数据
维普
