Research on Power Line Detection Method from UAV Aerial Images Based on LSD Algorithm
The use of UAV images for power line safety inspection and post-maintenance is the mainstream way of working. The tradi-tional method of using edge detection operator for power line extraction has poor stability in the situation of complex background ob-jects. In order to solve this problem,this paper proposes a power line extraction method based on LSD linear detection algorithm. First of all,the image preprocessing is carried out to eliminate the influence of noise. According to the image characteristics of the power lines,it adjusts the parameters of the LSD algorithm to obtain the straight line segments of the power lines to be determined. Then,the method of statistical slope and intercept and screening is used to eliminate the straight line segments that do not meet the slope and in-tercept thresholds,and further accurately locate the straight line segments of power lines. Finally,the least square method is used to fit the complete straight lines,and the final power line extraction result is obtained. Experimental results show that the power line ex-traction effect of the proposed algorithm is better than that of Canny,Sobel,Prewitt and Roberts operators,which can well suppress the influence of complex background objects on the extraction results,save the cost of power engineering projects to a certain extent,and improve work efficiency.
NETL
NSTL
万方数据
