Accurate power line extraction method under complex background

Abstract

The invention relates to the transmission line system fault diagnosis technology and particularly relates to an accurate power line extraction method under the complex background. The method comprisessteps that firstly, a Ratio operator is utilized to realize detection of the power line edge, under the premise of guaranteeing continuity of power lines, less noise is introduced, a reference rangeof the line characteristic detection threshold lth is provided, and four-link clustering analysis is performed on the edge detection result to eliminate the introduced background noise; secondly, Hough transform is utilized to realize initial extraction of the power lines, although the background noise is largely eliminated, problems of fracture and overlapping of the extracted power lines are caused by the rough edge of the power lines; and lastly, a linear grouping algorithm is finally designed to connect the broken power lines and eliminate overlapped parts to acquire the final power line extraction result. The method is advantaged in that the reference range of the line characteristic detection threshold lth of the Ratio algorithm is provided, not only can continuity and completeness of the power lines be guaranteed, but also plenty of background noise can be eliminated.

Description

technical field [0001] The invention belongs to the technical field of transmission line system fault diagnosis, and in particular relates to a method for accurately extracting power lines under complex backgrounds. Background technique [0002] Transmission lines have the characteristics of wide coverage, long transmission distance, and high reliability requirements, and are an important part of the power system. Power lines are often located in a complex external environment, and vegetation and buildings of different heights distributed on the ground pose potential threats to them. If these objects are too close to the high-voltage transmission line, it may cause accidents such as line tripping. Therefore, the inspection of the transmission line channel environment is very important. [0003] With the rapid development of small unmanned aerial vehicles and high-resolution visible light cameras, it has become a new research idea to realize the environmental inspection of ...

AI Technical Summary

Problems solved by technology

Because the anti-noise performance of the Canny edge detection algorithm is weak, it cannot effectively detect the edge of the power line in the complex background, so it is impossible to use the Hough transform to accurately extract and fit the power line; in recent years, more researchers use Ratio edge with better anti-noise performance The detection algorithm is used to realize the detection of the edge of the power line under the background of complex ground objects, but it is unable to accurately define the line feature detection threshold l th , there are some missed detections and false detections in power line extraction; PCNN (PCNN-Pulse Coupled Neural Network) is used to filter out background noise and combined with Hough transform to extract power lines. Although the accuracy of power line extraction is better, its calculation The speed is slow; in the field of straight line extraction, the classic LSD (Line Segment Detector) algorithm has been widely used, but in complex backgrounds, it is seriously interfered by linear structures such as branches and trunks

Images