Computer vision target detection algorithm

Abstract

The invention relates to a computer vision target detection algorithm, which is used for detecting a target object in a target image, and comprises the following steps of: S1, performing graying processing on a source image and the target image to generate a gray source image and a gray target image; S2, extracting edge information of the gray source image, and generating an edge source image; s3, extracting edge information of the grayscale target image, and generating an edge target image; s4, suppressing noise of the edge target image, and generating a filtered edge target image; s5, extracting feature points of the edge source image and the filtered edge target image, and matching the feature points to obtain matching points; and S6, eliminating error points in the matching points to obtain accurate matching points and the position of the target object in the target image. According to the method, improvement is made for the problem existing in the feature point matching aspect in the prior art, the recognition accuracy is improved, and the method has high robustness and high operation speed and is suitable for power transmission line U-shaped hanging ring image defect detection.

Description

technical field [0001] The invention relates to the fields of image processing and computer vision, in particular to a computer vision target detection algorithm applied to the field of power system drone inspection operations. Background technique [0002] The U-shaped hanging ring in the transmission line is an important part of the power system. It is used to change the angle and lengthen the tension insulator. It is usually exposed to the complex external environment, and there are many uncertain factors that will damage it. Inspections are essential. The traditional method is manual inspection, but it is greatly affected by random factors such as weather, terrain and man-made, and the cost is high. In recent years, UAV technology has developed rapidly, and UAV inspection operations have become one of the means of power line inspection. [0003] The operation method of the UAV inspection operation is to carry a small high-definition camera on the UAV, fly along the pow...

AI Technical Summary

Problems solved by technology

[0004] At present, the mainstream algorithm of target detection technology adopts SURF algorithm (Speeded-Up Robust Features, accelerated version has robust feature algorithm, an image recognition algorithm), SURF algorithm has the advantages of fast recognition speed and strong real-time performance, but At the same time, there are also the disadvantages of poor recognition effect and low accuracy in the case of a lot of noise, and the power transmission line inspection is performed in an outdoor complex environment, often with weather or natural background interference, resulting in the use of the SURF algorithm due to many error points However, the recognition rate is not high, which cannot meet the needs of drone inspection operations.

Images