Insulator image detection method based on unmanned aerial vehicle inspection

Abstract

The invention relates to the technical field of image recognition and detection applied to insulators, and provides an insulator image detection method based on unmanned aerial vehicle inspection, which comprises the following steps: 1, acquiring an aerial image set during cruising through shooting equipment carried by an unmanned aerial vehicle; 2, classifying the aerial image set by adopting a manual labeling mode and forming a plurality of related task packets; 3, amplifying a plurality of related task packets in a data amplification mode, and performing parallel learning training on the insulator detection model by utilizing the amplified data packets; 4, in multi-task learning training, introducing a training evaluation formula; if a result value generated by calculation of the training evaluation formula is greater than a set threshold value, immediately stopping continuing to learn the auxiliary task; and 5, verifying the effectiveness of insulator detection through quantitativeanalysis and comparison of experiment results; and the detection performance and the accuracy are improved.

Description

technical field [0001] The invention relates to the technical field of image recognition and detection applied to insulators, and more specifically to an insulator image detection method based on drone inspection. Background technique [0002] In the transmission line inspection, fault detection and troubleshooting of insulators by identifying aerial images taken by drones plays an important role in maintaining the safe and stable operation of the transmission system. With the help of drones, the detection of insulators can be achieved based on image recognition algorithms. Traditional image recognition algorithms, such as the insulator detection method based on skeleton feature extraction, the insulator detection method based on insulator string feature extraction, and the insulator detection based on image threshold segmentation, etc., these insulator detection algorithms are easily affected by the environmental background. The stickiness is poor, and it is prone to false...

AI Technical Summary

Problems solved by technology

However, FCN will reduce the resolution of the feature map when sampling multiple times, and then lose detailed information such as the target position. Therefore, it is difficult for FCN to accurately locate the insulator image with complex background characteristics, resulting in the final detection result. have lower accuracy

[0006] In addition, existing methods only regard insulator detection as a segmentation task or a bounding box detection task, ignoring the interconnection between the two, which also limits the detection performance of the model

Images