Fittings Detection Method Based on Multi-Scale Geometric Transformation and Attention-Masking Mechanism

Abstract

Overhead transmission lines are important lifelines in power systems, and the research and application of their intelligent patrol technology is one of the key technologies for building smart grids. The main reason for the low detection performance of fittings is the wide range of some fittings’ scale and large geometric changes. In this paper, we propose a fittings detection method based on multi-scale geometric transformation and attention-masking mechanism. Firstly, we design a multi-view geometric transformation enhancement strategy, which models geometric transformation as a combination of multiple homomorphic images to obtain image features from multiple views. Then, we introduce an efficient multiscale feature fusion method to improve the detection performance of the model for targets with different scales. Finally, we introduce an attention-masking mechanism to reduce the computational burden of model-learning multiscale features, thereby further improving model performance. In this paper, experiments have been conducted on different datasets, and the experimental results show that the proposed method greatly improves the detection accuracy of transmission line fittings.

Deep Power Vision Technology and Intelligent Vision Sensors

“…This Special Issue aims to provide some up-to-date solutions to the problems of inspection in the power system and offer helpful reference for further research of deep power vision technology and intelligent vision sensors. It includes ten papers covering the tasks of detection for the inspection of transmission lines and substation [ 1 , 2 , 3 , 4 , 5 , 6 , 7 ], classification related to the requirements of inspection [ 8 , 9 ], and image defogging for transmission lines [ 10 ].…”

“…To achieve a better performance in the detection tasks of the transmission line, the following methods were proposed. Wang et al [ 1 ] proposed a fitting detection method based on multi-scale geometric transformation and an attention-masking mechanism, which demonstrated its effectiveness in improving the detection accuracy of transmission line fittings. In order to solve the problem of background interference and overlap caused by the axis-aligned bounding boxes in the tilting insulator detection tasks, Zhao et al [ 2 ] designed a normal orientation detection method incorporating the angle regression and a priori constraints.…”