Improved YOLOv7x-Based Defect Detection Algorithm for Power Equipment

TL;DR

This paper presents an improved YOLOv7x-based algorithm for power equipment defect detection, incorporating advanced attention mechanisms and a new loss function to significantly enhance detection accuracy and robustness.

Contribution

The paper introduces novel attention modules and a modified loss function into YOLOv7x, improving defect detection performance for power equipment.

Findings

Detection accuracy achieved 93.5% mAP@0.5

Precision reached 97.1%

Recall was 97%

Abstract

The normal operation of power equipment plays a critical role in the power system, making anomaly detection for power equipment highly significant. This paper proposes an improved YOLOv7x-based anomaly detection algorithm for power equipment. First, the ACmix convolutional mixed attention mechanism module is introduced to effectively suppress background noise and irrelevant features, thereby enhancing the network's feature extraction capability. Second, the Biformer attention mechanism is added to the network to strengthen the focus on key features, improving the network's ability to flexibly recognize feature images. Finally, to more comprehensively evaluate the relationship between predicted and ground truth bounding boxes, the original loss function is replaced with the MPDIoU function, addressing the issue of mismatched predicted bounding boxes. The improved algorithm enhances detection accuracy, achieving a mAP@0.5/% of 93.5% for all target categories, a precision of 97.1%, and a recall of 97%.