Foreign-Object Detection in High-Voltage Transmission Line Based on Improved YOLOv8m

TL;DR

This paper presents an improved YOLOv8m model with attention mechanisms and advanced loss functions for more accurate detection of foreign objects on high-voltage transmission lines, enhancing safety inspections.

Contribution

The paper introduces specific modifications to YOLOv8m, including a Global Attention Module, a new feature extraction module, and a Focal-EIoU loss, tailored for foreign object detection on transmission lines.

Findings

Achieved a 2.7% increase in mAP_0.5

Achieved a 4% increase in mAP_0.5:0.95

Achieved a 6% increase in recall

Abstract

The safe operation of high-voltage transmission lines ensures the power grid's security. Various foreign objects attached to the transmission lines, such as balloons, kites and nesting birds, can significantly affect the safe and stable operation of high-voltage transmission lines. With the advancement of computer vision technology, periodic automatic inspection of foreign objects is efficient and necessary. Existing detection methods have low accuracy because foreign objects at-tached to the transmission lines are complex, including occlusions, diverse object types, significant scale variations, and complex backgrounds. In response to the practical needs of the Yunnan Branch of China Southern Power Grid Co., Ltd., this paper proposes an improved YOLOv8m-based model for detecting foreign objects on transmission lines. Experiments are conducted on a dataset collected from Yunnan Power Grid. The proposed model enhances the original YOLOv8m by in-corporating a Global Attention Module (GAM) into the backbone to focus on occluded foreign objects, replacing the SPPF module with the SPPCSPC module to augment the model's multiscale feature extraction capability, and introducing the Focal-EIoU loss function to address the issue of high- and low-quality sample imbalances. These improvements accelerate model convergence and enhance detection accuracy. The experimental results demonstrate that our proposed model achieves a 2.7% increase in mAP_0.5, a 4% increase in mAP_0.5:0.95, and a 6% increase in recall.