Attention-Guided Autoencoder Fusion for Insulator Defect Detection Using UAV Transmission-Line Imaging

基于注意力引导自编码器融合的无人机输电线路绝缘子缺陷检测

Abstract: Automated defect detection in high-voltage transmission-line insulators remains challenging due to severe class imbalance, large scale variation, and the small spatial extent of defect instances in Unmanned Aerial Vehicle (UAV) imagery.

摘要： 由于无人机（UAV）影像中存在严重的类别不平衡、尺度变化大以及缺陷实例空间范围小等问题，高压输电线路绝缘子的自动化缺陷检测仍然面临巨大挑战。

To address these challenges, this paper proposes AE-YOLO, an Attention-Guided AutoEncoder-Enhanced YOLO framework for robust insulator defect detection. The architecture integrates lightweight bottleneck autoencoders within a Feature Pyramid Network-Path Aggregation Network (FPN-PAN) neck. This preserves anomaly-sensitive information during multi-scale feature fusion.

为了解决这些挑战，本文提出了 AE-YOLO，这是一种用于鲁棒绝缘子缺陷检测的注意力引导自编码器增强型 YOLO 框架。该架构在特征金字塔网络-路径聚合网络（FPN-PAN）颈部集成了轻量级瓶颈自编码器，从而在多尺度特征融合过程中保留了对异常敏感的信息。

Convolutional Block Attention Modules (CBAM) are used throughout the backbone, enhancing feature discrimination and suppressing background interference. The framework also introduces a variance-maximizing autoencoder regularization strategy, which encourages diverse, defect-discriminative latent representations.

卷积块注意力模块（CBAM）被应用于整个骨干网络，以增强特征辨别能力并抑制背景干扰。该框架还引入了一种方差最大化自编码器正则化策略，旨在促进多样化且具有缺陷辨别力的潜在表示。

The network trains using a unified objective that combines focal loss, Complete IoU (CIoU) loss, and autoencoder regularization to address foreground-background imbalance and improve localization accuracy. During inference, Weighted Boxes Fusion (WBF) combines predictions from YOLOv8, YOLOv10, and YOLO11. An autoencoder-guided confidence boosting mechanism improves sensitivity to rare defect categories.

该网络使用结合了焦点损失（Focal Loss）、完整交并比（CIoU）损失和自编码器正则化的统一目标函数进行训练，以解决前景-背景不平衡问题并提高定位精度。在推理阶段，加权框融合（WBF）技术整合了来自 YOLOv8、YOLOv10 和 YOLO11 的预测结果。此外，一种自编码器引导的置信度提升机制提高了对罕见缺陷类别的敏感度。

Experiments on the Insulator-Defect Detection dataset show that AE-YOLO with an EfficientNetV2 backbone achieves 95.10 percent mAP at 0.5, 96.40 percent precision, and 93.80 percent recall. This performance surpasses the strongest YOLO-family baseline by 5.0 points in mAP at 0.5 and 6.7 points in recall. These results confirm the effectiveness and adaptability of the framework. The model is a practical and scalable solution for UAV-based transmission-line inspection and defect monitoring.

在绝缘子缺陷检测数据集上的实验表明，采用 EfficientNetV2 作为骨干网络的 AE-YOLO 在 mAP@0.5 指标上达到了 95.10%，精确率为 96.40%，召回率为 93.80%。这一性能表现比最强的 YOLO 系列基准模型在 mAP@0.5 上高出 5.0 个百分点，在召回率上高出 6.7 个百分点。这些结果证实了该框架的有效性和适应性。该模型为基于无人机的输电线路巡检和缺陷监测提供了一种实用且可扩展的解决方案。