LiteYOLO-ID: A Lightweight Object Detection Network for Insulator Defect Detection

Insulator defect detection is of great significance to ensure the normal operation of power transmission and distribution networks. In response to the problems of low speed, low accuracy, and difficulty in deploying to embedded terminals in existing insulator defect detection, this article proposes a lightweight insulator defect detection model based on an improved YOLOv5s, named LiteYOLO-ID. First, to significantly reduce the model parameters while maintaining detection accuracy, we design a new lightweight convolution module called ECA-GhostNet-C2f (EGC). Second, based on the EGC module, we construct the EGC-CSPGhostNet backbone network, which optimizes the feature extraction process and achieves model compression. Additionally, we design a lightweight neck network, EGC-PANet, to further reduce the parameter count and achieve efficient feature fusion. Experimental results show that on the IDID-Plus dataset, compared to the original YOLOv5s model, not only does LiteYOLO-ID reduce the model parameters by 47.13%, but it also improves the mAP (0.5) by 1%. Furthermore, the generalization of the model is validated on the Pascal VOC dataset and the SFID dataset. Importantly, after TensorRT optimization, the inference speed of the LiteYOLO-ID algorithm on the Jetson TX2 NX reaches 20.2 frames/s, meeting the real-time detection requirements of insulator defects. Our code, weight models, and datasets can be obtained at the following URL: https://github.com/LuYang-2023/Insulator-defect-detection.

I. Introduction

As societal, economic, and technological advancements continue, the scale of transmission lines consistently expands. Due to prolonged exposure to harsh environments, insulators are prone to faults, and pose obstacles to the stable operation of the power grid. Consequently, insulator defect detection has become an indispensable and crucial component in the detection of faults in transmission lines [1].