AdIn-DETR: Adapting Detection Transformer for End-to-End Real-Time Power Line Insulator Defect Detection

Abstract

In the daily inspection tasks of electric power companies, detecting defects of the equipment on the high-voltage transmission lines is an essential task, especially the power line insulators which can pose a significant impact on the stability and security of power grid operations. Collecting and labeling data for training a well-performing deep-leaning model can be labor-intensive tasks and reducing the amount of training data can help reduce the costs and increase the efficiency. Pretrained weights may be better initialization points for the object detection optimization process in downstream tasks and small-sized datasets, such as defect detection tasks. To effectively adapt the pretrained weights of common object datasets for power line insulator detection, this article proposes adapter-enhanced insulator detection transformer (AdIn-DETR), a defect detection model with two proposed adapter modules, GSG-Adapter with Gaussian saliency guidance for convolutional feature modulation and LFO-Adapter with looking-forward ability to refract the learned relational modeling of the decoder layers. Our proposed method can achieve competitive performance on relatively small-sized datasets to detect bunch-drop defects for composite and glass insulators. This article experimentally demonstrates that our model can achieve 95.4% and 96.1% AP50 accuracy with R50 and R101 backbone on real-world insulators meanwhile reaching 104 and 71 frames per second (FPS) which are faster than the state-of-the-art you only look once (YOLO) models.

Topics & Concepts