End‐to‐end power equipment detection and localization with RM transformer

Abstract

Power equipment detection and localization is the key component of automatic inspection tasks in substations. To solve the challenges such as complex environment and lack of training data, utilization of context information is considered here. For substation scenes, object relation modelling (RM) is proven to be useful, but an end‐to‐end efficient framework which is suitable for non‐Convolutional Neural Networks (CNN) is still missing. Therefore, an extended Transformer network with an elaborately designed RM module is proposed. As the foundation, transformer network is better than CNN in terms of context dependency construction. On top of that, an RM module is plugged to adjust the decoded feature embeddings based on their appearance, position and class information. The module is based on a graph attention neural network which uses similarity as weights of nodes. The experiments show that the proposed method has a 16.2% improvement in accuracy compared to pipeline, and even 6.4% higher than the most recent models, largely promoting the construction of intelligent substations.

Electrical insulator defect detection with incomplete annotations and imbalanced samples

“…However, feature design is time-consuming and costly, and requires the assistance of experienced experts. In recent years, deep learning technology has made a breakthrough in image classification [6], object detection [15], image segmentation [16], etc. The deep learning-based detectors were introduced in this field [17][18][19][20], including both You Only Look Once (YOLO) family [21][22][23][24] and Region-based convolutional neural network (RCNN) series [25][26][27] detectors.…”

Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection

“…However, other kinds of images can also be used, including images taken in the visible spectrum. In all cases, any such inspection automation must rely on the explicit or implicit equipment localization in the image, along with its classification [20], which makes it a well-suited application for the data augmentation approach studied in this work.…”

Electrical insulator defect detection with incomplete annotations and imbalanced samples

“…However, feature design is time-consuming and costly, and requires the assistance of experienced experts. In recent years, deep learning technology has made a breakthrough in image classification [6], object detection [15], image segmentation [16], etc. The deep learning-based detectors were introduced in this field [17]- [20], including both You Only Look Once (YOLO) family [21]- [24] and Regionbased CNN (RCNN) series [25]- [27] detectors.…”