Algorithms for Object Detection in Substations
This addresses the problem of automatic power equipment inspection for electrical grid operators, representing an incremental improvement by adding relationship modeling to existing transformer approaches.
The paper tackles object detection in electrical substations by proposing a Relation Transformer Model that incorporates object relationship modeling, achieving significantly better performance than three commonly used models.
Inspection of high-voltage power equipment is an effective way to ensure power supply reliability. Object recognition, one of the key technologies in automatic power equipment inspection, attracts attention of many researchers and engineers. Although quite a few existing models have some their own advantages, object relationship between equipment which is very important in this task is scarcely considered. This paper combining object relationship modeling and Transformer Model proposes a Relation Transformer Model. It has four parts -- backbone, encoder, decoder and prediction heads. With this structure, the proposed method shows in experiments a much better performance than other three commonly used models in object recognition in substation, largely promoting the development of automatic power equipment inspection.