Substation rotational object detection based on multi-scale feature fusion and refinement  

作　　者：Bin Li Yalin Li Xinshan Zhu Luyao Qu Shuai Wang Yangyang Tian Dan Xu 

机构地区：[1]The Key Laboratory of Smart Grid of Ministry of Education,Tianjin University,Tianjin 300072,China [2]State Grid Henan Electric Power Research Institute,Zhengzhou 450000,China [3]XJ Group Corporation,Xuchang 461000,China

出　　处：《Energy and AI》2023年第4期490-499,共10页能源与人工智能（英文）

基　　金：This work was supported by Science and Technology Project of State Grid Corporation of China(Research and application of audiovisual active perception and collaborative cognitive technology for smart grid operation and maintenance scenarios)(5600–202046347 A-0–0–00).

摘　　要：In modern energy systems,substations are the core of electricity transmission and distribution.However,similar appearance and small size pose significant challenges for automatic identification of electrical devices.To address these issues,we collect and annotate the substation rotated device dataset(SRDD).Further,feature fusion and feature refinement network(F3RNet)are constructed based on the classic structure pattern of backbone-neck-head.Considering the similar appearance of electrical devices,the deconvolution fusion module(DFM)is designed to enhance the expression of feature information.The balanced feature pyramid(BFP)is embedded to aggregate the global feature.The feature refinement is constructed to adjust the original feature maps by considering the feature alignment between the anchors and devices.It can generate more accurate feature vectors.To address the problem of sample imbalance between electrical devices,the gradient harmonized mechanism(GHM)loss is utilized to adjust the weight of each sample.The ablation experiments are conducted on the SRDD dataset.F3RNet achieves the best detection performance compared with classical object detection networks.Also,it is verified that the features from global feature maps can effectively recognize the similar and small devices.

关 键 词：SUBSTATION Rotated device Object detection Feature fusion Feature refinement 

分 类 号：G63[文化科学—教育学]