基于改进YOLOv8的遥感影像变电站目标识别OA

Aiming at the limitation in existing studies focused on the detection of substation local structures,such as lacking methods for rapid discovery and dynamic monitoring over large areas,the capability of identifying poten-tial safety hazards in power grids was enhanced through high-resolution satellite imagery.Firstly,a substation object detection dataset based on high-resolution optical satellite imagery was constructed.Subsequently,an improved YOLOv8 algorithm was proposed,embedding the SimAM lightweight attention module into the backbone network to enhance the ability to focus on detailed features,and replacing the neck with an Efficient-RepGFPN,combined with a DySample dynamic upsampling module to design a novel neck named GDFPN,addressing issues of multi-level feature semantic misalignment.Experimental results demonstrated that the improved method outperformed ma-instream detection algorithms,with mAP75 and mAP50-95 increasing to 96.8%and 87.1%,respectively,confir-ming its superiority in substation detection tasks.The improved YOLOv8 approach proposed could effectively sup-port the rapid discovery and dynamic monitoring of substations over large areas,providing reliable technical support for the safety management of power grids.