Improvement of feature point filtering algorithm for dynamic scenarios in substations based on fusion of YOLOv5 and ORB-SLAM
Maintanence and Inspection based on AI|更新时间:2026-03-09
|
Improvement of feature point filtering algorithm for dynamic scenarios in substations based on fusion of YOLOv5 and ORB-SLAM
“Experts propose an enhanced positioning and map construction architecture that integrates improved CA-YOLOv5 object detection to address the issue of decreased accuracy in intelligent inspection robot positioning and mapping under complex dynamic working conditions in substations. This provides an effective solution to address dynamic interference problems.”
BLASTINGVol. 48, Issue 2, Pages: 47-58(2026)
作者机构:
1.青岛大学 电气工程学院,山东 青岛 266071
2.山东广域科技有限责任公司,山东 东营 257029
3.国家电投东 北电力有限公司抚顺热电分公司,辽宁 抚顺 113010
4.青岛海尔智能技术研发有限公司,山东 青岛 266101
作者简介:
基金信息:
Funds for Local Science and Technology Development Projects(YDZX2024060┫Central Guidance)
HE Longqing,LI Xiaoyong,SHI Xin,et al.Improvement of feature point filtering algorithm for dynamic scenarios in substations based on fusion of YOLOv5 and ORB-SLAM[J].BLASTING,2026,48(02):47-58.
HE Longqing,LI Xiaoyong,SHI Xin,et al.Improvement of feature point filtering algorithm for dynamic scenarios in substations based on fusion of YOLOv5 and ORB-SLAM[J].BLASTING,2026,48(02):47-58. DOI: 10.3969/j.issn.2097-0706.2026.02.005.
Improvement of feature point filtering algorithm for dynamic scenarios in substations based on fusion of YOLOv5 and ORB-SLAM