智能系统学报2023，Vol.18Issue(6)：1213-1222,10.DOI:10.11992/tis.202303030
融合知识迁移和改进YOLOv6的变电设备热像检测方法
Thermd image detection method for substation equipment by incorporat-ing knowledge migration and improved YOLOv6
摘要
Abstract
To address the problems of insufficient complex background samples and difficulty in device location in sub-station equipment thermal image detection,a fusion knowledge transfer and improved YOLOv6 detection method are proposed.The diffusion model was used to extract background knowledge from extraterritorial data for generating back-ground images,solving the problem of insufficient complex background samples.The device samples were then mi-grated to the background images to generate artificial images.The multi-head self-attention mechanism and explicit visual center module were integrated into YOLOv6 to improve its feature extraction capability,solving the issue of diffi-culty in detecting devices.The experiment shows that the mAP and mAR of the proposed method reach 86.4%and 89.4%,indicating an improvement of 3.1%and 1.5%compared to the baseline model,respectively.This study provides a new implementation method for thermal image detection of substation equipment.关键词
变电设备/热红外图像/知识迁移/样本生成/目标检测/扩散模型/数据扩增/深度学习Key words
substation equipment/thermal infrared image/knowledge migration/sample generation/object detection/diffusion model/data augmentation/deep learning分类
信息技术与安全科学引用本文复制引用
赵振兵,冯烁,赵文清,翟永杰,王洪涛..融合知识迁移和改进YOLOv6的变电设备热像检测方法[J].智能系统学报,2023,18(6):1213-1222,10.基金项目
国家自然科学基金项目(61871182,U21A20486) （61871182,U21A20486）
河北省自然科学基金项目(F2020502009,F2021-502008,F2021502013). （F2020502009,F2021-502008,F2021502013）
