基于改进YOLOv7的输电线路异物检测模型OA北大核心CSTPCD
Foreign Object Detection Model of Transmission Line Based on Improved YOLOv7
针对输电线路异物检测中存在背景干扰、图像分辨率低且异物尺度变化大等问题,提出了一种基于改进YOLOv7的输电线路异物检测模型.首先,通过空间深度卷积(space to depth conconvolution,SPD-Conv)和多维协作注意力(multidimensional collaborative attention,MCA)机制构造新的骨干网络,加强模型对低分辨率图像特征提取及抑制背景干扰的能力,同时增加对小目标异物的关注度.其次,使用…查看全部>>
Aiming at the problems of background interference,low image resolution,and large scale variations of foreign objects in the detection of foreign objects on power transmission lines,a foreign object detection model of power transmission line based on improved YOLOv7 is proposed.Firstly,a new backbone network is constructed through space to depth conconvolution(SPD-Conv)and multidimensional collaborative attention(MCA)mechanism to enhance the model's ability t…查看全部>>
严宇平;杨秋勇;谢翰阳;史建勋;邓琨;温启良
广东电网有限责任公司,广州 510623中国南方电网有限责任公司,广州 510663广东电网有限责任公司,广州 510623中国农业大学 经济管理学院,北京 100083南方电网深圳数字电网研究院有限公司,广东 深圳 518053南方电网深圳数字电网研究院有限公司,广东 深圳 518053
动力与电气工程
输电线路异物YOLOv7多维协作注意力小目标SPD幻影卷积
foreign object of transmission lineYOLOv7MCAsmall objectSPDGhost-Conv
《南方电网技术》 2024 (9)
47-58,12
国家自然科学基金资助项目(51977210)广东电网有限责任公司2020年信息中心个性化运营管控建设(生产监控指挥中心优化子项)(037800HK42200016).Supported by the National Natural Science Foundation of China(51977210)the 2020 Personalized Operation and Control Construction of Information Center of Guangdong Power Grid Co.,Ltd.,(Production Monitoring and Command Center Optimization Sub-Project)(037800HK42200016).
评论