改进YOLOv10的天台光伏涉电区域行为人预警算法  

Improvement of Early Warning Algorithm of YOLOv10 for Actors in Rooftop Photovoltaic Power-Related Area

作　　者：李军[1] 房志远 周昊星 LI Jun;FANG Zhiyuan;ZHOU Haoxing(School of Electric Power Engineering,Nanjing Institute of Technology,Nanjing 210000,China)

机构地区：[1]南京工程学院电力工程学院,南京210000

出　　处：《计算机工程与应用》2025年第5期211-221,共11页Computer Engineering and Applications

基　　金：江苏省产业前瞻与关键核心技术-碳达峰碳中和科技创新项目(BE2022003-4)。

摘　　要：随着分布式光伏接入规模的日益增大,安装于私人用户天台区域的光伏电池板及其附属发电系统可能对用户带来触电风险。针对区域监控设备算力受限和天台涉电范围内行为人越界预警问题,讨论采用一种改进YOLOv10、DeepSort和PNPOLY的天台光伏板区域行为人跟踪预警算法。基于YOLOv10重新设计了特征融合模块,模块引入部分卷积思想,解决了特征融合部分运算量大问题。同时针对受光伏电池板遮挡的行为人检测,引入了针对遮挡目标的损失函数(Repulsion-IoU损失函数),并在渐进特征融合结构AFPN(asymptotic feature pyramid network for object detection)基础上设计了更好融合多层次目标的三层特征提取结构AFPN-3。在改进目标检测的基础上,利用DeepSort实现对行为人的持续跟踪定位,使用轻量化分类网络Fasternet替代原本特征提取网络,有效降低了模型的体积,提高了行为人跟踪的质量。为了解决行为人越界判定问题,采用PNPOLY算法,使用检测行为人脚部坐标位置进行精确的越界判别。实验表明,与YOLOv10n相比,在仅损失检测精度0.3个百分点的前提下,改进后行为人检测模型运算量下降了18%,参数量下降了19%,结合改进后的DeepSort模型,平均跟踪精度较之前提升1.4个百分点,模型大小只有8.7 MB。真实场景实验中,所提算法天台光伏涉电区域行为人预警正确率达到94%,具有轻量化、精确度高的特点,能满足天台光伏板区域行为人跟踪预警的实际检测需求。With the increasing scale of distributed photovoltaic(PV)installations,PV panels and their associated power generation systems installed on private rooftops may pose an electric shock hazard to users.To address the issues of boundary crossing warnings and the limited computational capacity of regional monitoring equipment,this paper proposes an improved tracking and warning algorithm based on YOLOv10,DeepSort,and PNPOLY.To reduce the high computational complexity in feature fusion,the feature fusion module in YOLOv10 is redesigned using the concept of partial convolution.Furthermore,to enhance the detection of individuals occluded by PV panels,the Repulsion-IoU loss function is introduced,and a three-layer feature extraction structure(AFPN-3)is designed based on the asymptotic feature pyramid network for object detection(AFPN)to better integrate multi-level targets.On this basis,continuous individual tracking is performed using DeepSort,and the lightweight Fasternet is used to replace the original feature extraction network,reducing the model size and improving tracking quality.To accurately determine boundary crossing,the PNPOLY algorithm is used to detect the coordinates of individuals’feet.Experimental results show that,compared to YOLOv10n,the improved model reduces computational complexity by 18%,reduces the number of parameters by 19%,and only loses 0.3 percentage points in detection accuracy.The improved DeepSort model increases the average tracking accuracy by 1.4 percentage points and reduces the model size to 8.7 MB.The proposed algorithm achieves a 94%accuracy rate in warning individuals in electrified rooftop PV areas,demonstrating its lightweight and high-precision characteristics,meeting the practical needs for tracking and warning individuals near rooftop PV panels.

关 键 词：天台光伏电池板涉电区域 YOLOv10 DeepSort 行为人跟踪 预警检测 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]