基于改进YOLOv8的电梯内电动车检测算法研究  

Research on Electric Vehicle Detection Algorithm in Elevators Based on Improved YOLOv8

作　　者：王俊博 孙皓月[1] 刘晓 WANG Junbo;SUN Haoyue;LIU Xiao(Hebei University of Architecture,Zhangjiakou Hebei 075000,China)

机构地区：[1]河北建筑工程学院,河北张家口075000

出　　处：《长江信息通信》2024年第11期11-14,共4页Changjiang Information & Communications

基　　金：校级研究生创新基金项目(No.XY2024039)。

摘　　要：随着城市化步伐的不断加快,电动车已成为城市居民日常出行的重要工具,许多居民为了充电方便,选择将电动车搬进居民楼,并通过电梯运输,这一行为导致了居民楼内电动车安全事故频发。因此,开发一种高效且准确的电梯内电动车检测算法显得尤为重要。首先,使用FasterNet中的FasterNet Block替换C2f中的Bottleneck,其降低了模型的计算量,提升了检测速度。在YOLOv8原结构中引入SEAttention注意力机制,把重要的特征进行强化来提升准确率。替换损失函数为Inner-CIoU损失函数,以提升模型检测性能和泛化能力。经过实验验证,改进后的YOLO-FSI模型在电梯内电动车数据集上的mAP50为93.7%,相较于原模型,参数量减少了23.3%,检测速度更是提升了5.2帧/秒。综上所述,YOLO-FSI模型可以有效提升电梯内电动车的检测能力,并且做到了轻量化及快速推理。With the accelerating pace of urbanization,electric vehicles have become an important tool for urban residents to travel daily.Many residents choose to move electric vehicles into residential buildings and transport them through elevators for the convenience of charging.This behavior has led to frequent safety accidents of electric vehicles in residential buildings.Therefore,it is particularly important to develop an efficient and accurate detection algorithm for electric vehicles in elevators.Firstly,the FasterNet Block in FasterNet is used to replace the Bottleneck in C2f,which reduces the computational complexity of the model and improves the detection speed.The SEAttention attention mechanism is introduced into the original structure of YOLOv8to strengthen the important features to improve the accuracy.The loss function is replaced by the Inner-CIoU loss function to improve the detection performance and generalization ability of the model.After experimental verification,the mAP50of the improved YOLO-FSI model on the electric vehicle data set in the elevator is 93.7%.Compared with the original model,the parameter amount is reduced by 23.3%,and the detection speed is increased by 5.2frames/second.In summary,the YOLO-FSI model can effectively improve the detection ability of electric vehicles in elevators,and achieve lightweight and fast reasoning.

关 键 词：目标检测 电动车识别 YOLOv8 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]