摘要
针对目前道路监控下识别车辆准确率不够高的问题,提出了一种基于YOLOv7的车辆检测方法.首先,建立了道路监控视角下的车辆数据集,其次,将GhostNet与YOLOv7结合以轻量化网络,最后,针对有效特征层增加通道注意力机制以减少车辆漏检.结果表明,改进后的YOLOv7检测精度为90.37%,与原始YOLOv7相比提高了1.73百分点,模型参数量缩减了14.83%,浮点计算量降低了54.73%.该方法轻量化模型的同时,提升了车辆目标检测精度,可以为交通监控中的车辆检测提供参考.
A YOLOv7-based vehicle detection method was proposed for the vehicle leakage detection problem under road monitor.Firstly,vehicle dataset were established from the angle of a transportation surveillance.Then GhostNet was combined with YOLOv7 to lighten the network.At last,a channel attention module was added for the effective feature layer to lower the probability of leak detection.The experimental results show that detection accuracy of the improved YOLOv7 is 90.37%,which is 1.73 percentage points better than the original YOLOv7.Additionally,the model parameter size has been reduced by 14.83%and the floating-point computation has decreased by 54.73%.The improved method effectively improves the vehicle target detection accuracy while lightweighting the model,which can provide a reference for vehicle detection in traffic monitoring.
作者
蔡刘畅
杨培峰
张秋仪
CAI Liu-chang;YANG Pei-feng;ZHANG Qiu-yi(College of Computer Science and Mathematics,Fujian University of Technology,Fuzhou 350118,China;College of Architecture and Planning,Fujian University of Technology,Fuzhou 350118,China)
出处
《陕西科技大学学报》
北大核心
2023年第6期155-161,175,共8页
Journal of Shaanxi University of Science & Technology
基金
国家自然科学基金项目(42201225)
福建省自然科学基金青创项目(2021J05220)。