摘要
随着科技的快速发展,智慧交通系统的建设对提升人们的生活品质,提升城市交通服务能力和城市交通管控的科学有效性有着重点意义。文章采用YOLOV5s目标检测算法对行人识别,首先分析YOLOv5s的架构和关键技术,然后通过YOLOv5s对标注好的数据集进行训练,最后就检测效果进行评估分析。实验结果体现出了YOLOv5s对行人检测的实时性满足于城市交通的需求,尤其对小尺度行人的检测精确度也提高了。
With the rapid development of science and technology,the construction of intelligent transportation system has a key significance for improving people's quality of life,improving the ability of urban traffic service and the scientific effectiveness of urban traffic control.In this paper,the YOLOV5S target detection algorithm is used for pedestrian recognition.Firstly,the architecture and key technologies of YOLOV5S are analyzed.Then,the labeled data sets are trained through YOLOV5S,and the detection effect is evaluated and analyzed.The experimental results show that the real-time performance of YOLOV5S in pedestrian detection meets the demand of urban traffic,and the detection accuracy of small-scale pedestrians is also improved.
作者
杨晓玲
蔡雅雯
YANG Xiao-ling;CAI Ya-wen(Zhuhai University of Science and Technology,Zhuhai 519041,China)
出处
《电脑与信息技术》
2022年第1期28-30,共3页
Computer and Information Technology
基金
广东省高校青年创新人才类项目(项目编号:2019KQNCX198)
广东省大学生创新创业训练计划项目(项目编号:S202013684026S)
广东省大学生创新创业训练计划项目(项目编号:S201913684044S)
吉林大学珠海学院教学质量工程项目(项目编号:ZLGC20191015)。
关键词
智慧交通
深度学习
行人检测
YOLOV5s
intelligent transportation
deep learning
pedestrian detection
YOLOV5s
