摘要
近年来,以深度学习为基础的机器视觉技术发展迅速,并在行人检测等领域得到大规模应用。根据行人检测任务的特点,文章设计了基于YOLO的单阶段行人目标检测网络模型,对其进行了训练并部署于Nvidia高性能边缘计算平台Xavier。经实验验证,该算法模型能够有效检测行人目标,具有较高的准确度及实时性。
In recent years,machine vision technology based on deep learning has developed rapidly and has been widely applied in fields such as pedestrian detection.According to the characteristics of pedestrian detection task,this paper designs a single-stage pedestrian target detection network model based on YOLO,trains it and deploys it on the Nvidia high-performance edge computing platform Xavier.Through experimental verification,the algorithm model can effectively detect pedestrian targets with high accuracy and real-time performance.
作者
陆宇骁
LU Yuxiao(Kunming Shipborne Equipment Research&Test Center,Kunming 650051,China)
出处
《计算机应用文摘》
2024年第8期89-92,96,共5页
Chinese Journal of Computer Application
关键词
机器视觉
深度学习
行人检测
边缘计算
matchine vision
deep learning
pedestrian detection
edge computing
