基于ROS与深度学习的移动机器人目标识别系统  

Mobile robot target recognition system based on ROS and deep learning

作　　者：詹润哲 姜飞[1] Zhan Runzhe;Jiang Fei(School of information engineering,Suzhou University,Suzhou Anhui,23400)

机构地区：[1]宿州学院信息工程学院,安徽宿州234000

出　　处：《电子测试》2018年第15期70-71,64,共3页Electronic Test

基　　金：宿州学院国家级大学生创新创业训练项目资助

摘　　要：本文基于ROS机器人操作系统与深度学习目标识别算法,利用嵌入式设备开发平台开发,以设计一个准确度与实时性均衡移动机器人目标识别系统进行了研究,并进行了性能测试。实验结果表明,该系统能满足上述要求并有较好的扩展性。In this paper, based on the ROS robot operating system and the depth learning target recognition algorithm, the development of the embedded equipment development platform is developed to design an accurate and real-time equilibrium mobile robot target recognition system, and the performance test is carried out. Experimental results show that the system can meet the above requirements and has good scalability.

关 键 词：ROS 目标识别 计算机视觉 深度学习 移动机器人 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]