首页 | 本学科首页   官方微博 | 高级检索  
     

一种适用于室内服务机器人的实时物体识别系统
引用本文:柯翔,陈小平,靳国强,王锋,郭群.一种适用于室内服务机器人的实时物体识别系统[J].计算机系统应用,2013,22(10):84-89.
作者姓名:柯翔  陈小平  靳国强  王锋  郭群
作者单位:中国科学技术大学 计算机科学与技术学院,合肥,230027
摘    要:针对室内服务机器人在实际应用中的需求,提出一种结合三维点云分割和局部特征匹配的实时物体识别系统.该系统首先基于三维点云实现快速有效的物体检测,然后利用物体检测的结果定位物体在彩色图像中的区域,并采用基于SURF特征匹配的方法识别出物体的标识.实验结果表明,该系统可较好地满足室内服务机器人物体检测与识别的实时性和可靠性要求.

关 键 词:室内服务机器人  三维点云分割  局部特征匹配  实时物体识别
收稿时间:4/1/2013 12:00:00 AM
修稿时间:2013/4/27 0:00:00

Real-Time Object Recognition System for Indoor Service Robot
KE Xiang,CHEN Xiao-Ping,JIN Guo-Qiang,WANG Feng and GUO Qun.Real-Time Object Recognition System for Indoor Service Robot[J].Computer Systems& Applications,2013,22(10):84-89.
Authors:KE Xiang  CHEN Xiao-Ping  JIN Guo-Qiang  WANG Feng and GUO Qun
Affiliation:School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China;School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China;School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China;School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China;School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, China
Abstract:For the requirements in practical application of indoor service robot, a real-time object recognition system is proposed which integrates 3D point cloud segmentation and local feature matching. First, it does fast and effective object detection based on 3D point cloud. Then, the areas of objects in color image are located using the result of object detection, and objects are identified using the approach based on SURF feature matching. The experiments show that the system could well meet the real-time and reliability requirements of indoor service robot's object detection and recognition.
Keywords:indoor service robot  3D point cloud segmentation  local feature matching  real-time object recognition
本文献已被 维普 万方数据 等数据库收录!
点击此处可从《计算机系统应用》浏览原始摘要信息
点击此处可从《计算机系统应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号