首页 | 本学科首页   官方微博 | 高级检索  
     

基于Kinect传感器的智能轮椅手势控制系统的设计与实现
引用本文:罗元,谢彧,张毅.基于Kinect传感器的智能轮椅手势控制系统的设计与实现[J].机器人,2012,34(1):110-113,119.
作者姓名:罗元  谢彧  张毅
作者单位:国家信息无障碍工程研发中心,重庆400065;重庆邮电大学智能系统及机器人研究所,重庆400065
基金项目:国家自然科学基金资助项目,科技部国际科技合作计划资助项目,重庆市科技攻关计划资助项目
摘    要:利用Kinect深度传感器所获取的图像深度信息实现手部从背景中的分割,并通过在Hu矩基础上加入3个表达式,使不变矩包含更多细节特征,对手势目标进行识别,最后把得到的识别结果转换成控制指令通过Ad-Hoc网络传送给智能轮椅,实现运动控制.实验表明,通过该方法实现的手势识别在图像旋转、缩放、平移的情况下具有不变性,对背景干扰具有较强的鲁棒性.

关 键 词:Kinect  深度信息  Hu矩  手势识别  智能轮椅

Design and Implementation of a Gesture-Driven System for Intelligent Wheelchairs Based on the Kinect Sensor
LUO Yuan , XIE Yu , ZHANG Yi.Design and Implementation of a Gesture-Driven System for Intelligent Wheelchairs Based on the Kinect Sensor[J].Robot,2012,34(1):110-113,119.
Authors:LUO Yuan  XIE Yu  ZHANG Yi
Affiliation:1,2) (1.National Engineering Research & Development Center for Information Accessibility,Chongqing 400065,China; 2.Research Center of Intelligent System and Robot,Chongqing University of Posts and Telecommunications,Chongqing 400065,China)
Abstract:First,hands are split from the background based on depth information from images got by the Kinect depth sensor.And then,three formulas are added to the Hu moment to make invariant moment contain more detailed characteristics for hand gesture recognition.At last,recognition results are translated into a control command which is transmitted to the intelligent wheelchair through Ad-Hoc network,to achieve motion control.Experiment shows that the gesture recognition achieved through this method has invariance all in images’ rotation,zooming,panning,and is of strong robustness to background interference.
Keywords:Kinect  depth information  Hu moment  hand gesture recognition  intelligent wheelchair
本文献已被 CNKI 万方数据 等数据库收录!
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