基于Realsense的手势识别与应用  

Gesture recognition and application based on Realsense

作　　者：张远来 王传江 黄灿[1] ZHANG Yuan-lai;WANG Chuan-jiang;HUANG Can(College of Electrical Engineering and Automation,Shandong University of Science and Technology,Qingdao 266590,China;Robotics and Intelligent Technology Laboratory of Shandong Province,Shandong University of Science and Technology,Qingdao 266590,China;School of Control Science and Engineering,Shandong University,Jinan 250061,China)

机构地区：[1]山东科技大学电气与自动化工程学院,山东青岛266590 [2]山东科技大学山东省机器人与智能技术实验室,山东青岛266590 [3]山东大学控制科学与工程学院,山东济南250061

出　　处：《计算机工程与设计》2019年第3期839-844,873,共7页Computer Engineering and Design

基　　金：山东省重点研发计划基金项目(2016GSF201197);山东省高等学校科技计划基金项目(J16LB11)

摘　　要：为解决现有手势识别方法易受外部环境干扰和特征提取繁琐的问题,提出一种基于Intel Realsense技术的深度图像手势识别的方法。根据SR300捕获的深度图像中获取的手部关节点和手指的信息,对这22个关节点进行几何建模;采用关节等效距离和手指伸直程度的特征,实现手势识别;将该方法应用到机械臂机器人的人机交互中去,成功实现抓取杯子到嘴边喝水等动作。实验结果表明,该方法特征简单,识别率高,通用性强,具有较强的鲁棒性。To solve the problem that the existing gesture recognition method is vulnerable to external environment disturbance and the feature extraction process is complex, a method of depth image gesture recognition based on Intel Realsense technology was proposed. Based on the information of the hand joints and fingers acquired in the depth image captured by the SR300, the geometrically model for the 22 joints was constructed. The features of joints equivalent distance and the degree of finger extension were used to achieve gesture recognition. The gesture recognition system was successfully used in a human-computer inte- raction of the arm robot to grab the cup to the mouth for drinking. Experimental results show that the proposed methods is rea- lized with characteristics of simple feature, high recognition rate, strong universality and strong robustness.

关 键 词：实感技术 手势识别 深度信息 关节距离 人机交互 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]