Journal of Computer Applications ›› 2017, Vol. 37 ›› Issue (1): 251-254.DOI: 10.11772/j.issn.1001-9081.2017.01.0251

Previous Articles     Next Articles

Gesture segmentation and positioning based on improved depth information

LIN Haibo, WANG Shengbin, ZHANG Yi   

  1. National Engineering Research and Development Center for Information Accessibility(Chongqing University of Posts and Telecommunications), Chongqing 400065, China
  • Received:2016-08-20 Revised:2016-09-06 Online:2017-01-10 Published:2017-01-09
  • Supported by:
    This work is supported by the Scientific and Technological Research Project Funds of Chongqing Municipal Education Commission (KJ130512).


林海波, 王圣彬, 张毅   

  1. 国家信息无障碍研发中心(重庆邮电大学), 重庆 400065
  • 通讯作者: 王圣彬
  • 作者简介:林海波(1965-),男,重庆人,教授,硕士,主要研究方向:智能系统与机器人;王圣彬(1989-),男,江苏徐州人,硕士研究生,主要研究方向:模式识别;张毅(1966-),男,重庆人,教授,博士,主要研究方向:机器人导航、多模人机交互。
  • 基金资助:

Abstract: Aiming at the problem that segmented gesture by Kinect depth information usually contains wrist data, which easily causes subsequent false gesture recognition, a gesture segmentation and positioning algorithm based on improved depth information was proposed. Firstly, the gesture binary image was detected based on depth information threshold limit in experimental space. Secondly, according to characteristics of common gestures, accurate gesture was segmented by gesture endpoint detection and variable threshold algorithm. In order to obtain stable segmentation results, morphological processing of segmented gesture was conducted. Lastly, the gesture positioning algorithm was proposed based on the method of combining gesture gravity center coordinates and maximum inscribed circle center coordinates. The experimental results show that the proposed gesture segmentation method has better accuracy and stability than the existing algorithm. The combined gesture positioning is more stable than gesture gravity center positioning and skeletal data positioning of Kinect Software Development Kit (SDK) and it has no singular points.

Key words: depth information, gesture segmentation, gesture positioning, variable threshold, maximum inscribed circle

摘要: 针对基于Kinect深度信息分割的手势往往包含手腕易造成后续手势误识别的问题,提出一种改进深度信息的手势分割与定位算法。首先,基于深度信息阈值限定在实验空间中检测出手势二值图;然后,根据普通手势特征,提出基于手势端点检测和可变阈值算法分割出准确手势。为得到稳定的分割效果,对分割手势进行形态学处理,最后选取基于手势重心坐标和最大内切圆圆心坐标的联合手势定位法定位手势。实验结果表明,该手势分割方法比已有分割方法更准确可靠,联合手势定位比Kinect软件开发工具包骨骼数据定位和手势重心定位稳定,无奇异点。

关键词: 深度信息, 手势分割, 手势定位, 可变阈值, 最大内切圆

CLC Number: