基于人体骨骼和深度图像信息的指尖检测方法

J4 ›› 2014, Vol. 36 ›› Issue (09): 1788-1794.

基于人体骨骼和深度图像信息的指尖检测方法

宋海声，刘平和，王全州，赵学深，王海燕

（西北师范大学物理与电子工程学院，甘肃兰州 730070）

收稿日期:2013-01-31 修回日期:2013-05-29 出版日期:2014-09-25 发布日期:2014-09-25
基金资助:
甘肃省自然基金资助项目（1208RJZA191）

A fingertip detection method based on
human skeleton and depth image information

SONG Haisheng,LIU Pinghe,WANG Quanzhou,ZHAO Xueshen,WANG Haiyan

(College of Physics and Electronic Engineering,Northwest Normal University,Lanzhou 730070,China)

Received:2013-01-31 Revised:2013-05-29 Online:2014-09-25 Published:2014-09-25

摘要/Abstract

摘要：

针对复杂环境下的指尖检测，从手部图像分割和指尖检测方法两方面进行改进，提出了一种基于人体骨骼和深度图像信息的指尖检测方法。首先采用Kinect获取人体骨骼和深度图像信息，通过人体骨骼信息锁定目标用户，利用锁定用户的手部节点位置从深度图像中提取手部区域图像；然后从手部骨架中搜索骨架端点，提出局部最优查找方法对轮廓凸包计算结果进行优化；最后结合手部轮廓特征找到指尖位置。实验结果表明，该方法具有良好的检测效果，满足实时性要求，能够实现复杂环境下的鲁棒检测。

关键词: 手部分割, 指尖检测, 人体骨骼, 深度图像, 复杂背景

Abstract:

Aiming at fingertip detection in a complex environment, from the two aspects of hand image segmentation and fingertip detection, a fingertip detection method based on human skeleton and depth image information is proposed. Firstly, Kinect is used to obtain the human skeleton and depth image information, the objective user is locked by the human skeleton information, and then the hand joint position of the locked user is used to extract the hand area image from the depth image. Secondly, the skeleton endpoints are searched from the hand skeleton, and the local optimal search method is proposed to optimize the results of contour convex hull computation. Finally, the fingertip position is found by combining the feature of hand contour. The experimental results show that the proposed method has good detection effect, meets the realtime requirements and can realize robust detection in a complex environment.

Key words: hand segmentation;fingertip detection;human skeleton;depth image;complex background

宋海声，刘平和，王全州，赵学深，王海燕. 基于人体骨骼和深度图像信息的指尖检测方法[J]. J4, 2014, 36(09): 1788-1794.

SONG Haisheng,LIU Pinghe,WANG Quanzhou,ZHAO Xueshen,WANG Haiyan . A fingertip detection method based on
human skeleton and depth image information [J]. J4, 2014, 36(09): 1788-1794.

参考文献［16］

［1］	Raheja J L, Chaudhary A, Singal K. Tracking of fingertips and centers of palm using Kinect ［C］∥Proc of 2011 the 3rd International Conference on Computational Intelligence, Modelling & Simulation, 2011:248252.
［2］	Yi Li. Hand gesture recognition using Kinect ［C］∥Proc of 2012 IEEE the 3rd International Conference on Software Engineering and Service Science, 2012:196199.
［3］	Oikonomidis I, Kyriazis N, Argyros A A. Efficient modelbased 3D tracking of hand articulations using Kinect ［C］∥Proc of the 22nd British Machine Vision Conference, 2011:101.1101.11.
［4］	Fahn C S, Sun H. Development of a fingertip glove equipped with magnetic tracking sensors ［J］. Sensors, 2010, 10(2):11191140.
［5］	Weng Hanliang, Zhan Yinwei. Visionbased hand gesture recognition with multiple cues ［J］. Computer Engineering & Science, 2012, 34(2):123127.(in Chinese)
［6］	Guo Kangde, Zhang Mingmin, Sun Chao, et al. 3D fingertip tracking algorithm based on computer vision ［J］. Journal of Computer Research and Development, 2010, 47(6):10131019.(in Chinese)
［7］	Li Bonan, Lin Fan. Fingertip detection method based on curvature ［J］. Journal of Nanjing University of Aeronautics & Astronautics, 2012, 44(4):587591.(in Chinese)
［8］	Schwarz L A, Mkhitaryan A, Mateus D, et al. Human skeleton tracking from depth data using geodesic distances and optical flow ［J］. Image and Vision Computing, 2011, 30 (3):217226.
［9］	Clark R A, Pua Y H, Fortin K, et al. Validity of the Microsoft Kinect for assessment of postural control ［J］. Gait & Posture, 2012, 36(3):372377.
［10］	He Jun, Ge Hong, Wang Yufeng. Survey on the methods of image segmentation research ［J］. Computer Engineering & Science, 2009, 31(12):5861.(in Chinese)
［11］	Gonzalez R C,Woods R E.Digital image processing ［M］. London：Prentice Hall, 2007.
［12］	Xie Junxi,Tang Zhaohui,Gui Weihua.Recognition of the twodimension bar code based on mathematical morphology ［J］. Computer Engineering & Science, 2009, 31(2):4455.(in Chinese)
［13］	Li Wensheng,Xie Mei,Deng Chunjian,et al.Dynamic gesture learning and recognition based on the Hermite neural network ［J］. Computer Engineering & Science, 2012, 34(2):116122.(in Chinese)
［14］	Li Chendan, Xu Jin. A preprocessing and minutiae extraction algorithm based on Matlab ［J］. Computer Engineering & Science, 2009, 31(7):6164.(in Chinese)
［15］	Zhang T Y,Suen C Y.A fast parallel algorithm for thinning digital paterns ［J］. Communications of the ACM, 1984, 27(3):236239.
［16］	Liu Wenjing，Tian Zheng, Zhang Zhaoyang. Convex hull sequence method using graph spectra in image point pattern matching ［J］. Computer Engineering and Applications, 2011, 47(23):197200.(in Chinese)
［17］	Homma K, Takenaka E. An image processing method for feature extraction of spaceoccupying lesions ［J］. Journal of Nuclear Medieine, 1985, 26(12):14721477.
	附中文参考文献：
［5］	翁汉良，战荫伟. 基于视觉的多特征手势识别［J］. 计算机工程与科学, 2012，34(2):123127.
［6］	郭康德，张明敏，孙超，等. 基于视觉技术的三维指尖跟踪算法［J］. 计算机研究与发展, 2010, 47(6):10131019.
［7］	李博男，林凡. 基于曲率的指尖检测方法［J］. 南京航空航天大学学报, 2012, 44(4):587591.
［10］	何俊，葛红，王玉峰. 图像分割算法研究综述［J］. 计算机工程与科学, 2009, 31(12):5861.
［12］	谢俊喜，唐朝晖，桂卫华. 基于数学形态学的二维条码识别［J］. 计算机工程与科学, 2009, 31(2):4455.
［13］	李文生，解梅，邓春健，等. 基于Hermite神经网络的动态手势学习和识别［J］. 计算机工程与科学, 2012, 34(2):116122.
［14］	李晨丹，徐进. 指纹图像预处理和特征提取算法的Matlab实现［J］. 计算机工程与科学, 2009, 31(7):6164.
［16］	刘文静，田铮，张朝阳. 图像点模式匹配的一种凸包序列的图谱方法［J］. 计算机工程与应用, 2011, 47(23):197200.

[1]	张寅, 蔡旭阳, 许倩倩, 闫钧华, 苏恺, 张琨 . 融合时空上下文的复杂背景下多运动目标检测[J]. 计算机工程与科学, 2020, 42(12): 2186-2192.
[2]	刘国华1,2，段建春1. 基于Kinect相机的深度图像空洞修复及超像素分割算法[J]. 计算机工程与科学, 2020, 42(05): 851-858.
[3]	谭志国1，2,欧建平1,张军1,沈先耿2. 多特征组合的深度图像分割算法[J]. 计算机工程与科学, 2018, 40(08): 1429-1434.
[4]	苏相阁，张为. 强光干扰下的火焰前景提取技术研究[J]. 计算机工程与科学, 2017, 39(11): 2060-2065.
[5]	王培玉1,2,李峰1,2,周书仁1,2，廖卓凡1，2. 复杂码头环境下的船舶检测与跟踪算法[J]. 计算机工程与科学, 2017, 39(05): 992-998.
[6]	郑传远，李良福，肖樟树，陆铖. 一种改进的各向异性扩散深度图像增强算法[J]. 计算机工程与科学, 2016, 38(09): 1823-1829.
[7]	张武，黄帅，汪京京，刘连忠. 复杂背景下小麦叶部病害图像分割方法研究[J]. J4, 2015, 37(07): 1349-1354.
[8]	屈燕琴，李昕，卢夏衍. 基于表观特征分析的手势识别及其应用[J]. J4, 2015, 37(01): 139-145.
[9]	许凯，王敏. 基于手轮廓的深度图像手势识别方法[J]. J4, 2014, 36(05): 941-946.
[10]	翁汉良，战荫伟. 基于视觉的多特征手势识别[J]. J4, 2012, 34(2): 123-127.
[11]	王志勇刘文奇. 基于数学形态学的快速运动物体检测[J]. J4, 2005, 27(1): 27-28.