MAO Yanming,RUAN Qunsheng,ZHANG Liliang.A fingertip detection method based on Kinect depth and skeleton data[J].Journal of Yanbian University,2016,42(03):235-240.
基于Kinect深度和骨架信息的指尖检测方法
- Title:
- A fingertip detection method based on Kinect depth and skeleton data
- Keywords:
- skeleton data; depth data; gesture segmentation; fingertip detection
- 分类号:
- TP391.41
- 文献标志码:
- A
- 摘要:
- 为克服指尖检测方法易受不同光照、复杂背景和手腕信息的影响,提出了一种基于深度和骨架信息的指尖检测方法.首先对Kinect获取的深度图像进行中值滤波和形态学闭操作处理,以消除噪声和填充空洞; 接着通过骨架跟踪得到的右手关节点锁定用户并进行手势分割; 然后在计算手心和最高指尖点位置的基础上,利用Freeman链码提取手势左右轮廓; 最后根据指尖点之间的轮廓曲线特征提取其他指尖点.实验结果表明,该方法具有良好的指尖检测效果,且对光照、背景和手腕信息鲁棒.
- Abstract:
- To overcome the fingertip detection method which is susceptible to the different illumination, complex background and wrist data, a fingertip detection method based on skeleton and depth data was proposed. First, in order to eliminate noises and fill holes, it used median filter and morphological closing operation to process the depth image captured by Kinect sensor; subsequently, it used right hand joint point obtained by the skeleton tracking for lock user and gesture segmentation; then, on the basis of calculating the positions of palm and the highest fingertip, it used Freeman Chain Code(FCC)to extract the left and right contours of the gesture; finally, the other fingertips were extracted according to the contour curve features between fingertips. Experimental results show that the proposed method has good finger detection effect and also robust to the illumination, background and wrist information.
参考文献/References:
[1] 毛雁明,章立亮.基于Kinect深度信息的手势分割与识别[J].系统仿真学报,2015,27(4):830-835.
[2] 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, Modeling & Simulation, 2011:248-252.
[3] Li Yi. Hand gesture recognition using Kinect[C]//Proc of 2012 IEEE the 3rd International Conference on Software Engineering and Service Science, 2012:196-199.
[4] Oikonomidis I, Kyriazis N, Argyros A A. Efficient model based 3D tracking of hand articulations using Kinect[C]//Proc of the 33nd British Machine Vision Conference, 2011:1-11.
[5] 梅萍华,李斌,朱中的,等.基于径向对称变换的实时指尖检测算法[J].中国科学技术大学学报,2011,41(2):101-107.
[6] Fahn C S, Sun H. Development of a fingertip glove equipped with magnetic tracking sensors[J]. Sensors, 2010,10(2):1119-1140.
[7] 谭同德,郭志敏.基于双目视觉的人手定位与手势识别系统研究[J].计算机工程与设计,2012,33(1):259-264.
[8] 张秋余,王道东,张墨逸,等.基于特征包支持向量机的手势识别[J].计算机应用,2012,32(12):3392-3396.
[9] 薛俊韬,纵蕴瑞,杨正瓴.基于改进的YCbCr空间及多特征融合的手势识别[J].计算机应用与软件,2016,33(1):151-155.
[10] 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.
[11] 徐义春,沈沆瑜,陈炼,等.鲁棒性指尖检测框架及其算法改进与分析[J].计算机工程与应用,2013,49(15):195-200.
[12] 毛雁明,章立亮.基于Kinect骨架追踪技术的PPT全自动控制方法研究[J].海南大学学报(自然科学版),2015,33(3):215-220.
[13] 李哲,彭四伟.基于深度信息的指尖跟踪与轨迹识别[J].计算机应用与软件,2016,33(4):155-172.
[14] 徐鹏飞,张红英.基于Kinect深度图像信息的手势分割和指尖检测算法[J].西南科技大学学报,2014,29(1):49-54.
相似文献/References:
[1]李思含,罗凯,金小峰.基于Kinect信息融合的移动平台目标定位算法研究[J].延边大学学报(自然科学版),2018,44(01):69.
LI Sihan,LUO Kai,JIN Xiaofeng*.Research on mobile platform target localization algorithmbased on Kinect information fusion[J].Journal of Yanbian University,2018,44(03):69.
备注/Memo
收稿日期: 2016-08-29 作者简介: 毛雁明(1982—),男,讲师,研究方向为计算机视觉、模式识别.基金项目: 福建省自然科学基金资助项目(2015J01660); 福建省教育厅A类科技项目(JA15543); 宁德师范学院青年科技项目(2015Q04)