华南师范大学物理与电信工程学院
纸质出版:2015
移动端阅览
[1]张金权,李榕,温俊,马晓阳.基于近红外TOF传感器的姿势识别研究[J].传感器与微系统,2015,34(07):33-35+39.
ZHANG Jin-quan, LI Rong, WEN Jun, et al. Gesture recognition research based on near infrared TOF sensor[J]. 2015, 34(7): 33-35+39.
[1]张金权,李榕,温俊,马晓阳.基于近红外TOF传感器的姿势识别研究[J].传感器与微系统,2015,34(07):33-35+39. DOI: 10.13873/J.1000-9787(2015)07-0033-03.
ZHANG Jin-quan, LI Rong, WEN Jun, et al. Gesture recognition research based on near infrared TOF sensor[J]. 2015, 34(7): 33-35+39. DOI: 10.13873/J.1000-9787(2015)07-0033-03.
现有的姿势识别系统普遍存在算法复杂度较高
不便嵌入式移植等问题。提出一种基于深度图像的姿势识别方法。SR4000获取深度图像进行前期预处理得到人体目标并骨骼化
计算各端点坐标和离地高度及离质心的骨架线距离
根据骨架线距离识别各端点属性
结合特定动作的特征可识别出大量姿势。用该算法成功识别交通警察的8个指挥动作作为例子
验证算法的有效性。实验表明:该算法复杂度低
识别率高。
Current gesture recognition systems exist some issues such as high complexity algorithm
inconvenient for embedded transplant. A gesture recognition algorithm based on depth image is proposed. Pretreat depth image from SR4000 to get goals and skeletonized. Extract coordinates and ground clearance of endpoint
calculate skeleton linear distance
identify endpoint based on skeleton linear distance so as to recognize a large number of gesture after connection with certain features. Eight actions of traffic police as an example to verify the algorithm.Experiments show that the algorithm has low complexity and high identify rate.
基于激光雷达的移动机器人障碍测距研究 [J]. 于金霞,蔡自兴,邹小兵,段琢华. 传感器与微系统 . 2006(05)
A survey of human motion analysis using depth imagery [J] . Lulu Chen,Hong Wei,James Ferryman. Pattern Recognition Letters . 2013
Conditional random field-based gesture recognition with depth information [J] . Hyunsook Chung,Hee-Deok Yang. Optical Engineering . 2013 (1)
Linear-time connected-component labeling based on sequential local operations [J] . Kenji Suzuki,Isao Horiba,Noboru Sugie. Computer Vision and Image Understanding . 2003 (1)
A fast parallel algorithm for thinning digital patterns [J] . T. Y. Zhang,C. Y. Suen. Communications of the ACM . 1984 (3)
0
浏览量
205
下载量
2
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621