摘要
为了准确地描述人体骨骼的运动细节以及3D骨骼间的几何关系,提出一种基于四元数3D骨骼表示的人体行为识别方法。首先,在已捕获的关键帧集合的基础上,对普通关键帧和变速关键帧分别采用线性插值和二次多项式插值,获得相同帧数的骨骼序列;然后,针对所得的骨骼序列,采用四元数对每帧中3D骨骼间的几何关系进行描述,获得四元数骨骼特征描述子;最后,采用支持向量机分类器对这一系列特征描述子进行训练和测试,得到最终的识别结果。在3个标准数据库上的实验结果均显示,四元数骨骼特征描述子对噪声、运动速度变化、视角变化和时域不对齐都具有很好的稳健性,可以显著提高人体行为识别的准确率。
We propose a new human action recognition method based on quaternion three-dimensional （3D） skeleton representation, in order to accurately describe the movement details of human skeletons and 3D geometric relationship of skeletons. Firstly, we obtain skeletal sequences with the same frame quantity by applying linear interpolation and quadratic polynomial interpolation to normal key frames and variable key frames, respectively, on the basis of the captured key frames. Secondly, we use quaternions to represent 3D geometric skeletal relationship of the obtained skeletal sequences to generate quaternion feature descriptors. Finally, we use the support vector machine classifier to train and test the quaternion feature descriptors to realize recognition. Experimental results based on three standard datasets prove that the quaternion feature descriptor is robust to noise, changes of moving rate and viewpoint, and time domain misalignment, and it is able to improve the identification accuracy of human behavior significantly.
作者
徐海洋
孔军
蒋敏
Xu Haiyang;Kong Jun;Jiang Min(School of lnternet of Things Engineering, Jiangnan University, Wuxi, Jiangsu 214122, China;College of Electrical Engineering, Xinjiang University, Urumqi, Xinjiang 830047, China)
出处
《激光与光电子学进展》
CSCD
北大核心
2018年第2期162-169,共8页
Laser & Optoelectronics Progress
基金
国家自然科学基金(61362030
61201429)
中国博士后科学基金(2015M571720
2016M606360)
江苏省博士后科学基金(1601416C)
中国公安部技术科研项目(2014JSYJB007)
关键词
图像处理
人体行为识别
四元数特征描述子
关键帧
动态时间规整算法
支持向量机
image processing
human action recognition
quaternion feature descriptor
key frames
dynamic time warping algorithm
support vector machine
