一种基于RGB-D特征融合的人体行为识别框架  

Human Action Recognition Framework with RGB-D Features Fusion

作　　者：毛峡[1] 王岚 李建军[1,2] MAO Xia;WANG Lan;LI Jian-jun(School of Electronic and Information Engineering,Beihang University,Beijing 100191,China;School of Information Engineering,Inner Mongolia University of Science and Technology,Baotou,Inner Mongolia 014010,China)

机构地区：[1]北京航空航天大学电子信息工程学院,北京100191 [2]内蒙古科技大学信息工程学院,内蒙古包头014010

出　　处：《计算机科学》2018年第8期22-27,共6页Computer Science

基　　金：国家自然科学基金项目(61603013)资助

摘　　要：人体行为识别是计算机视觉和模式识别领域内一个重要的研究方向。人体行为的复杂性和不同人执行同一动作的差异性,使得行为识别仍然是一个具有挑战性的课题。采用新一代传感技术的RGB-D相机能够同时记录RGB图像和深度图像,并能够实时提取骨骼点信息。充分利用以上信息,成为行为识别领域的研究热点和突破点。文中提出了一种新的基于高斯加权金字塔式梯度方向直方图的RGB图像特征提取方法,并构建了一种多模特征融合的行为识别框架。在UTKinect-Action3D,MSR-Action 3D和Florence 3DActions 3个数据库上对本研究所提特征和框架进行实验,结果表明,所提框架在3个行为数据库上的识别正确率分别达到了97.5%,93.1%,91.7%,从而证明了该行为识别框架的有效性。Human action recognition is an important research direction in the field of computer vision and pattern recognition.The complexity of human behavior and the variety of action performing make behavior recognition still as a challenging subject.With the new generation of sensing technology,RGB-D cameras can simultaneously record RGB images,depth images,and extract skeleton information from depth images in real time.How to take advantages of above information has become the new hotspot and breakthrough point of behavior recognition research.This paper presented a new feature extraction method based on Gaussian weighted pyramid histograms of orientation gradients for RGB images,and built an action recognition framework fusing multiple features.The feature extraction method and the framework proposed in this paper were researched on three databases：UTKinect-Action3D,MSR-Action 3D and Florence 3D Actions.The results indicate that the proposed action recognition framework achieves the accuracy of 97.5%,93.1%,91.7% respectively.It shows the effectiveness of the proposed action recognition framework.

关 键 词：行为识别 特征融合 高斯加权 梯度直方图 稀疏表示分类器 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]