详细信息
文献类型:期刊文献
中文题名:基于RGB-D图像特征的人体行为识别
英文题名:Human Action Recognition Using RGB-D Image Features
作者:唐超[1];王文剑[2];张琛[1];彭华[3];李伟[4]
机构:[1]合肥学院人工智能与大数据学院,合肥230601;[2]山西大学计算机与信息技术学院,太原030006;[3]绍兴文理学院计算机科学与工程系,绍兴312000;[4]厦门理工学院计算机与信息工程学院,厦门361024
年份:2019
卷号:32
期号:10
起止页码:901
中文期刊名:模式识别与人工智能
外文期刊名:Pattern Recognition and Artificial Intelligence
收录:CSTPCD、、EI(收录号:20212010365289)、北大核心2017、Scopus(收录号:2-s2.0-85075273374)、CSCD2019_2020、北大核心、CSCD
基金:收稿日期:2019-06-15;录用日期:2019-09-16 Manuscript received June 15, 2019; accepted September 16, 2019 国家自然科学基金项目(No. 61673249,61806068,61662025)、 安徽高校优秀拔尖人才培育项目(No. gxfx2017099)、福建省 出国留学奖学金项目、厦门市科技规划指导项目(No.3502Z 20179038)、合肥学院教学研究重点项目(No. 018hfjyxm09) 资助 Supported by National Natural Science Foundation of China(No. 61673249,61806068,61662025), Excellent Talents Training Project of Universities of Anhui Province(No. gxfx2017099), Scholarship for Studying Abroad Program of Fujian, Science and Technology Planning Guidance Project of Xiamen ( No. 3502Z20179038), Key Teaching and Research Project of Hefei
语种:中文
中文关键词:人体动作识别;RGB-深度;多学习器;多模态特征;最近邻分类器
外文关键词:Human Action Recognition;RGB-Depth(RGB-D);Multiple Learner;Multimodal Feature;Nearest Neighbor Classifier
中文摘要:针对现有的多模态特征融合方法不能有效度量不同特征的贡献度的问题,文中提出基于RGB-深度(RGB-D)图像特征的人体动作识别方法.首先获取基于RGB模态信息的方向梯度直方图特征、基于深度图像模态信息的时空兴趣点特征和基于关节模态信息的人体关节点位置特征,分别表征人体动作.采用不同距离度量公式的最近邻分类器对这3种不同模态特征表示的预测样本进行集成决策分类.在公开数据集上的实验表明,文中方法具有简单、快速,高效的特点.
外文摘要:Since the existing multi-modal feature fusion methods cannot measure the contribution of different features effectively,a human action recognition method based on RGB-depth image features is proposed.Firstly,the histogram of oriented gradient feature based on RGB modal information,the space-time interest points feature based on depth modal information,and the joints relative position feature based on joints modal information are acquired to express human actions,respectively.Then,nearest neighbor classifiers with different distance measurement formulas are utilized to classify prediction samples expressed by the three modal features.The experimental results on public datasets show that the proposed method is simple,fast and efficient.
参考文献:
正在载入数据...