沈阳航空航天大学学报2017，Vol.34Issue(2)：55-65,11.DOI:10.3969/j.issn.2095-1248.2017.02.010
基于多特征融合的动作识别方法
Multi-feature-fusion based human action recognition method
摘要
Abstract
This paper proposed a novel action recognition method based on multi-feature fusion.In this method,the spatial-temporal features and depth features were merged in a random forest framework.The human body joint coordinates obtained from depth image sequences were processed into displacement feature and part-center feature as two new depth features.We applied these two depth features to describe the three-dimension structure of human.We densely sampled the trajectories from RGB image sequences,and utilized the foreground detection approach to reduce the effect of complex background.Then spatial-temporal features were constructed by the Bag-of-Words model with trajectories from the foreground.Finally,the robust random forest framework fused both the spatial-temporal features and the depth features for recognizing human actions in RGB-D image sequences.Experimental results on MSR Daily Activity 3D dataset demonstrated the effectiveness of the proposed method.关键词
人的动作识别/特征融合/随机森林Key words
human action recognition/multi-feature fusion/random forest分类
信息技术与安全科学引用本文复制引用
石祥滨,李菲,刘翠微..基于多特征融合的动作识别方法[J].沈阳航空航天大学学报,2017,34(2):55-65,11.基金项目
国家自然科学基金(项目编号:61170185,61602320) （项目编号:61170185,61602320）
辽宁省博士启动基金(项目编号:201601172) （项目编号:201601172）
辽宁省教育庁一般项目(项目编号:L201607,L2014070) （项目编号:L201607,L2014070）
沈阳航空航天大学校博士启动基金项目(项目编号:15YB37) （项目编号:15YB37）
