Learning contrastive feature distribution model for interaction recognition

被引:47
作者
Ji, Yanli [1 ]
Cheng, Hong [1 ]
Zheng, Yali [1 ]
Li, Haoxin [1 ]
机构
[1] UESTC, Ctr Robot, Sch Automat Engn, Chengdu, Peoples R China
关键词
Interaction recognition; CFDM; Contrast mining; CR-UESTC database; SBU database; Human skeleton; Action recognition; HRI; REPRESENTATION;
D O I
10.1016/j.jvcir.2015.10.001
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we learn a Contrastive Feature Distribution Model (CFDM) for interaction recognition. Our contributions are three-folded. First of all, we introduce an intra-inter-frame skeleton feature for interaction description. Secondly, we learn CFDM for a discriminative representation of interactions. In this step, we mine contrastive features to create a dictionary, and learn the probability distribution of dictionary words to construct CFDM in positive and negative training samples. With CFDM, we represent interactions in a discriminative way for recognition. Since there is few skeleton based interaction databases now, we capture a new database, CR-UESTC, which is the third contribution. We evaluate the proposed CFDM approach on CR-UESTC and SBU interaction databases, and compare the result of CFDM with the CM and the BoW approach. The comparison indicates that the recognition accuracy of three approaches is: CFDM > CM > BoW. Compared with Yun et al. (2012), the proposed CFDM also obtain a better result on SBU database. (C) 2015 Elsevier Inc. All rights reserved.
引用
收藏
页码:340 / 349
页数:10
相关论文
共 30 条
[1]  
Alazrai R., 2015, PATTERN RECOGN, V48, P2761
[2]  
[Anonymous], P BMVC
[3]  
[Anonymous], P CVPR
[4]  
[Anonymous], 2005, P CVPR
[5]  
[Anonymous], P ICCV
[6]   An adaptable system for RGB-D based human body detection and pose. estimation [J].
Buys, Koen ;
Cagniart, Cedric ;
Baksheev, Anatoly ;
De Laet, Tinne ;
De Schutter, Joris ;
Pantofaru, Caroline .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2014, 25 (01) :39-52
[7]  
DONG G, 1999, P ACM SIGKDD
[8]   Human interaction representation and recognition through motion decomposition [J].
Du, Youtian ;
Chen, Feng ;
Xu, Wenli .
IEEE SIGNAL PROCESSING LETTERS, 2007, 14 (12) :952-955
[9]  
Ji Y., 2014, P ICME WORKSH
[10]   Contribution estimation of participants for human interaction recognition [J].
Ji, Yanli ;
Shimada, Atsushi ;
Nagahara, Hajime ;
Taniguchi, Rin-ichiro .
IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING, 2013, 8 (03) :269-276