[1]JI Xiaofei,WANG Changhui,WANG Yangyang.Human interaction behavior-recognition method based on hierarchical structure[J].CAAI Transactions on Intelligent Systems,2015,10(6):893-900.[doi:10.11992/tis.201505006]
Copy

Human interaction behavior-recognition method based on hierarchical structure

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 10 Number of periods: 2015 6 Page number: 893-900 Column: 学术论文—机器感知与模式识别 Public date: 2015-12-25
Title:
Human interaction behavior-recognition method based on hierarchical structure
Author(s):
JI Xiaofei;  WANG Changhui;  WANG Yangyang
School of Automation, Shenyang Aerospace University, Shenyang 110136, China
Keywords:
computer vision; human interaction; action recognition; histogram of oriented gradient; layered model; nearest neighbor classifier; ut-interaction database; weighted fusion
CLC:
TP391.4
DOI:
10.11992/tis.201505006
Abstract:
To solve the problem of double interaction behavior recognition, in this paper we propose a novel interaction behavior-recognition method based on hierarchical structure. First, the interactive behavior of both areas of body contact is determined as the cut-off point. The interaction process is then divided into three stages-the start, execution, and end stages. We extract the left and right human body regions in the start and end stages, respectively. Both human body regions are extracted as a whole in the execute stage. Next, we utilize a histogram of oriented gradients(HOG) descriptor to describe information on the regions of interest of each stage. Thereafter, we use the nearest neighbor classifier to obtain the recognition probability of each object in each stage. Finally, we obtain the recognition result from the weighted fusion of this recognition probability. The experimental results, using the UT-interaction dataset, demonstrate that the proposed approach is easy to implement and has good recognition effect.
References:
[1] WEINLAND D, RONFARD R, BOYER E. A survey of vision-based methods for action representation, segmentation and recognition[J]. Computer Vision and Image Understanding, 2011, 115(2):224-241.
[2] SEO H J, MILANFAR P. Action recognition from one example[J]. IEEE Transactions on pattern Analysis and Machine Intelligence, 2011, 33(5):867-882.
[3] 吴联世, 夏利民, 罗大庸. 人的交互行为识别与理解研究综述[J]. 计算机应用与软件, 2011, 28(11):60-63. WU Lianshi, XIA Limin, LUO Dayong. Survey on human interactive behaviour recognition and comprehension[J]. Computer Applications and Software, 2011, 28(11):60-63.
[4] YU Gang, YUAN Junsong, LIU Zicheng. Propagative hough voting for human activity recognition[C]//Proceedings of the 12th European Conference on Computer Vision, Florence, Italy. Berlin Heidelberg:Springer, 2012:693-706.
[5] YU T H, KIM T K, CIPOLLA R. Real-time action recognition by spatiotemporal semantic and structural forests[C]//Proceedings of the 21st British Machine Vision Conference. United Kingdom, 2010:1-12.
[6] YUAN Fei, SAHBI H, PRINET V. Spatio-temporal context kernel for activity recognition[C]//Proceedings of the 1st Asian Conference on Pattern Recognition. Beijing, China, 2011:436-440.
[7] BURGHOUTS G J, SCHUTTE K. Spatio-temporal layout of human actions for improved bag-of-words action detection[J]. Pattern Recognition Letters, 2013, 34(15):1861-1869.
[8] LI Nijun, CHENG Xu, GUO Haiyan,et al. A hybrid method for human interaction recognition using spatio-temporal interest points[C]//Proceedings of the 22nd International Conference on Pattern Recognition. Stockholm, Sweden, 2014:2513-2518.
[9] KONG Yu, JIA Yunde, FU Yun. Interactive phrases:semantic descriptions for human interaction recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(9):1775-1788.
[10] SLIMANI K, BENEZETH Y, SOUAMI F. Human interaction recognition based on the co-occurrence of visual words[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops. Columbus, Ohio, USA, 2014:461-466.
[11] JIANG Zhuolin, LIN Zhe, DAVIS L S. Recognizing human actions by learning and matching shape-motion prototype trees[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(3):533-547.
[12] JI Xiaofei, ZHOU Lu, LI Yibo. Human action recognition based on adaboost algorithm for feature extraction[C]//Proceedings of 2014 IEEE International Conference on Computer and Information Technology. Xi’an, China, 2014:801-805.
[13] RYOO M S, AGGARWAL J K. Spatio-temporal relationship match:Video structure comparison for recognition of complex human activities[C]//Proceedings of the IEEE International Conference on Computer Vision. Kyoto, Japan, 2009:1593-1600.
[14] KONG Y, LIANG W, DONG Z, et al. Recognising human interaction from videos by a discriminative model[J]. Institution of Engineering and Technology Computer Vision, 2014, 8(4):277-286.
[15] PATRON-PEREZ A, MARSZALEK M, REID I, et al. Structured learning of human interactions in TV shows[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(12):2441-2453.
[16] MUKHERJEE S, BISWAS S K, MUKHERJEE D P. Recognizing interaction between human performers using "key pose doublet"[C]//Proceedings of the 19th ACM International Conference onMultimedia. Scottsdale, AZ, United states, 2011:1329-1332.
[17] BRENDEL W, TODOROVIC S. Learning spatiotemporal graphs of human activities[C]//Proceedings of the IEEE International Conference on Computer Vision. Barcelona, Spain, 2011:778-785.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems