全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

视点无关的行为识别综述

DOI: 10.11834/jig.20130205

Keywords: 视点无关,行为识别,状态空间,降维,轨迹

Full-Text   Cite this paper   Add to My Lib

Abstract:

目前,基于视觉的人体的行为识别是一个非常活跃的研究领域。它在智能监控、感知接口和基于内容的视频检索等领域具有广泛的应用前景,然而,一些困难仍然减慢了行为识别的发展,比如现实场景中动作往往是从任意角度拍摄。因此与视点无关的行为识别就十分重要,大量的研究者开始致力于行为识别的视点无关性。对视点无关的姿态与运动识别进行了综述。从基于时空特征的方法,基于状态空间的方法,基于降维的方法和基于运动轨迹的方法4个方面分析了研究进展情况,并列举了视点无关行为识别的公共数据集,评价了目前的研究情况,并对未来的研究提出了展望。

References

[1]  Bobick A, Davis J. The recognition of human movement using temporal templates[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(3):257-267.
[2]  Yu H, Sun G, Song W, et al. Human motion recognition based on neural network[C]//Proceedings of International conference on Communications, Circuits and Systems. Hong Kong, China: IEEE, 2005,2:982-989.
[3]  Chen H, Chen H, Chen Y, et al. Human action recognition using star skeleton[C]//Proceedings of the 4th ACM International Workshop on Video Surveillance and Sensor Networks. Santa Barbara, CA, USA: ACM, 2006: 171-178.
[4]  Raytchev B, Kikutsugi Y, Tamaki T, et al. Class-specific low-dimensional representation of local features for viewpoint invariant object recognition[C]//Proceedings of ACCV. Queenstown, New Zealand: Springer, 2010: 250-261.
[5]  Srestasathiern P, Yilmaz A. View invariant object recognition[C]//Proceedings of 19th International Conference on Pattern Recognition. Tampa, Florida, USA: IEEE, 2008: 1-4.
[6]  Ashraf A, Lucey S, Chen T. Learning patch correspondences for improved viewpoint invariant face recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA: IEEE, 2008: 1-8.
[7]  Tian C, Fan G, Gao X. Multi-view face recognition by nonlinear tensor decomposition[C]//Proceedings of 19th International Conference on Pattern Recognition. Tampa, Florida, USA: IEEE, 2008: 1-4.
[8]  Jean F, Bergevin R, Albu A. Trajectories normalization for viewpoint invariant gait recognition[C]//Proceedings of 19th International Conference on Pattern Recognition. Tampa, Florida, USA: IEEE, 2008: 1-4.
[9]  Bremond F, Thonnat M, Zuniga M. Video understanding framework for automatic behavior recognition[J]. Behavior Research Methods, 2006, 38(3):416-426.
[10]  Luo Y, Wu T, Hwang J. Object-based analysis and interpretation of human motion in sports video sequences by dynamic bayesian networks[J].Computer Vision and Image Understanding, 2003, 92(2):196-216.
[11]  Mahmood T S, Vasilescu A, Sethi S. Recognizing action events from multiple viewpoints[C]//Proceedings of IEEE Workshop on Detection and Recognition of Events in Video. Vancouver, BC, Canada: IEEE, 2001: 64-72.
[12]  Yilmaz A, Shah M. Actions as objects: a novel action representation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA: IEEE,2005: 984-989.
[13]  Rao C, Yilmaz A, Shah M. View-invariant representation and recognition of actions[J]. International Journal of Computer Vision, 2002, 50(2):203-226.
[14]  Weinland D, Ronfard R, Boyer E. Free viewpoint action recognition using motion history volumes[J]. Computer Vision and Image Understanding, 2006, 104(2):249-257.
[15]  Roh M, Shin H, Lee S. View-independent human action recognition with volume motion template on single stereo camera[J]. Pattern Recognition Letters, 2010, 31(7):639-647.
[16]  Ferrer C C, Casas J R, Pardas M. Human model and motion based 3D action recognition in multiple view scenarios[C]//Proceedings of Conf. European Signal Process. Italy:, 2006: 1-5.
[17]  Yan P, Khan S, Shah M. Learning 4D action feature models for arbitrary view action recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA: IEEE, 2008: 1-7.
[18]  Natarajan P, Singh V, Nevatia R. Learning 3D action models from a few 2D videos for view invariant action recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, CA, USA: IEEE, 2010: 2006-2013.
[19]  Taylor C. Reconstruction of articulated objects from point correspondences in a single uncalibrated image[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Hilton Head Island, SC, USA: IEEE, 2000,1:677-684.
[20]  Wang Y, Huang K, Tan T. Multi-view gymnastic activity recognition with fused hmm[C]//Proceedings of Computer Vision-ACCV. Tokyo, Japan: Springer, 2007: 667-677.
[21]  更多...
[22]  Pan H, Levinson S, Huang T, et al. A fused hidden markov model with application to bimodal speech processing[J]. IEEE Transactions on Signal Processing, 2004, 52(3):573-581.
[23]  Frey B, Jojic N. Learning graphical models of images, videos and their spatial transformations[C]//Proceedings of the sixteenth Conference on Uncertainty in Artificial Intelligence. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc, 2000: 184-191.
[24]  Toyama K, Blake A. Probabilistic tracking in a metric space[C]//Proceedings of the 8 IEEE International Conference on Computer Vision. Vancouver, BC, Canada: IEEE, 2001, 2: 50-57.
[25]  Weinland D, Boyer E, Ronfard R. Action recognition from arbitrary views using 3d exemplars[C]//Proceedings of 11th International Conference on Computer Vision. Rio de Janeiro, Brazil: IEEE, 2007: 1-7.
[26]  Ahmad M, Lee S. Hmm-based human action recognition using multi-view image sequences[C]//Proceedings of 18th International Conference on Pattern Recognition. Hong Kong, China: IEEE, 2006, 1: 263-266.
[27]  Ogale A S, Karapurkar A, Guerra-filho G, et al. View-invariant identification of pose sequences for action recognition[C/OL]//Proceedings of VACE, 2004.[2012-9-22]. http://citeseerx.ist.psu.edu/viewdoc/summary?.doi=10.1.1.117.6884.
[28]  Ogale A, Karapurkar A, Aloimonos Y. View-invariant modeling and recognition of human actions using grammars[J]. Dynamical vision, 2007, 4358: 115-126.
[29]  Natarajan P, Nevatia R. View and scale invariant action recognition using multi-view shape-flow models [C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA: IEEE, 2008: 1-8.
[30]  Song Y, Morency L, Davis R. Multi-view latent variable discriminative models for action recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA: IEEE, 2012: 2120-2127.
[31]  Quattoni A, Wang S, Morency L P, et al. Hidden conditional random fields[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29:1848-1852.
[32]  Morency L, Quattoni A, Darrell T. Latent-dynamic discriminative models for continuous gesture recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, MN, USA: IEEE, 2007: 1-8.
[33]  Wold S, Esbensen K, Geladi P. Principal component analysis[J]. Chemometrics and Intelligent Laboratory Systems, 1987, 2(1):37-52.
[34]  Balakrishnama S, Ganapathiraju A. Linear discriminant analysis-a brief tutorial. Institute for Signal and Information Processing, 1998.. http://www.music.mcgill.ca/ich/classes/mumt611_07/classifiers/lda_theory.pdf.
[35]  Huang F, Xu G. Viewpoint insensitive action recognition using envelop shape[C]//Proceedings of the 8th Asian Conference on Computer Vision. Tokyo, Japan: Springer, 2007, 2:477-486.
[36]  Rogez G, Guerrero J, Martinez J, et al. Viewpoint independent human motion analysis in man-made environments[C]//Proceedings of British Machine Vision Conference.Edinburgh, United Kingdom:, 2006: 659-668.
[37]  Gkalelis N, Nikolaidis N, Pitas I. View indepedent human movement recognition from multi-view video exploiting a circular invariant posture representation[C]//Proceedings of IEEE International Conference on Multimedia and Expo. New York, NY, USA: IEEE, 2009: 394-397.
[38]  Ramagiri S, Kavi R, Kulathumani V. Real-time multi-view human action recognition using a wireless camera network[C]//Proceedings of fifth ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC). Ghent, Belguim: IEEE, 2011: 1-6.
[39]  Jia C, Wang S, Xu X, et al. Tensor analysis and multi-scale features based multi-view human action recognition//Proceedings of 2nd International Conference on Computer Engineering and Technology (ICCET). Chengdu, China: IEEE, 2010, 4: 60-64.
[40]  Peng B, Qian G, Rajko S. View-invariant full-body gesture recognition from video[C]//Proceedings of the 19th International Conference on Pattern Recognition. Tampa, FL, USA: IEEE, 2008: 1-5.
[41]  Weinland D, ?zuysal M, Fua P. Making action recognition robust to occlusions and viewpoint changes[C]//Proceedings of ECCV. Heraklion, Crete, Greece:Springer, 2010: 635-648.
[42]  Lewandowski M, Rincon J M, Makris D, et al. Temporal extension of laplacian eigenmaps for unsupervised dimensionality reduction of time series[C]//Proceedings of the 20th International Conference on Pattern Recognition. Istanbul, Turkey: IEEE, 2010: 161-164.
[43]  Balasubramanian M, Schwartz E. The isomap algorithm and topological stability[J]. Science, 2002, 295(5552):7.
[44]  Lewandowski M, Makris D, Nebel J. View and style-independent action manifolds for human activity recognition[C]//Proceedings of ECCV. Heraklion, Crete, Greece: Springer, 2010: 547-560.
[45]  Zhang J, Zhuang Y. View-independent human action recognition by action hyper sphere in nonlinear subspace[J]. Advances in Multimedia Information Processing-PCM, 2007: 108-117.
[46]  Law M, Jain A. Incremental nonlinear dimensionality reduction by manifold learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(3):377-391.
[47]  Rao C, Yilmaz A, Shah M. View-invariant representation and recognition of actions[J]. International Journal of Computer Vision, 2002, 50(2):203-226.
[48]  Zhou F, la Torre F D. Canonical time warping for alignment of human behavior[C]//Proceedings of Advances in Neural Information Processing Systems. Vancouver, BC, Canada: Curran Associates, Inc., 2009, 22: 2286-2294.
[49]  Yilma A, Shah M. Recognizing human actions in videos acquired by uncalibrated moving cameras[C]//Proceedings of 10th IEEE International Conference on Computer Vision. Beijing, China: IEEE, 2005, 1: 150-157.
[50]  Junejo I, Dexter E, Laptev I, et al. Cross-view action recognition from temporal self-similarities[C]//Proceedings of Computer Vision-ECCV. Marseille, France: Spinger, 2008: 293-306.
[51]  Junejo I, Dexter E, Laptev I, et al. View-independent action recognition from temporal self-similarities[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(1): 172-185.
[52]  Shen Y, Foroosh H. View-invariant recognition of body pose from space-time templates[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA: IEEE, 2008: 1-6.
[53]  Ashraf N, Shen Y, Foroosh H. View-invariant action recognition using rank constraint[C]//Proceedings of the 20th International Conference on Pattern Recognition. Istanbul, Turkey: IEEE, 2010: 3611-3614.
[54]  Shen Y, Foroosh H. View-Invariant Action Recognition Using Fundamental Ratios[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA: IEEE, 2008: 1-6.
[55]  Shen Y, Foroosh H. View-invariant action recognition from point triplets[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(10):1898-1905.
[56]  Weinland D.INRIA xmas motion acquisition sequences(IXMAS)[DB/OL]. (2008-1-22)[2012-9-29]. http://4drepository.inrialpes.fr/public/viewgroup/6.
[57]  Velastin S A. ViHASi: virtual human action silhouette data[DB/OL]. (2009-1-13)[2012-9-29]. http://dipersec.king.ac.uk/VIHASI/.
[58]  Kulathumani V.Wvu multi-view action recognition dataset[DB/OL].[2012-9-29]. http://csee.wvu.edu/vkkulathumani/wvu-action.html.
[59]  Velastin S A. MuHAVi: multicamera human action video data[DB/OL]. (2011-4-12)[2012-9-29]. http://dipersec.king.ac.uk/MuHAVi-MAS/.
[60]  Parameswaran V, Chellappa R. View invariance for human action recognition[J]. International Journal of Computer Vision, 2006, 66(1):83-101.
[61]  Parameswaran V, Chellappa R. Human action recognition using mutual invariants[J]. Computer Vision and Image Understanding, 2005, 98(2):294-324.
[62]  Ali S, Basharat A, Shah M. Chaotic invariants for human action recognition[C]//Proceedings of the 11th International Conference on Computer Vision. Rio de Janeiro, Brazil: IEEE, 2007: 1-8.
[63]  Gong D, Medioni G. Dynamic manifold warping for view invariant action recognition[C]//Proceedings of IEEE International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 571-578.
[64]  Listgarten J, Neal R M, Roweis S T, et al. Multiple alignment of continuous time series[J]. Advances in Neural Information Processing Systems, 2005,17:817-824.
[65]  Rao C, Gritaiand A, Shah M, et al. View-invariant alignment and matching of video sequences[C]//Proceedings of ICCV. Nice, France: IEEE, 2003: 939-945.
[66]  Van der Maaten L. Learning a parametric embedding by preserving local structure[J]. Journal of Machine Learning Research-Proceedings Track, 2009: 384-391.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133