VIEW-ROBUST HUMAN ACTION RECOGNITION BASED ON SPATIO-TEMPORAL SELF SIMILARITIES

Authors:

K. Pradeep Reddy,G. Apparao Naidu,B Vishnu Vardhan,

DOI NO:

https://doi.org/10.26782/jmcms.2020.01.00010

Keywords:

Computer Vision,Human Action Recognition,Multiple Views,Self- Similarity Matrix,Gaussian,Gabor,Wavelet,Accuracy,

Abstract

Multi-View Human Action Recognition, as a hot research area in computer vision, has many more applications in various fields. Despite its popularity, more precise recognition still remains a major challenge due to various constraints. Extracting the robust and discriminative feature from video sequence is a crucial step in the Human Action Recognition system. In this paper, a new feature extraction technique is proposed based on the integration of three different features such as intensity, Orientation and Contour features. Unlike the earlier approaches which applied feature extraction directly over actions videos, this approach applies the feature extraction only over key frames which are extracted from a large set of frames. The key frames selection is accomplished based on a new mechanism, called Gradient Self-Similarity Matrix (GSSM). GSSM is proposed as an extension to the most popular Self-Similarity Matrix (SSM) by evaluating the gradients of actions frames before SSM accomplishment. Once the key frames are extracted, the hybrid feature extraction mechanism is applied and the obtained features are processed for classification through Support Vector Machine Classifier. The proposed framework is systematically evaluated on IXMAS dataset and NIXMAS dataset. Experimental results enumerate that our method outperforms the conventional techniques in terms of recognition accuracy.

Refference:

I. Aryanfar, R. Yakob, and A. A. Halin, “Multi-View Human Action
recognition Using Wavelet data Reduction and Multi-class Classification”,
In: Prof. of international Conf. on Soft Computing and Software Engineering,
Berkeley, Suta, pp.585-592, 2015.
II. A. Cohen, I. Daubechies, and J. Feauveau, “Bi-orthogonal bases of compactly
supported wavelets”, Communications and Pure Applied Mathematics., Vol.
45, No. 5, pp. 485–560, 1992
III. A. Eweiwi, M.S. Cheema, C. Bauckhage, J. Gall, Efficient pose-based action
recognition, in: Asian Conference on Computer Vision, Springer, 2014, pp.
428–443.
IV. A. Farhadi and M. K. Tabrizi, “Learning to recognize activities from the A.
wrong view point,” in Proc. Eur. Conf. Comput. Vis., 2008, pp. 154–166.
V. A. Gilbert, J. Illingworth, and R. Bowden, “Scale invariant action recognition
using compound features mined from dense Spatio-temporal corners,” in
Proc. ECCV, 2008, pp. I: 222–233.
VI. C. H. Lampert, H. Nickisch, S. Harmeling. Learning to detect unseen object
classes by between-class attribute transfer. In CVPR, 2009.
J. Mech. Cont.& Math. Sci., Vol.-15, No.-1, January (2020) pp 128-146
Copyright reserved © J. Mech. Cont.& Math. Sci.
K. Pradeep Reddy et al
144
VII. C. Rao, A. Yilmaz, and M. Shah, View-invariant representation and
recognition of actions, Int. J. Comput. Vis., vol. 50, no. 2, pp. 203–226, 2002.
VIII. C. Schuldt, I. Laptev, and B. Caputo, ‘‘Recognizing human actions: A local
SVM approach,’’ in Proc. 17th Int. Conf. Pattern Recognit., vol. 3. Aug.
2004, pp. 32–36.
IX. D. Weinland, E. Boyer, and R. Ronfard, “Action recognition from arbitrary
views using 3D exemplars,” in Proc. IEEE Int. Conf. Comput. Vis., Oct.
2007, pp. 1–7.
X. D. Weinland, M. Özuysal, and P. Fua, “Making action recognition robust to
occlusions and viewpoint changes,” in Proc. 11th Eur. Conf. Comput. Vis.,
2010, pp. 635–648.
XI. E. Shechtman and M. Irani. Matching local self-similarities across images
and videos. In CVPR, 2007.
XII. H. Wang, A. Klaser, C. Schmid, and C. Liu, “Action recognition by dense
trajectories,” in Computer Vision and Pattern Recognition (CVPR), 2011
IEEE Conference on. IEEE, 2011, pp. 3169–3176.
XIII. I. Junejo, “Self-similarity based action recognition using conditional random
fields,” in Information Retrieval Knowledge Management (CAMP), 2012
International Conference on, march 2012, pp. 254 –259.
XIV. I. N. Junejo, E. Dexter, I. Laptev, and P. Perez, “View-independent action
recognition from temporal self-similarities,” IEEE Transactions on Pattern
Analysis and Machine Intelligence, vol. 99, no. PrePrints, 2010.
XV. Ivo Everts, Jan C. van Gemert and Theo Gevers, Evaluation of Color STIPs
for Human Action Recognition, IEEE Conference on Computer Vision and
Pattern Recognition, Portland, OR, USA, 2013.
XVI. Jing Wang, and Huicheng Zheng, “View-robust action recognition based on
temporal self-similarities and dynamic time warping”, IEEE International
Conference on Computer Science and Automation Engineering (CSAE),
Zhangjiajie, China, 2012.
XVII. J. Wang, Z. Chen, and Y. Wu, “Action recognition with multiscale Spatiotemporal
contexts,” in Computer Vision and Pattern Recognition (CVPR),
2011 IEEE Conference on. IEEE, 2011, pp. 3185–3192.
XVIII. K. Chatfield, J. Philbin, and A. Zisserman. Efficient retrieval of deformable
shape classes using local self-similarities. In NORDIA Workshop at ICCV
2009, 2009.
XIX. K. G. C. Manosha, Ranga Rodrigo, Faster Human Activity Recognition with
SVM, The International Conference on Advances in ICT for Emerging
Regions – ICTER 2012 : 197-203.
XX. K. Huang, Y. Zhang, and T. Tan, “A discriminative model of motion and
cross ratio for view-invariant action recognition,” Image Processing, IEEE
Transactions on, vol. 21, no. 4, pp. 2187–2197, 2012.
XXI. K. Pradeep Reddy, G. Apparao Naidu, B.VishnuVardhan, “View-Invariant
Feature Representation for Action Recognition under Multiple Views”,
International Journal of Intelligent Engineering and Systems, Vol.12, No.6,
2019.
J. Mech. Cont.& Math. Sci., Vol.-15, No.-1, January (2020) pp 128-146
Copyright reserved © J. Mech. Cont.& Math. Sci.
K. Pradeep Reddy et al
145
XXII. L. Gorelick, M. Blank, E. Shechtman, M. Irani, and R. Basri, “Actions as
space-time shapes,” PAMI, vol. 29, no. 12, pp. 2247–2253, December 2007.
XXIII. M. Abd-el-Kader, W. Abd-Almageed, A. Srivastava, and R. Chellappa,
“Silhouette-based gesture and action recognition via modeling trajectories on
Riemannian shape manifolds,” CVIU, vol. 115, no. 3, pp. 439–455, 2011.
XXIV. M. Everingham, L. Van Gool, C. Williams, J. Winn, and A. Zisserman. The
PASCAL Visual Object Classes Challenge 2007.
XXV. M. Stark, M. Goesele, and B. Schiele. A shape-based object class model for
knowledge transfer. In ICCV, 2009.
XXVI. Paul, S.N.; Singh, Y.J. Survey on Video Analysis of Human Walking
Motion. Int. J. Signal Process. Image Process. Pattern Recognit. 2014, 7, 99–
122.
XXVII. P. Matikainen, R. Sukthankar, and M. Hebert, “Feature seeding for action
recognition,” in Computer Vision (ICCV), 2011 IEEE International
Conference on. IEEE, 2011, pp. 1716–1723.
XXVIII. Q. Le, W. Zou, S. Yeung, and A. Ng, “Learning hierarchical invariant Spatiotemporal
features for action recognition with independent subspace analysis,”
in CVPR. IEEE, 2011, pp. 3361–3368.
XXIX. R. Poppe, A survey on vision-based human action recognition, Image Vision
Comput. 28 (6) (2010) 976–990.
XXX. SamySadek, Ayoub Al-Hamadi, Bernd Michaelis, and UsamaSayed, “An
Action Recognition Scheme Using Fuzzy Log-Polar Histogram and
Temporal Self-Similarity”, Hindawi Publishing Corporation EURASIP
Journal on Advances in Signal Processing, Volume 2011, Article ID 540375,
9 pages.
XXXI. S. Maji, L. Bourdev, and J. Malik, “Action recognition from a distributed
representation of pose and appearance,” in Computer Vision and Pattern
Recognition (CVPR), 2011 IEEE Conference on. IEEE, 2011, pp.3177–3184.
XXXII. S. Singh, S. A. Velastin, and H. Ragheb, ‘‘MuHAVi: A multi-camera human
action video dataset for the evaluation of action recognition methods,’’ in
Proc. 17th IEEE Int. Conf. Adv. Video Signal Based Surveill. (AVSS), Sep.
2010, pp. 48–55.
XXXIII. Stephen Karungaru, Masayuki Daikoku, Kenji Terada, “Multi Cameras
Based Indoors Human Action Recognition Using Fuzzy Rules”, JPRR Vol
10, No 1 (2015).
XXXIV. S. Vishwakarma, A. Agrawal, A survey on activity recognition and behavior
understanding in video surveillance, Visual Computer 29 (10) (2013) 983–
1009
XXXV. S. Wu, O. Oreifej, and M. Shah, “Action recognition in videos acquired by a
moving camera using motion decomposition of Lagrangian particle
trajectories,” in Computer Vision (ICCV), 2011 IEEE International
Conference on. IEEE, 2011, pp. 1419–1426.
XXXVI. T. Deselaers and V. Ferrari, “Global and efficient self-similarity for object
classification and detection,” in Computer Vision and Pattern Recognition
(CVPR), 2010 IEEE Conference on. IEEE, 2010, pp. 1633–1640.
J. Mech. Cont.& Math. Sci., Vol.-15, No.-1, January (2020) pp 128-146
Copyright reserved © J. Mech. Cont.& Math. Sci.
K. Pradeep Reddy et al
146
XXXVII. T. SyedaMahmood, M. Vasilescu, and S. Sethi, Recognizing action events
from multiple viewpoints, in Proc. EventVideo, 2001, pp. 64–72.
XXXVIII. X. Wu, D. Xu, L. Duan, and J. Luo, “Action recognition using context and
appearance distribution features,” in CVPR 2011. IEEE, 2011, pp. 489–496.
XXXIX. Yen-Pin HsuChengyin Liu Tzu-Yang Chen Li-Chen Fu, “Online viewinvariant
human action recognition using RGB-D Spatio-temporal matrix”,
Pattern recognition, Volume 60, December 2016, Pages 215-226.

View Download