Recognition of Human Action and Identification Based on SIFT and Watermark
详细信息 查看全文
- 作者：Khawlah Hussein Ali (22)
Tianjiang Wang (22) - 关键词：action recognition ; water mark ; SIFT ; K ; mean ; PCA
- 刊名：Lecture Notes in Computer Science
- 出版年：2014
- 出版时间：2014
- 年：2014
- 卷：8589
- 期：1
- 页码：298-309
- 全文大小：895 KB
- 参考文献：1. Zhang, Z., Jia, L.: Recognizing Human and Identity Based on Affine-SIFT. In: IEEE Symposium on Electrical & Electronics Engineering (2012)
2. Fabio, C.: Using Bilinear Models for View-invariant Action and Identity Recognition. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR 2006), New York, NY, vol.聽2 (June 2006)
3. khamis., S., Morariu, V.I., Larry, S.D.: A Flow Model for Joint Action Recognition and Identity Maintenance. In: IEEE (2012)
4. Langelaar, G., Setyawan, I., Lagendijk, R.: Watermarking Digital Image and Video Data. IEEE Signal Processing Magazine聽17, 20鈥?3 (2000) CrossRef
5. Meerwald, P., Uhl, A.: A Survey of Wavelet-domain Watermarking Algorithms. In: Proc. of SPIE, Electronics Imaging, Security and Watermarking of Multimedia Contents III, CA, USA (2001)
6. Wong, S.F., Cipolla, R.: Extracting Spatiotemporal Interest Points Using Global Information. In: Proc. of IEEE International Conference on Computer Vis ion (ICCV), pp. 1鈥? (2007)
7. Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised learning of Human Action Categories using Spatial-temporal Words. In: Proceedings of the British Machine Vision Conference, vol.聽79(3), pp. 299鈥?18 (2008)
8. Duchenne, O., Laptev, I., Sivic, J., Bach, F., Ponce, J.: Automatic Annotation of Human Actions in Video. In: Proceedings of the International Conference On Computer Vision (ICCV 2009), Kyoto, Japan (September 2009)
9. Lowe, D.G.: Distinctive Image Features from Scale Invariant Key Points. J. Computer Vision, IJCV聽60(2), 91鈥?10 (2004) CrossRef
10. Zhu, G., Xu, C., Gao, W., Qingming, H.: Using Optical Flow and Support Vector Machine. Springer, Berlin (2006)
11. Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as Space-time Shapes. In: ICCV (2005)
12. Enrique, F.M., Angel, S., Jose, V.: Support Vector Machines Versus Multi-layer Perceptron for Efficient Off-line Sig-nature Recognition. In: Biometry and Artificial Vision Group(GAVAP), Madrid, Spain,
13. Xiaojun, Q.: An Efficient Wavelet-Based Watermarking Algorithm, Xiaojun.Qi@usu.edu
14. Gao, R.: Dynamic Feature Description in Human Action Recognition. M.Sc. Computer Science (2009)
15. Agreste, S., Guido, A., Daniela, P., Luigia, P.: An Image Adaptive, Wavelet-based Watermarking of Digital Images. J. of Computational and Applied Mathematics聽210 (2007)
16. Lai, K.-T., Hsieh, C.-H., Lai, M.-F., Chen, M.-S.: Human Action Recognition Using Key Points Displacement. In: Elmoataz, A., Lezoray, O., Nouboud, F., Mammass, D., Meunier, J. (eds.) ICISP 2010. LNCS, vol.聽6134, pp. 439鈥?47. Springer, Heidelberg (2010) CrossRef
17. Moussa, M.M., Fayek, M.B., Heba, A., Nemr, E.: An Enhanced Method for Human Action Recognition. Journal of Advanced Research (2013)
18. Lian, Z., Godil, A., Sun, X.: Visual Similarity Based 3D Shape Retrieval Using Bag-of-Features. In: IEEE Proceedings of the Shape Modeling International Conference (2010)
19. Sipiran, I., Bustos, B.: A Robust 3D Interest Points Detector Based on Harris Operator. Presented at the Proc. Euro-graphics Workshop on 3D Object Retrieval (3DOR 2010) (2010)
20. Schuldt, C., Laptev, I., Caputo, B.: Recognize Human Actions Local SVM Approach. In: IEEE Int. Conf. ICPR, vol.聽3, pp. 32鈥?6 (2004)
21. Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior Recognition via Sparse Spatio-temporal Features. In: IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, pp. 65鈥?2 (2005)
22. Klaser, A., Marszaek, M., Schmid, C.: A Spatio-temporal Descriptor Based on 3D-Gradients. In: British Mach Vision Conf. BMVC (2008)
23. Zhang, Z., Hu, Y., Chan, S., Chia, L.-T.: Motion Context: A New Representation for Human Action Recognition. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol.聽5305, pp. 817鈥?29. Springer, Heidelberg (2008) CrossRef
24. Chang, C., Lin, C.: LIBSVM: A Library for Support Vector Machines. ACM Trans. Intell. Syst. Technol. TIST (2011)
25. Fathi, A., Mori, G.: Action Recognition by Learning Mid-level Motion Features. In: Conference of CVPR IEEE (2008)
26. Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: Actions as Space-time Shapes. In: ICCV IEEE (2005)
27. Ke, Y., Sukthanka, R., Hebert, M.: Efficient Visual Event Detection Using Volumetric Features. In: ICCV IEEE (2005)
28. Sheikh, Y., Sheikh, M., Shah, M.: Exploring the space of a human action. In: ICCV IEEE, pp. 144鈥?49 (2005)
29. Chen, M.Y., Hauptmann, A.: MoSIFT: Recognizing human actions in surveillance videos. In: Technological Report. Carnegie Mellon University (2009) - 作者单位：Khawlah Hussein Ali (22)
Tianjiang Wang (22)
22. Huazhong University of Science and Technology, Wuhan, Hubei, China - ISSN：1611-3349
文摘
This paper presents a fast and simple method for action recognition and identity at the same time. A watermark embedding as a 2-D wavelet in the training data at the first step to identify the identity of who makes the action. The proposed technique relies on detecting interest points using SIFT (scale invariant feature transform) from each frame of the video for action recognition. More specifically, we propose an action representation based on computing a rich set of descriptors from 2D-SIFT key points. Since most previous approaches to human action recognition typically focus on action classification or localization, these approaches usually ignore the information about human identity. A compact yet discriminative semantics visual vocabulary was built by a K-means for high-level representation. Finally a multi class linear Support Vector Machine (SVM) is utilized for classification. Our algorithm can not only categorize human actions contained in the video, but also verify the person who performs the action. We test our algorithm on three datasets: the KTH human motion dataset, Weizmann and our action dataset. Our results reflect the promise of our approach.