Abstract
Ship tracking plays a key role in inland waterway closed circuit television (CCTV) video surveillance. Although much success has been demonstrated in the construction of effective appearance model, numerous issues remain to be addressed due to factors such as pose and illumination change, partial or full occlusion, abrupt scale variation and motion blur. In this paper, we firstly inherit the intrinsical merits of subspace representation which demonstrates robustness to partial or full occlusion, pose and illumination variation. A very sparse measurement matrix is adopted to extract the features for the appearance model. A naive Bayes classifier with online update is employed to determine whether the image patch belongs to the foreground or background. Secondly, in order to increase the randomness of the random projection matrix and further reduce memory load, we develop our ship appearance model based on fern features in the compressed domain. Thirdly, we track the scale by enhancing the tracker with a mechanism of feedback. Finally, both qualitative and quantitative evaluations on numerous challenging CCTV videos demonstrate that the proposed algorithm achieves favorable performance in terms of efficiency and accuracy.
Similar content being viewed by others
References
Coudert, F.: Towards a new generation of CCTV networks: erosion of data protection safeguards? Comput. Law Secur. Rev. 25(2), 145–154 (2009)
Dadashi, N., Stedmon, A.W., Pridmore, T.P.: Semi-automated CCTV surveillance: the effects of system confidence, system accuracy and task complexity on operator vigilance, reliance and workload. Appl. Ergon. 44(5), 730–738 (2013)
Davies, A.C., Velastin, S.A.: A progress review of intelligent CCTV surveillance systems. In: IDAACS, Institute of Electrical and Electronics Engineers Inc., Sofia, Bulgaria, pp. 417–423 (2005)
Babenko, B., Yang, M.H., Belongie, S.: Robust object tracking with online multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell. 33(8), 1619–1632 (2011)
Teng, F., Liu, Q., Gao, X.Y., Zhu, L.: Real-time ship tracking via enhanced MIL tracker. In: IETET, Conference Publishing System, Kurukshetra, India, pp. 399–404 (2013)
Kalal, Z., Mikolajczyk, K., Matas, J.: Tracking-learning-detection. IEEE Trans. Pattern Anal. Mach. Intell. 34(7), 1409–1422 (2012)
Koohzadi, M., Keyvanpour, M.: OTWC: an efficient object-tracking method. Signal Image Video Process 1–13 (2013). doi:10.1007/s11760-013-0557-8
Zhang, S., Qi, Z., Zhang, D.: Ship tracking using background subtraction and inter-frame correlation. In: CISP (2009). doi:10.1109/CISP.2009.5302115
Shan, D.J., Zhang, C.: Visual tracking using IPCA and sparse representation. Signal Image Video Process 1–9 (2013). doi:10.1007/s11760-013-0525-3
Sheng, G., Yang, W., Yu, L., Sun, H.: Cluster structured sparse representation for high resolution satellite image classification. In: ICSP, Institute of Electrical and Electronics Engineers Inc., Beijing, China, pp. 693–696 (2012)
Julazadeh, A., Marsousi, M., Alirezaie, J.: Classification based on sparse representation and Euclidian distance. In: VCIP, IEEE Computer Society, San Diego, CA, United states, pp. 1–5 (2012)
Mahoor, M.H., Mu, Z., Veon, K.L., Mavadati, S.M., Cohn, J.F.: Facial action unit recognition with sparse representation. In: FG, IEEE Computer Society, Santa Barbara, CA, United states, pp. 336–342 (2011)
Wang, Z., Huang, M., Ying, Z.: The performance study of facial expression recognition via sparse representation. In: ICMLC, IEEE Computer Society, Qingdao, China, pp. 824–827 (2010)
Zhang, S., Yao, H., Sun, X., Lu, X.: Sparse coding based visual tracking: review and experimental comparison. Pattern Recognit. 46(7), 1772–1788 (2013)
Liu, B., Huang, J., Yang, L., Kulikowsk, C.: Robust tracking using local sparse appearance model and K-selection. In: CVPR, IEEE Computer Society, Colorado Springs, CO, United States, pp. 1313–1320 (2011)
Zhang, S., Yao, H., Lu, X.: Robust visual tracking using feature-based visual attention. In: ICASSP, Institute of Electrical and Electronics Engineers Inc., Dallas, TX, United states, pp. 1150–1153 (2010)
Gai, S., Yang, G., Wan, M.: Employing quaternion wavelet transform for banknote classification. Neurocomputing 118, 171–178 (2013)
Gai, S., Yang, G., Zhang, S.: Multiscale texture classification using reduced quaternion wavelet transform. AEU Int. J. Electron. Commun. 67(3), 233–241 (2013)
Zhang, K., Zhang, L., Yang, M.H.: Real-time compressive tracking. In: ECCV, Springer Verlag, Florence, Italy, pp. 864–877 (2012)
Achlioptas, D.: Database-friendly random projections: Johnson–Lindenstrauss with binary coins. J. Comput. Syst. Sci. 66(4), 671–687 (2003)
Chang, L., Wu, J.: Achievable angles between two compressed sparse vectors under norm/distance constraints imposed by the restricted isometry property: a plane geometry approach. IEEE Trans. Inf. Theory 59(4), 2059–2081 (2013)
Li, H., Shen, C. Shi, Q.: Real-time visual tracking using compressive sensing. In: CVPR, IEEE Computer Society, Colorado Springs, CO, United States, pp. 1305–1312 (2011)
Liu, L., Fieguth, P.: Texture classification from random features. IEEE Trans. Pattern Anal. Mach. Intell. 34(3), 574–586 (2012)
Acknowledgments
The authors would like to thank the editor and reviewers for their valuable comments and suggestions that lead to an improved manuscript. This work is supported by the National Science Foundation of China (NSFC 51279152).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Teng, F., Liu, Q. Multi-scale ship tracking via random projections. SIViP 8, 1069–1076 (2014). https://doi.org/10.1007/s11760-014-0629-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-014-0629-4