Object Tracking Using Features Extracted From Compressed Domain

International Journal of Computer Trends and Technology (IJCTT)          
© 2015 by IJCTT Journal
Volume-30 Number-2
Year of Publication : 2015
Authors : Miss. Pratiksha R.Bhalekar, Ms. Vaishali Suryawanshi


Miss. Pratiksha R.Bhalekar, Ms. Vaishali Suryawanshi "Object Tracking Using Features Extracted From Compressed Domain". International Journal of Computer Trends and Technology (IJCTT) V30(2):75-80, December 2015. ISSN:2231-2803. www.ijcttjournal.org. Published by Seventh Sense Research Group.

Abstract -
It is a challenging task to develop effective and efficient models for robust object tracking due to factors such as pose variation, illumination changes, occlusion, and movement obscure. Our methodology is Object tracking using features extracted from Compressed Domain. Features are extracted from the compressed domain with a Discrete Cosine Transform. We pack test of pictures of the frontal range target and the establishment using the same Discrete Cosine Transform. The system can be considered as generative because the target can be well represented theoretically with the features generated randomly. It is additionally discriminative since it utilizes these features to discrete the objective from the encompassing foundation. Calculating similarity measure utilizing Euclidian distance. Position tracking after is similarly done using Euclidian separation. These tracking results are compared with mean shift tracking.

[1] He, Yan, et al. "An improved real-time compressive tracking method." Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service. ACM, 2013.
[2] Yilmaz, Alper, Omar Javed, and Mubarak Shah. "Object tracking: A survey."Acm computing surveys (CSUR) 38.4 (2006): 13.
[3] Zhang, Kaihua, Lei Zhang, and Ming-Hsuan Yang. "Real-time compressive tracking." Computer Vision–ECCV 2012. Springer Berlin Heidelberg, 2012. 864-877.
[4] Kekre, H. B., Tanuja K. Sarode, and M. S. Ugale. "An efficient image classifier using discrete cosine transform." Proceedings of the International Conference & Workshop on Emerging Trends in Technology. ACM, 2011.
[5] http://en.wikipedia.org/wiki/ Discrete Cosine Transform.
[6] Horprasert, Thanarat, David Harwood, and Larry S. Davis. "A statistical approach for real-time robust background subtraction and shadow detection." IEEE ICCV. Vol. 99. 1999.
[7] http://en.wikipedia.org/wiki/Euclidean_distance.
[8] Bashir, Faisal, and Fatih Porikli. "Performance evaluation of object detection and tracking systems." IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS). Vol. 5. 2006.
[9] COMANICIU, D. AND MEER, P. 1999. Mean shift analysis and applications. In IEEE International Conferenceon Computer Vision (ICCV). Vol. 2. 1197–1203.
[10] http://en.wikipedia.org/wiki/Scale invariant_feature_transform [12] S.-B. Cho and J.-Y. Lee, “A human-oriented image retrieval system using interactive genetic algorithm,” IEEE Trans. Syst., Man, Cybern. A,Syst.,Humans, vol. 32, no. 3, pp. 452–458, May 2002.
[11] G. David Lowe. Object recognition from local scale-invariant features. Proceedings ofthe International Conference on Computer Vision. 2. pp. 1150–1157,1997.
[12] Zhu, Chaoyang. "Video object tracking using SIFT and mean shift." (2011).
[13] Quast, Katharina, and André Kaup. "Shape adaptive mean shift object tracking using gaussian mixture models." Analysis, Retrieval and Delivery of Multimedia Content. Springer New York, 2013. 107-122.

Object Tracking, Discrete Cosine Transform (DCT), Background Subtraction Method, Euclidian distance, Scale Invariant Feature Transform (SIFT)