Open Access Open Access  Restricted Access Subscription or Fee Access

Detection Tracking and Classification of Object in Forest Surveillance Video Footage

N. Bhuvaneswari, H. Mercy

Abstract


Object tracking is to find the state of the target object in the image sequence. It plays an important role in numerous applications like surveillance, recognition, motion analysis and user interface. Many improvements are made in recent years but the challenging problem is the illumination variation, camera motion, occlusion, shape variation and pose variation. A new proposed approach is provided for efficient object tracking using SDC classifier. This approach first split the given video into key frames, uses SDC classifier to split the frame into positive template and negative template and trained in the classifier after that occlusion in the frame is converted into 8*8 blocks. The SGM classifier uses batches for handling occlusions. When a new video is given as input the video is converted into frames and sent to the SDC classifier the classifier will test the input frame with the trained frame and produce the result. Dynamic appearance changes are also effectively handled by this system. In this we consider animal video to track the animal in the given video. This proposed method efficiently tracks the animals in the given frame when compared with other methods.


Full Text:

PDF

References


Wei Zhong, Huachuca Lu, Senior Member, and Ming-Husain Yang, Senior Member, “Robust Object Tracking via Sparse Collaborative Appearance Model” IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 23, NO. 5, MAY 2014.

D. Rosi, J. Lima, R.-S. Lin, and M.-H. Yang, “Incremental learning for visual tracking,” Int. J. Comput. Vis., vol. 77, nos. 1–3, pp. 125–141, 2008.

B.Babenko,M.-H.Yang, and S.Belongie, “Visual tracking with multiple instance learning,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jan. 2009, pp. 983 990.

B. Liu, L. Yang, J. Huang, P. Meer, L. Gong, and C. Kulikowski, “Robust and fast collaborative tracking using two stage sparse representation,” in Proc. 11th Eur. Conf. Comput. Vis., 2010, pp. 624–637.

Prajna Parimita Dash, Dipti patra, Sudhansu Kumar Mishra, Jagannath Sethi, “Kernel based Object Tracking using Color Histogram Technique” IEEE Conf. Comput.Vis. Pattern Recognit, Jun. 2010, pp. 723–730.

Michael J. Black and Allan D.Jepson, “Eigen Tracking” in Proc.IEEE Conf. CVPR, Jun. 2010, pp. 3555–3561.

J. Kwon and K. M. Lee, “Visual tracking decomposition” in Proc. IEEE Conf. CVPR, Jun. 2010, pp. 1–10.

B. Liu, J. Huang, L. Yang, and C. Kulikowsk, “Robust visual tracking using local sparse representation and k-selection,” in Proc. IEEE Conf.Comput. Vis. Pattern Recognit., Jun. 2011, pp. 1313–1320.

Q.Wang, F. Chen, W. Xu, and M.-H. Yang, “Online discriminative object tracking with local sparse representation,” in Proc. IEEE Workshop Appl. Comput. Vis., Jan. 2012, pp. 425–432.9.

X. Jia, H. Lu, and M.-H. Yang, “Visual tracking via adaptive structural local sparse representation model,” in Proc. IEEE Conf. Comput. Vis.Pattern Recognit., Jun. 2012, pp. 1822–1829.10.

T. Zhang, B. Ghanem, S. Liu, and N. Ahuja, “Robust visual tracking via multi-task sparse learning,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2012, pp. 2042–2049.

T. B. Dinh and G. G. Medioni, “Co-training framework of generative and discriminative tracking with partial occlusion handling,” in Proc. IEEE Workshop Appl. Comput. Vis., Jan. 2011, pp. 642–649.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.