Object Tracking in Motion Blurred Images with Adaptive Mean Shift and Wavelet Feature

Authors: Iman Iraei, Mina Sharifi

Abstract:

A method for object tracking in motion blurred images is proposed in this article. This paper shows that object tracking could be improved with this approach. We use mean shift algorithm to track different objects as a main tracker. But, the problem is that mean shift could not track the selected object accurately in blurred scenes. So, for better tracking result, and increasing the accuracy of tracking, wavelet transform is used. We use a feature named as blur extent, which could help us to get better results in tracking. For calculating of this feature, we should use Harr wavelet. We can look at this matter from two different angles which lead to determine whether an image is blurred or not and to what extent an image is blur. In fact, this feature left an impact on the covariance matrix of mean shift algorithm and cause to better performance of tracking. This method has been concentrated mostly on motion blur parameter. transform. The results reveal the ability of our method in order to reach more accurately tracking.

Keywords: Mean shift, object tracking, blur extent, wavelet transform, motion blur.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1316051

References:

[1] J. Ning, L. Zhang, D. Zhang, and C. wu, “Scale and Orientation Adaptive Mean Shift Tracking,” IET Computer Vision, vol. 8, pages. 52-61, January 2012.
[2] B. Z. de Villiers, W.A. Clarke, P. E. Robinso, “Mean Shift Object Tracking with Occlusion Handling,” Proceedings of the Twenty-Third Annual Symposium of the Pattern Recognition Association of South Africa, pp 192-199, November 2012.
[3] A, Salhi. Y, Ameni “Object Tracking System Using Camshift, Meanshift and Kalman Filter,” International Journal of Electrical, Computer, Energetic, Electronic and Communication Engineering, Vol 6, No 4, April 2012.
[4] D. Comaniciu, and P. Meer, “Mean Shift: A Robust Approach Toward Feature Space Analysis,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, issue. 5, pp. 603 - 619, May 2002.
[5] Chengpo Mu, Zhijie Yuan, Jia Song, Yuanqian Chen, “A New Approach to Track Moving Target With improved Mean Shift Algorithm and Kalman Filter,” 4th International Conference on Intelligent Human-Machine vol. 1, pp. 359 - 362, August 2012.
[6] Georgescu, B., Shimshoni, I. & Meer, P. “Mean shift based clustering in high dimensions: A texture classification example”, In International Conference on Computer Vision, vol. 1, no. 3, pp. 456–463, October 2003.
[7] M. Sanjeev Arulampalam, “A tutorial on particle filters for linear/nonlinear- Gaussian Bayesian tracking,” in IEEE Transactions on Signal Processing, vol. 50, issue. 2, pp. 174 - 188, February 2002.
[8] Jing Ren, Jie Hao, “Mean shift tracking algorithm combined with Kalman Filter,” 5th International Congress on Image and Signal Processing (CISP) , pp. 727-730, October 2012.
[9] Youngmin Park. et al. “Handling Motion-Blur in 3D Tracking and Rendering for Augmented Reality,” IEEE Transactions on Visualization and Computer Graphics, Volume 18, Issue 9, Pages 1449–1459, September 2012.
[10] Yi Wu. et al. “Blurred Target Tracking by Blur-driven Tracker,” Computer Vision (ICCV), 2011 IEEE International Conference on, Pages 1634–1640, March 2011.
[11] Rahim Panahi, Iman Golamipour, Mansour Jamzad, “Real Time Occlusion Handling Using Kalman Filter and Mean-Shift,” 8th Iranian Conference on Machine Vision and Image Processing (MVIP), pages. 320–323, September 2013.
[12] Iman Iraei, Karim Faez, “Object Tracking with Occlusion Handling Using Mean Shift, Kalman Filter and Edge Histogram,” Pattern Recognition and Image Analysis (IPRIA) 2015 2nd International Conference on, pp. 1-6, 2015.
[13] Dash, R. Majhi, B “Motion blur parameters estimation for image restoration,” Optik - International Journal for Light and Electron Optics, Volume 125, Issue 5, Pages 1634–1640, March 2014.
[14] Mina Sharifi, Iman Iraei, Yaser Baleghi “Blur Parameter Estimation Using SUMFC and Wavelet Transform” 3rd International Conference on Applied Research in Computer Engineering and Information Technology, Tehran, Malek Ashtar University of Technology, February 2016. https://www.civilica.com/Paper-CITCONF03-CITCONF03_558.html.
[15] Tong, H. et al. “Blur Detection for Digital Images Using Wavelet Transform,” Multimedia and Expo (ICME), Vol. 1, No. 5, PP. 17 - 20, June 2004.
[16] Yi Zhang, Y. “Blur Processing Using Double Discrete Wavelet transform”, Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), PP. 1091 - 1098, June 2013.
[17] Hui Ji. et al. “Image deconvolution using a characterization of sharp images in wavelet domain,” Applied and Computational Harmonic Analysis, Volume 32, Issue 2, Pages 295–304, March 2012.