Study on the Comparison of Two Metrics Used in the Fields of Object Tracking

Abstract:

The paper researches on the comparison of two metrics methods under Riemannian metric and under Log-Euclidean metric respectively. Firstly, Experiments are done for comparing the distance and mean values worked out under the two metrics. And the time required for computing under these two metrics is also shown. Lastly, the two methods are applied to the field of image tracking. The performance of the two methods is compared, and the time required for tracking each frame is gained. Experiments results show that the two methods can gain similar distance and mean values, and similar tracking results, while the time required under Log-Euclidean metric is less than under Riemannian metric.

• Periodical: Applied Mechanics and Materials (Volume 483)
• Pages: 419-422
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.483.419
• Online since: December 2013
• Authors: Ying Hong Xie*, Cheng Dong Wu
• Keywords: Log-Euclidean Metric, Riemannian Metric, Visula Tracking

References

[1] O. Tuzel, F. Porikli, P. Meer. Region covariance: A fast descriptor for detection and classification. Proceeding of 9th European Conference on Computer Vision, Springer Berlin Heidelberg, Graz , Austria (2006), p.589–600.

DOI: 10.1007/11744047_45

[2] Yinghong Xie, Chengdong Wu, Yunzhou Zhang, Mengxin Li, Xiaowei Han. Object tracking based on bilateral structure tensor. Journal of Computational Information Systems, Vol. 8 (2012) pp.5983-5990.

[3] Quanquan Gu, Jie Zhou. A novel similarity measure under Riemannian metric for stereo matching, IEEE International Conference on Acoustics, Speech and Signal Processing, Las Vegas, U.S.A. (2008), p.1073 – 1076.

DOI: 10.1109/icassp.2008.4517799

[4] G. W. Li, Y.P. Liu, J. Yin, Target tracking with feature covariance based on an improved Lie group structure, Chinese Journal of Scientific Instrument Vol. 31 (2010), pp.111-116.

[5] Y. Wu, J.O. Wang AND H.Q. Lu, Real-time visual tracking via incremental covariance model update on Log-Euclidean Riemannian manifold, in Proceedings of Chinese Conference on Pattern Recognition, Nanjing(2009), pp.1-5.

DOI: 10.1109/ccpr.2009.5344069

[6] Xi Li, Weiming Hu, Zhongfei Zhang, Xiaoqin Zhang, Mingliang Zhu, Jian Cheng. Visual tracking via incremental Log-Euclidean Riemannian subspace learning.  IEEE Conference on  Computer Vision and Pattern Recognition, Anchorage, AK(2008), pp.1-8.

DOI: 10.1109/cvpr.2008.4587516

[7] Quanquan Gu, Jie Zhou. A similarity measure under Log-Euclidean metric for stereo matching, 19th International Conference on Pattern Recognition, Tampa, FL (2008), pp.1-4.

DOI: 10.1109/icpr.2008.4761347