在360度視訊的電腦視覺應用中，物件追蹤(object tracking)可縮小待處理之感興趣區域(region of interest)，而對於三百六十度視訊(360-degree video)的等距長方投影(equirectangular mapping projection, ERP)，由於影像扭曲，造成大多數現有的物件追蹤演算法準確率大幅降低。因此，本論文基於粒子濾波器(particle filter)，提出於球體域(sphere domain)預測目標物狀態，使運動模型(motion model)不須考量等距長方投影中幾何形變(geometric distortions)的問題。由於ERP為全景影像，因此需進行模數(modulus)處理，使得預測後粒子之位置避免落於ERP邊界之外。此外，由於Oriented Fast and Rotated BRIEF (ORB)特徵具有影像幾何失真(geometric distortions)之不變性，且計算複雜度較低，因此本論文採用ORB描述子(descriptor)以進行粒子濾波器之更正階段(correction stage)。實驗結果顯示，相較於快速L1追蹤器，本論文所提方案雖然於目標進入ERP影像邊界前的幾張畫面時，追蹤準確率略低於快速L1追蹤器，但是當目標進入ERP影像邊界後再出現在ERP影像另一側，或是當目標被遮蔽時，本論文所提方案追蹤準確率皆高於快速L1追蹤器。

For applications of 360-degree videos in computer vision, object tracking can reduce regions of interest to be processed. For equirectangular projection of 360-degree videos, the distorted images significantly decreases tracking accuracy. Hence, this thesis proposes to predict the target state in the sphere domain in the framework of particle filter. Accordingly, the motion model does not need to consider geometric distortions in the equirectangular mapping projection. Because images of equirectangular mapping projection are panorama images, the modulus operation avoids the positions of the predicted particles out of the boundary of the equirectangular mapping projection. In addition, since the Oriented Fast and Rotated BRIEF(ORB) feature is geometric distortions invariant and is featured with lower computation complexity, this thesis adopts the ORB descriptor at the correction stage of particle filter. Experimental results show that the proposed scheme outperforms the fast L1 tracker when the target appears at the other side of the equirectangular mapping projection after the target moves into the boundary or the target is occluded. However, the fast L1 tracker slightly outperforms the proposed scheme before the target moves into the boundary.

[1] F. Rameau, D.D. Sidibe, C. Demonceaux, and D. Fofi, “Visual tracking with omnidirectional cameras: an efficient approach,” Electronics Letters, Vol. 47, No. 21, pp. 1183-1184, October 2011.
[2] Y. Tang, Y. Li, Senior Member, Shuzhi Sam Ge, Jun Luo, and Hongliang Ren, “Parameterized distortion-invariant feature for robust tracking in omnidirectional vision,” IEEE Trans. on Automation Science And Engineering, Vol. 13, No. 2, pp. 743-756, April 2016.
[3] G. Tong and J. Gu, “Locating objects in spherical panoramic images,” in Proceedings of IEEE International Conference on Robotics and Biomimetics, pp. 818-823, December 2011.
[4] B. S. Kim and J. S. Park, “Estimating deformation factors of planar patterns in spherical panoramic images,” Multimedia Systems, Vol. 23, DOI 10.1007/s00530-016-0513-x, pp. 607-625, April 2016.
[5] K. Chi Liu, Y. T. Shen, and L. G. Chen, “Simple online and realtime tracking with spherical panoramic camera,” in Proceedings of IEEE International Conference on Consumer Electronics, National Taiwan University, pp. 1-6, Jan. 2018.
[6] J. Redmon and A. Farhadi, “YOLO9000: better, faster, stronger,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Vol. abs/1612.08242, pp. 6517-6525, July 2017. [Online]. Available: http://arxiv.org/abs/1612.08242.
[7] N. Wojke, A. Bewley, and D. Paulus, “Simple online and realtime tracking with a deep association metric,” in Proceedings of IEEE International Conference on Image Processing, Vol. abs/1703.07402, pp. 3645-3649, September 2017. [Online]. Available: http://arxiv.org/abs/1703.07402.
[8] E. Rublee, V. Rabaud, K. Konolige, and G. Bradski, “ORB: An efficient alternative to SIFT or SURF,” in Proceedings of International Conference on Computer Vision, Willow Garage, Menlo Park, California, pp. 256-2571, Nov. 2011.
[9] E. Karami, S. Prasad, and M. Shehata, “Image matching using SIFT, SURF, BRIEF and ORB: Performance comparison for distorted images,” in Proceedings of Newfoundland Electrical and Computer Engineering Conference, November 2015.
[10] H. Bay, T. Tuytelaars, and L. Van Gool, “SURF: Speeded up robust features,” in Proceedings of the European Conference on Computer Vision, pp. 404-417, May 2006.
[11] C. Bao, Y. Wu, H. Ling, and H. Ji, “Real time robust l1 tracker using accelerated proximal gradient approach,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1830-1837, June 2012.
[12] A. Yilmaz, O. Javed, and M. Shah, “Object tracking: A survey,” ACM Computing Surveys, Vol. 38, No. 4, pp. 1-45, December 2006.
[13] N. J. Gordon, D. J. Salmond, and A. F. M. Smith, “Novel approach to nonlinear/non-Gaussian Bayesian state estimation,” IEE Proceedings F - Radar and Signal Processing, Vol. 140, pp. 107-113, April 1993.
[14] M. S. Arulampalam, S. Maskell, N. Gordan, and T. Clapp, “A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking,” IEEE Trans. signal processing, Vol. 50, No. 2, pp. 174-188, Feb. 2002.
[15] K. Nummiaro, E. Koller-Meier, and L. V. Gool, “An adaptive color-based particle filter,” Image and Vision Computing, Vol. 21, No. 1, pp. 99-110, Jan. 2003.
[16] F. Wallhoff, M. Zobl, and G. Rigoll, “Face tracking in meeting room scenarios using omnidirectional views,” in Proceedings of IEEE Conf. on Pattern Recognition, Washington, DC, USA, Vol. 4, pp. 933–936, Aug. 2004.
[17] Z. Zhou, B. Niu, C. Ke, and W. Wu, “Static object tracking in road panoramic videos,” in Proceedings of IEEE International Symposium on Multimedia, pp. 57-64, Dec. 2010.
[18] M. Budagavi, J. Furton, G. Jin, A. Saxena, J. Wilkinson, and A. Dickerson, “360 degrees video coding using region adaptive smoothing,” in Proceedings of IEEE International Conference on Image Processing, pp. 750-754, September 2015.
[19] C. Chen, M.-Y. Liu, O. Tuzel, and J. Xiao, “R-CNN for Small Object Detection,” Springer International Publishing, pp. 214–230, March 2017.
[20] H. Hu, Y. Lin, M. Liu, H. Cheng, Y. Chang, and M. Sun, “Deep 360 pilot: Learning a deep agent for piloting through 360-degree sports video,” in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Vol. abs/1705.01759, pp. 1396-1405, July 2017.
[21] P. Torr and A. Zisserman, “Robust computation and parametrization of multiple view relations,” in Proceedings of International Conference on Computer Vision, pp. 727-732, Jan. 1998.
[22] Y. Ye, E. Alshina, and J. Boyce, ”Algorithm descriptions of projection format conversion and video quality metrics in 360Lib Version 4,” Joint Video Exploration Team (JVET) of ITU-T SG 16 WP 3 and ISO/IEC JTC 1/SC 29/WG 11 7th Meeting: Torino, IT, 13–21 July 2017.
[23] X. Corbillon, F. De Simone, and G. Simon, “360-degree video head movement dataset,” in Proceedings of ACM Multimedia Systems, pp. 1-4, June 2017.
[24] https://www.mettle.com/360vr-master-series-free-360-downloads-page.
[25] F. Duanmu, Y. Mao, S. Liu, S. Srinivasan and Y. Wang, “A subjective study of viewer navigation behaviors when watching 360-degree videos on computers,” in Proceedings of IEEE International Conference on Multimedia Expo, San Diego, California, USA, Feb. 2018.
[26] X. Mei and H. Ling, “Robust visual tracking using l1 minimization,” in Proceedings of IEEE International Conference on Computer Vision, pp. 1436-1443, Kyoto, Japan, Sep.-Oct. 2009.
[27] Y. Wu, J.W. Lim, and M.-H. Yang, “Online object tracking: A benchmark,” in Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2411–2418, June 2013.