透過您的圖書館登入
IP:18.118.32.213
  • 學位論文

360度全景視訊系統設計

360-degree Panoramic Video System Design

指導教授 : 郭峻因
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

並列摘要


In this thesis, a low-complexity video stitching algorithm is proposed. With the proposed algorithm, users can obtain a high-resolution, high quality and seamless 360-degree panoramic video immediately by stitching the images with overlapped region. In a traditional flow of image stitching, most methods of the existing researches were so complex that it is hard to achieve real-time processing. Moreover, it is not suitable for panoramic video applications such as surveillance system. The most presence of works are focused on image stitching, instead of video stitching. Hence, the problems like moving objects and dynamic scene must be considered when stitching the videos. In the proposed design, we propose some novel methods to solve the problem of color difference in image stitching. Moreover, we can also avoid the moving objects in overlapped area by using the dynamic seam scheme. In addition, we remove the drift problem to obtain a better visual effects when displaying the 360 degree panoramic video scenes.

參考文獻


[26] Xiaofeng Wang, Weijia Feng, Qingjie Liu, Baofeng Zhang, Zuoliang Cao, “Calibration Research on Fish-eye lens,” Proc. 2010 IEEE International Conference on Information and Automation, pp.385-390, 20-23 June 2010.
[1] Li Zhong-xin, Xu Wan-he, Zhang Yue, MaoYao-bin,Wang zhi-quan, “Video Mosaic with Block Matching and M-estimation,” Proc. 2009 WRI World Congress on Computer Science and Information Engineering, vol.6, pp.632-635, March 31 2009-April 2, 2009.
[3] Chiou-Ting Hsu; Tzu-Hung Cheng; Beuker, R.A.; Jyh-Kuen Horng, “Feature-based video mosaic,” Proc. 2000 International Conference on Image , vol.2, pp.887-890, vol.2, Sept. 10-13, 2000.
[2] Matthew Brown and David G. Lowe, “Automatic Panoramic Image Stitching using Invariant Features,” International Journal of Computer Vision, vol.74, no.1,pp.59-73, 2007.
[5] Richard Szeliski, Heung-Yeung Shum, “Creating Full View Panoramic Image Mosaics and Environment Maps,” Microsoft Research.

延伸閱讀


國際替代計量