An automatic panoramic image mosaic method based on graph model

详细信息    查看全文

• 作者：Zhicheng Wang ; Yufei Chen ; Zewei Zhu ; Weidong Zhao
• 关键词：Automatic mosaic ; 360 degree ; panoramic image generation ; Weighted shortest path algorithm ; Graph model
• 刊名：Multimedia Tools and Applications
• 出版年：2016
• 出版时间：March 2016
• 年：2016
• 卷：75
• 期：5
• 页码：2725-2740
• 全文大小：14,385 KB
• 参考文献：1.Bay H, Ess A, Tuytelaars T, Gool LV (2008) Speeded-up robust feature (SURF). Comput Vis Image Underst 110(3):336–359CrossRef
  2.Brown M, Lowe DG (2007) Automatic panoramic image stitching using invariant features. Int J Comput Vis 74(1):59–73CrossRef
  3.Calonder M, Lepetit V, Strecha C, Fua P (2010) BRIEF: Binary robust independent elementary features. In: Daniilidis K, Maragos P, Paragios N (eds) ECCV 2010, Part IV. LNCS, vol 6314. Springer, Heidelberg, pp 778–792
  4.Chen SE (1995) Quicktime VR: an image-based approach to virtual environment navigation. In: Proceedings of the 22nd annual conference on Computer graphics and interactive techniques, pp 29–38, 1995. doi:10.​1145/​218380.​218395
  5.Dewangan AK, Raja R, Singh R (2014) An implementation of multi sensor based mobile robot with image stitching application. Int J Comput Sci Mobile Comput 3(6):603–609
  6.Geng N, He D, Song Y (2012) Camera image mosaicing based on an optimized SURF algorithm. TELKOMNIKA Indones J Electr Eng 10(8):2183–2193
  7.Gonalez MC, Holifield P, Varley M (1998) Improved video mosaic construction by accumulated alignment error distribution. In: Nixon M, Carter J (eds) Proceedings of the British Machine Conference. BMVA Press, September 1998, pp 38.1–38.11. doi:10.​5244/​C.​12.​38
  8.Hu WC, Chang CH, Liang YF et al. (2007) An effective blending method for panoramic images in image based virtual reality. Proceedings of 2007 International Conference on Advanced Information Technologies. http://​www.​inf.​cyut.​edu.​tw/​ait2007/​021.​pdf
  9.Kalayeh HM (2013) Image stitching and related method therefor. US Patent 8,600,193 B2 Dec. 2013
  10.Lindeberg T (1998) Feature detection with automatic scale selection. Int J Comput Vis 30(2):91–116
  11.Lowe D (2004) Distinctive image features from scale-invariant key points. Int J Comput Vis 2(60):91–110CrossRef
  12.Mikolajczyk K, Schmid C (2005) A performance evaluation of local descriptors. IEEE Trans Pattern Anal Mach Intell 10(27):1615–1630CrossRef
  13.Nikolaidis N and Pitas I (2005) Computationally efficient image mosaicing using spanning tree representations. In: Bozanis P, Houstis EN (eds) Advances in Informatics. Lecture Notes in Computer Science. 10th Panhellenic Conference on Informatics, PCI 2005, Volas, Greece, November 11–13, 2005. Proceedings, pp 716–724
  14.Reichmann M (2009). Realviz Stitcher 4.0 Review. http://​www.​luminous-landscape.​com/​reviews/​software/​stitcher-4.​shtml
  15.Sakharkar MVS, Gupta SR (2013) Image stitching techniques-an overview. Int J Comput Sci Appl 6(2). http://​www.​researchpublicat​ions.​org/​IJCSA/​NCAICN-13/​230.​pdf
  16.Szeliski R (2006) Image alignment and stitching: a tutorial. Foundations and Trends® in Computer Graphics and Vision 2(1): 1–104
  17.Szeliski R, Shum HY (1997) Creating full view panoramic image mosaics and environment maps. Proceedings of the 24th annual conference on Computer graphics and interactive techniques. ACM Press, Addison-Wesley Publishing Co. pp 251–258
  18.Tan YF, Sain M, Gook LB (2014) User detection in real-time panoramic view through image synchronization using multiple camera in cloud. Advanced Communication Technology (ICACT), 2014 16th International Conference on. IEEE, Pyeongchang, 16–19 Feb 2014, pp 1118–1123
  19.Triggs B, McLauchlan PF, Hartley RI, Fitzgibbon AW (1999) Bundle adjustment — a modern synthesis. Vision algorithms: theory and practice. Lecture notes in computer science. International workshop on vision algorithms corfu, Greece, September 21–22, 1999 Proceedings, pp 298–372
  20.VisualSize mosaic 3D: http://​www.​visualsize.​com/​mosaic3d/​index.​php
  21.Wang Z, Fan B, Wu F (2011) Local intensity order pattern for feature description. In: IEEE International Conference on Computer Vision, pp 603–610
  22.Yang XH, Wang M (2013) Seamless image stitching method based on ASIFT. Comput Eng 39(2):241–244
  23.Yi-Li Z, Yan X (2013) Automatic panorama recognition and stitching based on graph structure. 2nd International Conference on Advances in Computer Science and Engineering (CSE 2013). www.​atlantis-press.​com/​php/​download_​paper.​php?​id=​6914
  24.Yongxi G, Yuan T, Yubo X et al (2009) A method for large scale microscope image mosaicking besed on minimum routing cost spanning tree. J Image Graph 6(14):1178–1187
  25.Zhou H (2006) Graph-based global optimization for the registration of a set of images. In: Advances in Image and Video Technology. Heidelberg, Berlin: Springer, pp 1206–1214
  
• 作者单位：Zhicheng Wang (1) (2)
  Yufei Chen (1) (2)
  Zewei Zhu (1) (2)
  Weidong Zhao (1) (2)
  
  1. Research Center of CAD, Tongji University, Shanghai, 200092, China
  2. The Engineering Research Center for Enterprise Digital Technology, Ministry of Education, Tongji University, Shanghai, 200092, China
  
• 刊物类别：Computer Science
• 刊物主题：Multimedia Information Systems
  Computer Communication Networks
  Data Structures, Cryptology and Information Theory
  Special Purpose and Application-Based Systems
  
• 出版者：Springer Netherlands
• ISSN：1573-7721

文摘

Image mosaic plays an important role in the fields of computer vision, robot navigation and virtual reality, and has become an active research field in recent years. There is a problem that the error will be accumulated and amplified in the case of aligning multi-images. This paper analyzes the looping path problem causing error accumulation, and introduces a multi-image stitching method based on graph model. We name the algorithm Weighted Shortest Path Algorithm, by which images can be stitched automatically. Matching Mean Square Error is introduced as the weight of edges on the graph, which is intuitive and easy to compute. Furthermore, the optimized Dijkstra algorithm is applied to speed up the path finding algorithm. Experiments show that the proposed algorithm causes less Matching Mean Square Error and obtains more stable results than other similar methods. Moreover, we extended our model to 360 ° panoramic image generation, and the quality of the stitched panorama is quite good.