Abstract
Multi-view image stitching is an efficient approach to resolve the limitation of single view angle, and it can be described as the process of fusing images under different viewpoints into a wide-view picture. This paper presents a multi-view image stitching algorithm based on CSIFT (Color Scale Invariant Features) features. Generally speaking, our proposed method contains two sections. First, multi-view image registration procedure is described based on CSIFT features. In this way, our method is robust to both geometrical and photometric changes. The second section is image blending, in order to smooth the generated wide-view image with a high speed, a linear blending algorithm is illustrated. Experimental results indicate that our proposed algorithm is accurate and effective.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kang, Y.-S., Lee, C., Ho, Y.-S.: An Efficient Rectification Algorithm for Multi-view Images in Parallel Camera Array. The True Vision - Capture, Transmission and Display of 3d Video, 61–64 (2008)
Xiong, Y., Pulli, K.: Fast Image Stitching and editing for panorama painting on mobile phones. In: Computer Vision and Pattern Recognition Workshops, pp. 47–52 (2010)
ISO/IEC JTC1/SC29/WG11 N6909, Survey of Algorithms used for Multi-view Video Coding (MVC), Hong Kong (2005)
Brown, M., Lowe, D.G.: Automatic Panoramic Image Stitching using Invariant Features. Computer Vision 74(1), 59–73 (2007)
Lowe, D.G.: Distinctive Image Features from Scale-Invariant Keypoints. J. Computer Vision 60(2), 91–110 (2004)
Mikolajczyk, K., Schmid, C.: A Performance Evaluation of Local Descriptors. J. Pattern Analysis and Machine Intelligence 27(10), 1615–1630 (2005)
Huynh, D.Q., Sanini, A., Liu, W.: Evaluation of Three Local Descriptors on Low Resolution Images for Robot Navigation. In: 24th International Conference on Image and Vision Computing, New Zealand, vol. 11, pp. 23–25 (2009)
Abdel-Hakim, A.E., Farag, A.A.: CSIFT: A SIFT Descriptor with Color Invariant Characteristics. Computer Vision and Pattern Recognition 2, 1978–1983 (2006)
Koen, E.A., van de Sande, et al.: Evaluating Color Descriptors for Object and Scene Recognition. Pattern Analysis and Machine Intelligence 32(9), 1582–1596 (2010)
Yong, D., Chu, S.: Two-View Motion Segmentation with Model Selection and Outlier Removal by RANSAC-Enhanced Dirichlet Process Mixture Models. Computer Vision 88, 489–501 (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag GmbH Berlin Heidelberg
About this chapter
Cite this chapter
Zhou, P., Luo, X. (2012). An Efficient Multi-view Image Stitching Algorithm Based on CSIFT Features. In: Zhang, Y. (eds) Future Communication, Computing, Control and Management. Lecture Notes in Electrical Engineering, vol 142. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27314-8_55
Download citation
DOI: https://doi.org/10.1007/978-3-642-27314-8_55
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-27313-1
Online ISBN: 978-3-642-27314-8
eBook Packages: EngineeringEngineering (R0)