Abstract
In order to save storage space of a pano-mapping table used in omni-image unwarping, a geometric symmetry method is proposed. First of all, this method partitions a 360° omni-image into eight 45° omni-image sectors. Then, we partition the pano-mapping table into eight regions accordingly, with each pano-mapping table region corresponding to exactly one omni-image sector. We analyze the geometric symmetry relationship among these omni-image sectors and pano-mapping table regions. We find that if we know the mapping data in any one pano-mapping table region, it is easy to calculate the mapping data of the other seven pano-mapping table regions. Thus, in the final step, we perform omni-image unwarping based on only one pano-mapping table region, which reduces pano-mapping table size by seven-eighths. Reducing the pano-mapping size is very useful for implementing omni-image unwarping in embedded systems. Experiments on TI DSP-based embedded systems indicate that the proposed method reduces seven-eighths of pano-mapping table size, and improves the unwarping speed by a factor of 2.74.
Similar content being viewed by others
References
Xiong, Z.H., Zhang, M.J., Wang, Y.L., Li, T., Li, S.K.: Fast panorama unrolling of catadioptric omni-directional images for cooperative robot vision system. In: Proceedings of the 11th International Conference on Computer Supported Cooperative Work in Design, Melbourne, Australia, pp. 1100–1104 (2007)
Andreasson H., Treptow A., Duckett T.: Self-localization in non-stationary environments using omni-directional vision. Robotics Auton. Syst. 55, 541–551 (2007)
Wu C.J., Tsai W.H.: Location estimation for indoor autonomous vehicle navigation by omni-directional vision using circular landmarks on ceilings. Robotics Auton. Syst. 57, 546–555 (2009)
Feng H.M., Chen C.Y., Horng J.H.: Intelligent omni-directional vision-based mobile robot fuzzy systems design and implementation. Expert Syst. Appl. 37, 4009–4019 (2010)
Liu, Y.C., Lin, K.Y., Chen, Y.S.: Bird’s-eye view vision system for vehicle surrounding monitoring. In: Proceedings Conference on Robot Vision, Berlin, Germany, pp. 207–218 (2008)
Boult T.E., Gao X., Micheals R.J., Eckmann M.: Omni- directional visual surveillance. Image Vis. Comput. 22, 515–534 (2004)
Gandhi T., Trivedi M.: Person tracking and reidentification: introducing Panoramic Appearance Map (PAM) for feature representation. Mach. Vis. Appl. 18, 207–220 (2007)
Ng K.C., Ishiguro H., Trivedi M.M., Sogo T.: An integrated surveillance system: human tracking and view synthesis using multiple omni-directional vision sensors. Image Vis. Comput. 22, 551–561 (2004)
Fiala M., Basu A.: Panoramic stereo reconstruction using non-SVP optics. Comput. Vis. Image Underst. 8, 363–397 (2005)
Koyasu H., Miura J., Shirai Y.: Recognizing moving obstacles for robot navigation using real-time omni-directional stereo vision. J. Robotics Mechatron. 14, 147–156 (2002)
Peleg, S., Pritch, Y., Ben-Ezra, M.: Cameras for stereo panoramic imaging. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Hyatt Regency, Hilton Head Island, South Carolina, pp. 208–214 (2000)
Svoboda T., Pajdla T.: Epipolar geometry for central catadioptric cameras. J. Comput. Vis. 49, 23–37 (2002)
Winters, N., Gaspar, J., Lacey, G., Victor, J.S.: Omni-directional vision for robot navigation. In: Proceedings of IEEE Workshop on Omnidirectional Vision, Hyatt Regency, Hilton Head Island, South Carolina, pp. 21–28 (2000)
Gaspar, J., Decco, C., Okamoto, J.: Constant resolution omni- directional cameras. In: Proceedings of IEEE Workshop on Omnidirectional Vision, Copenhagen, Denmark, pp. 27–34 (2002)
Wu C.J., Tsai W.H.: Unwarping of images taken by misaligned omnicameras without camera calibration by curved quadrilateral morphing using quadratic pattern classifiers. Opt. Eng. 48, 087003(1)–087003(11) (2009)
Jeng S.W., Tsai W.H.: Using pano-mapping tables for unwarping of omni-images into panoramic and perspective-view images. IET Image process. 1, 149–155 (2007)
Chen, C.W., Ku, C.J., Chang, C.H.: Designing a high performance and low energy-consuming embedded system with considering code compressed environments. In: Proceedings of 11th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, Hong Kong, pp. 317–322 (2005)
Noergaard T.: Embedded Systems Architecture: A Comprehensive Guide for Engineers and Programmers. Elsevier, Amsterdam (2005)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xiong, Z., Cheng, I., Basu, A. et al. Efficient omni-image unwarping using geometric symmetry. Machine Vision and Applications 23, 725–737 (2012). https://doi.org/10.1007/s00138-010-0312-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-010-0312-x