Advertisement

Linear Clutter Removal from Urban Panoramas

  • Mahsa Kamali
  • Eyal Ofek
  • Forrest Iandola
  • Ido Omer
  • John C. Hart
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6939)

Abstract

Panoramic images capture cityscapes of dense urban structures by mapping multiple images from different viewpoints into a single composite image. One challenge to their construction is that objects that lie at different depth are often not stitched correctly in the panorama. The problem is especially troublesome for objects occupying large horizontal spans, such as telephone wires, crossing multiple photos in the stitching process. Thin lines, such as power lines, are common in urban scenes but are usually not selected for registration due to their small image footprint. Hence stitched panoramas of urban environments often include “dented” or “broken” wires. This paper presents an automatic scheme for detecting and removing such thin linear structures from panoramic images. Our results show significant visual clutter reduction from municipal imagery while keeping the original structure of the scene and visual perception of the imagery intact.

Keywords

Power Line Aerial Image Building Facade Urban Scene Wire Detection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Agarwala, A., Agrawala, M., Cohen, M., Salesin, D., Szeliski, R.: Photographing long scenes with multi-viewpoint panoramas. ACM Trans. Graph 25, 853–861 (2006)CrossRefGoogle Scholar
  2. 2.
    Battiato, S., et al.: 3D stereoscopic image pairs by depth-map generation. In: Symposium on 3D Data Processing, Visualization, and Transmission (2004)Google Scholar
  3. 3.
    Beylkin, G.: Discrete radon transform. IEEE Trans. Acoustics, Speech, and Signal Processing 35, 162–172 (1987)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Blazquez, C.H.: Detection of problems in high power voltage transmission and distribution lines with an infrared scanner/video system. In: SPIE, pp. 27–32 (1994)Google Scholar
  5. 5.
    ColorPilot. Retouch Unwanted Objects on Your Photos (2011), http://www.colorpilot.com/wire.html
  6. 6.
    Fu, S.Y., et al.: Image-based visual servoing for power transmission line inspection robot. International J. of Modelling, Identification and Control 6, 239–254 (2009)CrossRefGoogle Scholar
  7. 7.
    Ginkel, M.V., Hendriks, C.L., Vliet, L.J.: A short introduction to the Radon and Hough transforms and how they relate to each other. Delft University of Technology Technical Report (2004)Google Scholar
  8. 8.
    Hirani, A., Totsuka, T.: Projection Based Method for Scratch and Wire Removal from Digital Images. United States Patent US 5974194 (1996)Google Scholar
  9. 9.
    Hirani, A.N., Totsuka, T.: Combining frequency and spatial domain information for fast interactive image noise removal. In: SIGGRAPH, pp. 269–276 (1996)Google Scholar
  10. 10.
    Hoiem, D., Efros, A., Herbert, M.: Closing the loop in scene interpretation. In: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 1–8 (2008)Google Scholar
  11. 11.
    Kent, B.: Automatic Identification and Removal of Objects in Image Such as Wires in a Frame of Video. United States Patent Application US 208, 053 (2008)Google Scholar
  12. 12.
    Kopf, J., Chen, B., Szeliski, R., Cohen, M.: Street slide: browsing street level imagery. ACM Trans. Graph 29 (2010)Google Scholar
  13. 13.
    Mu, C., Yu, J., Feng, Y., Cai, J.: Power lines extraction from aerial images based on Gabor filter. In: SPIE (2009)Google Scholar
  14. 14.
    Pulli, K., Tico, M., Xiong, Y.: Mobile panoramic imaging system. In: CVPRW, pp. 108–115 (2010)Google Scholar
  15. 15.
    Rav-Acha, A., Engel, G., Peleg, S.: Minimal Aspect Distortion (MAD) Mosaicing of Long Scenes. International J. of Computer Vision 78, 187–206 (2007)CrossRefGoogle Scholar
  16. 16.
    Roman, A., Garg, G., Levoy, M.: Interactive design of multi-perspective images for visualizing urban landscapes. IEEE Visualization, 537–544 (2004)Google Scholar
  17. 17.
    Roman, A., Lensch, H.P.: Automatic Multiperspective Images. In: Eurographics Symposium on Rendering Techniques, pp. 83–92 (2006)Google Scholar
  18. 18.
    Seymour, M.: The Art of Wire Removal (2007), http://www.fxguide.com/article453.html
  19. 19.
    Szeliski, R.: Image Alignment and Stitching: A Tutorial. Foundations and Trends in Com-puter Graphics and Vision 2, 1–104 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  20. 20.
    Tao, L., Yuan, L., Sun, J.: SkyFinder: Attribute-based Sky Image Search. ACM Trans. Graph. 28 (2009)Google Scholar
  21. 21.
    Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: IEEE International Conf. on Computer Vision, ICCV (1998)Google Scholar
  22. 22.
    Vallance, S.: Multi-perspective images for visualisation. In: Pan-Sydney Area Symposium on Visual Information Processing, VIP (2001)Google Scholar
  23. 23.
    Xiao, Z.: Study on methods to extract transmission line information from high-resolution imagery. In: SPIE (2009)Google Scholar
  24. 24.
    Yan, G., et al.: Automatic Extraction of power lines from aerial images. IEEE Geoscience and Remote Sensing Letters 4, 387–391 (2007)CrossRefGoogle Scholar
  25. 25.
    Zuta, M.: Wire Detection System and Method. United States Patent US 6278409 (2001)Google Scholar
  26. 26.
    Rheingold, H.: Tools for Thought: The History and Future of Mind-Expanding Technology, ch.6. The MIT Press, Redmond (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Mahsa Kamali
    • 1
  • Eyal Ofek
    • 2
  • Forrest Iandola
    • 1
  • Ido Omer
    • 2
  • John C. Hart
    • 1
  1. 1.University of IllinoisUrbana ChampaignUSA
  2. 2.Microsoft ResearchUSA

Personalised recommendations