Locating key views for image indexing of spaces

ABSTRACT

Image is a dominant medium for visualizing spatial environment and creating virtual access on the Internet. Where to capture images is however subjective and relies on artistic sense of photographers so far. In this paper, we will not only visualize areas with images, but also determine where the most distinct viewpoints should be located. Starting from elevation data of an area, we present spatial and content information in ground based images such that (1) a given number of images can have maximum coverage on informative scenes; (2) a sequence of views can be concatenated with minimum continuity along most-exposed-paths. According to scene visibility, continuity, and data redundancy we evaluate viewpoints numerically with an object-emitting illumination model. Our view exploration may eventually reduce data to archive and transmit, facilitate image acquisition, indexing and interaction, and enhance human perception of spaces. Real images are captured based on our planned key positions to form a visual network to index the area.

REFERENCES

• 1: Jiang Yu Zheng , Saburo Tsuji, Panoramic representation for route recognition by a mobile robot, International Journal of Computer Vision, v.9 n.1, p.55-76, Oct. 1992
• 2: Shenchang Eric Chen, QuickTime VR: an image-based approach to virtual environment navigation, Proceedings of the 22nd annual conference on Computer graphics and interactive techniques, p.29-38, September 1995 [doi>10.1145/218380.218395]
• 3: Richard Szeliski , Heung-Yeung Shum, Creating full view panoramic image mosaics and environment maps, Proceedings of the 24th annual conference on Computer graphics and interactive techniques, p.251-258, August 1997 [doi>10.1145/258734.258861]
• 4: Lyndon Kennedy , Mor Naaman , Shane Ahern , Rahul Nair , Tye Rattenbury, How flickr helps us make sense of the world: context and content in community-contributed media collections, Proceedings of the 15th international conference on Multimedia, September 25-29, 2007, Augsburg, Germany [doi>10.1145/1291233.1291384]
• 5: S. Coorg , N. Master , S. Teller, Acquisition of a Large Pose-Mosaic Dataset, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p.872, June 23-25, 1998
• 6: Seth Teller, Toward Urban Model Acquisition from Geo-Located Images, Proceedings of the 6th Pacific Conference on Computer Graphics and Applications, p.45, October 26-29, 1998
• 7: S. Coorg S. Teller. Extracting textured vertical facades from controlled close-range imagery. IEEE CVPR, pages 625--632, 1999.
• 8: S. K. Nayar, V. Peri, Folded catadioptric cameras. IEEE CVPR, Vol. II, pp. 217--223, 1999.
• 9: S. K. Nayar, A. Karmarkar, 360 × 360 mosaics. IEEE CVPR vol. II, pp. 388--395, 2000.
• 10: Daniel G. Aliaga , Thomas Funkhouser , Dimah Yanovsky , Ingrid Carlbom, Sea of images, Proceedings of the conference on Visualization '02, October 27-November 01, 2002, Boston, Massachusetts
• 11: http://www.ptgrey.com/products/legacy.asp
• 12: Daniel G. Aliaga , Thomas Funkhouser , Dimah Yanovsky , Ingrid Carlbom, Sea of Images: A Dense Sampling Approach for Rendering Large Indoor Environments, IEEE Computer Graphics and Applications, v.23 n.6, p.22-30, November 2003 [doi>10.1109/MCG.2003.1242379]
• 13: Yasushi Yagi , Masahiko Yachida, Real-Time Omnidirectional Image Sensors, International Journal of Computer Vision, v.58 n.3, p.173-207, July-August 2004 [doi>10.1023/B:VISI.0000019684.35147.fc]
• 14: Shigang Li , Masao Nakano , Norishige Chiba, Acquisition of Spherical Image by Fish-eye Conversion Lens, Proceedings of the IEEE Virtual Reality 2004, p.235, March 27-31, 2004 [doi>10.1109/VR.2004.8]
• 15: Augusto Roman , Gaurav Garg , Marc Levoy, Interactive Design of Multi-Perspective Images for Visualizing Urban Landscapes, Proceedings of the conference on Visualization '04, p.537-544, October 10-15, 2004 [doi>10.1109/VIS.2004.50]
• 16: Matthew Uyttendaele , Antonio Criminisi , Sing Bing Kang , Simon Winder , Richard Szeliski , Richard Hartley, Image-Based Interactive Exploration of Real-World Environments, IEEE Computer Graphics and Applications, v.24 n.3, p.52-63, May 2004 [doi>10.1109/MCG.2004.1297011]
• 17: Yasushi Yagi , Kousuke Imai , Kentaro Tsuji , Masahiko Yachida, Iconic Memory-Based Omnidirectional Route Panorama Navigation, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.27 n.1, p.78-87, January 2005 [doi>10.1109/TPAMI.2005.11]
• 18: Jiang Yu Zheng , Yu Zhou , Panayiotis Mili, Scanning Scene Tunnel for City Traversing, IEEE Transactions on Visualization and Computer Graphics, v.12 n.2, p.155-167, March 2006 [doi>10.1109/TVCG.2006.37]
• 19: Aseem Agarwala , Maneesh Agrawala , Michael Cohen , David Salesin , Richard Szeliski, Photographing long scenes with multi-viewpoint panoramas, ACM SIGGRAPH 2006 Papers, July 30-August 03, 2006, Boston, Massachusetts
• 20: Noah Snavely , Steven M. Seitz , Richard Szeliski, Photo tourism: exploring photo collections in 3D, ACM Transactions on Graphics (TOG), v.25 n.3, July 2006
• 21: T. N. Thanh, et al., Robust and real-time rotation estimation of compound omni-directional sensor, IEEE Int. Conf. Robotics and Automation, pp. 4226--4231, 2007.
• 22: Bryan C. Russell , Antonio Torralba , Kevin P. Murphy , William T. Freeman, LabelMe: A Database and Web-Based Tool for Image Annotation, International Journal of Computer Vision, v.77 n.1-3, p.157-173, May 2008 [doi>10.1007/s11263-007-0090-8]
• 23: Alex Rav-Acha , Giora Engel , Shmuel Peleg, Minimal Aspect Distortion (MAD) Mosaicing of Long Scenes, International Journal of Computer Vision, v.78 n.2-3, p.187-206, July 2008 [doi>10.1007/s11263-007-0101-9]
• 24: Google StreetView: http://maps.google.com/
• 25: Jinhui Hu , Suya You , Ulrich Neumann, Integrating LiDAR, Aerial Image and Ground Images for Complete Urban Building Modeling, Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06), p.184-191, June 14-16, 2006 [doi>10.1109/3DPVT.2006.82]
• 26: Jiang Yu Zheng , Xiaolong Wang, Pervasive views: area exploration and guidance using extended image media, Proceedings of the 13th annual ACM international conference on Multimedia, November 06-11, 2005, Hilton, Singapore [doi>10.1145/1101149.1101354]
• 27: B Chen, A Kaufman, Q Tang, Image-Based Rendering of Surfaces from Volume Data, Volume Graphics, pp. 279--295, 2001.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.4 Systems

Additional Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.8 Database applications
          Subjects: Image databases; Spatial databases and GIS
  H.4 INFORMATION SYSTEMS APPLICATIONS
      H.4.3 Communications Applications
          Subjects: Information browsers

  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.7 Three-Dimensional Graphics and Realism
          Subjects: Virtual reality
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.1 Digitization and Image Capture
          Subjects: Imaging geometry; Sampling

General Terms:
Algorithms, Design, Documentation, Experimentation, Human Factors, Management, Measurement, Performance

Keywords:
camera placement, image indexing, key view, panorama, spatial visualization, virtual environments, visibility