Validation of vector data using oblique images

ABSTRACT

Oblique images are aerial photographs taken at oblique angles to the earth's surface. Projections of vector and other geospatial data in these images depend on camera parameters, positions of the entities, surface terrain, and visibility. This paper presents a robust and scalable algorithm to detect inconsistencies in vector data using oblique images. The algorithm uses image descriptors to encode the local appearance of a geospatial entity in images. These image descriptors combine color, pixel-intensity gradients, texture, and steerable filter responses. A Support Vector Machine classifier is trained to detect image descriptors that are not consistent with underlying vector data, digital elevation maps, building models, and camera parameters. In this paper, we train the classifier on visible road segments and non-road data. Thereafter, the trained classifier detects inconsistencies in vectors, which include both occluded and misaligned road segments. The consistent road segments validate our vector, DEM, and 3-D model data for those areas while inconsistent segments point out errors. We further show that a search for descriptors that are consistent with visible road segments in the neighborhood of a misaligned road yields the desired road alignment that is consistent with pixels in the image.

REFERENCES

• 1: McGlone, J. C. and Shufelt, J. A. projective and object Space geometry for monocular building extraction. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle. 54--61, 1994.
• 2: Jefferey A. Shufelt, Performance Evaluation and Analysis of Monocular Building Extraction From Aerial Imagery, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.21 n.4, p.311-326, April 1999 [doi>10.1109/34.761262]
• 3: Wyszecki, G. and Stiles, W. S. Color Science, Concepts and Methods, Quantitative Data and Formulae. John Wiley & Sons, 1983.
• 4: Stricker, M. and Orengo, M. Similarity of color images. In Proceedings of SPIE Conference on Storage and Retrieval for Image and Video Databases III, volume 2420, 381--392, 1995.
• 5: Ma, W. and Zhang, H. Benchmarking of image features for content-based retrieval. In Proceedings of IEEE 32nd Asilomar Conference on Signals, Systems, Computers, Volume 1, 253--257, 1998.
• 6: William T. Freeman , Edward H. Adelson, The Design and Use of Steerable Filters, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.13 n.9, p.891-906, September 1991 [doi>10.1109/34.93808]
• 7: Schölkopf, B. and Smola, A. J. Learning with Kernels. MIT Press, 2002.
• 8: Saalfeld, A. Conflation: automated map compilation, in Technical Report, Computer Vision Laboratory, Center for Automation Research, University of Maryland, 1993.
• 9: Ching-Chien Chen , Craig A. Knoblock , Cyrus Shahabi , Yao-Yi Chiang , Snehal Thakkar, Automatically and accurately conflating orthoimagery and street maps, Proceedings of the 12th annual ACM international workshop on Geographic information systems, November 12-13, 2004, Washington DC, USA [doi>10.1145/1032222.1032231]
• 10: Chen, C. C., Thakkar, S., Knoblock, C. A., and Shahabi, C. Automatically annotating and integrating spatial datasets. In Proceedings of International Symposium on Spatial and Temporal Databases. Santorini Island, Greece, 2003.
• 11: Hild, H. and Fritsch, D. Integration of vector data and satellite imagery for geocoding. In International Archives of Photogrammetry and Remote Sensing (IAPRS), 32, 1998.
• 12: Price, K. Road grid extraction and verification. In International Archives of Photogrammetry and Remote Sensing (IAPRS), 32, 101--106, 1999.
• 13: J. B. Mena, State of the art on automatic road extraction for GIS update: a novel classification, Pattern Recognition Letters, v.24 n.16, p.3037-3058, December 2003 [doi>10.1016/S0167-8655(03)00164-8]
• 14: Xiaqing Wu , Rodrigo Carceroni , Hui Fang , Steve Zelinka , Andrew Kirmse, Automatic alignment of large-scale aerial rasters to road-maps, Proceedings of the 15th annual ACM international symposium on Advances in geographic information systems, November 07-09, 2007, Seattle, Washington [doi>10.1145/1341012.1341035]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.8 Scene Analysis
          Subjects: Surface fitting

General Terms:
Algorithms

Keywords:
computer vision, conflation, machine learning, mapping, multi-cue integration, oblique image analysis, pixel statistics, vector data