Statistical analysis of local 3D structure in 2D images

KALKAN S., Wörgötter F., Krüger N.

2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, New York, United States Of America, 17 - 22 June 2006, vol.1, pp.1114-1121 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 1
  • Doi Number: 10.1109/cvpr.2006.291
  • City: New York
  • Country: United States Of America
  • Page Numbers: pp.1114-1121
  • Middle East Technical University Affiliated: No


For the analysis of images, a deeper understanding of their intrinsic structure is required. This has been obtained for 2D images by means of statistical analysis [15, 18]. Here, we analyze the relation between local image structures (i.e., homogeneous, edge-like, corner-like or texture-like structures) and the underlying local 3D structure, represented in terms of continuous surfaces and different kinds of 3D discontinuities, using 3D range data with the true color information. We find that homogeneous image patches correspond to continuous surfaces, and discontinuities are mainly formed by edge-like or comer-like structures. The results are discussed with regard to existing and potential computer vision applications and the assumptions made by these applications. © 2006 IEEE.