Line Segment Detection and Vanishing Point

Line Segment Detection in Equirectangular Images

In this work, we present a line segment detector in a scene represented by an equirectangular image, i.e. a spherical image of the 360° longitude and 180° latitude field of view. Since the straight lines appears curved in equirectangular images, the standard line detection algorithm cannot be used directly in this context. We extend the LSD [1] to deal with the equirectangular images instead of planar images. So the proposed method has most of the advantages of the LSD method, which gives accurate results with a controlled number of false detections but requires no parameter tuning. This algorithm is tested and compared to other algorithm on a wide set of images.

Vanishing Point Estimation in Equirectangular Images

In this work, an algorithm that quickly and effectively estimates orthogonal vanishing points in equirectangular images of urban environment is presented. Our algorithm is based on the RANSAC (RAndom SAmple Consensus) algorithm and on the characteristics of the line segment in the spherical panorama image of the 360° longitude and 180° latitude field of view. These characteristics can be used to reduce the geometric ambiguity in the line segment classification as well as to improve the robustness of vanishing point estimation. The proposed algorithm is validated experimentally on a wide set of images. The results show that our algorithm provides excellent levels of accuracy for the vanishing point estimation as well as line segment classification.

Publication

  • S. H. Oh and S. K. Jung, “A Great Circle Arc Detector in Equirectangular Images,” in Computer Vision Theory and Applications (VISAPP 2012), International Conference on, 2012, pp. 346–351.
  • S. H. Oh and S. K. Jung, “Vanishing Point Estimation in Equirectangular Images,” in Multimedia Information Technology and Applications (MITA 2012), 2012 8th International Conference on, 2012, pp. 45–47.
  • S. H. Oh and S. K. Jung, “RANSAC-based Orthogonal Vanishing Point Estimation in the Equirectangular Images,” JOURNAL OF KOREA MULTIMEDIA SOCIETY, vol. 15, pp. 1430–1441, 2012.

Reference

  1. R. G. von Gioi, J. Jakubowicz, J.-M. Morel, and G. Randall, “LSD: A Fast Line Segment Detector with a False Detection Control,” Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 32, no. 4, pp. 722–732, Apr. 2010.