Free-Shape Polygonal Object Localization

  • Xiaolu Sun
  • C. Mario Christoudias
  • Pascal Fua
Conference paper

DOI: 10.1007/978-3-319-10599-4_21

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8694)
Cite this paper as:
Sun X., Christoudias C.M., Fua P. (2014) Free-Shape Polygonal Object Localization. In: Fleet D., Pajdla T., Schiele B., Tuytelaars T. (eds) Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8694. Springer, Cham

Abstract

Polygonal objects are prevalent in man-made scenes. Early approaches to detecting them relied mainly on geometry while subsequent ones also incorporated appearance-based cues. It has recently been shown that this could be done fast by searching for cycles in graphs of line-fragments, provided that the cycle scoring function can be expressed as additive terms attached to individual fragments. In this paper, we propose an approach that eliminates this restriction. Given a weighted line-fragment graph, we use its cyclomatic number to partition the graph into managebly-sized sub-graphs that preserve nodes and edges with a high weight and are most likely to contain object contours. Object contours are then detected as maximally scoring elementary circuits enumerated in each sub-graph. Our approach can be used with any cycle scoring function and multiple candidates that share line fragments can be found. This is unlike in other approaches that rely on a greedy approach to finding candidates. We demonstrate that our approach significantly outperforms the state-of-the-art for the detection of building rooftops in aerial images and polygonal object categories from ImageNet.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Xiaolu Sun
    • 1
  • C. Mario Christoudias
    • 1
  • Pascal Fua
    • 1
  1. 1.CVLab, EPFLLausanneSwitzerland

Personalised recommendations