Multispectral piecewise planar stereo using Manhattan-world assumption

Fernando Barrera, Felipe Lumbreras, Angel D. Sappa

Research output: Contribution to journalArticleResearchpeer-review

26 Citations (Scopus)

Abstract

This paper proposes a new framework for extracting dense disparity maps from a multispectral stereo rig. The system is constructed with an infrared and a color camera. It is intended to explore novel multispectral stereo matching approaches that will allow further extraction of semantic information. The proposed framework consists of three stages. Firstly, an initial sparse disparity map is generated by using a cost function based on feature matching in a multiresolution scheme. Then, by looking at the color image, a set of planar hypotheses is defined to describe the surfaces on the scene. Finally, the previous stages are combined by reformulating the disparity computation as a global minimization problem. The paper has two main contributions. The first contribution combines mutual information with a shape descriptor based on gradient in a multiresolution scheme. The second contribution, which is based on the Manhattan-world assumption, extracts a dense disparity representation using the graph cut algorithm. Experimental results in outdoor scenarios are provided showing the validity of the proposed framework. © 2012 Elsevier B.V. All rights reserved.
Original languageEnglish
Pages (from-to)52-61
JournalPattern Recognition Letters
Volume34
Issue number1
DOIs
Publication statusPublished - 1 Jan 2013

Keywords

  • Color and infrared images
  • Dense disparity maps from multispectral stereo
  • Multispectral stereo rig

Fingerprint Dive into the research topics of 'Multispectral piecewise planar stereo using Manhattan-world assumption'. Together they form a unique fingerprint.

Cite this