3-D Corridor Scene Modeling from a Single View under Natural Lighting Conditions

Takeshi Shakunaga

Research output: Contribution to journalArticlepeer-review

14 Citations (Scopus)

Abstract

This paper discusses a modeling 3-D indoor scene from a single view using a generic object model. It is assumed that an image is made by a well-calibrated camera, and the camera height above the floor is known. The image is assumed to be a projection of a natural corridor scene for which a generic model is known, but the specific model is unknown. This system can model any corridor that satisfies the following conditions: 1) the corridor is a rectangular parallelepiped, 2) there are several lines along each axis of the rectangle parallelepiped, 3) there are not many parallel lines in directions other than along the principle axes, and 4) corridor height is within a known range. The system for 3-D modeling from a single view of such a corridor consists of a robust bottom-up image processing part and a top-down, model-based interpretation part. Image processing treats difficult problems, such as shading, reflection, and high lights, which are invoked by natural lighting conditions. Interpretation extracts feasible 3-D interpretations of the image guided by the generic 3-D corridor model. Both parts are robust enough to make specific corridor models from an image. Experimental results show that specific corridor models can be recovered from a single view with an approximately 1% estimation error.

Original languageEnglish
Pages (from-to)293-298
Number of pages6
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume14
Issue number2
DOIs
Publication statusPublished - Feb 1992
Externally publishedYes

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Fingerprint

Dive into the research topics of '3-D Corridor Scene Modeling from a Single View under Natural Lighting Conditions'. Together they form a unique fingerprint.

Cite this