The Robotics Institute

Carnegie Mellon Robotics Institute

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

We derive a new class of photometric invariants that can be used for a variety of vision tasks including lighting invariant material segmentation, change detection and tracking, as well as material invariant shape recognition. The key idea is the formulation of a scene radiance model for the class of ?separable? BRDFs, that can be decomposed into material related terms and object shape and lighting related terms. All the proposed invariants are simple rational functions of the appearance parameters (say, material or shape and lighting). The invariants in this class differ from one another in the number and type of image measurements they require. Most of the invariants in this class need changes in illumination or object position between image acquisitions. The invariants can handle large changes in lighting which pose problems for most existing vision algorithms. We demonstrate the power of these invariants using scenes with complex shapes, materials, textures, shadows and specularities.

Keywords

photometric invariants, illumination invariants, material classification

Notes

Associated Center(s) / Consortia: Vision and Autonomous Systems Center

Associated Lab(s) / Group(s): Illumination and Imaging Lab

Number of pages: 8

Text Reference

Srinivasa G. Narasimhan, Visvanathan Ramesh, and Shree Nayar, "A Class of Photometric Invariants: Separating Material from Shape and Illumination," Proceedings of the Ninth IEEE International Conference on Computer Vision (ICCV '05), October, 2003, pp. 1387 - 1394.

BibTeX Reference

@inproceedings{Narasimhan_2003_5038,
   author = "Srinivasa G Narasimhan and Visvanathan Ramesh and Shree Nayar",
   title = "A Class of Photometric Invariants: Separating Material from Shape and Illumination",
   booktitle = "Proceedings of the Ninth IEEE International Conference on Computer Vision (ICCV '05)",
   pages = "1387 - 1394",
   month = "October",
   year = "2003",
   volume = "2",
}

The Robotics Institute

Menu