3 October 1995 Color characterization for landmark selection by a neural network
Author Affiliations +
Many of visual navigation strategies for an autonomous mobile robot are landmark based. A vehicle to determine its position needs to refer to absolute references in the environment, so landmarks are required to be invariant for rotation, translation, scale and perspective. A straightforward alternative is to be able to characterize invariantly the context where landmarks are placed. In this paper, we show as a neural network appropriately trained, is able to recognize context where landmarks are located in the scene. The early results seem to be interesting.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ettore Stella, Ettore Stella, F. Monte, F. Monte, Laura Caponetti, Laura Caponetti, Arcangelo Distante, Arcangelo Distante, "Color characterization for landmark selection by a neural network", Proc. SPIE 2588, Intelligent Robots and Computer Vision XIV: Algorithms, Techniques, Active Vision, and Materials Handling, (3 October 1995); doi: 10.1117/12.222670; https://doi.org/10.1117/12.222670


Breaking out of the black box a new approach...
Proceedings of SPIE (January 07 1999)
A self-learning machine vision system
Proceedings of SPIE (March 03 2004)
Machine vision techniques for rose grading
Proceedings of SPIE (November 28 1993)
Pyramid nets for computer vision
Proceedings of SPIE (February 28 1991)

Back to Top