30 April 1992 Three-dimensional range image segmentation and fitting by quadratic surfaces
Author Affiliations +
Abstract
This paper presents a robust segmentation and fitting technique. The method randomly samples appropriate range image points and fits them into selected primitive type. From K samples we measure residual consensus to choose one set of sample points which determines an equation to have the best fit for a homogeneous patch in the current processing region. A method with compressed histogram is used to measure and compare residuals on various noise levels. The method segments range image into quadratic surfaces, and works very well even in smoothly connected regions.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xinming Yu, Tien D. Bui, Adam Krzyzak, "Three-dimensional range image segmentation and fitting by quadratic surfaces", Proc. SPIE 1611, Sensor Fusion IV: Control Paradigms and Data Structures, (30 April 1992); doi: 10.1117/12.57954; https://doi.org/10.1117/12.57954
PROCEEDINGS
10 PAGES


SHARE
RELATED CONTENT

Object-Oriented Image Analysis
Proceedings of SPIE (June 06 1987)
Vision system for ALV
Proceedings of SPIE (September 25 1998)
Joint high dynamic range imaging and color demosaicing
Proceedings of SPIE (October 26 2011)

Back to Top