Range Image Segmentation Based on Differential Geometry: A Hybrid Approach

  title={Range Image Segmentation Based on Differential Geometry: A Hybrid Approach},
  author={Naokazu Yokoya and Martin D. Levine},
  journal={IEEE Trans. Pattern Anal. Mach. Intell.},
  • N. YokoyaM. Levine
  • Published 1 June 1989
  • Mathematics
  • IEEE Trans. Pattern Anal. Mach. Intell.
The authors describe a hybrid approach to the problem of image segmentation in range data analysis, where hybrid refers to a combination of both region- and edge-based considerations. The range image of 3-D objects is divided into surface primitives which are homogeneous in their intrinsic differential geometric properties and do not contain discontinuities in either depth of surface orientation. The method is based on the computation of partial derivatives, obtained by a selective local… 

Segmentation of range images: an orthogonal moment-based integrated approach

A new approach to range image segmentation is presented, in which the region and edge information detected using a set of orthogonal Zernike moment-based operators are combined to provide robust segmentation of range images.

Combined edge- and region-based method for range image segmentation

This paper introduces a method for range image segmentation which combines the useful properties of edge and region-based approaches. In the region-based approach the partial derivatives are first

Segmentation of cross-sectional images using fuzzy logic

  • O. StraussM. Aldon
  • Computer Science
    [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems
  • 1993
The authors present a new segmentation method for range images consisting of a set of planar cross-sectional contours that uses fuzzy criteria for grouping primitives and identifying homogeneous regions using a fuzzy decision-making algorithm.

An Integrated Approach for Segmentation and Representation of Range Images

An integrated approach for segmentation and representation of objects in range images based on the association of edge detection with clustering techniques, and it produces a set of labeled regions plus the coefficients of the plane fitted to each region.

Range-data-based object surface segmentation via edges and critical points

A novel method for range image segmentation based on an integration of edge and region information is presented, which shows that the method is efficient for segmentation of the range images that contain polyhedral objects.

Range Image Segmentation Based on Decomposition of Surface Normals

A method for segmenting range images into homogeneous regions is presented. The resulting regions are either planar or smooth curved surfaces. Surface continuity is estimated by inspecting the values

Integrating edge and surface information for range image segmentation

It is shown that the synergetic combination of both surface- and edge-based segmentation processes can lead to more accurate segmentation results than just either of them alone.

Edge-based image segmentation using curvature sign maps from reflectance and range images

A new approach to image segmentation by edge detection is proposed for preserving objects topology and shape while retrieving precisely located, one-pixel-wide edges. The method is based on mean (H)



Segmentation through Variable-Order Surface Fitting

  • P. BeslR. Jain
  • Computer Science
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 1988
A piecewise-smooth surface model for image data that possesses surface coherence properties is used to develop an algorithm that simultaneously segments a large class of images into regions of arbitrary shape and approximates image data with bivariate functions so that it is possible to compute a complete, noiseless image reconstruction based on the extracted functions and regions.


The approaches presented here are applicable not only to sensor range data corresponding to anyone view of the scene, but also to 3-D model data obtained using the Computer-Aided Geometric Design (CAGD) techniques, and to 3D model built using the sensor data such as the data obtained by combining several views of an object.

Invariant surface characteristics for 3D object recognition in range images

  • P. BeslR. Jain
  • Computer Science
    Comput. Vis. Graph. Image Process.
  • 1986

A facet model for image data

A Perspective on Range Finding Techniques for Computer Vision

  • R. Jarvis
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1983
A variety of approaches to generalized range finding are surveyed and a perspective on their applicability and shortcomings in the context of computer vision studies is presented.

Three-dimensional object recognition

A precise definition of the 3-D object recognition problem is proposed, basic concepts associated with this problem are discussed, and techniques for obtaining, processing, and characterizing range data are surveyed.

Laser range finder based on synchronized scanners.

A new geometrical arrangement is proposed to improve performances of optical triangulation, which allows considerable reduction of the optical head size compared with usual geometries, so the shadow effects are reduced proportionally.