Model-Based Recognition and Localization from Sparse Range or Tactile Data
W. Eric L. Grimson, Tomás Lozano‐Pérez · The International Journal of Robotics Research · 1984
This paper discusses how local measurements of three- dimensional positions and surface normals ( recorded by a set of tactile sensors, or by three-dimensional range sensors), may be used to identify and locate objects from among a set of known objects. The objects are modeled as polyhedra having up to six degrees of freedom relative to the sensors. We show that inconsistent hypotheses about pairings between sensed points and object surfaces can be discarded efficiently by using local constraints on distances between faces, angles between face normals, and angles (relative to the surface normals) of vectors between sensed points. We show by simu lation and by mathematical bounds that the number of hy potheses consistent with these constraints is small. We also show how to recover the position and orientation of the object from the sensory data. The algorithm's performance on data obtained from a triangulation range sensor is illustrated.
Cited by 586 works. doi:10.1177/027836498400300301
Authors
References
- Mathematical handbook for scientists and engineers
- Spatial Planning: A Configuration Space Approach
- Description and recognition of curved objects☆
- A Perspective on Range Finding Techniques for Computer Vision
- From Images to Surfaces
- Texture gradient as a depth cue
- Multilevel computational processes for visual surface reconstruction
- Psychophysical and computational studies towards a theory of human stereopsis
- Recognizing and Locating Partially Visible Objects: The Local-Feature-Focus Method
- Depth from edge and intensity based stereo