Recognition of parameterized objects from 3D data: a parallel implementation

doi:10.1016/0262-8856(94)90011-6

Image and Vision Computing

Volume 12, Issue 9, November 1994, Pages 573-582

https://doi.org/10.1016/0262-8856(94)90011-6 Get rights and content

Abstract

We present a parallel implementation of an algorithm designed to recognize fully parameterized objects from 3D data. For the purpose of recognition, the mapping of sensed features with model features is structured as an interpretation tree. However, with the use of parameterized models, most of the computation performed during the tree search is actually spent in the updating step of the object parameters, this process being executed through a SUP/INF network. A major contribution of our implementation is the exploitation of the intrinsic parallelism of the SUP/INF network, while the interpretation tree search is also distributed on our transputer based MIMD architecture.

References (16)

WEL Grimson et al.
I Model-based recognition and localization from sparse range or tactile data
Int. J. Robotics Res.
(1984)
WEL Grimson
Object Recognition by Computer: The Role of geometric constraints
(1991)
ID Reid
Recognizing parameterized objects from range data
Reid, I D and Brady, J M ‘Recognition of object classes from range data’, Artif. Intell. (to...
AM Flynn et al.
Recognition algorithms for the connection machine
D Holder et al.
Polyhedral object recognition with sparse data in SIMD processing mode
TS Newman et al.
3D object recognition: Interpretation tree search on a MIMD machine
Proc. 11th IAPR Int. Conf. on Patt. Recogn.
(1992)
WW Bledsoe
The sup-inf method in presburger arithmetic

There are more references available in the full text version of this article.

Cited by (6)

Projective calibration of a laser-stripe range finder
1996, Image and Vision Computing
We discuss the calibration of a laser triangulation range system mounted on a robot vehicle. Range sensing in general is briefly reviewed, followed by a description of the Oxford/NEL range finder, a sensor mounted on the Oxford AGV for use in object recognition and acquisition tasks. Calibration of the range sensor is achieved by modelling it as a projectivity between two planes: the plane of the light stripe and the plane of the camera's detector array. The vehicle is driven to a known location where there exists an arrangement of orthogonal planes whose equations expressed in world coordinates have been premeasured accurately. Known vehicle position relative to world coordinates, known sensor position relative to vehicle coordinates, and a set of world plane to image point correspondences lead to an overdetermined set of linear equations which can be solved to give the required eight unknown parameters of the projectivity.
Recognition of object classes from range data
1995, Artificial Intelligence
We develop techniques for recognizing instances of 3D object classes (which may consist of multiple and/or repeated sub-parts with internal degrees of freedom, linked by parameterized transformations), from sets of 3D feature observations. Recognition of a class instance is structured as a search of an interpretation tree in which geometric constraints on pairs of sensed features not only prune the tree, but are used to determine upper and lower bounds on the model parameter values of the instance. A real-valued constraint propagation network unifies the representations of the model parameters, model constraints and feature constraints, and provides a simple and effective mechanism for accessing and updating parameter values.
Recognition of objects with multiple internal degrees of freedom, including non-uniform scaling and stretching, articulations, and sub-part repetitions, is demonstrated and analysed for two different types of real range data: 3D edge fragments from a stereo vision system, and position/surface normal data derived from planar patches extracted from a range image.
Image Analysis and Computer Vision: 1994
1995, Computer Vision and Image Understanding
This paper presents a bibliography of over 1900 references related to computer vision and image analysis, arranged by subject matter. The topics covered include computational techniques; feature detection and segmentation; image analysis; two-dimensional shape; pattern; color and texture; matching and stereo; three-dimensional recovery and analysis; three-dimensional shape; and motion. A few references are also given on related topics, such as geometry and graphics, compression and processing, sensors and optics, visual perception, neural networks, artificial intelligence, and pattern recognition, as well as on applications.
Automatic space analysis using laser scanning and a 3d grid: To industrial plant facilities
2020, Sustainability (Switzerland)
Modeling tower crane operator visibility to minimize the risk of limited situational awareness
2014, Journal of Computing in Civil Engineering
Automated recognition of 3D CAD objects in site laser scans for project 3D status visualization and performance control
2009, Journal of Computing in Civil Engineering

^∗: F Chenavier is with Matra Marconi Space, and is attached to the University of Oxford.

²: {fred, ian, jmb}@robots.ox.ac.uk

View full text

Recognition of parameterized objects from 3D data: a parallel implementation

Abstract

I Model-based recognition and localization from sparse range or tactile data

Int. J. Robotics Res.

Object Recognition by Computer: The Role of geometric constraints

Recognizing parameterized objects from range data

Recognition algorithms for the connection machine

Polyhedral object recognition with sparse data in SIMD processing mode

3D object recognition: Interpretation tree search on a MIMD machine

Proc. 11th IAPR Int. Conf. on Patt. Recogn.

The sup-inf method in presburger arithmetic