Award Date

1-1-2003

Degree Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Mechanical Engineering

First Committee Member

Georg Mauer

Number of Pages

107

Abstract

In flexible automated manufacturing, robots can perform routine operations as well as recover from atypical events, provided that process-relevant information is available to the robot controller. Real time vision is among the most versatile sensing tools, yet the reliability of machine-based scene interpretation can be questionable. The effort described here is focused on the development of machine-based vision methods to support autonomous nuclear fuel manufacturing operations in hot cells; This thesis presents a method to efficiently recognize 3D objects from 2D images based on feature-based indexing. Object recognition is the identification of correspondences between parts of a current scene and stored views of known objects, using chains of segments or indexing vectors. To create indexed object models, characteristic model image features are extracted during preprocessing. Feature vectors representing model object contours are acquired from several points of view around each object and stored. Recognition is the process of matching stored views with features or patterns detected in a test scene; Two sets of algorithms were developed, one for preprocessing and indexed database creation, and one for pattern searching and matching during recognition. At recognition time, those indexing vectors with the highest match probability are retrieved from the model image database, using a nearest neighbor search algorithm. The nearest neighbor search predicts the best possible match candidates. Extended searches are guided by a search strategy that employs knowledge-base (KB) selection criteria. The knowledge-based system simplifies the recognition process and minimizes the number of iterations and memory usage; Novel contributions include the use of a feature-based indexing data structure together with a knowledge base. Both components improve the efficiency of the recognition process by improved structuring of the database of object features and reducing data base size. This data base organization according to object features facilitates machine learning in the context of a knowledge-base driven recognition algorithm. Lastly, feature-based indexing permits the recognition of 3D objects based on a comparatively small number of stored views, further limiting the size of the feature database; Experiments with real images as well as synthetic images including occluded (partially visible) objects are presented. The experiments show almost perfect recognition with feature-based indexing, if the detected features in the test scene are viewed from the same angle as the view on which the model is based. The experiments also show that the knowledge base is a highly effective and efficient search tool recognition performance is improved without increasing the database size requirements. The experimental results indicate that feature-based indexing in combination with a knowledge-based system will be a useful methodology for automatic target recognition (ATR).

Keywords

Based; Dimensional; Feature; Indexing; Machine Vision; Manufacturing; Nuclear Fuel; Pattern; Pattern Recognition; Recognition; Rule; Search

Controlled Subject

Mechanical engineering; Nuclear engineering

File Format

pdf

File Size

4065.28 KB

Degree Grantor

University of Nevada, Las Vegas

Language

English

Permissions

If you are the rightful copyright holder of this dissertation or thesis and wish to have the full text removed from Digital Scholarship@UNLV, please submit a request to digitalscholarship@unlv.edu and include clear identification of the work, preferably with URL.

Identifier

https://doi.org/10.25669/vmgk-vp6h


Share

COinS