Paper Info
Title
Parallel robot vision using genetic algorithm and object centroid
Abstract
Parallel Robots are playing a very important role in the medical, automotive, food and many manufacturing applications. Due to its high speed and efficient operation, it is gaining an increasing popularity in these application domains. For making the parallel robots more automated and an intelligent a machine vision system with robust performance is needed. Here, a Machine Vision Algorithm based on Genetic Evolutionary principles for object detection in the Delta Parallel Robot based systems is proposed. The solution applies a simple, robust and high speed algorithm to accurately detect objects for the application domain. The Image Acquisition of a robot's workspace is performed by using a camera mounted on the end-effector of the robot. The system is trained with the object database and with the most significant visual features of every class of objects. Images are assessed periodically for detecting the Region of Interest (ROI) within an image of the robot's workspace. The ROI is defined as an area in which a presence of object features is detected. The ROI detection is achieved by applying a random sampling of pixels and an assessment of color threshold of every pixel. The color intensity is assumed as one of the features for classification that is based on the training data. After classification process, the Genetic Algorithm is applied to locate the centroid of an object in every class. In a given application class, the Centroid is considered as the most important feature. Knowledge of an approximate location of the Centroid of objects helps to maintain a high speed and reliable pick and place operations of the Delta robot system. The proposed algorithm is tested by detecting presence of electronic components in the workspace. Experimental results show that the suggested approach offers a reliable solution for the Delta robot system.
Year
DOI
Venue
2011
10.1007/978-3-642-27579-1_22
EUROCAST (2)
Keywords
Field
DocType
application domain,roi detection,delta robot system,object feature,genetic algorithm,object detection,parallel robot,high speed,object centroid,object database,parallel robot vision,delta parallel robot,machine vision system
Parallel manipulator,Object detection,Computer vision,Machine vision,Delta robot,Workspace,Computer science,Artificial intelligence,Region of interest,Robot,Centroid,Machine learning
Conference
Volume
ISSN
Citations 
6928
0302-9743
1
PageRank 
References 
Authors
0.63
5
3
Name
Order
Citations
PageRank
Anup Kale121.33
Zenon Chaczko29036.74
Imre Rudas3425.22