Object recognition for obstacle avoidance in mobile robots

Authors:
José M. Bolanos;Wilfredis Medina Meléndez;Leonardo Fermín;José Cappelletto;Gerardo Fernández-López;Juan C. Grieco
Affiliations:
Mechatronics Group, ELE-302, Simon Bolivar University, Sartenejas, Miranda, Venezuela;Mechatronics Group, ELE-302, Simon Bolivar University, Sartenejas, Miranda, Venezuela;Mechatronics Group, ELE-302, Simon Bolivar University, Sartenejas, Miranda, Venezuela;Mechatronics Group, ELE-302, Simon Bolivar University, Sartenejas, Miranda, Venezuela;Mechatronics Group, ELE-302, Simon Bolivar University, Sartenejas, Miranda, Venezuela;Mechatronics Group, ELE-302, Simon Bolivar University, Sartenejas, Miranda, Venezuela
Venue:
ICAISC'06 Proceedings of the 8th international conference on Artificial Intelligence and Soft Computing
Year:
2006

Citing 5
Cited 1

Use of Fourier and Karhunen-Loeve Decomposition for Fast Pattern Matching With a Large Set of Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine Learning

Machine Learning
Remote Sensing Digital Image Analysis: An Introduction

Remote Sensing Digital Image Analysis: An Introduction
Digital Image Processing

Digital Image Processing
Real-Time Pattern Matching Using Projection Kernels

IEEE Transactions on Pattern Analysis and Machine Intelligence

Dynamic Velocity Field Angle Generation for Obstacle Avoidance in Mobile Robots Using Hydrodynamics

IBERAMIA '08 Proceedings of the 11th Ibero-American conference on AI: Advances in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper is shown an obstacle avoidance strategy based on object recognition using an artificial vision application. Related works focus on the implementation of efficient algorithms for image processing. This work emphasizes in using minimum information from an image in order to generate free obstacles trajectories. The algorithm used is based on Pattern Matching for detection of the robot and Classification for the rest of objects. Each form of detection has its particular algorithm: Cross Correlation for Pattern matching and Nearest Neighbor for Classification. The objective pursued is to demonstrate that, with a very simple system, precise information can be provided to a navigation system in order to find free obstacle paths.