ANN design and implementation for real-time object tracking using quadrotor AR.Drone 2.0

KAMEL BOUDJIT, Cherif LARBES, Naeem Ramzan

Research output: Contribution to journalArticle

Abstract

Real-time object detection is crucial for many applications of Unmanned Aerial
Vehicles (UAVs) such as reconnaissance and surveillance, search-and-rescue, and infrastructure inspection. In the last few years, Artificial Neural Networks (ANNs) have emerged as a powerful class of models for recognizing image content, and are widely considered in the computer vision community to be the de facto standard approach for most problems. This paper aims to use a visual- based control mechanism to control a quadrotor, which is in pursuit of a target. The
nonlinear nature of a quadrotor, on the one hand, and the difficulty of obtaining an exact model for it, on the other hand, constitute two serious challenges in designing a controller for this UAV. A potential solution for such problems is the use of intelligent control methods such as those that rely on artificial neural networks.

A novel technique based on Artificial Neural Networks (ANNs) is proposed in this work for the identification and tracking of targets. Multilayer Perceptron (MLP) is used for this purpose. Experimental results and simulations are shown to demonstrate the feasibility of the proposed method for target tracking.
LanguageEnglish
Number of pages22
JournalJournal of Experimental & Theoretical Artificial Intelligence
Early online date30 Aug 2018
DOIs
StateE-pub ahead of print - 30 Aug 2018

Fingerprint

Unmanned aerial vehicles (UAV)
Neural networks
Intelligent control
Multilayer neural networks
Target tracking
Computer vision
Inspection
Controllers
Drones
Object detection

Keywords

  • Artificial intelligence
  • intelligent systems
  • Command and control systems
  • Image recognition

Cite this

@article{bbd54773742244c080503dd59a424be9,
title = "ANN design and implementation for real-time object tracking using quadrotor AR.Drone 2.0",
abstract = "Real-time object detection is crucial for many applications of Unmanned AerialVehicles (UAVs) such as reconnaissance and surveillance, search-and-rescue, and infrastructure inspection. In the last few years, Artificial Neural Networks (ANNs) have emerged as a powerful class of models for recognizing image content, and are widely considered in the computer vision community to be the de facto standard approach for most problems. This paper aims to use a visual- based control mechanism to control a quadrotor, which is in pursuit of a target. Thenonlinear nature of a quadrotor, on the one hand, and the difficulty of obtaining an exact model for it, on the other hand, constitute two serious challenges in designing a controller for this UAV. A potential solution for such problems is the use of intelligent control methods such as those that rely on artificial neural networks.A novel technique based on Artificial Neural Networks (ANNs) is proposed in this work for the identification and tracking of targets. Multilayer Perceptron (MLP) is used for this purpose. Experimental results and simulations are shown to demonstrate the feasibility of the proposed method for target tracking.",
keywords = "Artificial intelligence, intelligent systems, Command and control systems, Image recognition",
author = "KAMEL BOUDJIT and Cherif LARBES and Naeem Ramzan",
year = "2018",
month = "8",
day = "30",
doi = "10.1080/0952813X.2018.1509896",
language = "English",
journal = "Journal of Experimental & Theoretical Artificial Intelligence",
issn = "0952-813X",
publisher = "Taylor & Francis",

}

TY - JOUR

T1 - ANN design and implementation for real-time object tracking using quadrotor AR.Drone 2.0

AU - BOUDJIT,KAMEL

AU - LARBES,Cherif

AU - Ramzan,Naeem

PY - 2018/8/30

Y1 - 2018/8/30

N2 - Real-time object detection is crucial for many applications of Unmanned AerialVehicles (UAVs) such as reconnaissance and surveillance, search-and-rescue, and infrastructure inspection. In the last few years, Artificial Neural Networks (ANNs) have emerged as a powerful class of models for recognizing image content, and are widely considered in the computer vision community to be the de facto standard approach for most problems. This paper aims to use a visual- based control mechanism to control a quadrotor, which is in pursuit of a target. Thenonlinear nature of a quadrotor, on the one hand, and the difficulty of obtaining an exact model for it, on the other hand, constitute two serious challenges in designing a controller for this UAV. A potential solution for such problems is the use of intelligent control methods such as those that rely on artificial neural networks.A novel technique based on Artificial Neural Networks (ANNs) is proposed in this work for the identification and tracking of targets. Multilayer Perceptron (MLP) is used for this purpose. Experimental results and simulations are shown to demonstrate the feasibility of the proposed method for target tracking.

AB - Real-time object detection is crucial for many applications of Unmanned AerialVehicles (UAVs) such as reconnaissance and surveillance, search-and-rescue, and infrastructure inspection. In the last few years, Artificial Neural Networks (ANNs) have emerged as a powerful class of models for recognizing image content, and are widely considered in the computer vision community to be the de facto standard approach for most problems. This paper aims to use a visual- based control mechanism to control a quadrotor, which is in pursuit of a target. Thenonlinear nature of a quadrotor, on the one hand, and the difficulty of obtaining an exact model for it, on the other hand, constitute two serious challenges in designing a controller for this UAV. A potential solution for such problems is the use of intelligent control methods such as those that rely on artificial neural networks.A novel technique based on Artificial Neural Networks (ANNs) is proposed in this work for the identification and tracking of targets. Multilayer Perceptron (MLP) is used for this purpose. Experimental results and simulations are shown to demonstrate the feasibility of the proposed method for target tracking.

KW - Artificial intelligence

KW - intelligent systems

KW - Command and control systems

KW - Image recognition

U2 - 10.1080/0952813X.2018.1509896

DO - 10.1080/0952813X.2018.1509896

M3 - Article

JO - Journal of Experimental & Theoretical Artificial Intelligence

T2 - Journal of Experimental & Theoretical Artificial Intelligence

JF - Journal of Experimental & Theoretical Artificial Intelligence

SN - 0952-813X

ER -