A vision-based object tracking system for weight sensitive unmanned systems

Other Title(s)

نظام تتبع بصري للمنظومات الذكية حساسة الوزن

Dissertant

Abu Ghaliyah, Karam Mahmud Hasan

Thesis advisor

Sababhah, Bilal

Comitee Members

al-Qarallah, Isam Ata Allah Y.
Rawashidah, Nadhir
al-Haj, Ali

University

Princess Sumaya University for Technology

Faculty

King Abdullah II Faculty of Engineering

Department

Department of Electrical Engineering

University Country

Jordan

Degree

Master

Degree Date

2016

English Abstract

Object detection and tracking are significant and complex tasks in the field of computer vision.

This field has many applications like surveillance as in detecting abandoned bags in airports or tracking a suspect, vehicle navigation, and autonomous robot navigation for unmanned vehicles or industrial robots.

Object tracking and detection in surveillance videos for humans, vehicle or any other object is a challenging research topic in computer vision; especially in a dynamic environment and non-static cameras.

Non-static cameras involves more challenges in motion classification.

Those challenges rise due to the virtual moving of the whole scene.

Object tracking and detection are essential technologies to fight against terrorism, crimes and for traffic management.

The ability of detecting and tracking targets could also play a significant role in robots’ navigation systems.

Visual tracking systems may issue the direction and speed of motion to the robot to keep the target in its angle of view either by moving the robot itself or the vision sensors.

In this work, a compact size tracking and guiding system that could be mounted on UAV platforms is presented.

The system combines a motion detection technique that could be used with non-static cameras in addition to color filtering to detect and track objects in the field of UAV view.

This hybrid system provides a more reliable tracking system.

The proposed system implements algorithms from literature in a hybrid approach that utilizes the best of each algorithm and avoids heavy resources usage.

Experimental tests showed the system’s ability to detect and track low detailed targets.

The system also showed flexible optimization for speed, as it is possible to keep tracking target objects even with frame skipping giving real-time processing.

Main Subjects

Electronic engineering

No. of Pages

67

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-693682