Publication Date

2019

Document Type

Dissertation/Thesis

First Advisor

Azad, Abul

Degree Name

M.S. (Master of Science)

Legacy Department

Department of Electrical Engineering

Abstract

The advances in IOT, Computer Vision, AI and Machine Learning have made these technologies ubiquitous to our daily lives. From Smart Phones to Connected Vehicles, Cyber Physical systems have been interspersed into everything we interact in today’s world. The aim or this thesis was to explore these advances in Cyber Physical Systems and analyze the different sectors they were affecting. We then hand-picked certain domains and explored further by carrying out practical projects using some of the latest software and hardware resources available. Technologies like Amazon Alexa services, NVIDIA Jetson boards, TensorFlow, OpenCV, NodeJS were heavily employed in our various projects throughout this thesis.

This research is commenced by developing a rail track obstruction monitoring system. Which had an onboard camera focusing on the rail tracks. The images were processed to detect any type of obstruction like sand or snow deposited on the tracks that would hinder the safe operation of railway. These obstruction levels were then sent to a remote server who was responsible to alert the concerned officials whenever obstruction reached beyond a threshold value.

The next project in this research was a collaborated network of IP cameras which were programmed to detect and track a common moving object in a given space. The cameras were governed by a central network system which would process the images from each of the cameras and instruct them to change their pan and tilt in accordance to track an identified moving object.

The collaborated network camera project was then superseded by an Amazon Alexa based text reader which was designed to help the visually impaired. A Raspberry Pi based camera system that could extract a written text from an image was utilized which could process these texts and send it to the Amazon’s Alexa system, which allowed Alexa to read the text for the reader.

Next came the Microsoft Hololens based virtual communication system. This system used the hologram feature of the Microsoft Hololens to project a person’s image onto a virtual environment. This process was realized in real-time using a Python based flask server. This based the foundation of a virtual communication system using holograms.

The thesis then developed systems using machine learning to develop a search and rescue based project using a drone and ground vehicles. The system designed utilized the Google’s TensorFlow machine learning library to train and develop image recognition systems to guide the drone in an unknown indoor environment autonomously. The drone was trained to detect a given object in space and translate the information on the location of the object to the ground vehicles. The ground vehicles would then move towards the object using graph search algorithms like A*.

With this research and practical implementation, this thesis presents some of the latest technologies and services available for one to develop and implement modern age Cyber Physical Systems. It brings one in contact with the different tools and services that are made available for someone to explore and develop cyber-physical systems.

Extent

120 pages

Language

eng

Publisher

Northern Illinois University

Rights Statement

In Copyright

Rights Statement 2

NIU theses are protected by copyright. They may be viewed from Huskie Commons for any purpose, but reproduction or distribution in any format is prohibited without the written permission of the authors.

Media Type

Text

Download

Share

COinS