Course introduction & Project overview

Loading...

來自 EIT Digital 的課程

Capstone: Autonomous Runway Detection for IoT

48 個評分

EIT Digital

Capstone: Autonomous Runway Detection for IoT

48 個評分

課程 4（共 4 門，Specialization Development of Secure Embedded Systems）

This capstone project course ties together the knowledge from three previous courses in IoT though embedded systems: Development of Real-Time Systems, Web Connectivity & Security and Embedded Hardware and Operating Systems. The students will develop a larger system using the learning outcomes from these courses, and the students will evaluate the developed system in a real-world programming environment. This course is a true engineering task in which the student must, not only implement the algorithm code, but also handle the interfaces between many different actors and hardware platforms. The students will learn how to motivate engineering decisions and how to choose implementations to make a system actually running. The students will also learn to evaluate the efficiency and the correctness of their system as well as real-world parameters such as energy consumption and cost.

從本節課中

Introduction and methods

Looking for a project where you actually learn practical software development? In this course you can show off your newly developed embedded software skills by putting together a large scale system consisting of a wide range of functionalities! This project makes you take a step into the most modern edge of software development for embedded systems, we implement a system for IoT-based autonomous aircraft landing for future airliners. In other words, a system based on embedded real-time processing devices, secure web connectivity and cloud-based high performance back ends. The project does not only focus on the implementation of the algorithms in these parts, but also something every embedded software designer faces sooner or later: the interfacing of the parts. We offer you the opportunity to participate in this project and let loose your engineering skills! Creativity and innovation are the key points to succeed as we give you free hands to pick all the software pieces together, and you show us the result of you innovative thinking in a project which can be applied in real industrial products today.

Course introduction & Project overview7:56

Algorithms and Framework10:07

與講師見面

Juha Plosila
Associate Professor
Information Technology

Landing is one of the most critical phases during a flight.

It is the second thing a pilot learns in training after basic flight control and

recovery techniques.

Touchdown is the first phase.

An aircraft has to dump all this kinetic energy that keeps the aircraft flying.

It's a fine maneuver that should be done right, not too soft, not too hard.

Landing also is one of the most dangerous phases and

most aircraft accidents take place either during the take off or landing.

Instrumental guidance systems are, therefore,

a great advantage to the pilots.

In this project,

we focus on runway detection by using image filtering techniques.

Our runway detection algorithm is based on video frames.

This means that we have a camera mounted on the aircraft

which is recording the approach.

The frames captured by the camera is then forwarded to image processing algorithms.

To easily spot the visual characteristic of the runway,

we will filter out other details than the edges in the frame.

This makes the image simpler to process

because now the picture only contains the most basic properties for

determining a square runway in an otherwise diverse landscape.

Okay, so runway detection already exists but

now we want to build the next generation of landing system based on IoT.

Let's consider the aircraft being a complex sensor system

capable of recording and sending filtered video frames.

These frames can now be sent to a Cloud server on ground,

in which high performance algorithms

such as deep learning can be applied on the video frames to optimize the landing.

This type of heavy processing can not be executed on site because of lacking

processing power and it must therefore be forwarded to a Cloud server.

Of course, with data transfer, we expose a risk to leak

confidential information that could endanger the safety of the aircraft.

Check out Norse, my website,

that visualizes the realtime attempts to break IT security worldwise.

The link must, therefore, be secured before data transfer can begin.

Let's recap the project.

Your task is to build an autonomous landing system or aircraft.

The system should detect a wrong way from a video frame.

This is done by recording the landing with a camera mounted on the aircraft,

the image is filtered by an edge detection algorithm and the filtered image is

encrypted and sent to a Cloud server for further processing over a secure link.

This course is built on three previous courses of this specialization.

From the course embedded operating system and

hardware, you will apply your skills for planning the embedded hardware platform.

Planning the performance required for the processing, the cost of building such

system and the energy such a system would consume.

You will need to program a lot in this course and most of the programming

will be based on the course development of realtime systems.

The realtime processing of system must match the system requirements and

correct scheduling must be ensured.

Finally, you will need to utilize your skills from course web connectivity and

security in embedded systems to establish the web connectivity and

ensure the secure transfer of data to the Cloud server.

My name is and

I am a teacher in computer science at the University of Turku in Finland.

You can check out our website to learn more about the University of Turku.

探索我們的目錄

免費加入並獲得個性化推薦、更新和優惠。

Coursera 致力於普及全世界最好的教育，它與全球一流大學和機構合作提供在線課程。

© 2019 Coursera Inc. 保留所有權利。

通過 App Store 下載

通過 Google Play 獲取