Project course in Machine Vision, 7.5 Credits

Contents

The course is about an application within one or more of the subjects Image Analysis, 3d Reconstruction, and Pattern Recognition. The relevant topics and theory about a project management model, e.g. Scrum, are introduced initially, followed by a larger software development project. The design of the project varies from year to year. Examples of possible projects are:

- Design an application that takes a set of images of a living room, builds a 3D model of it and visualizes it together with the IKEA bookcase "Billy" (or another piece of furniture).

- Design an application that given a number of scanned itemized phone bills calculates the phone subscription plan that would be the cheapest.

- Design an application that given a point cloud acquired by a laser scanner in a sparse forest, identifies trees and calculates their diameter at breast height.

- Develop a method that given inputs such as digital images and/or 3D point clouds from a forest, detects trees and classifies tree species.

- Identify and localize fruits in images using classifier fusion.

- Analyze 3D images from a Kinect-camera and detect people, trees, shrubs, and stones.

Expected learning outcomes

Syfte/mål:

Knowledge and understanding

After having completed the course the student will be able to:

- explain central concepts within image analysis, 3D reconstruction, and/or pattern recognition (FSR 1),

- account for the priciples of the used project management model, e.g. Scrum (FSR 2), and

- explain the varios roles used by the project management model (FSR 3).

Skills and abilities

After having completed the course the student will be able to:

- demonstrate an ability to work in projects in groups of at least 4 people, including working in non-self-selected groups (FSR 4),

- analyze a problem within one or more of the subjects image analysis, 3D reconstruction, and pattern recognition (FSR 5),

- demonstrate skills in working in a project management model (FSR 6),

- demonstrate an ability to group-wise collect, present, and apply knowledge neccessary to solve the problem (FSR 7),

- identify ambiguities in the given problem specification and to propose clarifications (FSR 8), and

- use a version control system for source code and other documentation (FSR 9).

Values and attitudes

After having completed the course the student will be able to:

- evaluate different proposed solutions for problems in one or more of the subjects image analysis, 3D reconstruction, and pattern recognition (FSR 10),

- reflect on their own effort in a project (FSR 11),

- assess the quality of the result of the group (FSR 12), and

- suggest how the results could be improved (FSR 13).

Required Knowledge

To be admitted you must have 60 ECTS-credits in Computing Science or 2 years of completed studies, in both cases including Statistics for Computer Scientists, 5MS005 and either Matrix Computations and Applications, 5DA002 or the courses Fundamentals of Artificial Intelligence, 5DV121, Linear Algebra 5MA019, Single variable Analysis 5MA009 and a basic course in Programming Methodology (e.g. 5DV104, 5DV105, 5DV106, or 5DV114) or equivalent. Proficiency in English equivalent to Swedish upper secondary course English A (IELTS (Academic) with a minimum overall score of 5.5 and no individual score below 5.0. TOEFL PBT
(Paper-based Test) with a minimum total score of 530 and a minimum TWE score of 4. TOEFL iBT (Internet-based Test) with a minimum total score of 72 and a minimum score of 17 on the Writing Section).
Where the language of instruction is Swedish, applicants must prove proficiency in Swedish to the level required for basic eligibility for higher studies.

Form of instruction

The course begins with an introduction in the form of lectures to the relevant topics and the project managament model. Then follows a larger programming project that is central to the course. The aim is
to get experience of working in a development team to generate a working prototype from a vague problem specification. A further goal is to individually and in groups gather knowledge necessary for the task. The work is primarily organized under an agile development model, such as Scrum. The work includes work in small and large groups and in-depth studies.

Examination modes

The examination on the course consists of a written account of the student's effort in the project, mainly as a time log (FSR 4, 6-7, 9), and a written final report in the form of a home exam (FSR 1-3, 5-8, 9-12). Since the practical work in a group is central to the course, the majority of the attendance during the practical work is mandatory.

On the course, the grades given are Fail (U), Pass (3) or Pass with Mark (4), or Pass with Distinction (5).

The course grade is an overall assessment of the two examinations parts and is set when both reports have been inspected. Individual students who do not pass at the end but who regularly participated in the project can get an extra task. In this case, the responsible teacher are allowed to limit the maximum grade to Pass (3). Students that have not passed at the end of the the course, optionally including time for the extra task, are given the grade Fail (U).

Limitation in the number of examinations:

Participants that do not pass the course are referred to the next instance of the course.

A student who has passed an examination may not be re-examined. A student who has failed twice on a course or segment of a course, has the right to have another examiner appointed, unless there exist special reasons (Higher Education Ordinance Chapter 6, section 22). Requests for new examiners are made to the head of the Department of Computing Science.

Other regulations

TRANSFER OF CREDITS

This course may not be used towards a degree, in whole or in part, simultaneously with another course of similar content. If in doubt, consult the student counselors at the Department of Computing Science and / or program director of your program.

In particular, this course can not, in whole, be used in a degree together with one of the courses Image Analysis (5DV015), Geometrical Image Analysis (5DV055) eller Pattern Classification (5DV025).

Transfer of credits is considered individually (see the University Code of Rules and regulations for transfer of credits). An application for transfer of credits is made on a special form and should be submitted to the Faculty of Science and Technology, Umeå University.