Scribd
Upload
371 views2 pages

Elg5163 PDC

This course outline provides information for an upper-level machine vision course offered in the fall 2013 semester. The course will introduce students to computer vision tools and techniques for developing autonomous systems. Topics covered include image processing, camera calibration, motion analysis, 3D imaging, modeling and object recognition. Students will complete assignments, a project involving a literature review and experimental work, an in-class presentation, and a final exam. The goal is for students to gain an understanding of machine vision beyond algorithms and learn how to design complete vision systems.

Uploaded by

J Jesús Villanueva García
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
371 views2 pages

Elg5163 PDC

This course outline provides information for an upper-level machine vision course offered in the fall 2013 semester. The course will introduce students to computer vision tools and techniques for developing autonomous systems. Topics covered include image processing, camera calibration, motion analysis, 3D imaging, modeling and object recognition. Students will complete assignments, a project involving a literature review and experimental work, an in-class presentation, and a final exam. The goal is for students to gain an understanding of machine vision beyond algorithms and learn how to design complete vision systems.

Uploaded by

J Jesús Villanueva García
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

ELG 5163 - Machine Vision Course Outline Fall 2013

Professor: Email: WEB Page: Lectures: Consultation: Reference Manual: Pierre Payeur, SITE 5066 ppayeur@site.uottawa.ca www.eecs.uottawa.ca/~ppayeur/ELG5163 Monday, 11:30 AM to 1:00 PM, SITE C0136 Thursday, 1:00 PM to 2:30 PM, SITE C0136 Monday, 2:00 PM to 4:00 PM, SITE 5066 Introductory Techniques for 3-D Computer Vision, by E. Trucco & A. Verri, Prentice Hall, 1998 Course notes - will be available online. Selected research papers - will be available online. Other references (optional): Machine Vision, by R. Jain, R. Kasturi, B. G. Schunck, McGraw Hill, 1995. Computer Vision, A Modern Approach, by D.A. Forsyth & J. Ponce, Prentice Hall, 2nd edition, 2012. Learning OpenCV, by G. Bradski & A. Kaehler, OReilly, 2008. Overview: Machine vision is the area of artificial intelligence concerned with the use of computer vision tools to collect and process information in order to provide automatic systems or robots with some autonomy. The objective of this course is to present an insight into the world of computer vision that goes beyond image processing algorithms. Students will acquire a knowledge and an understanding of artificial vision from a practical implementation perspective and gain the capability to design vision systems. Various aspects will be examined and the main approaches currently found in the literature will be discussed, opening the door to many research themes. Prerequisites: It is not mandatory for students to be already familiar with the basic concepts of computer vision or image processing. However, some preliminary exposure to the concepts of spatial transformations in 3-D space will be helpful. Some programming experience in high-level languages (C/C++, Java or Matlab) is required to be able to implement existing algorithms in computer vision. Some preliminary exposure to computer vision or image processing might be helpful but the course will also review the basic concepts.

Course Content: The following list of topics will be covered but will likely evolve. Basics of computer vision Nature of images, homogeneous transformations, quaternions, geometrical and optical image formation, perspective projection, camera technologies and vision systems design. Basics of image processing Filtering, edge detection, features detection, contours, segmentation, morphological operators. Calibration Camera model, intrinsic and extrinsic camera parameters, camera calibration. Motion Motion detection, optical flow, object tracking, motion capture. Three-dimensional imaging Epipolar geometry, stereoscopic vision, active range imaging, structured lighting. Modeling and registration Modeling techniques for autonomous systems, data fusion, uncertainty mapping, registration, pose estimation. Applications Quality control, visual feedback, mapping and robot guidance, activity monitoring, motion estimation, autonomous systems, biomedical imaging devices. Evaluation: Project proposal: 5% A project proposal will be submitted early in the term. It will identify a topic relevant to machine vision that you wish to explore futher, as well as a number of sources of documentation from the literature, and present a framework and timeline that will guide your project over the term. Two or three assignments will be given on selected topics. These will involve some programming and evaluation of algorithms in machine vision. Toward the end of the term, every student will present his/her project work, including the literature review and the experimental component. A final project report taking the form of a formal scientific paper will be submitted at the end of the term. It will include a literature review, details on the implementation of solutions to a given problem, and some experimental testing and analysis. The originality of the treatment of the approach and the analytical content, as well as the presentation style and format, will be considered and graded. A final exam will be written in class. Date to be determined.

Assignments:

20%

Presentation:

20%

Project paper:

20%

Exam:
Update: September 3rd, 2013

35%

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy