Advanced Vision Course from The university of Edinburgh

Link: https://www.learn.ed.ac.uk/webapps/blackboard/content/listContent.jsp?course_id=_54479_1&content_id=_2584712_1

• Advanced Vision Course Materials

  The goal of this course is provide you with the skills to understand and sketch out solutions to a variety of computer vision applications. You should end up with the skills to tackle novel situations and incompletely defined applications. We will approach this by looking at 6 simplified computer vision systems that cover a large portion of the range of both applied and research computer vision.

  IMPORTANT INFORMATION: This course is not taught by the traditional lectures. Instead, AV uses an Inverted Classroom method. This means that you will have about 15 hours of video to watch in your own time. This material is assessible. There are still 2 full class meetings each week. Normally, at the first meeting we will be discussing any questions that you either suggest in advance or raise in class on the day. The second meeting will be a guest lecture teaching you some advanced vision technology and applications (these talks are not assessed).

  Syllabus

  This module looks at several approaches to building vision systems. The order of the topics might change depending on the practicals. See links to the systems in the left side navigation panel. 

  • System 1: Orthographically viewed non-rigid 2D objects
  • System 2: Recognising classes of shape
  • System 3: Video Tracking (2D)
  • System 4: 3D objects from range data (recognition)
  • System 5: Video based human behaviour understanding
  • System 6: 3D objects from stereo vision (recognition)
  • System 7: Deep nets for Vision

  In the process of doing this, we will encounter a variety of topics in low, middle and high level computer vision

  Other References, Course Notes and Other Study Materials

  There is no perfect text book for this course.

  Recommended course textbooks (All available electronically from the University library)

  
  

  • E.R. Davies - Machine Vision - Theory, Algorithms and Practice, Elsevier, 5th Edition, 2005. (content for about 1/2 of course)

  • Solomon & Breckon, "Fundamentals of Digital Image Processing - A Practical Approach with Examples in Matlab", "Support Web Site", Wiley-Blackwell, 2010, ISBN: 978-0470844731. (content for about 1/2 of course)

  • R. Szeliski, "Computer Vision", Springer, 2011, ISBN: 978-1-84882-934-3. (content for about 1/2 of course)

  Optional supplementary textbooks

  
  

  • T. Morris - "Computer Vision and Image Processing" (Palgrave, 1st Edition, 2004)
  • D. A. Forsyth & J. Ponce - "Computer Vision - a modern approach" (Prentice Hall, 2nd Edition, 2012)

  Online computer vision resources at University of Edinburgh (and beyond)

  
  

  • An index to online notes on some topics covered in the lectures.
  • Online computer vision books.
  • The HIPR image processing summary and on-line interactive demonstration package. Direct access is via HIPR2
  • CVonline - an online encyclopedia of computer vision. (About 1200 of the 1600 topics have entries so far.)
  • Illustrated Dictionary of Computer Vision (UoE internal access only, not wireless)
  • Online documentation for the matlab image processing toolkit.
  • Recent academic and industrial research in computer vision/graphics:
    • ACM SIGGRAPH (graphics)
    • Eurographics Digital Library (graphics)
    • USC Bibliography (computer vision)

  
  

  Online computer vision and image processing courses

  • Online computer vision lectures from the University of Central Florida.
  • Robotic Vision - 50 hour MOOC from Queensland University of Technology
  • Robotics: Perception - MOOC from University of Pennsylvania

  Online MATLAB introductions and tutorials

  • MathWorks - Learn with MATLAB and Simulink Tutorials
  • MATLAB Courses
  • Learn to Code with MATLAB
  • MATLAB Tutorial
  • Introduction to MATLAB | MIT OpenCourseWare

  MATLAB code for the systems demonstrated in the lectures.
• 

  Summary of In-class Activities

  There is a summary of the questions that students emailed to me before class meetings and a summary of the in-class discussion exercises.

  
  
• 

  Inverted Classroom Advice

  Introduction: The expectation is that you take more control of your education in this course. There are no lectures in the traditional sense. Instead, we have pre-recorded 50-60 short videos (typically 15 minutes each) on different topics. You are to watch the videos in your own time (about 2 hours/week).

  There are six main topics and the videos for each topic are intended to be watched in the order listed on the Learn page. However, the topics themselves can largely be watched in any order. There are cross references from one topic to others.

  Using the materials: Each topic has a set of subtopics in a suggested order. You can get to the topic by clicking on one of the "View details" links. On the page for each of the topics, there are links to the subtopics. You can expose these by clicking on the topic name. Each subtopic has potentially 4 resources:

  1. PDF: There are 3 PDF files. The first file is a full size set of the slides that are used in the video. The second file is a 4 slide to a page version. The third set generally has an unfilled box on each content slide. The idea is that you fill in the box while listening to the video; writing helps you remember the concept. The 4-to-a-page format is to save paper if you decide to print the file.
  2. Review question + answer: A question based on the material presented in this subtopic that helps you better understand the material. A brief answer to the question is given
  3. Video: A video explaining the content. It should be playable inline by clicking on the video, or the video can be downloaded in 3 different formats.
  4. References/Examples/Online: Other resources that will help you understand the topic, and also additional topics.

  Timing: The topics are given a planned order and the main course web page has suggested a set of subtopics to be covered each week. You are expected to have watched the videos for that week before the start of the week. The class sessions are used: a) to answer questions that you email to me or ask in class and b) do some non-assessed group discussion on a vision problem related to the week's videos.

  The order and timing of the topics is chosen so that you will have covered the materials needed for the practicals in time.

3D reconstruction projects link

Li Sun - Research fellow at Oxford Robotics Institute, University of Oxford
https://sites.google.com/site/lisunspersonalsite/
He joined H2020 project: http://iliad-project.eu/

Toshiba Cambridge Research Laboratory: https://www.toshiba.eu/eu/Cambridge-Research-Laboratory/Computer-Vision/

Martim Brandao: Vision research http://www.martimbrandao.com/friction-from-vision/

Camera-3D Object recognition-Cloud project at Ryerson Multimedia Research Laboratory: https://www.ryerson.ca/multimedia-research-laboratory/projects/

Devices for 3D camera: http://vislab.isr.ist.utl.pt/rbcog-lab/

Research group of ISR - Institute for systems and robotics including VisLab, DSOR, LaSEEB, IRSg and SIPG: http://welcome.isr.tecnico.ulisboa.pt/research/groups/

Online courses 2019

Algorithm: Link for an undirected graph
Book: Algorithms 4th Edition

IoT with Raspberry Link