TU Delft
Year
print this page print this page     
NEDERLANDSENGLISH
Organization
2017/2018 Electrical Engineering, Mathematics and Computer Science Master Computer Science
IN4393
Computer Vision
ECTS: 5
Responsible Instructor
Name E-mail
Dr. J.C. van Gemert    J.C.vanGemert@tudelft.nl
Contact Hours / Week x/x/x/x
0/0/2/2 lecture & 0/0/2/2 seminar & 3h lab
Education Period
3
4
Start Education
4
Exam Period
4
5
Course Language
English
Expected prior knowledge
You are expected to have a working understanding of image processing, linear algebra, and of probability and statistics. Knowledge about pattern recognition and/or machine learning is preferred.

The parallel course "Deep Learning" will combine well with Computer Vision.
Course Contents
The central theme of the computer vision course is the automatic analysis and interpretation of images and videos using computer algorithms. The course explores a range of techniques for image analysis, image matching, image stiching, 3D reconstruction.

The course will have lectures, a seminar and a lab practical:
- The lectures will be on generic topics; building the backbone.
- The seminar will have students read, critique, and present recent deep learning research papers.
- The lab will have students do a project for 3d reconstruction from internet photos.
Study Goals
After successfully completing this course:

- You are able to explain and implement various techniques for feature point detection, and can explain the type of feature points these detectors identify.
- You are able to explain and implement techniques for feature point description and feature point matching. You are able to use these techniques in applications such as object detection and image stitching.
- You are able to explain and implement techniques for image stitching. The student understands the key problems in developing image-stitching algorithms
- You are able to explain and implement basic techniques for feature tracking.
- You are able to develop and explain computer vision systems for real-world applications. In particular, you are able to select computer vision techniques that are to solve a specific image analysis or image understanding problem, to motivate this selection, and to combine the selected techniques into a working computer vision system.
Education Method
Lectures
Lab project.
Seminar: paper reading, critiquing, and presenting.
Assessment
1. Presentation: during the seminar a small group of students presents a paper.
2. The groups that are not presenting have to submit *relevant* questions about the paper the day before.
3. Lab assignment: in a small group of students you experiment with one or more of the discussed techniques and write a research report, and you present your findings.
4. Participation in class
5. Exam about the papers and the theory.
Tags
Artificial intelligence
Image processing