Copyright 2017 - CSIM - Asian Institute of Technology

Selected Topic: Introduction to Machine Vision for Robotics and HCI

Course code: AT70.9007
Credits: 3(3–0)
This course is elective

Course objectives

This special topics course will be a primer on the use of machine vision in robotics applications, information systems, and human-computer interfaces. The course will be a mixture of lectures on basic material, presentations of research from the primary academic literature, and individual projects involving application of machine vision technology to real-world problems. The course will prepare students to do thesis research in the field.

Learning outcome

Techniques and applications of machine vision in robotics, HCI, and information systems.

Prerequisite(s)

Some programming experience and mathematical sophistication

Course outline

I. Introduction  

II. Basic image processing

1. Camera geometry and calibration
2. Convolution
3. Smoothing
4. Filtering  

III . Basic mathematical techniques

1. Singular Value Decomposition (SVD)
2. Principle Components Analysis (PCA)
3. Expectation Maximization (EM)
4. Extended Kalman Filter (EKF)
5. Particle Filter  

 

IV. Research and development tools

1. Matlab
2. OpenCV library  

V. Applications (student presentations)

1. Matching over multiple views
2. 3D structure estimation
3. Tracking and motion estimation
4. Object detection and recognition
5. Face detection and recognition
6. Content-based image retrieval
7. People tracking
8. Vision for robot control
9. Geographic information systems  

VI. Project presentations

Learning resources

Textbook

Lecture notes provided by instructor

Journals

International Journal of Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Computer Vision and Pattern Recognition Conference
European Conference on Computer Vision
International Conference on Computer Vision
IEEE International Conference on Robotics and Automation

Reference books

D. Forsyth and J. Ponce: Computer Vision - A Modern Approach , Prentice-Hall, 2003.  
C. Tomasi: Convolution, smoothing, and image derivatives .  
C. Tomasi: Estimating Gaussian mixture densities with EM - A Tutorial .  
C. Tomasi: Mathematical Modeling of Continuous Systems .  
Selected readings from primary academic literature (papers will be posted to course web site)

Grading

The final grade will be computed from the following constituent parts:
in-class discussion (20%),
presentations (30%),
project (50%).
Closed-book examination is used for both mid-semester and final exam.

Back to the list

 

Login Form

Search

School of Engineering and technologies     Asian Institute of Technology