Advanced Computer Vision

Recommended Prerequisites

Linear algebra and analytic geometry, Matrix Calculus, Differential Calculus, Stochastic Estimation, Computer Vision, Signal Processing

Teaching Methods

The teaching methodologies in this course are based on the presentation of fundamental and conceptual aspects of computer vision in magister classes (theoretical classes), including presentations by students (based on book chapters and papers), complemented with a strong laboratory component where students are able to implement and validate the concepts presented and learened learned on the master classes. The algorithms and applications are implementations based on Matlab. 

Learning Outcomes

This course covers advanced research topics in computer vision. Building on the introductory materials in Computer Vision, this class will prepare students in both the theoretical foundations of computer vision and in  the practical approaches to building real Computer Vision systems. The goal of this course is to give students the background and skills necessary to perform research in computer vision and to develop applications in  domains such as robotics, biometrics, surveillance, biomodeical applications and graphics. Students should understand the strengths and weaknesses of current approaches to research problems and identify interesting open questions and future research directions.  It also aims at  improving students' critical reading and communication skills.

Work Placement(s)

No

Syllabus

1. Feature detection and matching: SIFT, SURF, HOG, MSER, FAST, BRIEF

2. Feature detection and matching: Bayesian-based and deep-learning based approaches

3. Object recognition: classic approaches

4. Object recognition: deep learning-based approaches

5. Visual detection and tracking

6. Activity recognition

7. Visual localization and mapping

Head Lecturer(s)

Hélder de Jesus Araújo

Assessment Methods

Assessment
Exam: 50.0%
Laboratory work or Field work: 50.0%

Bibliography

”Computer Vision: Algorithms and Applications”, Richard Szeliski

 “An Invitation to 3-D Vision: From Images to Geometric Models”,  Yi Ma, S. Soatto, J. Kosecka, S. Sastry

 “Deep Learning”, I. Goodfellow, Y. Bengio, A. Courville

“Machine Learning: A Probabilistic Perspective”, Kevin P. Murphy

“Deep Learning for Computer Vision”, R. Shanmugamani