OVERVIEW

The course offers an introduction to state-of-the-art methods for visual data analysis. In particular it deals with image and video understanding.

AIMS AND CONTENT

LEARNING OUTCOMES

Learning how to represent image content adaptively by means of shallow or deep computational models and biologically-inspired hierarchical models, and how to tackle image classification and categorization problems.

AIMS AND LEARNING OUTCOMES

At the end of the course, students will be able to:

- Understand the main computational vision methods, including classical methods and deep learning approaches.

- Design and implement a CV algorithm of medium difficulty and to analyse/modify algorithms created by others.

- Analyze the results obtained critically and exhaustively. Ability to present the methods studied with an adequate use of technical terms and tools.

PREREQUISITES

Calculus and linear algebra.

Digital image processing and machine learning principles.

TEACHING METHODS

Theoretical classes complemented by practical activities 
Final project (individual or pairs)

SYLLABUS/CONTENT

Learn the principles and practical on: filters and local features. Image similarity: scale invariant interest points, descriptors and matching. Motion analysis and optical flow. 3D vision.  Image representations. Object detection. Image segmentation Pose estimation and action recognition.

RECOMMENDED READING/BIBLIOGRAPHY

material provided by the instructors (slides and papers), see course Aulaweb page

additional reference online book http://szeliski.org/Book/

TEACHERS AND EXAM BOARD

Exam Board

FRANCESCA ODONE (President)

NICOLETTA NOCETI

LORENZO ROSASCO (President Substitute)

ANNALISA BARLA (Substitute)

ALESSANDRO VERRI (Substitute)

LESSONS

LESSONS START

In agreement with the calendar approved by the Degree Program Board of Computer Science.

Class schedule

The timetable for this course is available here: Portale EasyAcademy

EXAMS

EXAM DESCRIPTION

• Actively attending students (delivering assignments on time) 50% project 50% oral  - otherwise 30% individual project - 70% oral

ASSESSMENT METHODS

• Knowledge of the main computational vision methods is assessed with the oral exam. Ability to design and implement a CV algorithm of medium difficulty is assessed by the final project; ability analyse/modify algorithms created by others is assessed by hand-on activities. Ability to analyze the results obtained critically and exhaustively is assessed during the oral, with questions on the project. Ability to present the methods studied with an adequate use of technical terms and tools is assessed by project report and oral exam.