Difference between revisions of "Stefan Karlsson/PersonalPage/Education/MultiScaleCourse"
| (14 intermediate revisions by one user not shown) | |||
| Line 1: | Line 1: | ||
| − | |||
| − | + | {{Infobox | |
| + | |image = [[Image:Segmentation-picture.png|200px]] | ||
| + | |header1 = Multiscale and Multidimensional Analysis | ||
| + | |header2 = '''Contact:''' [[Fernando Alonso-Fernandez]], [[Stefan Karlsson]] | ||
| + | }} | ||
| − | == | + | ='''Multiscale and Multidimensional Analysis course (Autumn 2014)'''= |
| − | + | ||
| − | + | This is the web page for the course '''Multiscale and Multidimensional Analysis'''. | |
| − | + | ||
| − | = | + | === Course information === |
| − | + | ||
| − | - | + | Instructors: [[Fernando Alonso-Fernandez]], [[Stefan Karlsson]] |
| − | + | Class time: The schedule for the course will be made ad hoc, using doodle or by agreement over email. | |
| − | + | Class location: E5. | |
| − | + | Office hours: by appoinment. | |
| + | Contact: Stefan.Karlsson(AHTT)hh.se or feralo(AHTT)hh.se. | ||
| − | + | ===Course description=== | |
| − | - | + | The course is focused on the topic of multi-scale and multi-dimensional signal analysis. More particularly, it will provide with advanced concepts and techniques to extract useful information from signals of arbitrary dimension (such as audio (1D) and video (3D) signals), drawing on topics from the signal/image processing and computer vision fields. |
| − | + | There will be exercises made available to you during some modules, and a project at the end of the course. For each exercise there are several tasks for you to perform. These are to be completed and discussed during the sessions. Instructions on how to report on them will be given in the descriptions for the exercises. Communication '''WILL NOT''' be done through blackboard. | |
| + | Office hours: There are no regularly scheduled office hours, but you can always arrange a meeting with the instructors. Just send an email or drop by. | ||
| − | + | Grading: by practical assignment | |
| − | - | + | Prerequisites: linear algebra (vector and matrix operations), probability theory/statistics, signal processing, image processing and multi-variate calculus. The course assumes a programing background (primarily in Matlab). |
| − | |||
| − | + | =Exercises and sessions (files will be made available before each session)= | |
| + | 1. [[Media:MultiScaleApproaches.pdf|'''Linear scale space''']] (<u>Stefan</u>): 1 WEEK | ||
| − | + | * Waveletets (Gabor, Mexican Hat) | |
| + | * Pyramids (Gaussian, Laplacian, etc.) | ||
| − | + | * Median filtering | |
| − | + | → [[Media:MultiDimE1.zip|PRACTICAL ASSIGNMENT]] | |
| − | |||
| − | |||
| + | 2. [http://islab.hh.se/mediawiki/Directionality_Analysis '''Directionality analysis'''] (<u>Fernando</u>): 1 WEEK | ||
| − | + | * Structure tensor, HOGs, Gabor | |
| − | + | * Edges, corners | |
| − | |||
| − | - | + | 3. '''Non-linear scale-space''' (<u>Stefan</u>): 1.5 WEEK |
| − | - FINAL PROJECT ASSIGNMENT | + | * Variational formulations |
| + | |||
| + | * Non-linear filtering | ||
| + | |||
| + | * De-noising | ||
| + | |||
| + | → PRACTICAL ASSIGNMENT | ||
| + | |||
| + | |||
| + | 4. '''Feature analysis''' (<u>Fernando</u>): 1.5 WEEK | ||
| + | |||
| + | * [http://islab.hh.se/mediawiki/Segmentation Segmentation, clustering] '''(video-lecture and video commenting the slides already available)''' | ||
| + | |||
| + | * [http://islab.hh.se/mediawiki/Feature_Extraction_And_Matching Feature extraction, pattern matching and classification] '''(video-lecture and video commenting the slides available soon)''' | ||
| + | |||
| + | → PRACTICAL ASSIGNMENT | ||
| + | |||
| + | |||
| + | 5. '''Applications for computer vision/object detection''' (<u>Fernando, Stefan</u>): 1 WEEK | ||
| + | |||
| + | Topics to be presented will include (but are not restricted to): | ||
| + | |||
| + | * SIFT | ||
| + | |||
| + | * Viola-Jones | ||
| + | |||
| + | * Perona-Malik | ||
| + | |||
| + | → FINAL PROJECT ASSIGNMENT | ||
Latest revision as of 17:17, 10 November 2016
| |
| Multiscale and Multidimensional Analysis | |
|---|---|
| Contact: Fernando Alonso-Fernandez, Stefan Karlsson |
Contents
Multiscale and Multidimensional Analysis course (Autumn 2014)
This is the web page for the course Multiscale and Multidimensional Analysis.
Course information
Instructors: Fernando Alonso-Fernandez, Stefan Karlsson
Class time: The schedule for the course will be made ad hoc, using doodle or by agreement over email.
Class location: E5.
Office hours: by appoinment.
Contact: Stefan.Karlsson(AHTT)hh.se or feralo(AHTT)hh.se.
Course description
The course is focused on the topic of multi-scale and multi-dimensional signal analysis. More particularly, it will provide with advanced concepts and techniques to extract useful information from signals of arbitrary dimension (such as audio (1D) and video (3D) signals), drawing on topics from the signal/image processing and computer vision fields.
There will be exercises made available to you during some modules, and a project at the end of the course. For each exercise there are several tasks for you to perform. These are to be completed and discussed during the sessions. Instructions on how to report on them will be given in the descriptions for the exercises. Communication WILL NOT be done through blackboard.
Office hours: There are no regularly scheduled office hours, but you can always arrange a meeting with the instructors. Just send an email or drop by.
Grading: by practical assignment
Prerequisites: linear algebra (vector and matrix operations), probability theory/statistics, signal processing, image processing and multi-variate calculus. The course assumes a programing background (primarily in Matlab).
Exercises and sessions (files will be made available before each session)
1. Linear scale space (Stefan): 1 WEEK
- Waveletets (Gabor, Mexican Hat)
- Pyramids (Gaussian, Laplacian, etc.)
- Median filtering
2. Directionality analysis (Fernando): 1 WEEK
- Structure tensor, HOGs, Gabor
- Edges, corners
3. Non-linear scale-space (Stefan): 1.5 WEEK
- Variational formulations
- Non-linear filtering
- De-noising
→ PRACTICAL ASSIGNMENT
4. Feature analysis (Fernando): 1.5 WEEK
- Segmentation, clustering (video-lecture and video commenting the slides already available)
- Feature extraction, pattern matching and classification (video-lecture and video commenting the slides available soon)
→ PRACTICAL ASSIGNMENT
5. Applications for computer vision/object detection (Fernando, Stefan): 1 WEEK
Topics to be presented will include (but are not restricted to):
- SIFT
- Viola-Jones
- Perona-Malik
→ FINAL PROJECT ASSIGNMENT
