Sport, Technology and Behaviour
5XSF0 (2020)
Group
Healthcare
Goal
Become acquainted with the theory and main concepts of digital signal and analysis; make a choice of an approach for a given basic signal/image processing problem; implement the chosen approach in MATLAB and critically evaluate the result; be able to operationalize theoretical concepts from signal/image analysis in a hands-on case study.
Contents
Signal sensing and health/medical imaging is the most important discipline for healthcare diagnosis. Besides this, video cameras play a very important role in the behavior analysis of people in real life and during sports exercises. This course provides in-depth knowledge on signal processing and image processing techniques and the principles of video signal analysis. This course starts with an introduction to 1-D signal sampling and the extension to multi-dimensional signal processing for images and video. Then the course proceeds with the principles and definitions for the frequency-domain representation of 1-D signals and 2-D images and the possibilities for filtering and other processing possibilities in the frequency domain. In a further module, the focus is on the signal and image quality enhancement in various ways. Various noise models are discussed and filtering approaches for reducing the noise. The introduction of color in images for improved understanding is addressed. The second part of the course provides an introduction to image understanding and object/area segmentation to learn 1-D signal and 2-D imaging for health diagnosis. This part starts with simple binary operators and then extends to the detection of points, lines, edges, etc. Secondly, specific region-based segmentation methods are discussed. Features are extracted from images, which is addressed in both the spatial domain directly in the image and a frequency-oriented domain, such as the Gabor transformation. The course concludes with a module on imaging techniques and use cases, where the learned techniques are applied. These cases include computer-aided cancer diagnosis, instrument detection, etc.
Lecturer:
Peter H.N. de With
Sveta Zinger
Arash Pourtaherian
Joost van der Putten
Saskia Camps
Schedule and location:
8 Weeks of lectures in 2 blocks of 4 hours
Slides
- Module 01 - Fundamentals
- Module 02 - Basics, Sampling, and Filters
- Module 03 - Discrete Fourier transform and filters
- Module 04 - Image enhancement
- Module 05 - Features
- Module 06 - Segmentation
- Module 07 - Motion estimation
- Instructions 01 - Introduction to Matlab (part 1)
- Instructions 01 - Spatial filtering of digital images (part 2)
- Instructions 02 - Signals, sampling, and Fourier
- Instructions 03 - Frequency domain processing
- Instructions 04 - Restoration and color
- Exercises 01 - Digital images in Matlab
- Exercises 02 - Basics of signals, sampling, and Fourier series
- Exercises 03 - Frequency domain processing
- Exercises 04 - Image restoration and color image processing
- Exercises 05 - Features
- Exercises 06 - Segmentation computer class (slides)
- Exercises 06 - Segmentation
- Exercises 07 - Motion estimation