5LSE0 (2021) - Multimedia video coding and architectures

Goal:
Learn the power of signal transformations
- For video compression, like as in transform coding
- For video analysis, like as in the Gabor wavelet transform
- For combining them with Deep Learning

Exploit the concept of “condensing information”
- This is useful for coding and compression
- But also applicable to video analysis: what is the key informative feature
- Use specific transformation for that, like the PCA

This course is divided in two parts
A. Video compression using Discrete Cosine Transformation
Learn the concept of entropy as information measure both for compression and video analysis
B. Analysis techniques, e.g. wavelet transform, for finding feature
Expand the tool set of computer vision and for Deep Learning

Preknowledge:
Stochastic Signal Processing

Slides: 
Module 01A - Introduction & Motivation for Compression
Module 01B - Probability and Information
Module 02A - Scalar Quantization
Module 02B - Transformation Theory
Module 03A - Adaptive Quantization and JPEG 2021
Module 03B - MPEG 1-2 standard 2021