TU/e logo VCA logo

Course detail

Multimedia video coding and architectures

5LSE0 (2021)

Groups

Automotive, Surveillance, Healthcare, Animal care

Teachers

Egor Bondarev, Herman Groot

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
  • Also applicable to video analysis: what is the key informative feature
  • Use specific transformations to condens the information, like the PCA

Course details

This course is divided in two parts:

  1. Video compressing using Discrete Cosine Transformation: learn the concept of entropy as information measure both for compression and video analysis
  2. Analysis techniques, e.g. wavelet transform, for finding features: Expand the tool set of computer vision and for Deep Learning

Required preknowledge: 

  • Stochastic signal processing

Lecturer(s):

  • prof. Peter de With
  • dr. Yue Sun

Schedule and locations:

 

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
  • Module 03C - MPEG 4 AVC standard 2021
  • Module 04 - Wavelets and JPEG2000
  • Module 05A - Gabor wavelets
  • Module 05B - Gabor wavelets
  • Module 06 - PCA
  • Module 07 - HMM
  • Module 08A - Object Detection