Computer Vision 2

Semester:
SS 2016
Type:
Lecture
Lecturer:
Credits:
Course Dates:
Type
Date
Room
Lecture Mo, 14:15 - 15:45 UMIC 025
Lecture/Exercise Do, 14:15 - 15:45 UMIC 025

The lecture will cover advanced topics in computer vision. A particular focus will be on state-of-the-art techniques for object detection, tracking, visual odometry and SLAM. There will be regular exercises accompanying the lecture.

Literature

In the last decades, Computer Vision has evolved into a rapidly growing field with research going into so many directions that no single book can cover them all. Some basic material can be found in the following book:

  • Computer Vision - A Modern Approach, D. Forsyth, J. Ponce, Prentice Hall, 2002
  • An Invitation to 3D Vision, Y. Ma, S. Soatto, J. Kosecka, S. Sastry, Springer, 2003

However, a good part of the material presented in this class is the result of very recent research, so it hasn't found its way into textbooks yet. Wherever research papers are necessary for a deeper understanding, we will make them available on this web page.

Matlab Resources

Course Schedule
Date Title Content Material
Introduction What is tracking? What is visual odometry? What is SLAM?
Template based Tracking LK Tracking, fast template matching, Generalized LK
Exercise 0 Intro Matlab
Tracking by Online Classification Tracking as Online Classification problem, Online Boosting, Online Feature Selection, Drift, Semi-Supervised Boosting, TLD
Tracking by Detection Tracking-by-Detection, State-of-the-Art Detectors: HOG, DPM, Viola-Jones, Integral Channel Features, VeryFast, Roerei, Hough Forests
Bayesian Filtering I Tracking with Linear Dynamic Models, Tracking as Inference, Prediction/Correction, Kalman Filter
- no class (Ascension)
Bayesian Filtering II Extended Kalman Filter, Particle Filter
Bayesian Filtering III Particle Filter Details
- no class (Excursion week)
- no class (Excursion week)
Exercise 1 Generalized LK Tracking, Kalman Filter
- no class (Corpus Christi)
Multi-Object Tracking I Data Association, Gating, Global NN, Linear Assignment Problem, Hungarian algorithm
Multi-Object Tracking II MHT, PDAF, JPDAF
Multi-Object Tracking III Min-cost Network Flow Optimization, LP formulation, QBPO formulation
Exercise 2 EKF, Particle Filter
Visual Odometry I Introduction, Basics, Indirect Point-Based Methods
Visual Odometry II Indirect Point-Based Methods cont., Direct Methods
Visual SLAM I Direct Visual Odometry Methods cont., Visual SLAM: Introduction, Basics
Exercise 3 Multi-Object Tracking, MHT
Visual SLAM II Online SLAM Methods, Tracking-and-Mapping, EKF-SLAM, MonoSLAM
Visual SLAM III Full SLAM Methods, SLAM Graph Optimization, Bundle Adjustment
Visual SLAM IV Full SLAM Methods cont., Pose Graph Optimization, Data Association
Exercise 4 Visual Odometry
Dense Reconstruction I Dense Depth Reconstruction from Two or More Views, Depth Cameras
Dense Reconstruction II Dense 3D Map Representations, Occupancy Grid Maps, Truncated Signed Distance Functions, Surfels
Repetition Repetition
Exercise 5 Visual SLAM
Disclaimer Home Visual Computing institute RWTH Aachen University