Website
Module guide

Modul RO4300-KP08

Machine Learning and Computer Vision (MLRAS)

Duration:


2 Semester
Turnus of offer:


normally each year in the winter semester
Credit points:


8
Course of studies, specific field and terms:
  • Master Robotics and Autonomous Systems 2019 (compulsory), Compulsory courses, 1st and 2nd semester
Classes and lectures:
  • Computer Vision (exercise, 1 SWS)
  • Computer Vision (lecture, 2 SWS)
  • Machine Learning (exercise, 1 SWS)
  • Machine Learning (lecture, 2 SWS)
Workload:
  • 90 Hours in-classroom work
  • 110 Hours private studies
  • 40 Hours exam preparation
Contents of teaching:
  • Representation learning, including manifold learning
  • Statistical learning theory
  • VC dimension and support vector machines
  • Boosting
  • Deep Learning
  • Limits of induction and importance of data ponderation
  • Introduction to human and computer vision
  • Sensors, cameras, optics and projections
  • Image features: edges, intrinsic dimension, Hough transform, Fourier descriptors, snakes
  • Range imaging and 3-D cameras
  • Motion and optical flow
  • Object recognition
  • Example applications
Qualification-goals/Competencies:
  • Students can understand and explain various machine-learning problems.
  • They can explain and apply different machine learning methods and algorithms.
  • They can chose and then evaluate an appropriate method for a particular learning problem.
  • They can understand and explain the limits of automatic data analysis.
  • Students can understand the basics of computer vision.
  • They can explain and perform camera choice and calibration.
  • They can explain and apply the basic methods for feature extraction, motion estimation, and object recognition.
  • They can indicate appropriate methods for different kinds of computer-vision applications.
Grading through:
  • Oral examination
Responsible for this module:
Teachers:
Literature:
  • Chris Bishop: Pattern Recognition and Machine Learning - Springer ISBN 0-387-31073-8
  • Vladimir Vapnik: Statistical Learning Theory - Wiley-Interscience, ISBN 0471030031
  • Richard Szeliski: Computer Vision: Algorithms and Applications - Springer, Boston, 2011
  • David Forsyth and Jean Ponce: Computer Vision: A Modern Approach - Prentice Hall, 2003
Language:
  • English, except in case of only German-speaking participants
Notes:

Admission requirements for taking the module:
- None

Admission requirements for participation in module examination(s):
- Successful completion of exercises of both sub-modules as specified at the beginning of the respective semester.

Module Exam(s):
- RO4300-L1: Machine Learning and Computer Vision, oral examination on the contents of both submodules, 100% of the module grade

Letzte Änderung:
2.9.2021