Module Handbook

  • Dynamischer Default-Fachbereich geändert auf INF

Module INF-73-52-M-6

Probabilistic methods for modeling and capturing human motion (M, 4.0 LP)

Module Identification

Module Number Module Name CP (Effort)
INF-73-52-M-6 Probabilistic methods for modeling and capturing human motion 4.0 CP (120 h)

Basedata

CP, Effort 4.0 CP = 120 h
Position of the semester 1 Sem. in WiSe
Level [6] Master (General)
Language [EN] English
Module Manager
Lecturers
Area of study [INF-KI] Intelligent Systems
Reference course of study [INF-88.79-SG] M.Sc. Computer Science
Livecycle-State [NORM] Active

Courses

Type/SWS Course Number Title Choice in
Module-Part
Presence-Time /
Self-Study
SL SL is
required for exa.
PL CP Sem.
2V+1U INF-73-52-K-6
Probabilistic methods for modeling and capturing human motion
P 42 h 78 h
U-Schein
- PL1 4.0 WiSe
  • About [INF-73-52-K-6]: Title: "Probabilistic methods for modeling and capturing human motion"; Presence-Time: 42 h; Self-Study: 78 h
  • About [INF-73-52-K-6]: The study achievement "[U-Schein] proof of successful participation in the exercise classes (ungraded)" must be obtained.

Examination achievement PL1

  • Form of examination: written exam (Klausur) (60-180 Min.)
  • Examination Frequency: each semester
  • Examination number: 67355 ("Probabilistic methods for modeling and capturing human motion")
    old title: Methods for human motion and capturing

Evaluation of grades

The grade of the module examination is also the module grade.


Contents

The focus of this course is on probabilistic methods and models for IMU (inertial measurement unit) based human motion modelling and capturing, aiming at biomechanically interpretable motion estimation (e.g. 3D kinematics). After motivating this general topic via different application examples and presenting an overview of different capturing modalities, the following topics are addressed:
  • Human body, kinematic models & marker-based optical motion capture.
  • 3D kinematics
  • Inertial measurement devices
  • Probabilistic model-based sensor fusion methods
  • Statistical machine learning techniques.

The techniques covered will be illustrated with practical examples from current research. The contents of the lectures are also presented in the form of laboratory exercises with implementations in Matlab and Python.

Competencies / intended learning achievements

Upon successful completion of the module, students will be able to
  • relate the different components for the appropriate modeling and detection of human motion,
  • combine knowledge from related disciplines (especially physics, mathematics and biomechanics)
  • apply suitable probabilistic methods of model-based sensor data fusion and machine learning in a problem-oriented way,
  • apply mathematical principles, models and methods to practical problems in modeling and recording human motion,
  • evaluate the advantages and disadvantages as well as limitations of the presented methods
  • implement suitable algorithms for modeling and recording human motion

Literature

  • Gustafsson, Fredrik. Statistical sensor fusion. Studentlitteratur, 2010.
  • Thrun, Sebastian, Wolfram Burgard, and Dieter Fox. Probabilistic robotics. MIT press, 2005.
  • Murphy, Kevin P. Machine Learning: A Probabilistic Perspective, MIT Press, 2013

Requirements for attendance of the module (informal)

None

Requirements for attendance of the module (formal)

None

References to Module / Module Number [INF-73-52-M-6]

Course of Study Section Choice/Obligation
[INF-88.79-SG] M.Sc. Computer Science [Specialisation] Specialization 1 [WP] Compulsory Elective