Important Note

The admission for the exam requires 50% of the full accomplishment of all program assignments. Thus, the minimum requirement is given by

  • Kalman Filter must be implemented for multiple sensors
  • Results must show an improvement based on sensor data fusion
  • In addition, one of the following extensions must be implemented:

    • Retrodiction
    • Inclusion of context information (maps) to the filtering process
    • Filtering of false detections with PDAF

The submission is allowed in groups of up to three students. Please send an email which includes names, matrikel number, the code and plotted figures of the results to Felix Govaers. Deadline for the submission is January, 23. A later submission cannot be accepted.

The lecture has been shifted to Hörsaal 7. Lecture and exercises will take place in Hörsaal 7 from now on.

The exam dates are Febuary 14 (room U.039), 24 (room 1.012), and 25 (room 1.012), and March 2 (room 1.009) building A (Poppelsdorf campus).

Due to the number of students, there wil be additional exams on February 21 (first try).

Lecture: Introduction to Sensor Data Fusion

Sensor data fusion is an omnipresent phenomenon that existed prior to its technological realization or the scientific reaction on it. In fact, all living creatures, including human beings, by nature or intuitively perform sensor data fusion. Each in their own way, they combine or fuse sensations provided by different and mutually complementary sense organs with knowledge learned from previous experiences and communications from other creatures. As a result, they produce a mental picture of their individual environment, the basis of behaving appropriately in their struggle to avoid harm or successfully reach a particular goal in a given situation. Sensor Data Fusion is the process of combining incomplete and imperfect pieces of mutually complementary sensor information in such a way that a better understanding of an underlying real-world phenomenon is achieved. Typically, this insight is either unobtainable otherwise or a fusion result exceeds what can be produced from a single sensor output in accuracy, reliability, or cost. Appropriate collection, registration and alignment, stochastic filtering, logical analysis, space-time integration, exploitation of redundancies, quantitative evaluation, and appropriate display are part of Sensor Data Fusion as well as the integration of related context information. Today, Sensor Data Fusion is evolving at a rapid pace and present in countless everyday systems and civilian products.

Course:

Exercises:

Other:

  • Term: Master Computer Science
  • Requirements:
  • Faculty: MA-INF 3310
  • Effort: 2L+2E
  • Exams: Information on the exams can be found in the Introduction Slides which are offered for download below. If you have further questions, please contact felix.govaers@fkie.fraunhofer.de.
  • Follow-up/Side-events:

Additional Information

Short Version of Prof. Koch's Book at SpringerundefinedKoch_Springer_Short_Version
Conference Publication of Prof. Koch's paper on undefinedOut-of-Sequence Processing.