Back close

Course Detail

Course Name Multi Sensor Data Fusion
Course Code 24AT736
Program M. Tech. in Automotive Engineering
Credits 3
Campus Coimbatore , Chennai , Bengaluru , Amritapuri , Kochi

Syllabus

Elective Streams Software Defined Vehicles

Unit 1

Introduction to data fusion process- Data fusion models- Configurations and architectures – Probabilistic Data Fusion-Maximum Likelihood- Bayesian- Maximum Entropy methods – Recursive Bayesian methods- Kalman filter theory- Kalman filter as a natural data-level fuser.

Unit 2

Data fusion Methods: Data fusion by nonlinear Kalman filtering- Information filtering-H∞ filtering- Multiple hypothesis filtering- Data fusion with missing measurements- Possibility theory and Dempster-Shafer Method- ANN based decision fusion.

Unit 3

Decision theory based fusion and Evaluation: Decision theory based fusion- Bayesian decision theory- Decision making with multiple information sources- Decision making based on voting- Performance- Evaluation of data fusion systems- Monte Carlo methods – JDL process-Review of algorithms used for object refinement- Situation refinement- Threat refinement and process refinement.

Objectives and Outcomes

Course Objectives

  1. To provide knowledge on the fundamental concepts of data fusion processes, including various models, configurations, and architectures used in integrating multiple data sources.
  2. To familiarize probabilistic data fusion techniques such as Maximum Likelihood, Bayesian methods, Maximum Entropy methods, and Recursive Bayesian methods.
  3. To provide knowledge in implementing and utilizing Kalman filtering theory for data fusion, including nonlinear Kalman filtering, information filtering, H∞ filtering, and multiple hypothesis filtering.
  4. To familiarize advanced data fusion methods including handling missing measurements, utilizing possibility theory and Dempster-Shafer Method etc.

Course Outcomes

CO

CO Description

CO1

Design data fusion systems using various probabilistic methods, including Maximum Likelihood

estimation, Bayesian inference, and Maximum Entropy methods.

CO2

Apply Kalman filtering theory for data fusion tasks, including understanding its theoretical foundations, implementing nonlinear Kalman filtering techniques, and utilizing information filtering

and multiple hypothesis filtering approaches.

CO3

Handle complex data fusion scenarios such as missing measurements, utilizing possibility theory and Dempster-Shafer Method for uncertainty management, and employing ANN-based decision fusion

techniques.

CO4

Evaluate the performance of data fusion systems using Monte Carlo methods, understanding the Joint

Directors of Laboratories (JDL) process, and reviewing algorithms for object refinement

CO-PO Mapping

 

PO1

PO2

PO3

PO4

PO5

CO1

3

1

1

 

3

CO2

2

 

1

1

3

CO3

3

2

1

1

3

CO4

3

2

1

2

3

Skills acquired

Proficiency in integrating and analyzing multiple data sources through probabilistic methods, Kalman filtering, and advanced fusion techniques and algorithms.

Text Books / References

Text Books / References

  1. Martin Liggins II, David Hall, and James Llinas, “Multi-Sensor Data Fusion: Theory and Practice”, CRC Press. – 2nd Ed., 2022,
  2. Hassen Fourati, “Advances in Multi-Sensor Data Fusion: Algorithms and Applications” CRC Press, 1st Ed., 2023.
  3. B. Mitchell , “Multi-Sensor Data Fusion: An Introduction”, CRC Press, 2nd Ed.,2020,
  4. David Hall and James Llinas, “Multi-Sensor Data Fusion: A Review of the State-of-the-Art”, Springer, 2nd Ed. 2021.
  5. David Hall, James Llinas, “Principles of Multi-Sensor Data Fusion” Wiley-IEEE Press 2nd Ed., 2019.
  6. Jitendra R Raol, “Data Fusion Mathematics: Theory and Practice”, CRC Press,

DISCLAIMER: The appearance of external links on this web site does not constitute endorsement by the School of Biotechnology/Amrita Vishwa Vidyapeetham or the information, products or services contained therein. For other than authorized activities, the Amrita Vishwa Vidyapeetham does not exercise any editorial control over the information you may find at these locations. These links are provided consistent with the stated purpose of this web site.

Admissions Apply Now