Heterogeneous Sensor Fusion: Verification and Optimization
(2017) In Master's Theses in Mathematical Sciences FMA820 20162Mathematics (Faculty of Engineering)
- Abstract
- The project analyzes, implements, and tests different types of heterogeneous sensor fusion, and comparatively checks them against a ground truth. Four different cases are tested, only image data, only non-image data, sequential fusion of data, and parallel fusion of data.
The tracking is done with a probabilistic data association filter, which is a variation of the standard Kalman filter. The metrics are the Clear MOT Metrics. Steepest descent optimization is performed on the parameters to improve result.
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/8904959
- author
- Lindelöf Bilski, Henrik LU
- supervisor
-
- Karl Åström LU
- Magnus Oskarsson LU
- organization
- course
- FMA820 20162
- year
- 2017
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- tracking, sensor fusion, parameter optimization, image analysis, kalman filter, pdaf
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMA-3312-2017
- ISSN
- 1404-6342
- other publication id
- 2017:E9
- language
- English
- id
- 8904959
- date added to LUP
- 2017-04-03 15:28:18
- date last changed
- 2018-10-11 16:21:06
@misc{8904959, abstract = {{The project analyzes, implements, and tests different types of heterogeneous sensor fusion, and comparatively checks them against a ground truth. Four different cases are tested, only image data, only non-image data, sequential fusion of data, and parallel fusion of data. The tracking is done with a probabilistic data association filter, which is a variation of the standard Kalman filter. The metrics are the Clear MOT Metrics. Steepest descent optimization is performed on the parameters to improve result.}}, author = {{Lindelöf Bilski, Henrik}}, issn = {{1404-6342}}, language = {{eng}}, note = {{Student Paper}}, series = {{Master's Theses in Mathematical Sciences}}, title = {{Heterogeneous Sensor Fusion: Verification and Optimization}}, year = {{2017}}, }