An exploration in segmentation and statistical modeling of highway map data
(2019) In Master's Theses in Mathematical Sciences FMSM01 20191Mathematical Statistics
- Abstract
- This thesis studies segmentation and categorization of highway road data, with the ambition that the understanding gained could be used for virtual verification of road scenarios for self-driving systems. We will look at a few approaches for segmentation of the road data, such as heuristics as well as methods involving optimization. The result of the segmentation is categorized and we then explore various Markov-based models for road generation. We also propose a way of quantifying the likelihood of road scenarios occurring.
- Popular Abstract
- By segmenting, classifying and modeling highways, we present a whole new way of looking at road data. The knowledge gained can be used for virtual verification of road scenarios - a crucial step towards the realization of fully autonomous cars.
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/8987980
- author
- Klinteberg, Christian LU
- supervisor
- organization
- course
- FMSM01 20191
- year
- 2019
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- Trajectory segmentation, Markov modeling, Autonomous driving
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMS-3377-2019
- ISSN
- 1404-6342
- other publication id
- 2019:E46
- language
- English
- id
- 8987980
- date added to LUP
- 2019-10-08 14:10:08
- date last changed
- 2019-10-08 14:10:08
@misc{8987980, abstract = {{This thesis studies segmentation and categorization of highway road data, with the ambition that the understanding gained could be used for virtual verification of road scenarios for self-driving systems. We will look at a few approaches for segmentation of the road data, such as heuristics as well as methods involving optimization. The result of the segmentation is categorized and we then explore various Markov-based models for road generation. We also propose a way of quantifying the likelihood of road scenarios occurring.}}, author = {{Klinteberg, Christian}}, issn = {{1404-6342}}, language = {{eng}}, note = {{Student Paper}}, series = {{Master's Theses in Mathematical Sciences}}, title = {{An exploration in segmentation and statistical modeling of highway map data}}, year = {{2019}}, }