Detecting road boundaries and drivable regions in challenging weather conditions

dc.contributor.advisorElgazzar, Khalid
dc.contributor.authorPatel, Dipkumar
dc.date.accessioned2022-03-08T20:55:09Z
dc.date.accessioned2022-03-29T16:46:48Z
dc.date.available2022-03-08T20:55:09Z
dc.date.available2022-03-29T16:46:48Z
dc.date.issued2022-02-01
dc.degree.disciplineElectrical and Computer Engineering
dc.degree.levelMaster of Applied Science (MASc)
dc.description.abstractRoad detection is a core component of self-driving vehicle perception, where it covers detecting road boundaries and drivable road regions. It can also help human drivers to drive safely in lower visibility. The majority of current road detection techniques use camera and lidar sensors. These sensors struggle in inclement weather conditions. MMwave radar works well in all weather conditions. However, due to the low resolution of the radar, it is currently limited to object detection for cruise control applications. This thesis investigates the impact of bad weather on vision-based systems and introduces a camera and radar-based method for efficient road detection. We propose a novel approach to overcome the sparse resolution of mmwave-radars and use it in the segmentation task. We augment the nuScenes dataset with fog and rain and use it for our validation. We achieve 20% and 18% better road boundary and drivable region detection in inclement weather.en
dc.description.sponsorshipUniversity of Ontario Institute of Technologyen
dc.identifier.urihttps://hdl.handle.net/10155/1423
dc.language.isoenen
dc.subjectRoad detectionen
dc.subjectAutonomous vehicleen
dc.subjectCamera radar fusionen
dc.subjectPerceptionen
dc.subjectMmwave radaren
dc.titleDetecting road boundaries and drivable regions in challenging weather conditionsen
dc.typeThesisen
thesis.degree.disciplineElectrical and Computer Engineering
thesis.degree.grantorUniversity of Ontario Institute of Technology
thesis.degree.nameMaster of Applied Science (MASc)

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Patel_Dipkumar.pdf
Size:
13.9 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.61 KB
Format:
Plain Text
Description: