Vakade, Shweta Mangesh (2017) Investigation of Line Marking Detection System Using Computer Vision in a Car. Coursework Masters thesis, University of Southern Queensland. (Unpublished)
Abstract
Detecting road lines which are disrupted or faded is difficult for a driverless car to follow road rules. Mainly, the car faces challenges during rains, poor lane marking or any objects on the road. It is important for driverless cars to detect lines under such conditions. Line detection system is used by driverless cars to detect lanes and follow the road rules. However, it is necessary to ensure that these systems can detect road lines of any quality such as faded, worn out or disrupted.
Various research work present a line detection algorithm that can detect road lines with no noise, however its reliability cannot be assured for a driverless car.
Hence, this research consists of studies and investigating the efficiency of a line detection system. The designed algorithm selects region of interest from road images captured by web camera, these images are then processed using image processing. This algorithm helps in avoiding the need to process large part of images. The output feature of the road image is based on the threshold that is robust to different environment conditions such as lighting, shadow, and rains. Line recognition is based on canny edge detector method followed by Hough Transform. Hough Transform will help in eliminating noise and localize the lane lines. Mainly faded and damaged road markings are tested under various road conditions.
The proposed system is designed well for driverless cars to work under various conditions on the roadways. This research does not guarantee for the best results however, efficiency of a line detection system for a driverless cars can be observed.
|
Statistics for this ePrint Item |
| Item Type: | Thesis (Non-Research) (Coursework Masters) |
|---|---|
| Item Status: | Live Archive |
| Additional Information: | Current UniSQ staff and students can request access to this thesis. Please email research.repository@unisq.edu.au with a subject line of SEAR thesis request and provide: Name of the thesis requested and Your name and UniSQ email address. |
| Faculty/School / Institute/Centre: | Current - Faculty of Health, Engineering and Sciences - No Department (1 Jul 2013 -) |
| Supervisors: | Low, Tobias |
| Qualification: | Masters of Engineering Science (Major Electrical/Electronic Engineering) |
| Date Deposited: | 17 Jul 2026 00:21 |
| Last Modified: | 17 Jul 2026 00:21 |
| Uncontrolled Keywords: | road lines, driverless car, lane marking, Line detection system, line detection algorithm |
| URI: | https://sear.unisq.edu.au/id/eprint/53266 |
Actions (login required)
 |
Archive Repository Staff Only |
