Chowdhury, Shahnewaz2021-08-162021-08-162021-05https://hdl.handle.net/11299/223098University of Minnesota M.S. thesis. May 2021. Major: Electrical Engineering. Advisor: Imran Hayee. 1 computer file (PDF); viii, 44 pages.Lane departure warning system (LDWS) has significant potential to reduce fatal crashes on roads. Most of the existing LDWSs use either image processing techniques with/without Global Positioning System (GPS) technology or high-resolution digital maps to detect unintentional lane departures. However, these are expensive to implement as well as have some limitations, such as harsh weather or irregular lane markings can drastically reduce their performance. In previous research, we proposed and developed an LDWS using a standard GPS receiver without any high-resolution digital maps. The previous system relies on low-resolution digital maps of a given road extracted from an open-source mapping database to detect an unintentional lane departure. The previous system can detect true lane departures accurately but occasionally gives false alarms i.e., it issues lane departure warnings even if a vehicle is within its lane. The false alarms occur due to the inaccuracy of road direction originated from inherent lateral error in open-source low-resolution maps. To address this problem, this thesis proposes a novel algorithm to generate an accurate road reference heading (RRH) for a given road using a vehicle’s past trajectories on that road. The newly proposed algorithm to generate an accurate RRH for any given road has been integrated with the existing LDWS and extensively evaluated in the field to detect unintentional lane departures. The field test results show that the newly developed RRH generation algorithm significantly improves the performance of LDWS by accurately detecting all true lane departures while practically reducing the frequency of false alarms to zero.enLane departure warning systemsRoad reference headingPast trajectoriesDetecting lane departuresThesis or Dissertation