Abstract
With the increasing need for road lane detection used in lane departure warning systems and autonomous vehicles, many studies have been conducted to turn road lane detection into a virtual assistant to improve driving safety and reduce car accidents. Most of the previous research approaches detect the central line of a road lane and not the accurate left and right boundaries of the lane. In addition, they do not discriminate between dashed and solid lanes when detecting the road lanes. However, this discrimination is necessary for the safety of autonomous vehicles and the safety of vehicles driven by human drivers. To overcome these problems, we propose a method for road lane detection that distinguishes between dashed and solid lanes. Experimental results with the Caltech open database showed that our method outperforms conventional methods.
Highlights
Accurate detection of road lanes is an important issue in lane departure warning systems and driver assistance systems
Lane boundaries are not always clearly visible. This can be caused, for instance, by poor road conditions, insufficient quantity of paint used for marking the lane boundary, environmental effects, or illumination conditions
If the two distances are less than the adaptive threshold from the perspective camera model, we assume that we identified the correct left and right boundaries of the lane
Summary
Accurate detection of road lanes is an important issue in lane departure warning systems and driver assistance systems. Detecting lane boundaries enables vehicles to avoid collisions and issue a warning if a vehicle passes a lane boundary. Lane boundaries are not always clearly visible This can be caused, for instance, by poor road conditions, insufficient quantity of paint used for marking the lane boundary, environmental effects (e.g., shadows from objects like trees or other vehicles), or illumination conditions (street lights, daytime and nighttime conditions, or fog). These factors make it difficult to discriminate a road lane from the background in a captured image.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
