Abstract
Lane detection and has always been a very challenging problem because traffic lines contain different categories are often blocked and worn by vehicles. In recent years, many sophisticated lane detection methods have been proposed. However, most methods focus on detecting the location of lans and ignore the importance of classification. This paper studies the network Line-CNN: End-to-End Traffic Line Detection With Line Proposal Unit (Line-CNN) and Towards End-to-End Lane Detection an Instance Segmentation Approach (LaneNet), proposes a lane recognition method based on Line-CNN network adding lane classification task. Compared with previous work, we can not only predict any number of lanes without post-processing, but also recognize between different categories of traffic lines. Experiment on two public datasets verify our method and achieve competitive results.
Published Version
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.
