Abstract
Detection and classification of road markings are a prerequisite for operating autonomous vehicles. Although most studies have focused on the detection of road lane markings, the detection and classification of other road markings, such as arrows and bike markings, have not received much attention. Therefore, we propose a detection and classification method for various types of arrow markings and bike markings on the road in various complex environments using a one-stage deep convolutional neural network (CNN), called RetinaNet. We tested the proposed method in complex road scenarios with three open datasets captured by visible light camera sensors, namely the Malaga urban dataset, the Cambridge dataset, and the Daimler dataset on both a desktop computer and an NVIDIA Jetson TX2 embedded system. Experimental results obtained using the three open databases showed that the proposed RetinaNet-based method outperformed other methods for detection and classification of road markings in terms of both accuracy and processing time.
Highlights
The U.S House of Representatives is quoted to have said “Self-driving cars seem like such a good idea that even Republicans and Democrats can agree on their merits” [1]
To overcome the limitations of previous studies, we propose the detection and classification method of various types of road markings on roads in various complex environments using a one-stage deep convolutional neural network (CNN), called RetinaNet
We propose a novel one-stage method based on deep RetinaNet that can detect and classify road markings in various conditions and at long-range distances with high accuracy
Summary
The U.S House of Representatives is quoted to have said “Self-driving cars seem like such a good idea that even Republicans and Democrats can agree on their merits” [1]. Autonomous vehicles are considered as the future of mobility. The most essential requirement for robust advanced driver assistance systems (ADAS) is to make the perception of the environment around the vehicle as comprehensive as possible. Road lane markings can be defined by a combination of horizontal and vertical lines, arrow markings vary. Arrow markings have different signature features such as straight forward, left, right, forward-left-right arrow, or different color intensities even within the same city or different character sets depending on the countries. The sizes of arrow markings vary when considering the distance and angular orientation of the front-view camera in the vehicle
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
