Abstract
High-definition (HD) maps determine the location of the vehicle under limited visibility based on the location information of safety signs detected by sensors. If a safety sign disappears or changes, incorrect information may be obtained. Thus, map data must be updated daily to prevent accidents. This study proposes a map update system (MUS) framework that maps objects detected by a road map detection system and the object present in the HD map. Based on traffic safety signs notified by the Korean National Police Agency, 151 types of objects, including traffic signs, traffic lights, and road markings, were annotated manually and semi-automatically. Approximately 3,000,000 annotations were trained based on the you only look once (YOLO) model, suitable for real-time detection by grouping safety signs with similar properties. The object coordinates were then extracted from the mobile mapping system point cloud, and the detection location accuracy was verified by comparing and evaluating the center point of the object detected in the MUS. The performance of the groups with and without specified properties was compared and their effectiveness was verified based on the dataset configuration. A model trained with a Korean road traffic dataset on our testbed achieved a group model of 95% mAP and no group model of 70.9% mAP.
Highlights
One of the important elements in an automated driving system (ADS) is the highdefinition (HD) map embedded in a vehicle
151 types of objects were applied as road objects for the HD-map updates based on the list of road traffic safety signs notified by the Korean National Police Agency (4 July 2014)
As shouwpdnaitneTsaybslteesm8 a(MndU9S,)thfreacmheawngoerskintothqeumickAlPy aunpddaretecatlhl eanHdDinmthaepF. 1It-sccaonrebveailnusetsacllaend be obsinermveadnybavseehdicolnesthtoe icnocmrebainseattihoenuopf dparete-ttriamineedfodr artoaa,dorcihgainnagleds,aotaw, ainngdtaoutghme elonwtatcioonst data. oIft tishea smysattetemr.of principle, but it can be observed from the experiment that optimal p(2er)forMmoarnectehiasno3b,t0a0i0n,e0d00oKnloyrewahnernotahdretreatfyfipceasnonfodtaattiaoanrde atrtaaihnaevdesbimeeunltbauneilot ufosrlyM
Summary
One of the important elements in an automated driving system (ADS) is the highdefinition (HD) map embedded in a vehicle. When sensors installed in autonomous vehicles do not detect the surrounding situation, high-definition maps that include spatial information on roads and road facilities should be used. The equipment required to update HD maps usually involves an MMS equipped with light detection and ranging (LiDAR), a global navigation satellite system (GNSS), an inertial navigation system (INS), and vision sensors [1,2]. Much of the work, such as processing and matching the information acquired from the MMS equipment, and extracting and converting spatial objects, is performed manually. An update system that can acquire road images and quickly update them by installing industrial cameras on many vehicles is required. An increasing number of domestic and foreign companies have started acquiring road image information from vehicles and automating HD map updates using camera-based mobile mapping technology to provide rapid updates
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.
