| Home | KSAE | E-Submission | Sitemap | Contact Us |  
International Journal of Automotive Technology > Volume 24(2); 2023 > Article
International Journal of Automotive Technology 2023;24(2): 469-481.
doi: https://doi.org/10.1007/s12239-023-0039-0
Yuki Endo 1, Ehsan Javanmardi 2, Yanlei Gu 3, Shunsuke Kamijo 2
1Graduate School of Information Science and Technology, Department of Information & Communication Engineering, The University of Tokyo
2The Institute of Industrial Science (IIS), The University of Tokyo
3College of Information Science and Engineering, Ritsumeikan University
PDF Links Corresponding Author.  Yuki Endo  , Email. engmech1@sina.com
Detecting object locations and semantic classes in an image, such as traffic signs, traffic lights, and guide signs, is the crucial problem for autonomous driving, known as object detection. However, stable object detection in complex real-world environments, such as urban environments, is still challenging because of clutter, time of day, blur etc., even with modern deep convolutional neural networks (DCNNs). On the other hand, a high definition (HD) map is a pre-built information resource for autonomous driving tasks, especially for controls. Besides controls, HD map utilization for detection tasks has been gaining attention in recent years, enabling us to stabilize detection even in complex real-world environments. However, it is challenging to use object information from an HD map as detection directly because the self-localization error affects the transformed object locations on the image coordinate system from the HD map’s coordinate system. This paper explores incorporating HD map information into deep feature maps of a DCNN-based model. Two proposed modules implicitly make the feature extraction efficient and stable by utilizing HD map information. As a result of the experiments, the proposed module improved a modern model for challenging images of the urban area Shinjuku by 37 % in mAP, even in self-localization errors.
Key Words: Autonomous driving, Object detection, Deep learning, High definition map, Self-localizat
Editorial Office
21 Teheran-ro 52-gil, Gangnam-gu, Seoul 06212, Korea
TEL: +82-2-564-3971   FAX: +82-2-564-3973   E-mail: manage@ksae.org
About |  Browse Articles |  Current Issue |  For Authors and Reviewers
Copyright © The Korean Society of Automotive Engineers.                 Developed in M2PI
Close layer
prev next