S&M2808 Research Paper of Special Issue
Published: January 31, 2022
Object Detection of Road Facilities Using YOLOv3 for High-definition Map Updates [PDF]
Tae-Young Lee, Myeong-Hun Jeong, and Almirah Peter
(Received November 15, 2021; Accepted January 4, 2022)
Keywords: high-definition (HD) map, object detection, autonomous driving, deep learning, YOLOv3
Autonomous driving technology is significantly based on the fusion of high-definition (HD) maps and sensors. Therefore, the construction and update of HD maps must be emphasized to achieve full driving automation. Herein, a method is proposed to detect road facilities using object detection with images, particularly for HD map updates utilizing the You Only Look Once version 3 (YOLOv3) algorithm. The proposed approach, a deep-learning-based object detection method, utilizes transfer learning, which can detect objects in road facilities and record road sections that require maintenance. To test the effectiveness of the detection method, we analyze video footage captured in the Korean road environment. The experimental results show that this method achieves a mean average precision (mAP) of 58 and can update HD maps using a crowdsourcing framework.Corresponding author: Myeong-Hun Jeong
This work is licensed under a Creative Commons Attribution 4.0 International License.
Cite this article
Tae-Young Lee, Myeong-Hun Jeong, and Almirah Peter, Object Detection of Road Facilities Using YOLOv3 for High-definition Map Updates, Sens. Mater., Vol. 34, No. 1, 2022, p. 251-260.