A Road Marking Detection System Using Partial Template Matching and Region Estimation by Deep Neural Network

DOI IR HANDLE Web Site 4 References
  • MII Yuya
    Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
  • MIYAZAKI Ryogo
    Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
  • YOSHIMOTO Yuma
    Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology Japan Society for the Promotion of Science Research Fellow
  • ISHIDA Yutaro
    Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
  • ITO Takuma
    Department of Mechanical Engineering, Graduate School of Engineering, The University of Tokyo
  • TOHRIYAMA Kyoichi
    Frontier Research Center, Toyota Motor Corporation
  • TAMUKOH Hakaru
    Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology Research Center for Neuromorphic AI Hardware, Kyushu Institute of Technology

Bibliographic Information

Other Title
  • 深層ニューラルネットワークを用いた領域推定と部分テンプレートマッチングによる道路標示検出システム

Search this article

Abstract

<p>We improve the performance of a road marking detection system by incorporating You Only Look Once (YOLO) into the processing for vehicle location estimation in autonomous driving technology. The conventional detection method uses a template matching process based on luminance values to detect road marking. However, there are some markings that cannot be detected by this method due to halation by sunlight or strong blurred of road markings. In contrast, the proposed method uses YOLO to search for areas where road marking exists and restricts the area of adaptation for template matching. Owing to this area restriction, the proposed method can prevent the occurrence of false detection, lower the detection threshold for template matching, and reduce the number of previously undetected road markings. In addition, the search area for template matching is restricted, which also can improve the processing speed. Experimental results show that the proposed method is able to reduce the number of undetected road markings compared to the conventional method while keeping the number of false detections to zero. The accuracy of the system was improved by 0.013 and the processing speed was increased by 4.6 FPS compared to the previous method.</p>

Journal

References(4)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top