English  |  正體中文  |  简体中文  |  Items with full text/Total items : 59720/92965 (64%)
Visitors : 832639      Online Users : 45
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/120549

    Title: Occluded Traffic Signs Recognition
    Authors: Yen, Shwu-Huey;Shu, Chun-Yung;Hsu, Hui-Huang
    Keywords: Occlusion;Traffic sign;Recognition;GTSRB;Convolutional Neural Network;Mask
    Date: 2020-03-05
    Issue Date: 2021-04-20 12:10:43 (UTC+8)
    Abstract: Traffic sign recognition is very important in the intelligent driving. It can remind drivers to react properly to the road condition and increase the driving safety. One of the challenges in recognizing traffic sign is occlusion. In this paper, we focus on this problem particularly in Taipei and the vicinity including Taipei and New Taipei City. We propose a convolution neural network equipped with the regional masks to solve the occlusion traffic sign recognition. Traffic sign images of Taipei and New Taipei City are collected mainly from Google Maps for training and testing. Finally, the proposed method is tested both on our own dataset and German public dataset GTSRB. The experimental results demonstrated the occlusion problem is being greatly alleviated and the result is very promising.
    Relation: Advances in Intelligent Systems and Computing 1130
    DOI: 10.1007/978-3-030-39442-4_58
    Appears in Collections:[Graduate Institute & Department of Computer Science and Information Engineering] Proceeding

    Files in This Item:

    File Description SizeFormat

    All items in 機構典藏 are protected by copyright, with all rights reserved.

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback