Occluded Traffic Signs Recognition
學年 108
學期 2
發表日期 2020-03-05
作品名稱 Occluded Traffic Signs Recognition
作品名稱（其他語言）
著者 Shwu-Huey Yen; Chun-Yung Shu; Hui-Huang Hsu
作品所屬單位
出版者
會議名稱 Future of Information and Communication Conference (FICC 2020)
會議地點 San Francisco, USA
摘要 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.
關鍵字 Occlusion;Traffic sign;Recognition;GTSRB;Convolutional Neural Network;Mask
語言 en_US
收錄於
會議性質 國際
校內研討會地點 無
研討會時間 20200305~20200306
通訊作者
國別 USA
公開徵稿
出版型式
出處 Advances in Intelligent Systems and Computing 1130
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/120549 )