模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2019, Vol. 32 Issue (5): 472-480    DOI: 10.16451/j.cnki.issn1003-6059.201905010
Researches and Applications Current Issue| Next Issue| Archive| Adv Search |
Semantic Segmentation Method for Complex Traffic Scene Based on DenseNet
JIANG Bin1, TU Wenxuan1, YANG Chao1, LIU Hongyu1, ZHAO Zilong1
1.College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082

Download: PDF (2007 KB)   HTML (0 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  An end-to-end multi-scale semantic segmentation model based on fully convolutional DenseNet is proposed, aiming at the problems of traditional semantic segmentation methods for street scene, such as the large number of parameters and low computational efficiency and precision. Firstly, convolution layers embedded with hybrid dilation convolution are stacked to establish a dense module, and then the modules are cascaded along channel dimension to extract features. Next, multi-scale visual information regarded as supervised signals are transferred back to original channels. Finally, the prediction results are obtained by bilinear interpolation method. Experimental results on Cityscapes dataset demonstrate that the proposed method achieves an efficient segmentation and performs a better accuracy for street scene parsing.
Key wordsTraffic Scene      Image Semantic Segmentation      Dilated Convolution      Multi-scale Feature Fusion     
Received: 15 September 2018     
ZTFLH: TP 391  
Fund:Supported by Young Scientists Fund of National Natural Science Foundation of China(No.61702176), Natural Science Foundation of Hunan Province(No.2017JJ3038)
Corresponding Authors: (JIANG Bin(Corresponding author), Ph.D., associate professor. His research interests include big data technology, computer vision and machine learning.)   
About author:: (TU Wenxuan, master student. His research interests include computer vision and machine learning.)(YANG Chao, Ph.D., associate professor. Her research interests include big data technology, social network computing and intelligent information processing.)(LIU Hongyu, master student. His research interests include computer vision and machine learning.)(ZHAO Zilong, master student. His research interests include computer vision and machine learning.)
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
JIANG Bin1
TU Wenxuan1
YANG Chao1
LIU Hongyu1
ZHAO Zilong1
Cite this article:   
JIANG Bin1,TU Wenxuan1,YANG Chao1等. Semantic Segmentation Method for Complex Traffic Scene Based on DenseNet[J]. , 2019, 32(5): 472-480.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.201905010      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2019/V32/I5/472
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn