模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2020, Vol. 33 Issue (5): 393-400    DOI: 10.16451/j.cnki.issn1003-6059.202005002
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Region Proposal Network Based on Effective Receptive Field
ZHANG Shengyu1,2, DONG Shifeng2, JIAO Lin2, WANG Qijin2, WANG Hongqiang2
1. Institutes of Physical Science and Information Technology, Anhui University, Hefei 230039;
2. Special Robot Laboratory, Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031

Download: PDF (2829 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Object detection methods based on convolutional neural network(CNN) optimize region proposal to achieve a higher detection accuracy. Therefore, an effective receptive field(eRF) based region proposal network is proposed. A sample matching method based on eRF is introduced into regional proposal network. Thus, the intersection over union(IoU) based sample matching rule is improved. The representation ability of feature information in the region proposal generation stage is enhanced. The number of region proposal and anchor boxes is greatly reduced. The parameter settings of anchor boxes are also simplified. The detection accuracy on Pascal VOC datasets is improved in combination with Fast R-CNN detector. The effectiveness of proposed method is verified.
Key wordsDeep Convolutional Network      Object Detection      Region Proposal      Effective Receptive Field      Region Proposal Network(RPN)     
Received: 29 November 2019     
ZTFLH: TP 391.41  
Fund:Supported by National Natural Science Foundation of China(No.61773360,61973295), Key Research and Development Project of Anhui Province(No.201904a07020092)
About author:: (ZHANG Shengyu, master student. His research interests include pattern recognition and object detection.);(DONG Shifeng, master student. His research interests include pattern recognition and object detection.);(JIAO Lin, Ph.D candidate. Her research interests include pattern recognition and deep learning.);(WANG Qijin, Ph.D candidate. His research interests include object detection and network security.);(WANG Hongqiang(Corresponding author), Ph.D. professor. His research inte-rests include pattern recognition, deep learning and big data analysis.)
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
ZHANG Shengyu
DONG Shifeng
JIAO Lin
WANG Qijin
WANG Hongqiang
Cite this article:   
ZHANG Shengyu,DONG Shifeng,JIAO Lin等. Region Proposal Network Based on Effective Receptive Field[J]. , 2020, 33(5): 393-400.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202005002      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2020/V33/I5/393
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