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
  2020, Vol. 33 Issue (6): 568-574    DOI: 10.16451/j.cnki.issn1003-6059.202006010
Researches and Applications Current Issue| Next Issue| Archive| Adv Search |
Occluded Pedestrian Detection Algorithm Based on Improved Network Structure of YOLOv3
LIU Li1,2, ZHENG Yang1,2,3, FU Dongmei1,2
1. School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083
2. Beijing Engineering Research Center of Industrial Spectrum Imaging, University of Science and Technology Beijing, Beijing 100083
3. Shunde Graduate School, University of Science and Technology Beijing, Foshan 528399

Download: PDF (1502 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Aiming at high missed detection rates of YOLOv3 for occluded pedestrian in surveillance video, a detection method for occluded pedestrian based on improved network structure of YOLOv3 is proposed. Firstly, the spatial pyramid pooling network is introduced into the fully connected layer to enhance the multi-scale feature fusion capability of the network. Secondly, the network structure pruning is employed to eliminate the network structure redundancy to avoid network degeneration and overfitting problem caused by the deepening of network layers and reduce the amount of parameters. Multi-scale training is performed on the corridor pedestrian dataset to obtain the best weight model. Experimental results indicate the improvement of average accuracy and detection speed of the proposed algorithm.
Key wordsPedestrian Detection      Deep Learning      YOLOv3      Spatial Pyramid Pooling Network      Network Pruning     
Received: 05 March 2020     
ZTFLH: TP 391.4  
Fund:Fundamental Research Funds for the Central Universities of University of Science and Technology Beijing(No.FRF-BD-19-002A)
Corresponding Authors: LIU Li, Ph.D., professor. Her research interests include computer network and pattern recognition.   
About author:: ZHENG Yang, master student. His research interests include deep learning, target detection and tracking. FU Dongmei, Ph.D., professor. Her research interests include deep learning and pa-ttern recognition.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
LIU Li
ZHENG Yang
FU Dongmei
Cite this article:   
LIU Li,ZHENG Yang,FU Dongmei. Occluded Pedestrian Detection Algorithm Based on Improved Network Structure of YOLOv3[J]. , 2020, 33(6): 568-574.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202006010      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2020/V33/I6/568
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