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 (10): 917-925    DOI: 10.16451/j.cnki.issn1003-6059.202010006
Current Issue| Next Issue| Archive| Adv Search |
Real-Time Road Element Detection Based on Keypoints Estimation
LIU Xianmei1, JING Yahong1, TIAN Feng1, LIU Fang1
1.School of Computer and Information Technology, Northeast Petroleum University, Daqing 163318

Download: PDF (1629 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Aiming at the problems of high cost of manually designing neural network structure, large amount of calculation of the classification and regression task based on the anchor boxes, and weak detection ability for small targets, a real-time road element detection model based on keypoint estimation is proposed. NAS-based EfficientNet-B3 is employed as the feature extraction network. An improved bi-directional feature pyramid network(BiFPN) method is exploited as the feature fusion network. Instead of anchor boxes, keypoint estimation is utilized for classification and regression tasks. The experiment on BDD100K dataset shows that the proposed model achieves a good precision in real-time detection and a high precision for small objects.
Key wordsDeep Learning      Road Element Detection      One-Stage Algorithm      Keypoint Estimation      Feature Fusion     
Received: 16 June 2020     
ZTFLH: TP391.4  
Fund:National Natural Science Foundation of China(No.61502094), Local Universities Reformation and Development Personnel Training Supporting Project from Central Authorities(No.140119001), Basic Scientific Research Business Fee Project of Provincial Undergraduate Colleges and Universities in Heilongjiang Province of China(Excellent Young and Middle-aged Scientific Research Innovation Team of Northeast Petroleum University)(No.KYCXTD201903)
Corresponding Authors: LIU Xianmei, master, professor. Her research interests include virtual reality and computer vision.   
About author:: JING Yahong, master student. Her research interests include target detection and tracking.TIAN Feng, Ph.D., professor. His research interests include computer vision and virtual reality.LIU Fang, Ph.D. candidate, associate pro-fessor. Her research interests include virtual reality and computer vision.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
LIU Xianmei
JING Yahong
TIAN Feng
LIU Fang
Cite this article:   
LIU Xianmei,JING Yahong,TIAN Feng等. Real-Time Road Element Detection Based on Keypoints Estimation[J]. , 2020, 33(10): 917-925.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202010006      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2020/V33/I10/917
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