Real-Time End-to-End Vehicle and Landmark Localization Based on Semi-Supervised Learning

Detection of vehicles along with their landmarks is important for many subsequent topics, such as monocular 3D detection, vehicle tracking, and vehicle re-identification. However, due to lack of fully annotated datasets, currently, most research addresses this problem based on time-consuming two-stage schemes, i.e., firstly, detecting the bounding boxes of vehicles, then, cropping the vehicles, and regressing their landmarks based on these snapshots. In this paper, the authors develop a semi-supervised learning mechanism, which utilizes partially annotated data to train an end-to-end network that can simultaneously detect vehicles and their landmarks. In addition, the model is scalable and also provides a light-weight version of the proposed detection network which can run at a real-time speed of over 20 FPS on an edge device. Experimental reports indicate that this approach achieves satisfactory performance and is efficient for real-world application.

• Record URL:
  • https://doi.org/10.1061/9780784484869.026
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9780784484869
• Supplemental Notes:
  • © 2023 American Society of Civil Engineers.
• Corporate Authors:

  American Society of Civil Engineers

  1801 Alexander Bell Drive
  Reston, VA  United States  20191-4400
• Authors:
  • Xiao, Nengfei
  • Xiong, Zhongxia
  • Ma, Yalong
  • Wu, Xinkai
• Conference:
  • 23rd COTA International Conference of Transportation Professionals
  • Location: Beijing , China
  • Date: 2023-7-14 to 2023-7-17
• Publication Date: 2023

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 268-278
• Monograph Title: CICTP 2023: Innovation-Empowered Technology for Sustainable, Intelligent, Decarbonized, and Connected Transportation

Subject/Index Terms

• TRT Terms: Automatic vehicle identification; Image processing; Machine learning; Real time data processing; Tracking systems
• Subject Areas: Highways; Operations and Traffic Management; Safety and Human Factors;

Filing Info

• Accession Number: 01894522
• Record Type: Publication
• ISBN: 9780784484869
• Files: TRIS, ASCE
• Created Date: Sep 25 2023 4:23PM