Fast Automatic Vehicle Annotation for Urban Traffic Surveillance

Automatic vehicle detection and annotation for streaming video data with complex scenes is an interesting but challenging task for intelligent transportation systems. In this paper, the authors present a fast algorithm: detection and annotation for vehicles (DAVE), which effectively combines vehicle detection and attributes annotation into a unified framework. DAVE consists of two convolutional neural networks: a shallow fully convolutional fast vehicle proposal network (FVPN) for extracting all vehicles’ positions, and a deep attributes learning network (ALN), which aims to verify each detection candidate and infer each vehicle’s pose, color, and type information simultaneously. These two nets are jointly optimized so that abundant latent knowledge learned from the deep empirical ALN can be exploited to guide training the much simpler FVPN. Once the system is trained, DAVE can achieve efficient vehicle detection and attributes annotation for real-world traffic surveillance data, while the FVPN can be independently adopted as a real-time high-performance vehicle detector as well. The authors evaluate the DAVE on a new self-collected urban traffic surveillance data set and the public PASCAL VOC2007 car and LISA 2010 data sets, with consistent improvements over existing algorithms.

• Record URL:
  • https://doi.org/10.1109/TITS.2017.2740303
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Supplemental Notes:
  • Copyright © 2018, IEEE.
• Authors:
  • Zhou, Yi
  • Liu, Li
  • Shao, Ling
  • Mellor, Matt
• Publication Date: 2018-6

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: pp 1973-1984
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 19
  • Issue Number: 6
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 1524-9050
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979

Subject/Index Terms

• TRT Terms: Automatic vehicle detection and identification systems; Data collection; Image analysis; Machine learning; Neural networks; Traffic surveillance; Vehicle detectors; Video imaging detectors
• Uncontrolled Terms: Deep learning
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Planning and Forecasting; Vehicles and Equipment;

Filing Info

• Accession Number: 01674432
• Record Type: Publication
• Files: TLIB, TRIS
• Created Date: Jul 3 2018 2:05PM