MG-GCT: A Motion-Guided Graph Convolutional Transformer for Traffic Gesture Recognition

For autonomous driving systems, it is crucial to recognize the actions and gestures of traffic conductors and cyclists on the road to ensure safety. However, traffic gesture recognition is more challenging than action recognition in general scenarios due to the differences in action posture and sample composition between traffic gesture datasets and general action datasets. Therefore, general action recognition methods cannot identify traffic gestures well. To overcome these problems, the authors propose a novel motion-guided graph convolutional transformer (MG-GCT) for traffic gesture recognition. Firstly, they proposed a two-stream network to fully utilize joint data and motion data for action recognition. Secondly, the authors designed and implemented a motion-guided module between two streams, which leverages the powerful spatial representation ability of the motion data to guide the learning of the joint data stream in the spatial dimension. Thirdly, they implemented a temporal transformer network to process the temporal features of the skeleton. Finally, the authors conducted extensive experiments on two public datasets and one dataset presented by themselves to demonstrate the effectiveness of their network in traffic gesture recognition, which has a significant advantage over the state-of-the-art methods.

• Record URL:
  • http://dx.doi.org/10.1109/TITS.2024.3394911
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Supplemental Notes:
  • Copyright © 2024, IEEE.
• Authors:
  • Guo, Xiaofeng
  • 0000-0002-7258-3060
  • Zhu, Qing
  • 0000-0001-7785-6374
  • Wang, Yaonan
  • 0000-0002-0519-6458
  • Mo, Yang
  • 0000-0001-6734-8691
• Publication Date: 2024-10

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 14031-14039
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 25
  • Issue Number: 10
  • 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: Autonomous vehicles; Cyclists; Detection and identification system applications; Hand signaling; Police traffic direction; Vehicle mix
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Pedestrians and Bicyclists; Safety and Human Factors; Vehicles and Equipment;

Filing Info

• Accession Number: 01942202
• Record Type: Publication
• Files: TRIS
• Created Date: Jan 13 2025 10:24AM