FRNet: DCNN for Real-Time Distracted Driving Detection Toward Embedded Deployment

Real-time running deep convolutional neural networks on embedded electronics is one recent focus for distracted driving detection. In this work, the authors proposed FRNet, which is a unique, efficient, and real-time architecture. The FRNet converts spatially distributed features into depth distribution by a feature reorganization block. This block compresses the volume of backbone, reduces the memory read/write volumes along with multiply-accumulate operations, and extracts key features faster. In addition, a ultra-lightweight backbone was designed, with an atypical reshape strategy. This atypical strategy designed based on pixel-level analysis, for compensating the accuracy decline along with feature reorganization. The proposed FRNet offered excellent real-time performance on low power embedded platforms, and has a competitive accuracy with previous state-of-the-art models. It achieved 97.55% accuracy on the SFD+AUCDD-V1, and 99.86% on 3MDAD. On an automotive-grade embedded demo board, it costs 16.93 ms per frame and achieved 59 FPS. As of today, this is the fastest record for end-to-end distraction detection. Experiments revealed the real-time and accuracy are best balanced with FRNet. The model is publicly available at https://github.com/congduan-HNU/FRNet.

• Record URL:
  • http://dx.doi.org/10.1109/TITS.2023.3270879
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Supplemental Notes:
  • Copyright © 2023, IEEE.
• Authors:
  • Duan, Cong
  • Gong, Y
  • Liao, Jiacai
  • Zhang, Minghai
  • Cao, Libo
• Publication Date: 2023-9

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 9835-9848
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 24
  • Issue Number: 9
  • 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: Detection and identification; Distracted driving; Embedded systems; Neural networks
• Subject Areas: Data and Information Technology; Highways; Safety and Human Factors;

Filing Info

• Accession Number: 01900969
• Record Type: Publication
• Files: TRIS
• Created Date: Nov 28 2023 4:28PM