An edge computing-based embedded traffic information processing approach:application of deep learning in existing traffic systems
CSTR:
Author:
Affiliation:

School of Physics and Electronic Engineering, Northwest Normal University, Lanzhou 730070, China[]

  • Article
  • | |
  • Metrics
  • |
  • Reference [10]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    To address traffic congestion, this study improves MobileNetv2-you only look once version 4 (YOLOv4) target detection algorithm (MobileNetv2-YOLOv4-K++F) and introduces an embedded traffic information processing solution based on edge computing. We transition models initially designed for large-scale graphics processing units (GPUs) to edge computing devices, maximizing the strengths of both deep learning and edge computing technologies. This approach integrates embedded devices with the current traffic system, eliminating the need for extensive equipment updates. The solution enables real-time traffic flow monitoring and license plate recognition at the edge, synchronizing instantaneously with the cloud, allowing for intelligent adjustments of traffic signals and accident forewarnings, enhancing road utilization, and facilitating traffic flow optimization. Through on-site testing using the RK3399PRO development board and the MobileNetv2-YOLOv4-K++F object detection algorithm, the upgrade costs of this approach are less than one-tenth of conventional methods. Under favorable weather conditions, the traffic flow detection accuracy reaches as high as 98%, with license plate recognition exceeding 80%.

    Reference
    [1] YOUNG M S, BIRRELL S A, STANTON N A. Safe driving in a green world:a review of driver performance benchmarks and technologies to support “smart” driving[J]. Applied ergonomics, 2011, 42(4):533-539.
    [2] WEN Y, LU Y, YAN J Q, et al. An algorithm for license plate recognition applied to intelligent transportation system[J]. IEEE transactions on intelligent transportation systems, 2011, 12(3):830-845.
    [3] CHENG Q, MA H T, SUN X. Vehicle LED detection and segmentation recognition based on deep learning for optical camera communication[J]. Optoelectronics letters, 2022, 18(8):508-512.
    [4] GUDIGAR A, CHOKKADI S U R. A review on automatic detection and recognition of traffic sign[J]. Multimedia tools and applications, 2016, 75:333-364.
    [5] ALOMARI A H, ABU LEBDEH E. Smart real-time vehicle detection and tracking system using road surveillance cameras[J]. Journal of transportation engineering, part A:systems, 2022, 148(10):04022076.
    [6] LI J, XU Z J, XU L. Vehicle and pedestrian detection method based on improved YOLOv4-tiny[J]. Optoelectronics letters, 2023, 19(10):623-628.
    [7] LIN H J, YUAN Z L, HE B, et al. A deep learning framework for video-based vehicle counting[J]. Frontiers in physics, 2022, 10:829734.
    [8] DAI Z, SONG H S, WANG X, et al. Video-based vehicle counting framework[J]. IEEE access, 2019, 7:64460-64470.
    [9] UMAIR M, FAROOQ M U, RAZA R H, et al. Efficient video-based vehicle queue length estimation using computer vision and deep learning for an urban traffic scenario[J]. Processes, 2021, 9(10):1786.
    [10] CHEN Y, LU J. A multi-loop vehicle-counting method
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

PING Haoyu, MA Yongjie, ZHU Guangya, ZHANG Jiaqi. An edge computing-based embedded traffic information processing approach:application of deep learning in existing traffic systems[J]. Optoelectronics Letters,2024,20(10):623-628

Copy
Share
Article Metrics
  • Abstract:29
  • PDF: 0
  • HTML: 0
  • Cited by: 0
History
  • Received:November 10,2023
  • Revised:April 03,2024
  • Online: September 03,2024
Article QR Code