10th Small Systems Simulation Symposium

Join leading researchers and practitioners in the field of system simulation at the University of Niš, Faculty of Electronic Engineering

February 12-14, 2026 | University of Niš, Faculty of Electronic Engineering

Application of Computer Vision for Detecting Electric Scooters in Vehicle Blind Spots

https://doi.org/10.46793/SSSS2026.106S



Authors:

  • Milan Stojanović
    https://orcid.org/0009-0008-5598-041X

    Faculty of Electronic Engineering, Niš, Serbia



    The paper is available at the following link: PDF



    Abstract:

    Due to the increasing use of electric scooters as a means of transportation in cities, ensuring the safety of their riders is very important. Limited visibility and the presence of blind spots in large vehicles, especially trucks and buses, and the difficulty of spotting electric scooters puts riders in dangerous situations. In this paper, we will demonstrate a computer vision approach for detecting electric scooters and present an evaluation of its performance. The idea is to create a system which can be implemented in large vehicles using dedicated cameras and software to warn drivers when an electric scooter is next to or behind the vehicle. The use of computer vision for this purpose is more effective than the use of simple sensors because this method accurately detects if there is an electric scooter, and not some other obstacle.



    Keywords:

    Computer vision, Electirc Scooters, Blind Spots, Traffic Safety.



    REFERENCES:

    [1] C. Cloud, S. Heß, and J. Kasinger, "Do shared e-scooter services cause traffic accidents? Evidence from six European countries," arXiv preprint arXiv:2209.06870, Sep. 2022.
    [2] A. R. Pathak, C. K. Patel, V. R. Patel, S. Jambhorkar, S. S. Lahane, and A. A. Ghatol, "A comprehensive review of object detection with deep learning," Digital Signal Processing, vol. 132, p. 103812, Jan. 2023
    [3] J. Liu, W. Ouyang, X. Wang, P. Fieguth, J. Chen, X. Liu, and M. Pietikäinen, "Deep Learning for Generic Object Detection: A Survey," International Journal of Computer Vision, vol. 128, pp. 261–318, Feb. 2020.
    [4] R. Kaur, S. Singh, "A Review of YOLO Object Detection Based on Deep Learning," Frontiers in Computing and Intelligent Systems, Jan, 2023.
    [5] M. Wang and W. Leelapatra, "A Review of Object Detection Based on Convolutional Neural Networks and Deep Learning," International Scientific Journal of Engineering and Technology (ISJET), vol. 6, no. 1, pp. 1–7, 2022.
    [6] Ultralytics, "Ultralytics Official Website," 2025. [Online]. Available: https://www.ultralytics.com/



  • Sponsored by:

    Placeholder image Placeholder image Placeholder image