Vehicle Speed Estimation using Convolutional Neural Networks

Lavika Khattar; Ishika Kansal; Cosmena Mahapatra; Meenu Chopra

Vehicle Speed Estimation using Convolutional Neural Networks

Authors

Lavika Khattar Vivekananda Institute of Professional Studies – TC, India
Ishika Kansal Vivekananda Institute of Professional Studies – TC, India
Cosmena Mahapatra Vivekananda Institute of Professional Studies – TC, India
Meenu Chopra Vivekananda Institute of Professional Studies – TC, India

Abstract

Speed detection plays a crucial role in traffic monitoring, significantly contributing to the enhancement of vehicle efficiency and safety on roads. This paper highlights the importance of computer vision techniques to analyze video frames captured by cameras for detecting vehicles on roads and calculating their absolute speeds. Convolutional Neural networks (CNN) have demonstrated high accuracy in this domain. In this study, we propose a CNN-based approach to estimate vehicle speeds from video data. Specifically, we employ CNN-based object detection algorithms YOLO (You Only Look Once) and SSD (Single Shot Detection) to identify vehicles in each frame of the video. These approaches are tested using real-world scenarios, demonstrating their potential to enhance vehicle detection systems and reduce road accidents. We then compute the absolute speed of each vehicle based on its detection across frames. The results highlight and compare the performance of YOLO and SSD in both vehicle detection and speed estimation, highlighting their effectiveness for real-time traffic monitoring applications.

References

A. Grents, V. Varkentin, and N. Goryaev, “Determining vehicle speed based on video using convolutional neural network,” Transportation Research Procedia, vol. 50, pp. 192–200, 2020, doi: https://doi.org/10.1016/j.trpro.2020.10.024.

“Speed Estimation from Vibrations Using a Deep Learning CNN Approach | IEEE Journals & Magazine | IEEE Xplore,” ieeexplore.ieee.org. https://ieeexplore.ieee.org/abstract/document/9340328 (accessed Feb. 26, 2024).

S. Patira, “Over speed detection using Artificial Intelligence,” doi: https://doi.org/10.31979/etd.u8qc-9d6e.

R. Itu and R. Danescu, “Fully Convolutional Neural Network for Vehicle Speed and Emergency-Brake Prediction,” Sensors, vol. 24, no. 1, p. 212, Jan. 2024, doi: https://doi.org/10.3390/s24010212.

Hamam Mokayed, Amirhossein Nayebiastaneh, Lama Alkhaled, Stergios Sozos, Olle Hagner, Björn Backe, "Challenging YOLO and Faster RCNN in Snowy Conditions: UAV Nordic Vehicle Dataset (NVD) as an Example", 2024 2nd International Conference on Unmanned Vehicle Systems-Oman (UVS), pp.1-6, 2024.

M. Dreher, E. Erçelik, T. Bänziger and A. Knoll, "Radar-based 2D Car Detection Using Deep Neural Networks," 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), Rhodes, Greece, 2020, pp. 1-8, doi: 10.1109/ITSC45102.2020.9294546.

I. A. Tarmizi and A. A. Aziz, "Vehicle Detection Using Convolutional Neural Network for Autonomous Vehicles," 2018 International Conference on Intelligent and Advanced System (ICIAS), Kuala Lumpur, Malaysia, 2018, pp. 1-5, doi: 10.1109/ICIAS.2018.8540563.

Unsplash, “Photo by Keszthelyi Timi on Unsplash,” unsplash.com, May 18, 2020. https://unsplash.com/photos/cars-on-road-during-daytime-P25wpQ8ndl8 (accessed Apr. 24, 2024).

V. Barth, R. de Oliveira, M. de Oliveira and V. do Nascimento, "Vehicle Speed Monitoring using Convolutional Neural Networks," in IEEE Latin America Transactions, vol. 17, no. 06, pp. 1000-1008, June 2019, doi: 10.1109/TLA.2019.8896823.

Kim, J., Sung, J.-Y., & Park, S. (2020). Comparison of Faster-RCNN, YOLO, and SSD for Real-Time Vehicle Type Recognition. 2020 IEEE International Conference on Consumer Electronics - Asia (ICCE-Asia). doi:10.1109/icce-asia49877.2020.9277040

R. Yamashita, M. Nishio, R. K. G. Do, and K. Togashi, “Convolutional Neural networks: an Overview and Application in Radiology,” Insights into Imaging, vol. 9, no. 4, pp. 611–629, Jun. 2018, doi: https://doi.org/10.1007/s13244-018-0639-9

P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma, “A Review of Yolo Algorithm Developments,” Procedia Computer Science, vol. 199, pp. 1066–1073, Jan. 2022, doi: https://doi.org/10.1016/j.procs.2022.01.135.

W. Liu et al., “SSD: Single Shot MultiBox Detector,” Computer Vision – ECCV 2016, vol. 9905, pp. 21–37, 2016, doi: https://doi.org/10.1007/978-3-319-46448-0_2.

L. Chen, F. Ye, Y. Ruan, H. Fan, and Q. Chen, “An algorithm for highway vehicle detection based on convolutional neural network,” EURASIP Journal on Image and Video Processing, vol. 2018, no. 1, Oct. 2018, doi: https://doi.org/10.1186/s13640-018-0350-2.

T. Keerthi et al., "An Automatic Vehicle Speed Controlling based on Traffic Signs Recognition using Convolutional Neural Network," 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), Delhi, India, 2023, pp. 1-9, doi: 10.1109/ICCCNT56998.2023.10306873.

Shepelev, V., Aliukov, S., Nikolskaya, K. and Shabiev, S. (2020). The Capacity of the Road Network: Data Collection and Statistical Analysis of Traffic Characteristics. Energies, 13(7), p.1765. doi:https://doi.org/10.3390/en13071765.

Year	Rate
2024	12.6%
2023	18.3%

Vehicle Speed Estimation using Convolutional Neural Networks