K. Jeevitha
- PG Student Department of Artificial Intelligence and Data Science, Sri Manakula Vinayagar Engineering College, Madagadipet Puducherry India
Abstract
The real-time vehicle classification, counting, and speed estimation system based on YOLOv8n is an important tool for monitoring traffic flow on highways. However, because they are distinct objects from their surroundings, it is still difficult to detect them, which has an impact on how accurate vehicle counts are. To tackle this concern, this paper suggests the implementation of a vision-centric system for real-time vehicle monitoring and identification. The approach involves utilizing a You Only Look Once (YOLOv8n)-based Deep SORT model to detect, count, and estimate the speed of vehicles from video clips. Additionally, the integration of a Deep SORT algorithm, based on deep learning, enhances the accuracy of tracking the actual presence of vehicles in video frames predicted by YOLOv8n. Two processes are involved in vehicle counting: first, the recorded video is fed into a deep learning framework based on YOLO to identify, count, and classify each vehicle. Multi-vehicular tracking is adopted using Deep SORT to enhance the tracking performance by associating detected vehicles across frames, ensuring reliable tracking in crowded and dynamic environments.
Keywords: Vehicle counting, object detection, tracking, YOLOv8n, Deep SORT
[This article belongs to Research & Reviews: A Journal of Embedded System & Applications(rrjoesa)]
References
- Mohammadnazar A, Arvin R, Khattak AJ. Classifying travelers’ driving style using basic safety messages generated by connected vehicles: application of unsupervised machine learning. Transport Res Part C: Emerg Technol. 2021; 122: Article 102917. doi: 10.1016/j.trc.2020.102917.
- Wang Y, Ban X, Wang H, Wu D, Wang H, Yang S, Liu S, Lai J. Detection and classification of moving vehicle from video using multiple spatio-temporal features. IEEE Access. 2019; 7: 80287–80299. doi: 10.1109/ACCESS.2019.2923199.
- Kusumah AP, Djayusman D, Setiadi GR, Nugraha AC, Hidayatullah P. Counting various vehicles using YOLOv4 and DeepSORT. J Integr Adv Eng. 2023; 3 (1): 1–6. doi: 10.51662/jiae.v3i1.68.
- Kejriwal R, Ritika HJ, Arora A, Mohana. Vehicle detection and counting using deep learning based YOLO and Deep SORT algorithm for urban traffic management system. In: 2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), Trichy, India, February 16–18, 2022. pp. 1–6. doi: 10.1109/ICEEICT53079.2022.9768653.
- Gomaa A, Abdelwahab MM, Abo-Zahhad M, Minematsu T, Taniguchi R. Robust vehicle detection and counting algorithm employing a convolution neural network and optical flow. Sensors. 2019; 19 (20): 4588.
- Sonnleitner E, Barth O, Palmanshofer A, Kurz M. Traffic measurement and congestion detection based on real-time highway video data. Appl Sci. 2020; 10 (18): 6270.
- Mandal V, Adu-Gyamfi Y. Object detection and tracking algorithms for vehicle counting: a comparative analysis. J Big Data Anal Transport. 2020; 2: 251–261.
- Meghana RK, Chitkara Y, Apoorva S. Mohana. Background-modelling techniques for foreground detection and tracking using Gaussian mixture model. In: 3rd International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, March 27–29, 2019. pp. 1129–1134.
- Chethan Kumar B, Punitha R, Mohana. Performance analysis of object detection algorithm for intelligent traffic surveillance system. In: Second International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India, July 15–17, 2020. pp. 573–579.
- Rishika AL, Aishwarya Ch, Sahithi A, Premchender M. Real-time vehicle detection and tracking using YOLO-based Deep SORT model: a computer vision application for traffic surveillance. Turk J Computer Math Educ. 2023; 14 (1): 255–264.
- Zhou Z, Li H. Vehicle object detection based on deep learning. Acad J Sci Technol. 2023; 5 (1): 38–45.
- Rouf MA, Wu Q, Yu X, Iwahori Y, Wu H, Wang A. Real-time vehicle detection, tracking and counting system based on YOLOv7. Embedded Self-Organ Syst. 2023; 10 (7): 4–8. doi: 10.14464/ess.v10i7.598.
- Wu JD, Chen BY, Shyr WJ, Shih FY. Vehicle classification and counting system using YOLO object detection technology. Traitement du Signal. 2021; 38 (4): 1087–1093.
Research & Reviews: A Journal of Embedded System & Applications
| Volume | 12 |
| Issue | 01 |
| Received | February 16, 2024 |
| Accepted | March 21, 2024 |
| Published | April 4, 2024 |