Deploying Android-Based Smart RSUs with YOLOv8 and SAHI for Enhanced Traffic Management
DOI:
https://doi.org/10.24237/djes.2025.18104Keywords:
YOLOv8, SAHI Algorithm, Traffic Monitoring, Real-Time Data Processing, Vehicle DetectionAbstract
Traffic congestion remains a major challenge in urban areas due to the high cost, scalability issues, and inefficiencies of traditional monitoring systems. This study proposes an innovative, cost-effective traffic monitoring system utilizing Android-based Smart Roadside Units (RSUs) to detect vehicles and analyze real-time traffic data. The system leverages the You Only Look Once, version 8 (YOLOv8) model, enhanced with the Slicing Aided Hyper Inference (SAHI) algorithm to improve detection accuracy for small and distant objects. Field experiments were conducted using three Android device categories high, medium, and low-cost to assess detection accuracy across different distances. Results indicated that high-cost devices could accurately detect vehicles up to 500 meters away, whereas medium and low-cost devices exhibited reduced detection accuracy and range. The findings highlight the impact of hardware specifications and environmental conditions on system performance. The proposed approach addresses limitations of conventional traffic monitoring by providing an adaptable, open-source infrastructure that reduces hardware costs while ensuring real-time processing. Utilizing mobile devices enhances scalability and cost-effectiveness compared to traditional RSUs, which are expensive and hard to deploy at scale. Future research will integrate functionalities like pedestrian detection and vehicle tracking to further enhance smart transportation systems. This study demonstrates the feasibility of Android-based RSUs, offering a practical alternative to conventional methods and advancing intelligent traffic management solutions.
Downloads
References
[1] United Nations. “2014 Revision of the World Urbanization Prospects | Latest Major Publications - United Nations Department of Economic and Social Affairs.” Un.org, 2014, www.un.org/en/development/desa/publications/2014-revision-world-urbanization-prospects.html.
[2] M. A. Balwan, T. Varghese and S. Nadeera, "Urban Traffic Control System Review - A Sharjah City Case Study," 2021 9th International Conference on Traffic and Logistic Engineering (ICTLE), Macau, China, 2021, pp. 46-50, doi: 10.1109/ICTLE53360.2021.9525750.
[3] Agarwal, P.K. “Intelligent Transportation Systems and Its Tools as a Solution for Urban Traffic Congestion: A Review.” Journal of Emerging Technologies and Innovative Research, 2020, www.academia.edu/80802555/Intelligent_Transportation_Systems_and_Its_Tools_as_a_Solution_for_Urban_Traffic_Congestion_A_Review. Accessed 20 Jan. 2025.
[4] Bista, Raghu, and Surendra Paneru. “Does Road Traffic Congestion Increase Fuel Consumption of Households in Kathmandu City?” Journal of Economic Impact, vol. 3, no. 2, 29 July 2021, pp. 67–79, https://doi.org/10.52223/jei3022102. Accessed 11 Sept. 2021.
[5] A. K. M., N. K. T., A. J. K., A. P., and M. I. P., "Economic evaluation of traffic congestion & design of traffic signal with simulation at Ottapalam," International Journal of Research in Applied Science and Engineering Technology, 2023. doi: 10.22214/ijraset.2023.53881.
[6] Cherednichenko, Oleksandra, and Asta Valackienė. “INTELLIGENT TRANSPORT SYSTEMS as TRAFFIC FLOW MANAGEMENT TOOL (the CASE of KYIV).” Urban Development and Spatial Planning, no. 80, 30 May 2022, pp. 416–450, https://doi.org/10.32347/2076-815x.2022.80.416-450. Accessed 17 Feb. 2023.
[7] SUBAIR, Sulaiman Olayinka, et al. “Evaluation of Traffic Congestion in an Urban Roads: A Review.” ABUAD Journal of Engineering and Applied Sciences, vol. 2, no. 2, 30 Aug. 2024, pp. 1–7, https://doi.org/10.53982/ajeas.2024.0202.01-j. Accessed 21 Oct. 2024.
[8] H. Abdelati, Mohamed. “Smart Traffic Management for Sustainable Development in Cities: Enhancing Safety and Efficiency.” International Journal of Advanced Engineering and Business Sciences, vol. 5, no. 1, 24 Feb. 2024, https://doi.org/10.21608/ijaebs.2024.242361.1088.
[9] Kadiyala Ramana, et al. “A Vision Transformer Approach for Traffic Congestion Prediction in Urban Areas.” “IEEE Transactions on Intelligent Transportation Systems,” vol. 24, no. 4, 1 Jan. 2023, pp. 3922–3934, https://doi.org/10.1109/tits.2022.3233801. Accessed 11 June 2023.
[10] None Prof. Vrushali Awle, et al. “Smart Traffic Management System.” International Journal of Advanced Research in Science, Communication and Technology, vol. 3, no. 1, 4 Dec. 2023, pp. 108–124, https://doi.org/10.48175/ijarsct-14013. Accessed 16 May 2024.
[11] Golhar, Yogesh, and Manali Kshirsagar. “Emerging Technologies for Driving Road Safety and Traffic Management for Urban Area.” Journal of Computer Science, vol. 17, no. 11, 1 Nov. 2021, pp. 1104–1115, https://doi.org/10.3844/jcssp.2021.1104.1115. Accessed 9 Feb. 2022.
[12] Drushya Kamuni, et al. “Density Based Traffic Congestion Control System and Emergency Vehicle Clearance.” 2022 International Conference on Power, Energy, Control and Transmission Systems (ICPECTS), 8 Dec. 2022, pp. 1–6, www.researchgate.net/publication/368857431_Density_Based_Traffic_Congestion_Control_System_and_Emergency_Vehicle_Clearance,https://doi.org/10.1109/ICPECTS56089.2022.10047102.
[13] Li, Shanwen. “Real-Time Traffic Congestion Detection Technology in Intelligent Transportation Systems.” 2022 IEEE 11th International Conference on Communication Systems and Network Technologies (CSNT), 6 Apr. 2024, pp. 1029–1033, ieeexplore.ieee.org/document/10546078, https://doi.org/10.1109/csnt60213.2024.10546078. Accessed 20 Jan. 2025.
[14] Ultralytics, "Introducing Ultralytics YOLOv8," 2023. [Online]. Available: https://www.ultralytics.com/blog/introducing-ultralytics-yolov8. Accessed: Jan. 18, 2025.
[15] DataDrivenInvestor, "YOLOv8: The Evolution of Real-Time Object Detection," 2023. [Online]. Available: https://medium.datadriveninvestor.com/yolov8-the-evolution-of-real-time-object-detection-7c158948e0de. Accessed: Jan. 18, 2025.
[16] Lou, Haitong, et al. “DC-YOLOv8: Small-Size Object Detection Algorithm Based on Camera Sensor.” Electronics, vol. 12, no. 10, 21 May 2023, pp. 2323–2323, https://doi.org/10.3390/electronics12102323.
[17] Keylabs, "Getting Started with YOLOv8: A Beginner's Guide," 2024. [Online]. Available: https://keylabs.ai/blog/getting-started-with-yolov8-a-beginners-guide. Accessed: Jan. 18, 2025.
[18] Plugger.ai, "The Evolution of Object Detection: A Journey from YOLO to YOLOv8 and Beyond - An Exploration of Advancements in the Last Seven Years," 2023. [Online]. Available: https://www.plugger.ai/blog/the-evolution-of-object-detection-a-journey-from-yolo-to-yolov8-and-beyond-an-exploration-of-advancements-in-the-last-seven-years.
[19] Ultralytics, "Ultralytics Documentation," 2024. [Online]. Available: https://docs.ultralytics.com. Accessed: Jan. 18, 2025
[20] Yousif, Adel Jalal, and Mohammed H Al-Jammas. “A Lightweight Visual Understanding System for Enhanced Assistance to the Visually Impaired Using an Embedded Platform.” Diyala Journal of Engineering Sciences, vol. 17, no. 3, 1 Sept. 2024, pp. 146–162, djes.info/index.php/djes/article/view/1377, https://doi.org/10.24237/djes.2024.17310. Accessed 20 Jan. 2025.
[21] Evans, Michael, et al. “Vehicle-To-Everything (V2X) Communication: A Roadside Unit for Adaptive Intersection Control of Autonomous Electric Vehicles.” ArXiv.org, 2024, arxiv.org/abs/2409.00866. Accessed 20 Jan. 2025.
[22] Raoul Kanschat, et al. “Wireless-Signal-Based Vehicle Counting and Classification in Different Road Environments.” IEEE Open Journal of Intelligent Transportation Systems, vol. 3, no. 90, 1 Jan. 2022, pp. 236–250, www.researchgate.net/publication/359683275_Wireless-Signal-Based_Vehicle_Counting_and_Classification_in_Different_Road_Environments, https://doi.org/10.1109/OJITS.2022.3160934.
[23] Nguyen, Justin, et al. “TrafficNNode: Low Power Vehicle Sensing Platform for Smart Cities.” IEEE, 2021.
[24] Martín, Juan, et al. “Traffic Monitoring via Mobile Device Location.” Sensors, vol. 19, no. 20, 17 Oct. 2019, p. 4505, https://doi.org/10.3390/s19204505. Accessed 23 May 2020.
[25] Vergis, Spiridon, et al. “A Low-Cost Vehicular Traffic Monitoring System Using Fog Computing.” Smart Cities, vol. 3, no. 1, 19 Mar. 2020, pp. 138–156, https://doi.org/10.3390/smartcities3010008.
[26] Wang, Kafeng, et al. “SenseMag: Enabling Low-Cost Traffic Monitoring Using Non-Invasive Magnetic Sensing.” IEEE Internet of Things Journal, vol. 8, no. 22, 2021, pp. 1–1, https://doi.org/10.1109/jiot.2021.3074907. Accessed 25 Apr. 2021.
[27] M. Won, S. Zhang, and S. H. Son, "WiTraffic: Low-cost and non-intrusive traffic monitoring system using WiFi," in 2017 26th International Conference on Computer Communication and Networks (ICCCN), July 2017, pp. 1–9. , https://doi.org/10.1109/icccn.2017.8038380. Accessed 25 Oct. 2023.
[28] Seid, Salahadin, et al. “A Low Cost Edge Computing and LoRaWAN Real Time Video Analytics for Road Traffic Monitoring.” IEEE Xplore, 1 Dec. 2020, ieeexplore.ieee.org/document/9394326. Accessed 2 Oct. 2022.
[29] Maus, Gerrit, and Dieter Brückmann. “A Non-Intrusive, Single-Sided Car Traffic Monitoring System Based on Low-Cost BLE Devices.” 2020 IEEE International Symposium on Circuits and Systems (ISCAS), Oct. 2020, pp. 1–5, ieeexplore.ieee.org/abstract/document/9181215, https://doi.org/10.1109/iscas45731.2020.9181215. Accessed 20 Jan. 2025.
[30] Ji, Wen, et al. “Trip-Based Mobile Sensor Deployment for Drive-by Sensing with Bus Fleets.” Transportation Research Part C: Emerging Technologies, vol. 157, 3 Nov. 2023, p. 104404, www.sciencedirect.com/science/article/abs/pii/S0968090X23003947, https://doi.org/10.1016/j.trc.2023.104404.
[31] Martuscelli, Giuseppe, et al. “V2V Protocols for Traffic Congestion Discovery along Routes of Interest in VANETs: A Quantitative Study.” Wireless Communications and Mobile Computing, vol. 16, no. 17, 21 Sept. 2016, pp. 2907–2923, https://doi.org/10.1002/wcm.2729. Accessed 29 Aug. 2021.
[32] Guastella, Davide Andrea, and Evangelos Pournaras. “Cooperative Multi-Agent Traffic Monitoring Can Reduce Camera Surveillance.” IEEE Access, vol. 11, 2023, pp. 142125–142145, ieeexplore.ieee.org/abstract/document/10360829/, https://doi.org/10.1109/access.2023.3343620. Accessed 20 Jan. 2025.
[33] Rahman, Abdul. “On-Demand Mobile Sensing Framework for Traffic Monitoring. (C2017).” Lau.edu.lb, 11 May 2017, laur.lau.edu.lb:8443/xmlui/handle/10725/6539, http://hdl.handle.net/10725/6539. Accessed 20 Jan. 2025.
[34] Yilmaz, Ozgun, et al. “Cloud-Assisted Mobile Crowd Sensing for Route and Congestion Monitoring.” IEEE Access, vol. 9, 2021, pp. 157984–157996, https://doi.org/10.1109/access.2021.3129932. Accessed 17 Feb. 2022.
[35] Ali, Qutaiba I. “Realization of a Robust Fog-Based Green VANET Infrastructure.” IEEE Systems Journal, vol. 17, no. 2, June 2023, pp. 2465–2476, https://doi.org/10.1109/jsyst.2022.3215845. Accessed 10 Nov. 2024.
[36] Ibrahim, Qutaiba. “An Efficient Power Management Strategy of a Solar Powered Smart Camera-Road Side Unit Integrated Platform.” International Journal of Sensors, Wireless Communications and Control, vol. 13, 24 Oct. 2022, https://doi.org/10.2174/2210327913666221024160809. Accessed 3 Dec. 2022.
[37] Ali, Q. I. (2008). An efficient simulation methodology of networked industrial devices. Proceedings of the 2008 5th International Multi-Conference on Systems, Signals and Devices (SSD), Amman, Jordan, 1–6, https://doi.org/10.1109/ssd.2008.4632835. Accessed 20 Jan. 2025.
[38] Ultralytics. “TensorRT.” Ultralytics.com, 2024, docs.ultralytics.com/integrations/tensorrt/?h=yolov8#what-are-the-performance-improvements-observed-with-yolov8-models-exported-to-tensorrt. Accessed 20 Jan. 2025.
[39] NVIDIA Corporation, "NVIDIA DGX A100 system datasheet," 2020. [Online]. Available: https://images.nvidia.com/aem-dam/Solutions/Data-Center/nvidia-dgx-a100-datasheet.pdf. Accessed: Jan. 20, 2025.
[40] GSMArena, "ZTE Blade A71 - Full phone specifications," [Online]. Available: https://www.gsmarena.com/zte_blade_a71-11240.php. Accessed: Jan. 20, 2025.
[41] GSMArena, "Samsung Galaxy A32 5G - Full phone specifications," [Online]. Available: https://www.gsmarena.com/samsung_galaxy_a32_5g-10648.php. Accessed: Jan. 20, 2025.
[42] GSMArena, "Samsung Galaxy S21 Ultra 5G - Full phone specifications," [Online]. Available: https://www.gsmarena.com/samsung_galaxy_s21_ultra_5g-10596.php. Accessed: Jan. 20, 2025.
[43] Ultralytics, "Using YOLOv8 with SAHI for Sliced Inference," [Online]. Available: https://docs.ultralytics.com/guides/sahi-tiled-inference. Accessed: Jan. 20, 2025.
[44] M. Muzammul, et al. “Enhancing UAV Aerial Image Analysis: Integrating Advanced SAHI Techniques with Real-Time Detection Models on the VisDrone Dataset.” IEEE Access, 1 Jan. 2024, pp. 1–1, https://doi.org/10.1109/access.2024.3363413. Accessed 2 June 2024.
[45] Akyon, Fatih Cagatay, et al. “Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection.” ArXiv:2202.06934 [Cs], 15 Feb. 2022, arxiv.org/abs/2202.06934.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Mohammed F. Rashad, Qutaiba I. Ali
This work is licensed under a Creative Commons Attribution 4.0 International License.
