Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 8, Issue 5, 2024

Research on Pothole Detection and Avoidance Unmanned Vehicle System Based on YOLOv8 and Raspberry Pi

Download as PDF

DOI: 10.23977/acss.2024.080517 | Downloads: 39 | Views: 1192

Author(s)

Fang Zeping 1, Wu Na 2, Liu Wenyuan 1

Affiliation(s)

1 School of Automation and Electrical Engineering, Zhongyuan University of Technology, Zhengzhou, China
2 Zhengzhou Railway Vocational and Technical College, Zhengzhou, China

Corresponding Author

Fang Zeping

ABSTRACT

In order to reduce the harm of road potholes to the safe driving of unmanned vehicles, it is necessary to create an efficient and accurate road pothole detection and avoidance strategy. Therefore, this paper proposes a road pothole detection and avoidance unmanned vehicle (PDA-UV) system based on YOLOv8 and Raspberry Pi. The system mainly includes unmanned vehicle, road pothole detection, avoidance motion controller and image sensor. YOLOv8 is used as a road pothole detection algorithm. The motion controller of unmanned vehicle takes Raspberry Pi 4B/4G as the core and four Mecanum wheels as the motion mechanism of unmanned vehicle. Firstly, the system obtains the road pothole image through the camera; Then, the road pothole detection model is obtained after training with YOLOv8 algorithm, and the collected road scenes are tested. Finally, the road pothole detection model is deployed to Raspberry Pi 4B/4G, and the real-time motion control of the unmanned vehicle is carried out according to the identified road pothole results, so as to realize the avoidance function of the unmanned vehicle to the road pothole. In this paper, the experimental results of road potholes detection and avoiding single road potholes are given. The experimental results show that the unmanned vehicle can accurately detect road potholes and realize the avoidance motion control of a single road pothole according to the preset trajectory at low speed.

KEYWORDS

Unmanned vehicle, Road potholes, Detection, Avoid, Raspberry Pi, YOLOv8

CITE THIS PAPER

Fang Zeping, Wu Na, Liu Wenyuan, Research on Pothole Detection and Avoidance Unmanned Vehicle System Based on YOLOv8 and Raspberry Pi. Advances in Computer, Signals and Systems (2024) Vol. 8: 145-156. DOI: http://dx.doi.org/10.23977/acss.2024.080517.

REFERENCES

[1] Raja G, Anbalagan S, Senthilkumar S, Dev K, Qureshi NM. SPAS: Smart pothole-avoidance strategy for autonomous vehicles [J]. IEEE Transactions on Intelligent Transportation Systems. 2022, 23(10):19827-19836.
[2] G. Raja, A. Ganapathisubramaniyan, S. Anbalagan, S. B. M. Baskaran, K. Raja, and A. K. Bashir, Intelligent reward-based data offloading in next-generation vehicular networks [J]. IEEE Internet Things J., 2020, 7(5): 3747–3758.
[3] Ahmed A, Ashfaque M, Ulhaq MU, Mathavan S, Kamal K, Rahman M. Pothole 3D reconstruction with a novel imaging system and structure from motion techniques. IEEE Transactions on Intelligent Transportation Systems. 2021, 23(5): 4685-4694.
[4] Fan R, Ozgunalp U, Wang Y, Liu M, Pitas I. Rethinking road surface 3-d reconstruction and pothole detection: From perspective transformation to disparity map segmentation. IEEE Transactions on Cybernetics. 2021, 52(7):5799-5808.
[5] S. Shah and C. Deshmukh, Pothole and bump detection using convolution neural networks[C]. In Proc. IEEE Transp. Electrific. Conf. (ITEC India), 2019(10): 1–4. 
[6] A. Kumar, D. J. Kalita, and V. P. Singh, A modern pothole detection technique using deep learning[C]. In Proc. 2nd Int. Conf. Data, Eng. Appl. (IDEA), 2020(2): 1–5.
[7] M. M. Garcillanosa, J. M. L. Pacheco, R. E. Reyes, and J. J. P. San Juan, Smart detection and reporting of potholes via image-processing using Raspberry-pi microcontroller[C]. In Proc. 10th Int. Conf. Knowl. Smart Technol. (KST), 2018(1): 191–195. 
[8] K. S. Ashwini, G. Bhagwat, T. Sharma, and P. S. Pagala, Triggerbased pothole detection using smartphone and OBD-II[C]. In Proc. IEEE Int. Conf. Electron., Comput. Commun. Technol. (CONECCT), 2020(7): 1–6.
[9] D. R. Reddy, G. P. C. Goud, and C. D. Naidu, Internet of Things based pothole detection system using Kinect sensor[C]. In Proc. 3rd Int. Conf., 2019(10): 232–236. 
[10] A. Vora, L. Reznik, and I. Khokhlov, Mobile road pothole classification and reporting with data quality estimates[C]. In Proc. 4th Int. Conf. Mobile Secure Services (MobiSecServ), 2018(2): 1–6. 
[11] A. Ahmed, S. Islam, and A. Chakrabarty, Identification and comparative analysis of potholes using image processing techniques[C]. In Proc. IEEE Region 10 Symp. (TENSYMP), 2019(6): 497–502. 
[12] Y. Li, C. Papachristou, and D. Weyer, Road pothole detection system based on stereo vision[C]. In Proc. IEEE Nat. Aerosp. Electron. Conf., 2018(6): 292–297. 
[13] A. Dhiman and R. Klette, Pothole detection using computer vision and learning [J]. IEEE Trans Intell. Transp. Syst., 2020, 21(8): 3536–3550.
[14] Kumari S, Gautam A, Basak S, et al. YOLOv8 based deep learning method for potholes detection[C]. 2023 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI). 2023.10465038.
[15] Luo Y, Ci Y, Jiang S, Wei X. A novel lightweight real-time traffic sign detection method based on an embedded device and YOLOv8 [J]. Journal of Real-Time Image Processing. 2024, 21(2):24.
[16] Si Wenzhan.Structural design and motion control system research of intelligent omnidirectional mobile platform [D].Jiangsu Ocean University, 2022.
[17] Q. Wang, S. Wang and H. Ni, Design of an odor search robot system based on open sampling system[C]. 2021 33rd Chinese Control and Decision Conference (CCDC), Kunming, China, 2021, 3383-3388.
[18] Li Sensen, Zhu Shiwei, Shi Liyu, et al. Automatic humidity control device based on RPi [J]. Electronic world, 2020: 91-93.  
[19] Zhao M, Su Y, Wang J, Liu X, Wang K, Liu Z, Liu M, Guo Z. MED-YOLOv8s: a new real-time road crack, pothole, and patch detection model [J]. Journal of Real-Time Image Processing. 2024, 21(2):26.
[20] Arya, D., Maeda, H., Ghosh, S.K., et al. Crowdsensing-based road damage detection challenge[C]. (CRDDC’2022). In: Proceedings of the 2022 IEEE International Conference on Big Data (Big Data), 2022.
[21] Kuan CW, Chen WH, Lin YC. Pothole detection and avoidance via deep learning on edge devices[C]. In 2020 international automatic control conference (CACS) 2020(10): 1-6.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 38553
Visits: 697916

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.