The Effect of Image Enhancement on Automatic Vehicle Detection Using Yolov8 Based on Jetson Nano Single Board Computer

Rakhmad Gusta Putra(1*), Wahyu Pribadi(2), Dirvi Eko Juliando Sudirman(3),

(1) State Polytechnic of Madiun
(2) State Polytechnic of Madiun
(3) State Polytechnic of Madiun
(*) Corresponding Author

Abstract


Vehicle counting systems using image processing and deep learning have been widely studied. Using images captured by CCTV cameras makes vehicle counting effective and efficient. Although much research has been done, there are still challenges in direct application in the field. Object detection methods such as YOLO are widely chosen. In field applications, challenges are found such as rainy, nighttime, or foggy conditions and the use of appropriate hardware. In this study, the YOLOv8s and YOLOv8n object detection methods are proposed using contrast-limited Adaptive Histogram Equalization (CLAHE) image enhancement in preprocessing and datasets and run using SBC Jetson Nano. From this study, the results obtained an increase in detection values of around 10% to 20% in dark image conditions and there was no improvement for bright images. The average accuracy is 0.873312 for YOLOv8s and 0.866906 for YOLOv8n with image enhancement. And the processing time on Jetson Nano is 59.5 ms for YOLOv8n.

Full Text:

PDF

References


[1] A. Stanley and R. Munir, “Vehicle Traffic Volume Counting in CCTV Video with YOLO Algorithm and Road HSV Color Model-based Segmentation System Development,” in 2021 15th International Conference on Telecommunication Systems, Services, and Applications (TSSA), 2021, pp. 1–5, doi: 10.1109/TSSA52866.2021.9768231.

[2] C.-J. Lin, S.-Y. Jeng, and H.-W. Lioa, “A Real-Time Vehicle Counting, Speed Estimation, and Classification System Based on Virtual Detection Zone and YOLO,” Math. Probl. Eng., vol. 2021, pp. 1–10, Nov. 2021, doi: 10.1155/2021/1577614.

[3] M. Majumder and C. Wilmot, “Automated Vehicle Counting from Pre-Recorded Video Using You Only Look Once (YOLO) Object Detection Model,” J. Imaging, vol. 9, no. 7, p. 131, Jun. 2023, doi: 10.3390/jimaging9070131.

[4] T.-N. Doan and M.-T. Truong, “Real-time vehicle detection and counting based on YOLO and DeepSORT,” in 2020 12th International Conference on Knowledge and Systems Engineering (KSE), 2020, pp. 67–72, doi: 10.1109/KSE50997.2020.9287483.

[5] Q. Chen, N. Huang, J. Zhou, and Z. Tan, “An SSD Algorithm Based on Vehicle Counting Method,” in 2018 37th Chinese Control Conference (CCC), 2018, pp. 7673–7677, doi: 10.23919/ChiCC.2018.8483037.

[6] Z. Al-Ariny, M. A. Abdelwahab, M. Fakhry, and E.-S. Hasaneen, “An Efficient Vehicle Counting Method Using Mask R-CNN,” in 2020 International Conference on Innovative Trends in Communication and Computer Engineering (ITCE), 2020, pp. 232–237, doi: 10.1109/ITCE48509.2020.9047800.

[7] L. Yao, “An Effective Vehicle Counting Approach Based on CNN,” in 2019 IEEE 2nd International Conference on Electronics and Communication Engineering (ICECE), 2019, pp. 15–19, doi: 10.1109/ICECE48499.2019.9058582.

[8] R. G. Putra, W. Pribadi, I. Yuwono, D. E. J. Sudirman, and B. Winarno, “Adaptive Traffic Light Controller Based on Congestion Detection Using Computer Vision,” in Journal of Physics: Conference Series, 2021, doi: 10.1088/1742-6596/1845/1/012047.

[9] “Design of Automatic Truck Axle Counter Using Deep Learning on NVIDIA Jetson Nano,” J. Smart Sci. Technol., vol. 3, no. 2, pp. 65–73, Sep. 2023, doi: 10.24191/jsst.v3i2.35.

[10] R.-C. Chen, C. Dewi, Y.-C. Zhuang, and J.-K. Chen, “Contrast Limited Adaptive Histogram Equalization for Recognizing Road Marking at Night Based on Yolo Models,” IEEE Access, vol. 11, pp. 92926–92942, 2023, doi: 10.1109/ACCESS.2023.3309410.

[11] D. E. J. Putra, Rakhmad Gusta ; Pribadi , Wahyu; Sudirman, “Sistem Penghitung dan Pengklasifikasi Jenis Kendaraan secara Real Time Menggunakan Pengolahan Citra pada Komputer Papan Tunggal Nvidia Jetson Nano,” JEECAE (Journal Electr. Electron. Control. Automot. Eng., vol. 7, no. 2, pp. 6–10, 2022.

[12] M. Hassaballah, M. A. Kenk, K. Muhammad, and S. Minaee, “Vehicle Detection and Tracking in Adverse Weather Using a Deep Learning Framework,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 7, pp. 4230–4242, Jul. 2021, doi: 10.1109/TITS.2020.3014013.

[13] A. Mishra, “Contrast Limited Adaptive Histogram Equalization (CLAHE) Approach for Enhancement of the Microstructures of Friction Stir Welded Joints,” Aug. 2021.




DOI: https://doi.org/10.24071/ijasst.v7i2.11640

Refbacks

  • There are currently no refbacks.









Publisher : Faculty of Science and Technology

Society/Institution : Sanata Dharma University

 

 

 

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