Implementasi Metode YOLOv9 untuk Mendeteksi Pelanggaran Parkir di Bahu Jalan Perkotaan

Adeste Charisma Lumenvitha Adhi, Christine Dewi

Abstract


Pelanggaran parkir merupakan salah satu faktor utama penyebab kemacetan lalu lintas di kawasan perkotaan. Penelitian ini bertujuan untuk mengembangkan sistem deteksi otomatis pelanggaran parkir berbasis algoritma YOLOv9, khususnya varian YOLOv9C yang mengutamakan efisiensi dan akurasi tinggi dalam pemrosesan real-time. Data pelatihan diperoleh dari frame video pengawasan yang telah dianotasi secara manual menjadi dua kategori: “Melanggar” dan “Tidak Melanggar”. Untuk meningkatkan generalisasi model terhadap kondisi lapangan, dilakukan teknik augmentasi data seperti rotasi, flipping, penyesuaian pencahayaan, dan mosaic augmentation. Model dilatih selama 50 epoch dan dievaluasi menggunakan metrik Confusion Matrix, Precision, Recall, F1-Score, dan Mean Average Precision (mAP). Hasil evaluasi menunjukkan bahwa YOLOv9C mampu mendeteksi pelanggaran dengan precision 0.995 dan mAP 0.822. Namun, ditemukan tantangan pada akurasi kelas minor akibat ketidakseimbangan data. Sistem ini berpotensi untuk diimplementasikan dalam skenario monitoring lalu lintas otomatis dengan dukungan edge computing. Rekomendasi pengembangan lanjutan meliputi integrasi metode segmentasi semantik dan balancing data untuk meningkatkan performa pada lingkungan kompleks.

Keywords


YOLOv9; Deteksi Objek; Pelanggaran Parkir; Pemrosesan Citra; Sistem Otomatis

Full Text:

PDF

References


R. Ramadhan, “EVEKTIVITAS PENERTIBAN PARKIR LIAR KOTA SURABAYA BERDASARKAN PERDA NOMOR 3 TAHUN 2018,” OURT Rev. J. Penelit. Huk. (e-ISSN 2776-1916), vol. 4, no. 06, pp. 20–29, 2024.

N. R. P. Kosudiwandi, “Implementasi Algoritma You Only Look Once (Yolo) Untuk Mendeteksi Pelanggaran Rambu Dilarang Parkir,” Univ. Komput. Indones., 2020, [Online]. Available: http://library.oum.edu.my/repository/725/2/Chapter_1.pdf

T. M. Shorten, C., Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, vol. 6, no. 1, 2019, doi: 10.1186/s40537-019-0197-0.

G. Liang, Q., Yao, R., Zhang, R., Chen, Z., & Wu, “Agent-Based Simulation Evaluation of CBD Tolling: A Case Study from New York City,” Forum Innov. Sustain. Transp. Syst., 2024, doi: 10.1109/FISTS60717.2024.10485607.

Y. H. Jung, J. H., & Eom, “Empirical analysis of congestion spreading in Seoul traffic network,” Phys. Rev. E, vol. 108, no. 5, pp. 1–12, 2023, doi: 10.1103/PhysRevE.108.054312.

S. W. Kwon, Y., Lee, M. J., & Son, “Quantifying Traffic Patterns with Percolation Theory: A Case Study of Seoul Roads,” J. Korean Phys. Soc., pp. 1–8, 2025, doi: 10.1007/s40042-025-01328-3.

S. Bose, “I-ROBOT New AI traffic lights being tested give priority to cyclists over cars in hope to ‘encourage more people to cycle,’” The Irish Sun. Accessed: May 05, 2025. [Online]. Available: https://www.thesun.co.uk/motors/30396037/ai-traffic-lights-stop-cars-cyclists/

F. Jupiter, “Implementasi Algoritma CNN dan YOLO untuk Mendeteksi Jenis Kendaraan pada Jalan Raya,” J. Sist. Inf. dan Telemat. (Telekomunikasi, Multimed. dan Inform., vol. 14, no. 2, 2023, doi: 10.36448/jsit.v14i2.3259.

F. M. Alwafi, “Pengembangan Sistem Deteksi Objek Pada Kendaraan Parkir Liar Menggunakan Metode You Only Look Once dan Optical Flow,” J. (Doctoral Diss. Inst. Teknol. Kalimantan), 2025.

J. V. Diwan, T., Anirudh, G., & Tembhurne, “Object detection using YOLO: challenges, architectural successors, datasets and applications,” Multimed. Tools Appl., vol. 82, no. 6, pp. 9243–9275, 2023.

P. Suarjaya, I. M. B., Wiriasto, G. W., & Paniran, “Deteksi Ketersediaan Lahan Parkir Mobil Menggunakan Yolo V4 Berbasis Website,” Smart Comp Jurnalnya Orang Pint. Komput., vol. 14, no. 105, pp. 218–229, 2025.

Ultralytics, “YOLOv9: A Leap Forward in Object Detection Technology,” Ultralytics YOLO Docs. Accessed: May 06, 2025. [Online]. Available: https://docs.ultralytics.com/models/yolov9/

Y. He, Y., Su, Y., Wang, X., Yu, J., & Luo, “An improved method MSS-YOLOv5 for object detection with balancing speed-accuracy,” Front. Phys., vol. 10, no. January, pp. 1–13, 2023, doi: 10.3389/fphy.2022.1101923.

A. M. Suparwito, H., Prakoso, B. H. G., Kumalasanti, R. A., & Polina, “Real-Time Vehicle Detection and Air Pollution Estimation Using YOLOv9,” J. Sisfokom (Sistem Inf. dan Komputer), vol. 14, no. 1, pp. 23–30, 2025.

G. An, R., Zhang, X., Sun, M., & Wang, “GC-YOLOv9: Innovative smart city traffic monitoring solution,” Alexandria Eng. J., vol. 106, no. June, pp. 277–287, 2024, doi: 10.1016/j.aej.2024.07.004.

I. B. Murat Bakirci, “YOLOv9-Enabled Vehicle Detection for Urban Security and Forensics Applications,” IEEE Xplore, 2024, doi: https://doi.org/10.1109/ISDFS60797.2024.10527304.

H. Y. M. Wang, C. Y., Bochkovskiy, A., & Liao, “YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors,” 2023, doi: 10.1109/cvpr52729.2023.00721.

B. Prasetio and N. Pratiwi, “Deteksi sampah organik dan anorganik menggunakan model yolov8,” vol. 10, no. 1, pp. 494–506, 2025.

P. N. Qu, W., Balki, I., Mendez, M., Valen, J., Levman, J., & Tyrrell, “Assessing and mitigating the effects of class imbalance in machine learning with application to X-ray imaging,” Int. J. Comput. Assist. Radiol. Surg., vol. 15, no. 12, pp. 2041–2048, 2020, doi: 10.1007/s11548-020-02260-6.

R. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” J. Mach. Learn. Res., vol. 15, no. 1, pp. 1929–1958, 2014.

A. B. Bento, J., Paixão, T., & Alvarez, “Performance Evaluation of YOLOv8 , YOLOv9 , YOLOv10 , and YOLOv11 for Stamp Detection in Scanned Documents,” Appl. Sci., vol. 15, no. 6, 2025.

J. Li, Z., Xiang, J., & Duan, “A low illumination target detection method based on a dynamic gradient gain allocation strategy,” Sci. Rep., vol. 14, no. 1, 2024, doi: 10.1038/s41598-024-80265-w.

J. Oh, S., Kwon, Y., & Lee, “Optimizing Real-Time Object Detection in a Multi-Neural Processing Unit System,” Sensors, vol. 25, no. 5, 2025, doi: 10.3390/s25051376.




DOI: https://doi.org/10.29100/jipi.v11i1.7731

Refbacks

  • There are currently no refbacks.


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

JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika)
ISSN 2540-8984
Published by
Prodi Pendidikan Teknologi Informasi
Universitas Bhinneka PGRI

Website :https://jurnal.stkippgritulungagung.ac.id/index.php/jipi/index
Email: jipistkippti@gmail.com

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