Deteksi Sampah Otomatis Pada Lingkungan Terbuka Menggunakan YOLOV8 Dan Dataset Roboflow

Dhimas Tribuana; Usman Usman; Dayanti Dayanti

doi:10.64476/jtbc.v1i1.4

Penulis

Dhimas Tribuana Universitas Komputer Indonesia
Usman Usman Politeknik Negeri Bombana
Dayanti Dayanti Universitas Patria Artha

DOI:

https://doi.org/10.64476/jtbc.v1i1.4

Kata Kunci:

deteksi sampah, YOLOv8, visi komputer, smart environment, deteksi objek real-time

Abstrak

Peningkatan volume sampah di ruang publik menuntut solusi cerdas untuk mendeteksi dan mengelola kebersihan secara efisien. Penelitian ini bertujuan untuk mengembangkan sistem deteksi sampah otomatis berbasis model deteksi objek YOLOv8 dengan fokus pada lima kategori sampah: plastik, kertas, logam, kaca, dan lainnya. Dataset diperoleh dari platform Roboflow, kemudian dianotasi secara manual dan digunakan untuk melatih dua varian model YOLOv8, yaitu YOLOv8s dan YOLOv8l. Hasil pelatihan menunjukkan bahwa YOLOv8l mencapai mAP@0.5 sebesar 93,1% dan F1-score 91,1%, sementara YOLOv8s memberikan kecepatan inferensi lebih tinggi dengan akurasi yang kompetitif. Evaluasi lapangan terbatas dilakukan menggunakan kamera laptop dan smartphone di lingkungan terbuka seperti taman dan trotoar. Hasil pengujian menunjukkan bahwa sistem mampu mendeteksi sampah secara real-time dengan tingkat akurasi visual yang baik, meskipun terdapat penurunan performa pada objek kecil atau tertutup sebagian. Studi ini menunjukkan potensi besar model YOLOv8 dalam mendukung pengembangan sistem monitoring lingkungan berbasis visi komputer. Ke depan, integrasi ke perangkat edge dan pelatihan ulang dengan data lokal direkomendasikan untuk meningkatkan ketahanan model dalam kondisi nyata.

Unduhan

Data unduhan belum tersedia.

Referensi

Alfattah Atalarais, Kana Saputra S, Hermawan Syahputra, Said Iskandar Al Idrus, & Insan Taufik. (2025). Automatic Waste Type Detection Using YOLO for Waste Management Efficiency. Journal of Artificial Intelligence and Engineering Applications (JAIEA), 4(2), 883–892. https://doi.org/10.59934/jaiea.v4i2.770

Gamani, A.-R. A., Arhin, I., & Asamoah, A. K. (2024). Performance Evaluation of YOLOv8 Model Configurations, for Instance Segmentation of Strawberry Fruit Development Stages in an Open Field Environment. https://arxiv.org/abs/2408.05661

He, Z., Khanal, S. R., Zhang, X., Karkee, M., & Zhang, Q. (2023). Real-time Strawberry Detection Based on Improved YOLOv5s Architecture for Robotic Harvesting in open-field environment. https://arxiv.org/abs/2308.03998

Jocher, G. (2023). YOLOv8 Docs and Model Architecture. . https://docs.ultralytics.com

Kaza, S., Yao, L. C., Bhada-Tata, P., & Van Woerden, F. (2018). What a Waste 2.0: A Global Snapshot of Solid Waste Management to 2050. World Bank. http://hdl.handle.net/10986/30317

KLHK. (2023). Data Pengelolaan Sampah Nasional 2022. https://sipsn.menlhk.go.id

Li, P., Xu, J., & Liu, S. (2024). Solid Waste Detection Using Enhanced YOLOv8 Lightweight Convolutional Neural Networks. Mathematics, 12(14), 2185. https://doi.org/10.3390/math12142185

Midigudla, R. S., Dichpally, T., Vallabhaneni, U., Wutla, Y., Sundaram, D. M., & Jayachandran, S. (2025). A comparative analysis of deep learning models for waste segregation: YOLOv8, EfficientDet, and Detectron 2. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-025-20647-y

Nafiz, Md. S., Das, S. S., Morol, Md. K., Juabir, A. Al, & Nandi, D. (2023). ConvoWaste: An Automatic Waste Segregation Machine Using Deep Learning. https://arxiv.org/abs/2302.02976

Nayfeh, A., Al-Azani, S., & Samma, H. (2025). A Two-Stage YOLOv8 Approach for Waste Detection and Classification in Cognitive Cities. Transportation Research Procedia, 84, 579–586. https://doi.org/10.1016/j.trpro.2025.03.111

Paudel, P., Shrestha, S., Shrestha, S., Gurung, S., & Adhikari, S. (2024). Automated Waste Sorting with Delta Arm and YOLOv8 Detection. Journal of Artificial Intelligence and Capsule Networks, 6(3), 299–315. https://doi.org/10.36548/jaicn.2024.3.004

ProjectVerba. (2022, September). YOLO Waste Detection Dataset. Roboflow Universe. https://universe.roboflow.com/projectverba/yolo-waste-detection

Recyclable waste. (2024, July). Trash Seperation Dataset. Roboflow Universe.

Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. https://arxiv.org/abs/1506.02640

Terven, J., Córdova-Esparza, D.-M., & Romero-González, J.-A. (2023). A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, 5(4), 1680–1716. https://doi.org/10.3390/make5040083

Ultralytics. (2023). YOLOv8. Ultralytics YOLOv8. https://github.com/ultralytics/ultralytics

Unnithan, A. P., Suresh, A., Pillai, A. S., & Smitha, P. (2025). A Comparative Study on Waste Detection using Satellite Images. International Journal of Engineering Research & Technology (IJERT), 14(3).

Vieri, D., Susanto, R., Purwanto, E. S., & Ario, M. K. (2024). Enhancing Waste Classification with YOLOv8 Models for Efficient and Accurate Sorting. Procedia Computer Science, 245, 889–895. https://doi.org/10.1016/j.procs.2024.10.316

Wang, Z., Zhou, D., Guo, C., & Zhou, R. (2024). Yolo-global: a real-time target detector for mineral particles. Journal of Real-Time Image Processing, 21(3), 85. https://doi.org/10.1007/s11554-024-01468-y

YOLOv8. (2024, February). Waste-Detection Dataset. Roboflow Universe.