Comparative performance analysis of YOLOv8 small and larger for real-time website-based monitoring
Main Article Content
Abstract
River trash pollution in Indonesia demands efficient real-time monitoring solutions. By using deep learning, while YOLOv8 is a promising model for implementation, it is a family of models with each variant differ in accuracy, speed, and computational demand. Among these, YOLOv8s and YOLOv8l come out as potential variants due to the balance between speed, accuracy, and computational demand. Therefore, to address this gap, this study intends to compare the YOLOv8 small (YOLOv8s) and YOLOv8 large (YOLOv8l) variants for real-time, website-based river trash monitoring systems, aiming to identify the optimal balance between accuracy and inference speed for practical real-time deployment. A combined dataset of 66 images, consisting of 86% images from Kaggle’s 2024 dataset and 14% AI-Generated images from Krea AI, was augmented using Roboflow to produce 591 annotated images. Both models were treated equally with the same dataset and method. The evaluation was conducted using Precision, Recall, mAP50, mAP50-95, Inference Speed, and Frame per Second (FPS) speed. Consequently, YOLOv8s exceeded YOLOv8l, achieving approximately 20% higher precision, 30% better detection quality, and 20% higher mAP across IoU threshold, and 150%-340% faster FPS. This finding indicates that YOLOv8s offer better accuracy and speed trade-off for real-time implementation than YOLOv8l. Moreover, successful integration to the website with real-time stream and threshold alert, confirm its feasibility for proactive waste and flood management.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
BRIN, “11.3 Juta Ton Sampah di Indonesia Tidak Terkelola dengan Baik.” 2025.
Databoks Katadata, “Data Sampah Laut di Indonesia 2018--2022.” 2025.
M. Rahman, A. Bakti, and T. Hemansyah, “Communication about Waste Intervention Perspective Study on the Pandawara Community,” J. Dakwah dan Komun., vol. 9, 2024.
L. Salsabila, K. T. Lodan, and E. Khairina, “Public Engagement Impact on Sustainable Waste Management in Indonesia,” JAP, vol. 13, no. 2, pp. 158–178, 2023.
P. Suwarno and N. Nurhayati, “Traditional Views and Attitude Toward Waste and Rivers in Indonesia,” in E3S Web of Conferences, 2021, vol. 317, p. 1002.
S. Zhao, H. Zhou, and H. Yang, “Smart Monitoring Method for Land-Based Sources of Marine Outfalls Based on an Improved YOLOv8 Model,” Water, vol. 16, no. 22, p. 3285, 2024.
Y. R. Marbun, Artiawati, and R. Azaria, “Pro-Environmental Behavior among Urban Millennial Workers,” JEHCP, pp. 214–233, 2025.
G. E. Bautista, P. A. D. Gargar, and R. G. Garcia, “Real-Time Object Detection in Tap Water Utilizing YOLOv8,” in IEEE Eurasia Conference on IoT, Communication and Engineering, 2025.
H. Agustina, H. Herdiansyah, and H. Adinegoro, “Analysis of Waste Management Processes Based on Peer Interaction,” JPPIPA, vol. 9, no. 10, pp. 8963–8973, 2023.
C. et al. Kruse, “Satellite monitoring of terrestrial plastic waste,” PLoS One, vol. 18, no. 1, p. e0278997, 2023.
D. D. Aboyomi and C. Daniel, “A Comparative Analysis of Modern Object Detection Algorithms,” ITEJ, vol. 8, no. 2, pp. 96–106, 2023.
M. L. Ali and Z. Zhang, “The YOLO Framework: A Comprehensive Review,” Computers, vol. 13, no. 12, p. 336, 2024.
N. A. Zailan, M. M. Azizan, K. Hasikin, A. S. M. Khairuddin, and U. Khairuddin, “An automated solid waste detection using the optimized YOLO model,” Front. Public Heal., vol. 10, p. 907280, 2022.
X. et al. Yang, “Detection of River Floating Garbage Based on Improved YOLOv5,” Mathematics, vol. 10, no. 22, p. 4366, 2022.
A.-R. A. Gamani, I. Arhin, and A. K. Asamoah, “Performance Evaluation of YOLOv8 Model Configurations.” 2024.
M. Yaseen, “What is YOLOv8.” 2024.
N. A. Megantara and E. Utami, “Object Detection using YOLOv8: A Systematic Review,” SISTEMASI, vol. 14, no. 3, p. 1186, 2025.
H. B. et al. Abdalla, “The Future of Artificial Intelligence in the Face of Data Scarcity,” Tech Sci. Press, 2025.
K. Man and J. Chahl, “A Review of Synthetic Image Data and Its Use in Computer Vision,” J. Imaging, vol. 8, no. 11, p. 310, 2022.
J. Song, H. Chen, and N. Yokoya, “SyntheWorld: A Large-Scale Synthetic Dataset.” 2023.
N. M. Alahdal, F. Abukhodair, L. H. Meftah, and A. Cherif, “Real-time Object Detection in Autonomous Vehicles with YOLO,” Procedia Comput. Sci., vol. 246, pp. 2792–2801, 2024.
A. Mumuni and F. Mumuni, “Data augmentation: A comprehensive survey of modern approaches,” Array, vol. 16, p. 100258, 2022.
O. G. Ajayi, P. O. Ibrahim, and O. S. Adegboyega, “Effect of Hyperparameter Tuning on YOLOv8,” Appl. Sci., vol. 14, no. 13, p. 5708, 2024.
A. M. Moraes, L. F. Pugliese, R. F. D. Santos, G. B. Vitor, R. A. D. S. Braga, and F. R. D. Silva, “Effectiveness of YOLO Architectures in Tree Detection,” Standards, vol. 5, no. 1, p. 9, 2025.
S. Nokhwal, P. Chilakalapudi, P. Donekal, S. Nokhwal, S. Pahune, and A. Chaudhary, “Accelerating Neural Network Training.” 2023.
J. Di, K. Xi, and Y. Yang, “An enhanced YOLOv8 model for accurate detection of solid floating waste,” Sci. Rep., vol. 15, p. 25015, 2025.
E. Panja, H. Hendry, and C. Dewi, “YOLOv8 Analysis for Vehicle Classification,” SJI, vol. 11, no. 1, pp. 127–138, 2024.
D. Tresnawati, S. Nurhidayanti, and N. Lestari, “Comparison of YOLOv8 Series Performance in Student Facial Expression Detection,” JOIN, vol. 10, no. 1, pp. 93–104, 2025.
Ultralytics, “YOLO Performance Metrics.” 2025.
O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Sci. Rep., vol. 14, p. 6086, 2024.
S. Oh, Y. Kwon, and J. Lee, “Optimizing Real-Time Object Detection in a Multi-Neural Processing Unit System,” Sensors, vol. 25, no. 5, p. 1376, 2025.
W. O. Braganca and I. E. Kho, “Comparative Analysis of Python Microframeworks.” 2023.
T. Kanjanapruthipong, S. Ampawong, U. Thaenkham, K. Tuentam, and D. Watthanakulpanich, “Survival of immature pre-adult Gnathostoma spinigerum in humans,” PLoS One, vol. 17, no. 3, p. e0264766, 2022.
D. Jepisah, “YOLOv12 Model Optimization for Monitoring Occupational Health and Safety,” J. Appl. Data Sci., vol. 6, no. 4, pp. 2666–2681, 2025.