Analysis of Optimized Datasets for Basic Image Processing Algorithms
DOI:
https://doi.org/10.5281/zenodo.18213771Keywords:
image processing, dataset, YOLOAbstract
In recent years, rapid advances in artificial intelligence and computer vision have significantly enhanced object detection systems, which are now widely used in fields such as autonomous driving, surveillance, and sports analytics. This study focuses on evaluating and comparing four state-of-the-art object detection architectures (YOLOv11, YOLOv12, Roboflow 3.0, and RF-DETR) to determine their effectiveness in real-time detection of basketball players. A publicly available dataset containing 170 annotated images from basketball game scenarios was obtained from the Roboflow platform. Each model was trained using identical hyperparameter configurations to ensure a fair comparison, and its performance was evaluated using mAP@50, Precision, and Recall metrics. The results demonstrate that RF-DETR achieved the highest overall accuracy (mAP@50 = 91.5%), while YOLOv11 showed the best balance between recall (84.3%) and precision (90.2%), making it ideal for real-time applications. These findings underscore the increasing capability of modern AI models to perform reliable object detection in complex and dynamic environments. As deep learning technologies continue to evolve, such comparative studies provide essential insights for selecting the most efficient architectures for real-world implementations.
References
Audu, A. I., & Ndirmbula, S. M. (2024). Machine learning based real-time detection of ripe and unripe sorghum. Nigerian Journal of Engineering Science and Technology Research, 10(2), 124–137.
Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv. https://doi.org/10.48550/arXiv.2004.10934
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In A. Vedaldi, H. Bischof, T. Brox, & J. M. Frahm (Eds.), Computer Vision – ECCV 2020 (pp. 213–229). Springer. https://doi.org/10.1007/978-3-030-58452-8_13
Chandana, R. K., & Ramachandra, A. C. (2022). Real time object detection system with YOLO and CNN models: A review. arXiv. https://doi.org/10.48550/arXiv.2208.00773
Ciaglia, F., Zuppichini, F. S., Guerrie, P., McQuade, M., & Solawetz, J. (2022). Roboflow 100: A rich, multi-domain object detection benchmark. arXiv. https://doi.org/10.48550/arXiv.2211.13523
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017).
Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115–118. https://doi.org/10.1038/nature21056
Jegham, N., Koh, C. Y., Abdelatti, M., & Hendawi, A. (2024). YOLO evolution: A comprehensive benchmark and architectural review of YOLOv12, YOLO11, and their previous versions. arXiv. https://doi.org/10.48550/arXiv.2411.00201
Khalili, B., & Smyth, A. W. (2024). SOD-YOLOv8—Enhancing YOLOv8 for small object detection in traffic scenes. arXiv. https://doi.org/10.48550/arXiv.2408.04786
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779–788. https://doi.org/10.1109/CVPR.2016.91
Sakib, K. S., Abir, T. I., Kareena, S. S., & Alam, R. (2023). Autonomous object detection dataset: A study on Bangladeshi roadways [Undergraduate thesis, Brac University]. Brac University Repository.
Simic, N., & Gavrovska, A. (2025). Comparative analysis of YOLOv11 and YOLOv12 for AI-powered aerial people detection. 12th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN), 1–4.
Sun, Y., Sun, Z., & Chen, W. (2024). The evolution of object detection methods. Engineering Applications of Artificial Intelligence, 133, 108458. https://doi.org/10.1016/j.engappai.2024.108458
Tao, X., Gong, X., Zhang, X., Yan, S., & Adak, C. (2022). Deep learning for unsupervised anomaly localization in industrial images: A survey. IEEE Transactions on Instrumentation and Measurement, 71, 1–21. https://doi.org/10.1109/TIM.2022.3196436
Trigka, M., & Dritsas, E. (2025). A comprehensive survey of machine learning techniques and models for object detection. Sensors, 25(1), 214. https://doi.org/10.3390/s25010214
Ultralytics. (2024). YOLOv12 official release documentation. https://docs.ultralytics.com (Erişim tarihi: 3 Eylül 2025).
Xiaozheng, Z., Zhongjun, Y., & Huaici, Z. (2025). DCS-YOLOv8: A lightweight context-aware network for small object detection in UAV remote sensing imagery. Remote Sensing, 17(17), 2989. https://doi.org/10.3390/rs17172989
Yigit, G. (2025). Crowd detection: Leveraging YOLO for human recognition. Turkish Journal of Engineering, 9(3), 571–577. https://doi.org/10.31127/tuje.1627839
Zhang, J., Zhang, H., Liu, B., Qu, G., Wang, F., Zhang, H., & Shi, X. (2023). Small object intelligent detection method based on adaptive recursive feature pyramid. Heliyon, 9(7), e17730. https://doi.org/10.1016/j.heliyon.2023.e17730
Zhao, Z. Q., Zheng, P., Xu, S. T., & Wu, X. (2019). Object detection with deep learning: A review. IEEE Transactions on Neural Networks and Learning Systems, 30(11), 3212–3232. https://doi.org/10.1109/TNNLS.2018.2876865
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Black Sea Journal of Artificial Intelligence
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
