YOLO modelleriyle Tek Nesne Lasot Verisetinde Geniş Ölçekli Çapraz Nesne Tanıma Uygulamaları

Öz

Bu çalışmada, LaSOT veri kümesi ile tekli nesne tespitinde en son YOLO modellerini, YOLOv8X, YOLOv9e, YOLOv10X, YOLO11X ve YOLO12X modelleri incelenmektedir. YOLO, nesne tespitinde büyük bir çığır açmıştır ve gerçek zamanlı uygulamalarda yüksek performans ile doğruluk arasındaki boşluğu doldurmaktadır. YOLO, doğruluğu makul bir hızla korumaya çalışır; bu da onu gerçek zamanlı nesne tanıma uygulamaları için oldukça uygun hale getirir. Bu çalışma, en son YOLO modellerini, tekli nesne içeren LaSOT veri kümesi üzerindeki çok büyük ölçekli bir nesne tespiti görevinde doğruluk ve hız açısından değerlendirmektedir. Çalışmada kullanılan tüm YOLO modelleri, COCO veri kümesi üzerinde önceden eğitilmiş ve LaSOT veri kümesi üzerinde değerlendirilmiştir. COCO ve LaSOT veri kümeleri, 1,5 milyondan fazla görüntü örneğini barındıran 30 ortak sınıfa sahiptir. Modellerin bir veri kümesinde eğitilip başka bir veri kümesinde test edildiği çapraz-veriseti deneyleri, makine öğrenimi modellerinin genellenebilirliği ve bütünlüğü için oldukça çetin zorluklar teşkil eder ve nihai bir test niteliğindedir. Deney sonuçları, YOLOv9e'nin 0.3859 mAP@0.5 ve 0.6490 duyarlılık (recall) değerleri ile doğruluk metrikleri açısından en iyi model olduğunu, buna karşın YOLOv10X'in 201.18 fps ile en hızlı YOLO modeli olduğunu göstermektedir.

Anahtar Kelimeler

• Nesne Tanıma
• YOLO
• Derin Öğrenme
• TensorRT
• LaSOT

VERY LARGE SCALE CROSS CORPUS OBJECT DETECTION APPLICATIONS WITH THE LATEST YOLO MODELS ON SINGLE OBJECT LASOT DATASET

Öz

In this study, we explore the latest YOLO models, namely, YOLOv8X, YOLOv9e, YOLOv10X, YOLO11X, and YOLO12X in the single object detection task with LaSOT dataset. YOLO is a great breakthrough in object detection and fills in the gap between high performance and accuracy in real time applications. YOLO tries to maintain accuracy with a reasonable speed which makes it very suitable for real time object recognition applications. This study evaluates the latest YOLO models in terms of accuracy and speed in a very large-scale object detection task on the single object LaSOT dataset. All YOLO models used in this study are pretrained on the COCO dataset and evaluated on the LaSOT dataset. COCO and LaSOT datasets have 30 common classes which include more than 1.5 million image samples. Cross corpus experiments are very formidable challenges and ultimate test for the generalizability and integrity of machine learning models where the models are trained in a dataset and tested in another dataset. Results of the experiments show that YOLOv9e is the best model in terms of accuracy metrics by 0.3859 mAP@0.5 and 0.6490 recall, however, YOLOv10X is the fastest YOLO model with 201.18 fps.

Anahtar Kelimeler

• Object detection
• YOLO
• Deep Learning
• TensorRT
• LaSOT

Kaynakça

1. Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
2. Çınarer, G. (2022). Deep learning based traffic sign recognition using yolo algorithm. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 12(1), 219-229.
3. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 248–255). IEEE.
4. Emara, M., Abushawareb, Y., & Şehirli, E. (2025). Detection of Small and Medium Sized Ships in Satellite Images Using YOLO Models. Current Trends in Computing, 3(1), 17-27.
5. Fan, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Bai, H., Xu, Y., Liao, C., Ling, H., & others. (2019). LaSOT: A high-quality benchmark for large-scale single object tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 5374–5383).
6. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 580–587). IEEE.
7. Girshick, R. (2015). Fast R-CNN. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 1440–1448). IEEE.
8. Jocher, G., Chaurasia, A., & Qiu, J. (2023). Ultralytics YOLO (Version 8.0.0) [Computer software]. https://github.com/ultralytics/ultralytics

9. Jocher, G., Chaurasia, A., & Qiu, J. (2024). Ultralytics YOLO (Version 11.0.0) [Computer software]. https://github.com/ultralytics/ultralytics
10. Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Duerig, T., & Ferrari, V. (2018). The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale. arXiv preprint arXiv:1811.00982.
11. Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., … Chu, X. (2022). YOLOv6: A single-stage object detection framework for industrial applications. arXiv. https://doi.org/10.48550/arXiv.2209.02976
12. Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014). Microsoft COCO: Common objects in context. In European Conference on Computer Vision (ECCV) (pp. 740–755). Springer. https://doi.org/10.1007/978-3-319-10602-1_48
13. Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision (pp. 2980-2988).
14. Liu, S., Qi, L., Qin, H., Shi, J., & Jia, J. (2018). Path aggregation network for instance segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 8759–8768).
15. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016). SSD: Single Shot MultiBox Detector. In B. Leibe, J. Matas, N. Sebe, & M. Welling (Eds.), European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science (Vol. 9905, pp. 21–37). Springer. https://doi.org/10.1007/978-3-319-46448-0_2
16. Nergiz, M. (2023). Enhancing strawberry harvesting efficiency through Yolo-v7 object detection assessment. Turkish Journal of Science and Technology, 18(2), 519-533.
17. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 779–788). IEEE.
18. Redmon, J., & Farhadi, A. (2017). YOLO9000: Better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 7263–7271). IEEE.
19. Redmon, J., & Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv preprint arXiv:1804.02767.
20. Ren, S., He, K., Girshick, R., & Sun, J. (2016). Faster R-CNN: Towards real-time object detection with region proposal networks. In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 39(6), 1137–1149.
21. Serttaş, E., & Gül, F. (2025). YOLO V8 Algoritması ile Otomatik Plaka Tanıma ve Görselleştirme Sistemi. Bilişim Teknolojileri Dergisi, 18(1), 1-10.
22. Tian, Y., Ye, Q., & Doermann, D. (2025). YOLOv12: Attention-Centric Real-Time Object Detectors. arXiv. https://doi.org/10.48550/arXiv.2502.12524 arXiv
23. Ultralytics. (2020). Ultralytics YOLOv5 (Version 7.0) [Software]. Zenodo. https://doi.org/10.5281/zenodo.3908559
24. Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv. http://arxiv.org/abs/2207.02696
25. Wang, C.-Y., Yeh, I.-H., & Liao, H.-Y. M. (2024). YOLOv9: Learning what you want to learn using programmable gradient information. arXiv. https://arxiv.org/abs/2402.13616
26. Wang, A., Chen, L., Hu, L., & Zhang, Y. (2024). YOLOv10: Real-Time End-to-End Object Detection. arXiv. https://arxiv.org/abs/2405.14458
27. Wang, C.-Y., Liao, H.-Y. M., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., & Yeh, I.-H. (2020). CSPNet: A new backbone that can enhance learning capability of CNN. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 390–391).
28. Yiğit, G. (2025). Crowd Detection: Leveraging YOLO for Human Recognition. Turkish Journal of Engineering, 9(3), 571-577.