TR-Dizin İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.14627/9
Browse
2 results
Search Results
Article Evaluation of Cutting-Edge Object Detection Architectures on Multi-Object and Single-Object Datasets(2026) Parlak, CevahirThis study focuses on the performance evaluation of cutting-edge object detection models, namely, YOLO12X, Mask R-CNN, RT-DETR-X, and RF-DETR-Large on the Open Images (Multi-Object) and LaSOT (Single-Object) datasets. Current cutting-edge trend applications involve CNN-based and Transformer-based object detection models. CNN-based models can use one-pass (YOLO family) or two-pass (R-CNN family) implementations. One-pass object detection models can be faster but suffer from accuracy compared to the two-pass models. Transformer-based models can use Detection Transformers or Vision Transformers. Transformer-based models are gaining popularity, and their performance surpasses CNN-based models. This study evaluates YOLO12X, Mask R-CNN from CNN-based family, and RT-DETR-X, RF-DETR-Large transformer-based architectures in terms of accuracy and time on the Open Images and the LaSOT datasets. All models are the largest available models and pretrained on COCO dataset. Transformer-based models incorporate special types of self-attention and pose significant improvement both on accuracy and speed. The experimental results demonstrate that attention and transformer-based models perform better than the traditional CNN-based object detectors and YOLO12X is the fastest method with a far margin. On the LaSOT dataset, RT-DETR-X posts 0.8804 IoU, 0.7047 F1-score, 0.6597 mAP@0.5, 28.64 fps whereas YOLO12X achieves 0.8572 IoU, 0.6657 F1-score, 0.5357 mAP@0.5, and 49.78 fps.Article A Comparative Assessment on the Novel Long-Term Real-Time Single Object Tracking Techniques Using YOLO-NAS and YOLO11(2025) Parlak, CevahirThis study sheds light on the daunting task of single-object tracking using state-of-the-art BoT-SORT, DeepSORT, SORT, and ByteTrack tracking algorithms with YOLO-NAS and YOLO11 object detectors. Object tracking is a step further of object detection and tries to detect the movement of objects in video files and it has enormous range of real-world application fields. Object tracking also assigns unique identifiers to each tracked object and tries to maintain the identity throughout the entire sequence. Current models can achieve great success in object tracking, however there are still too many obstacles and challenges lying ahead to resolve. YOLO-NAS and YOLO11 are the latest and most used object detection models. YOLO can be combined with different tracking methods such as ByteTrack, BoT-SORT, SORT, and DeepSORT for object tracking. The advantage of YOLO is its extremely fast implementation compared to the other methods. When accompanied by specialized tracking algorithms, YOLO achieves the best scores in object tracking. This study focuses on the implementation of YOLO-NAS and YOLO11 in tracking and results demonstrate that YOLO11 is more accurate and stable with BoT-SORT, however, it is faster using ByteTrack method.