Research Article
BibTex RIS Cite

A Comparative Assessment on the Novel Long-Term Real-Time Single Object Tracking Techniques Using Yolo-Nas and YOLO11

Year 2025, Volume: 8 Issue: 2, 17 - 18
https://doi.org/10.34248/bsengineering.1596008

Abstract

Bu çalışma, YOLO-NAS ve YOLO11 nesne dedektörleriyle en son teknoloji BoT-SORT, DeepSORT, SORT ve ByteTrack izleme algoritmalarını kullanarak tek nesne izlemenin zorlu görevine ışık tutuyor. Nesne izleme, nesne algılamanın bir adım ilerisidir ve video dosyalarındaki nesnelerin hareketini algılamaya çalışır ve çok çeşitli gerçek dünya uygulama alanlarına sahiptir. Nesne izleme ayrıca izlenen her nesneye benzersiz tanımlayıcılar atar ve tüm dizi boyunca kimliği korumaya çalışır. Mevcut modeller nesne izlemede büyük başarılar elde edebilir, ancak önümüzde çözülmesi gereken çok fazla engel ve zorluk vardır. YOLONAS ve YOLO11 en son ve en çok kullanılan nesne algılama modelleridir. YOLO, nesne takibi için ByteTrack, BoT-SORT, SORT ve DeepSORT gibi farklı izleme yöntemleriyle birleştirilebilir. YOLO'nun avantajı, diğer yöntemlere kıyasla son derece hızlı uygulanmasıdır. Özelleştirilmiş izleme algoritmalarıyla birlikte kullanıldığında, YOLO nesne takibinde en iyi puanları elde eder. Bu çalışma, YOLO-NAS ve YOLO11'in izlemede uygulanmasına odaklanmıştır ve sonuçlar, YOLO11'in ByteTrack izleme yöntemini kullanarak daha iyi ve daha hızlı performans gösterdiğini göstermektedir.

References

  • Aharon N, Orfaig R, Bobrovsky BZ. 2022. BoT-SORT: Robust associations multi-pedestrian tracking. arXiv, 2206: 14651.
  • Aharon S, Dupont L, Masad O, Yurkova K, Fridman L, Lkdci, Khvedchenya E, Rubin R, Bagrov N, Tymchenko B, Keren T, Zhilko A, Deci E. 2021. Supergradients. Github Repository, URL: https://github.com/Deci-AI/super-gradients (accessed date: December 4, 2024).

A Comparative Assessment on the Novel Long-Term Real-Time Single Object Tracking Techniques Using Yolo-Nas and YOLO11

Year 2025, Volume: 8 Issue: 2, 17 - 18
https://doi.org/10.34248/bsengineering.1596008

Abstract

This 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 is still too many obstacles and challenges lying ahead to resolve. YOLONAS 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 performs better and faster using ByteTrack tracking method.

References

  • Aharon N, Orfaig R, Bobrovsky BZ. 2022. BoT-SORT: Robust associations multi-pedestrian tracking. arXiv, 2206: 14651.
  • Aharon S, Dupont L, Masad O, Yurkova K, Fridman L, Lkdci, Khvedchenya E, Rubin R, Bagrov N, Tymchenko B, Keren T, Zhilko A, Deci E. 2021. Supergradients. Github Repository, URL: https://github.com/Deci-AI/super-gradients (accessed date: December 4, 2024).
There are 2 citations in total.

Details

Primary Language English
Subjects Information Systems (Other)
Journal Section Research Articles
Authors

Cevahir Parlak 0000-0002-5500-7379

Publication Date
Submission Date December 4, 2024
Acceptance Date January 17, 2025
Published in Issue Year 2025 Volume: 8 Issue: 2

Cite

APA Parlak, C. (n.d.). A Comparative Assessment on the Novel Long-Term Real-Time Single Object Tracking Techniques Using Yolo-Nas and YOLO11. Black Sea Journal of Engineering and Science, 8(2), 17-18. https://doi.org/10.34248/bsengineering.1596008
AMA Parlak C. A Comparative Assessment on the Novel Long-Term Real-Time Single Object Tracking Techniques Using Yolo-Nas and YOLO11. BSJ Eng. Sci. 8(2):17-18. doi:10.34248/bsengineering.1596008
Chicago Parlak, Cevahir. “A Comparative Assessment on the Novel Long-Term Real-Time Single Object Tracking Techniques Using Yolo-Nas and YOLO11”. Black Sea Journal of Engineering and Science 8, no. 2 n.d.: 17-18. https://doi.org/10.34248/bsengineering.1596008.
EndNote Parlak C A Comparative Assessment on the Novel Long-Term Real-Time Single Object Tracking Techniques Using Yolo-Nas and YOLO11. Black Sea Journal of Engineering and Science 8 2 17–18.
IEEE C. Parlak, “A Comparative Assessment on the Novel Long-Term Real-Time Single Object Tracking Techniques Using Yolo-Nas and YOLO11”, BSJ Eng. Sci., vol. 8, no. 2, pp. 17–18, doi: 10.34248/bsengineering.1596008.
ISNAD Parlak, Cevahir. “A Comparative Assessment on the Novel Long-Term Real-Time Single Object Tracking Techniques Using Yolo-Nas and YOLO11”. Black Sea Journal of Engineering and Science 8/2 (n.d.), 17-18. https://doi.org/10.34248/bsengineering.1596008.
JAMA Parlak C. A Comparative Assessment on the Novel Long-Term Real-Time Single Object Tracking Techniques Using Yolo-Nas and YOLO11. BSJ Eng. Sci.;8:17–18.
MLA Parlak, Cevahir. “A Comparative Assessment on the Novel Long-Term Real-Time Single Object Tracking Techniques Using Yolo-Nas and YOLO11”. Black Sea Journal of Engineering and Science, vol. 8, no. 2, pp. 17-18, doi:10.34248/bsengineering.1596008.
Vancouver Parlak C. A Comparative Assessment on the Novel Long-Term Real-Time Single Object Tracking Techniques Using Yolo-Nas and YOLO11. BSJ Eng. Sci. 8(2):17-8.

                                                24890