SFSORT: Scene Features-based Simple Online Real-Time Tracker
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911836004155392 |
|---|---|
| author | Morsali, M. M. Sharifi, Z. Fallah, F. Hashembeiki, S. Mohammadzade, H. Shouraki, S. Bagheri |
| author_facet | Morsali, M. M. Sharifi, Z. Fallah, F. Hashembeiki, S. Mohammadzade, H. Shouraki, S. Bagheri |
| contents | This paper introduces SFSORT, the world's fastest multi-object tracking system based on experiments conducted on MOT Challenge datasets. To achieve an accurate and computationally efficient tracker, this paper employs a tracking-by-detection method, following the online real-time tracking approach established in prior literature. By introducing a novel cost function called the Bounding Box Similarity Index, this work eliminates the Kalman Filter, leading to reduced computational requirements. Additionally, this paper demonstrates the impact of scene features on enhancing object-track association and improving track post-processing. Using a 2.2 GHz Intel Xeon CPU, the proposed method achieves an HOTA of 61.7\% with a processing speed of 2242 Hz on the MOT17 dataset and an HOTA of 60.9\% with a processing speed of 304 Hz on the MOT20 dataset. The tracker's source code, fine-tuned object detection model, and tutorials are available at \url{https://github.com/gitmehrdad/SFSORT}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_07553 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SFSORT: Scene Features-based Simple Online Real-Time Tracker Morsali, M. M. Sharifi, Z. Fallah, F. Hashembeiki, S. Mohammadzade, H. Shouraki, S. Bagheri Computer Vision and Pattern Recognition This paper introduces SFSORT, the world's fastest multi-object tracking system based on experiments conducted on MOT Challenge datasets. To achieve an accurate and computationally efficient tracker, this paper employs a tracking-by-detection method, following the online real-time tracking approach established in prior literature. By introducing a novel cost function called the Bounding Box Similarity Index, this work eliminates the Kalman Filter, leading to reduced computational requirements. Additionally, this paper demonstrates the impact of scene features on enhancing object-track association and improving track post-processing. Using a 2.2 GHz Intel Xeon CPU, the proposed method achieves an HOTA of 61.7\% with a processing speed of 2242 Hz on the MOT17 dataset and an HOTA of 60.9\% with a processing speed of 304 Hz on the MOT20 dataset. The tracker's source code, fine-tuned object detection model, and tutorials are available at \url{https://github.com/gitmehrdad/SFSORT}. |
| title | SFSORT: Scene Features-based Simple Online Real-Time Tracker |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.07553 |