LWIRPOSE: A novel LWIR Thermal Image Dataset and Benchmark
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_ | 1866917641242804224 |
|---|---|
| author | Upadhyay, Avinash Dhupar, Bhipanshu Sharma, Manoj Shukla, Ankit Abraham, Ajith |
| author_facet | Upadhyay, Avinash Dhupar, Bhipanshu Sharma, Manoj Shukla, Ankit Abraham, Ajith |
| contents | Human pose estimation faces hurdles in real-world applications due to factors like lighting changes, occlusions, and cluttered environments. We introduce a unique RGB-Thermal Nearly Paired and Annotated 2D Pose Dataset, comprising over 2,400 high-quality LWIR (thermal) images. Each image is meticulously annotated with 2D human poses, offering a valuable resource for researchers and practitioners. This dataset, captured from seven actors performing diverse everyday activities like sitting, eating, and walking, facilitates pose estimation on occlusion and other challenging scenarios. We benchmark state-of-the-art pose estimation methods on the dataset to showcase its potential, establishing a strong baseline for future research. Our results demonstrate the dataset's effectiveness in promoting advancements in pose estimation for various applications, including surveillance, healthcare, and sports analytics. The dataset and code are available at https://github.com/avinres/LWIRPOSE |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_10212 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LWIRPOSE: A novel LWIR Thermal Image Dataset and Benchmark Upadhyay, Avinash Dhupar, Bhipanshu Sharma, Manoj Shukla, Ankit Abraham, Ajith Computer Vision and Pattern Recognition Human pose estimation faces hurdles in real-world applications due to factors like lighting changes, occlusions, and cluttered environments. We introduce a unique RGB-Thermal Nearly Paired and Annotated 2D Pose Dataset, comprising over 2,400 high-quality LWIR (thermal) images. Each image is meticulously annotated with 2D human poses, offering a valuable resource for researchers and practitioners. This dataset, captured from seven actors performing diverse everyday activities like sitting, eating, and walking, facilitates pose estimation on occlusion and other challenging scenarios. We benchmark state-of-the-art pose estimation methods on the dataset to showcase its potential, establishing a strong baseline for future research. Our results demonstrate the dataset's effectiveness in promoting advancements in pose estimation for various applications, including surveillance, healthcare, and sports analytics. The dataset and code are available at https://github.com/avinres/LWIRPOSE |
| title | LWIRPOSE: A novel LWIR Thermal Image Dataset and Benchmark |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.10212 |