Image Prior and Posterior Conditional Probability Representation for Efficient Damage Assessment
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908478155522048 |
|---|---|
| author | Wei, Jie Feng, Weicong Blasch, Erik Ardiles-Cruz, Erika Ling, Haibin |
| author_facet | Wei, Jie Feng, Weicong Blasch, Erik Ardiles-Cruz, Erika Ling, Haibin |
| contents | It is important to quantify Damage Assessment (DA) for Human Assistance and Disaster Response (HADR) applications. In this paper, to achieve efficient and scalable DA in HADR, an image prior and posterior conditional probability (IP2CP) is developed as an effective computational imaging representation. Equipped with the IP2CP representation, the matching pre- and post-disaster images are effectively encoded into one image that is then processed using deep learning approaches to determine the damage levels. Two scenarios of crucial importance for the practical use of DA in HADR applications are examined: pixel-wise semantic segmentation and patch-based contrastive learning-based global damage classification. Results achieved by IP2CP in both scenarios demonstrate promising performances, showing that our IP2CP-based methods within the deep learning framework can effectively achieve data and computational efficiency, which is of utmost importance for the DA in HADR applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_17801 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Image Prior and Posterior Conditional Probability Representation for Efficient Damage Assessment Wei, Jie Feng, Weicong Blasch, Erik Ardiles-Cruz, Erika Ling, Haibin Computer Vision and Pattern Recognition I.4.6, I.5.3 It is important to quantify Damage Assessment (DA) for Human Assistance and Disaster Response (HADR) applications. In this paper, to achieve efficient and scalable DA in HADR, an image prior and posterior conditional probability (IP2CP) is developed as an effective computational imaging representation. Equipped with the IP2CP representation, the matching pre- and post-disaster images are effectively encoded into one image that is then processed using deep learning approaches to determine the damage levels. Two scenarios of crucial importance for the practical use of DA in HADR applications are examined: pixel-wise semantic segmentation and patch-based contrastive learning-based global damage classification. Results achieved by IP2CP in both scenarios demonstrate promising performances, showing that our IP2CP-based methods within the deep learning framework can effectively achieve data and computational efficiency, which is of utmost importance for the DA in HADR applications. |
| title | Image Prior and Posterior Conditional Probability Representation for Efficient Damage Assessment |
| topic | Computer Vision and Pattern Recognition I.4.6, I.5.3 |
| url | https://arxiv.org/abs/2310.17801 |