Computer vision for wildfire research: An evolving image dataset for processing and analysis |
| |
| Affiliation: | 1. UMR CNRS 6134 SPE, University of Corsica, 20250, Corte, France;2. School of Computer Science, University of the Witwatersrand, Johannesburg, South Africa;3. Computer Science Department, University of Moncton, Moncton, NB, Canada;1. Laboratoire Central de la Préfecture de Police, 39 bis rue de Dantzig, 75015 Paris, France;2. Chairman of ISO TC 92 WG 13 “Fire Safety - Statistical data collection”, 5 route d''Évrecy, 14210 Amayé-sur-Orne, France;1. Inha University, Incheon, Republic of Korea;2. Sejong University, Seoul, Republic of Korea |
| |
| Abstract: | The last decade has witnessed the use of computer vision for wildfire detection and measurement. The first and most important step for computer vision analysis is the fire pixel detection because it determines the accuracy of the following processing. The evaluation and the comparison of the wildfire detection algorithms of the literature and the development of new ones needs open datasets with a large number of annotated images and their ground truth. We address this issue by presenting a publicly evolving wildfire annotated image database with ground truth data with examples of use. Currently, it contains 500 visible images and, in a more limited number, multimodal images and videos with frame by frame annotations. This is currently the largest dataset released in this research field. |
| |
| Keywords: | Database Image Wildfire Pixel detection |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
