Climatic changes, which are increasingly responsible for the increase in the incidence and intensity of natural calamities, demand prompt and precise response and recovery actions. This research aims at determining how AI computer vision methodologies can be applied to aerial and satellite images related to a disastrous management system. We study different AI techniques that can be used in damage assessment, resource allocation, and recovery planning. This paper reviews data sources starting with aerial imagery from drones, to aircraft and satellite imagery, and encompasses all the diversity in sensors and resolutions. Key AI techniques brought into discussion include CNNs, semantic segmentation, and logistics optimization models. Key challenges identified are data quality, model generalization, and ethics. Applications in real-world settings are illustrated through case studies including rapid damage assessment following hurricane Maria, monitoring the Australian bushfires, and optimization of resources allocation during the COVID-19 pandemic. The survey outlines proposed future research directions with an emphasis on real-time analysis, integration of IoT and edge computing, improvement of model interpretability, and collaborative platforms. Surveying creates demands for continuous innovation and collaboration and underlines improvement for enhanced disaster preparedness and resilience.