Autonomous Unmanned Aerial Vehicle (UAV) technology is able to serve physical disaster recovery needs in Smart Cities (SC). Such critical situations require instant treatment to avoid scaling of the disaster in the whole area of a city. In case of a physical disaster such as a fire in the SC infrastructure is possible to lead to a high coverage area damage. Fire expansion may produce serious problems in disaster recovery and should be treated accordingly by certain municipality fightfighters which are dedicated to extinguish such fires. However, firefighters, vehicles, and UAVs that are available to treat a fire in the city are limited and cannot serve all the areas simultaneously thus transforming the upcoming situation to a resource allocation problem. In this paper, to handle such a problem there is not a need to serve each incident with the same priority since there are cases of low, medium, or high significance. Specifically, SC infrastructure has a limited number of UAVs to heal certain fire cases. On a trigger occurrence, such as a phone call from a fire section area, the nearest UAV reaches a certain fire incident where the assigned personnel at the SC control center assess the severity of the problem based on the video and audio provided by the camera and the microphone embedded in the UAV. Dedicated personnel then evaluate if it is a high significance fire incident and a vehicle with assigned firefighters is invoked to reach and fix the problem in real time.