Search and Rescue Base of Operation Prioritization with Aerial Orthomosaics

Alyssa Hargis, Ananya Rao, Howie Choset

Abstract: Efficiently and accurately determining the location of bases of operations (BOOs) is essential for maximizing the effectiveness of response teams in emergency situations. A BOO is a location from which assets are deployed and, in many cases, resources are used for some centralized purpose. Identifying where BOOs should be located can be quite challenging as many factors, such as travel time, size, and proximity to the disaster, must be taken into consideration. We present an algorithm to automatically determine BOO locations. Through image segmentation of aerial orthomosaics, potential BOOs can be identified and subsequently evaluated, identifying prioritized locations for operators to initialize robot or human operations for rescue. We annotated a dataset for image segmentation of disaster sites and trained a custom model to create annotated maps for use by operators. Using annotated maps, we developed an algorithm to prioritize BOOs based on factors gathered from operators. Our methodology was experimentally evaluated for BOO selection from previous disaster scenarios and evaluated by users for utility and accuracy. The result is a proof of concept to create annotated disaster aerial imagery with prioritized BOOs.

External IDs:dblp:conf/ssrr/HargisRC24