Improving Drone Imagery For Computer Vision/Machine Learning in Wilderness Search and Rescue

This paper describes gaps in acquisition of drone imagery that make it difficult to use with computer vision/machine learning (CV/ML) models and makes four recommendations to maximize image suitability for CV/ML post-processing. It describes a notional work process for wilderness search and rescue drone. The large volume of data from the wide area search phase offers the greatest opportunity for CV/ML techniques because of the nearly intractable number of images that would otherwise have to be manually inspected. The 2023 Wu-Murad search in Japan, one of the largest missing person searches conducted in that area, serves as a case study. Although drone teams conducting wide area searches may not know in advance if the data they collect is going to be used for CV/ML post-processing, there are data collection procedures that can improve the search in general with automated collection software. If the drone teams do expect to use CV/ML, then they can exploit knowledge about the model to further optimize flights. The paper identifies opportunities for AI path planning for image acquisition, including managing altitude and adaption to mountainous terrain, multirobot coordination and tasking, and platform design, especially in terms of choice of sensors and software functionality.