Coalitions of UAVs for victims localization in post-avalanche events using advanced image processing techniquesCoalitions of UAVs for victims localization in post-avalanche events using advanced image processing techniques Πλήρης Δημοσίευση σε Συνέδριο Conference Full Paper 2024-09-192022enThis paper puts forward a novel coalition formation framework to enable teams of Unmanned Aerial Vehicles (UAVs) to assist in victims localization and rescue in the case of post-avalanche events. Our framework consists of multiple components. First, a novel initial UAVs placement algorithm (adapting a known Brain-Storming Optimization algorithm to our setting); second, a novel coalition structure generation protocol that allows for the “online” calculation of coalition values that will eventually guide the rescue effort; and third, a simple but effective opinion aggregation protocol, that can be used to prioritize certain rescue operations in the event of “ambiguous” findings. Moreover, for the recognition task itself we employ two image recognition algorithms, used for the first time for the analysis of post-avalanche Search & Rescue Operations images. Our experimental evaluation verifies the applicability and effectiveness of our framework and its individual components.http://creativecommons.org/licenses/by/4.0/12th Hellenic Conference on Artificial IntelligenceProceedings of the 12th Hellenic Conference on Artificial Intelligence Trigkas Nikolaos Τριγκας Νικολαος Chalkiadakis Georgios Χαλκιαδακης Γεωργιος Association for Computing Machinery (ACM) Search & rescue Image processing Multi-agent systems