This survey article is concerned with the emergence of vision augmentation AI tools for enhancing the situational awareness of first responders (FRs) in rescue operations. More specifically, the article surveys three families of image restoration methods serving the purpose of vision augmentation under adverse weather conditions. These image restoration methods are: (a) deraining; (b) desnowing; (c) dehazing ones. The contribution of this article is a survey of the recent literature on these three problem families, focusing on the utilization of deep learning (DL) models and meeting the requirements of their application in rescue operations. A faceted taxonomy is introduced in past and recent literature including various DL architectures, loss functions and datasets. Although there are multiple surveys on recovering images degraded by natural phenomena, the literature lacks a comprehensive survey focused explicitly on assisting FRs. This paper aims to fill this gap by presenting existing methods in the literature, assessing their suitability for FR applications, and providing insights for future research directions.
In our previous work, a novel approach emphasizing a Knowledge Graph-based, distributed, and Collaborative conversational Artificial Intelligence (AI) multi-chatBot system (GraphCoBots) for museums was introduced, towards addressing limitations in scalability, knowledge reuse, and coordinated interaction across conversational services. The architecture was designed to deliver an efficient deployment solution where cultural knowledge can be distributed and shared among different chatbots that collaborate when needed. In this paper, we investigate the realization and effectiveness of this architecture through the implementation and evaluation of the GraphCoBots system. Three chatbot services were developed: (a) Nikos Kazantzakis Museum in Crete, (b) life and work of Nikos Kazantzakis and (c) selected artifacts of the museum. Two knowledge graphs (KGs) were designed and implemented, enabling structured knowledge representation, interoperability, and collaborative reasoning. The system was also designed to utilize external Linked Open Data (LOD) sources. An expert’s evaluation was conducted to assess usability and interaction quality. The outcome indicated that users prefer receiving comprehensive information delivered in a human-like manner, without encountering technological barriers or complexity. Based on these findings, the researchers integrated Generative AI services, addressing limitations and improving system efficiency. Finally, a broad audience evaluation was conducted, leading to further improvements.