Unmanned Aerial Vehicles (UAVs) have become a major part of everyday life, as well as an emerging research field, by establishing their versatility in a variety of applications. Nevertheless, this rapid spread of UAVs reputation has provoked serious security issues that can probably affect homeland security. Defence communities have started to investigate large field-of-view sensor-based methods to enable various civil protection applications, including the detection and localisation of flying threat objects. Counter-UAV (c-UAV) detection challenges may be granted from a fusion of sensors to enhance the confidence of flying threats identification. The real-time monitoring of the environment is absolutely rigorous and demands accurate methods to detect promptly the occurrence of harmful conditions. Deep learning (DL) based techniques are capable of tackling the challenges that are associated with generic objects detection and explicitly UAV identification. In this paper, we present a novel multimodal DL methodology that combines data from individual unimodal approaches that are associated with UAV detection. Specifically, this work aims to identify and classify potential targets of UAVs based on fusion methods in two different cases of operational environments, i.e. rural and urban scenarios. A dedicated architecture is designed based on the development of deep neural networks (DNNs) frameworks that has been trained and validated employing real UAV flights scenarios. The proposed approach has achieved prominent detection accuracies over different background environments, exhibiting potential employment even in major defence applications.