Urban landmark detection using A-KAZE features and vector of aggregated local descriptors

Urban landmarks detection systems represent a research topic that is continuously pursued in the Computer Vision domain. These systems play an important role in tourism and cultural heritage storytelling augmented reality applications in urban environments. In this paper, we propose a system that aims to recognize landmarks from urban scenarios using A-KAZE features and aggregated local descriptors. The proposed system was evaluated on popular public datasets like ZuBuD and TMBuD obtaining positive results.