Human identification and tracking using ultra-wideband-vision data fusion in unstructured environments

<p class="Abstract">Nowadays, the importance of working in changing and unstructured environments such as logistics warehouses through cooperation between Automated Guided Vehicles (AGV) operator is increasingly demanded. The challenge addressed this article aims to solve two crucial functions autonomy: identification, tracking. These tasks are necessary enable an AGV follow selected along his path. This paper presents innovative, accurate, robust, autonomous, low-cost real-time tracking system, leveraging inherent complementarity uncertainty regions (2D ellipses) ultra-wideband (UWB) transceivers cameras. test campaign shows how UWB system has higher angular direction. In contrast, case vision predominant radial coordinate. Due nature data, a sensor fusion demonstrates improvement accuracy goodness final tracking.</p>