Fusion of 3D Vision Techniques and RFID Technology for Object Recognition in Complex Scenes

Abstract

This work presents a new method for object recognition in complex scenes combining vision-based techniques applied to the 3D data obtained using range sensors, and object identification coming from Radio Frequency tags (RFID technology). Vision based algorithms for 3D recognition have many restrictions in practical applications: uncertainty, incapability for real time tasks; but they work well for pose determination once the object is recognized. On the other hand, RFID technology allows detecting the presence of specific objects in a scene but it cannot provide their localization. In this paper, we show the powerful recognition tool obtained by fusioning both techniques. The phases of the proposed procedure are described and an in depth experimental demonstration is included. A performance analysis of the method is made by comparing the recognition algorithm with and without the RFID phase. Obtained results, concerning to success rate increasing and computational cost reduction, confirm the robustness of this fusion approach and prove its effectiveness.