Hybrid tracking system for robust fiducials registration in augmented reality

Madjid Maidi (1) , Fakhreddine Ababsa (2) , Malik Mallem (2) , Marius Preda (1, 3)

1 TSP - ARTEMIS - Département Advanced Research And Techniques For Multidimensional Imaging Systems
2 IBISC - Informatique, Biologie Intégrative et Systèmes Complexes
3 ARMEDIA-SAMOVAR - ARMEDIA

An effective augmented reality system requires an accurate registration of virtual graphics on real images. In this work, we developed a multi-modal tracking architecture for object identification and occlusion handling. Our approach combines several sensors and techniques to overcome the environment changes. This architecture is composed of a first coded targets registration module based on a hybrid algorithm of pose estimation. To manage partial target occlusions, a second module based on a robust method for feature points tracking is developed. The latest component of the system is the hybrid tracking module. This multi-sensors part handles total target occlusions issue. Experiments with the multi-modal system proved the effectiveness of the proposed tracking approach and occlusion handling in augmented reality applications.

Mots clés: Augmented reality; Computer vision; Hybrid tracking; Multi-sensors systems; Real-time tracking

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Madjid Maidi, Fakhreddine Ababsa, Malik Mallem, Marius Preda. Hybrid tracking system for robust fiducials registration in augmented reality. Signal, Image and Video Processing, 2015, 9 (4), pp.831--849. ⟨10.1007/s11760-013-0508-4⟩. ⟨hal-00844984⟩