This paper proposes an effective algorithm for recognizing objects and accurately estimating their 6DOF pose in scenes acquired by a RGB-D sensor. The proposed method is based on a combination of different recognition pipelines, each exploiting the data in a diverse manner and generating object hypotheses that are ultimately fused together in an Hypothesis Verification stage that globally enforces geometrical consistency between model hypotheses and the scene. Such a scheme boosts the overall recognition performance as it enhances the strength of the different recognition pipelines while diminishing the impact of their specific weaknesses. The proposed method outperforms the state-of-the-art on two challenging benchmark datasets for object recognition comprising 35 object models and, respectively, 176 and 353 scenes.
Multimodal cue integration through Hypotheses Verification for RGB-D object recognition and 6DOF pose estimation / A. Aldoma; F. Tombari; J. Prankl; A. Richtsfeld; L. Di Stefano; M. Vincze. - ELETTRONICO. - 1:(2013), pp. 2104-2111. (Intervento presentato al convegno 2013 IEEE International Conference on Robotics and Automation tenutosi a Karlsruhe nel 6-10 May 2013) [10.1109/ICRA.2013.6630859].
Multimodal cue integration through Hypotheses Verification for RGB-D object recognition and 6DOF pose estimation
TOMBARI, FEDERICO;DI STEFANO, LUIGI;
2013
Abstract
This paper proposes an effective algorithm for recognizing objects and accurately estimating their 6DOF pose in scenes acquired by a RGB-D sensor. The proposed method is based on a combination of different recognition pipelines, each exploiting the data in a diverse manner and generating object hypotheses that are ultimately fused together in an Hypothesis Verification stage that globally enforces geometrical consistency between model hypotheses and the scene. Such a scheme boosts the overall recognition performance as it enhances the strength of the different recognition pipelines while diminishing the impact of their specific weaknesses. The proposed method outperforms the state-of-the-art on two challenging benchmark datasets for object recognition comprising 35 object models and, respectively, 176 and 353 scenes.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.