Title :
Pose Estimation Through Cue Integration: A Neuroscience-Inspired Approach
Author :
Chinellato, Eris ; Grzyb, Beata J. ; Pobil, Angel P del
Author_Institution :
Robotic Intell. Lab., Jaume I Univ., Castellon de la Plana, Spain
fDate :
4/1/2012 12:00:00 AM
Abstract :
The aim of this paper is to improve the skills of robotic systems in their interaction with nearby objects. The basic idea is to enhance visual estimation of objects in the world through the merging of different visual estimators of the same stimuli. A neuroscience-inspired model of stereoptic and perspective orientation estimators, merged according to different criteria, is implemented on a robotic setup and tested in different conditions. Experimental results suggest that the integration of multiple monocular and binocular cues can make robot sensory systems more reliable and versatile. The same results, compared with simulations and data from human studies, show that the model is able to reproduce some well-recognized neuropsychological effects.
Keywords :
grippers; intelligent robots; pose estimation; robot vision; stereo image processing; visual perception; binocular cue integration; monocular cue integration; neuropsychological effects; neuroscience-inspired model; object estimation; perspective orientation estimator; pose estimation; robot sensory systems; stereoptic orientation estimator; visual estimation; Cameras; Computational modeling; Estimation; Humans; Reliability; Robots; Visualization; Biological system modeling; grasping; intelligent robots; robot vision systems; stereo vision; Computer Simulation; Cybernetics; Depth Perception; Humans; Image Processing, Computer-Assisted; Models, Neurological; Reproducibility of Results; Robotics; Task Performance and Analysis;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/TSMCB.2011.2168952
