Pose Estimation Through Cue Integration: A Neuroscience-Inspired Approach

TitlePose Estimation Through Cue Integration: A Neuroscience-Inspired Approach
Publication TypeJournal Article
Year of Publication2012
AuthorsChinellato, E, Grzyb, BJ, del Pobil, AP
JournalSystems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
Keywordsbinocular cue integration, Biological system modeling, Cameras, Computational modeling, Computer Simulation, Computer-Assisted, Cybernetics, Depth Perception, Estimation, Grasping, grippers, Humans, Image Processing, Intelligent robots, Models, monocular cue integration, Neurological, neuropsychological effects, neuroscience-inspired model, object estimation, perspective orientation estimator, pose estimation, Reliability, Reproducibility of Results, robot sensory systems, robot vision, robot vision systems, Robotics, Robots, stereo image processing, stereo vision, stereoptic orientation estimator, Task Performance and Analysis, visual estimation, visual perception, Visualization

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.