3-D objects motion estimation based on Kalman filter and BSP tree models for robot stereo vision

The problem of the real time estimation of the position and orientation of moving objects for position-based visual servoing control of robotic systems is considered in this paper. A computationally efficient algorithm is proposed based on Kalman filtering of the visual measurements of the position of suitable feature points selected on the target objects. The efficiency of the algorithm is improved by adopting a pre-selection technique of the feature points, based on Binary Space Partitioning (BSP) tree geometric models of the target objects, which takes advantage of the Kalman filter prediction capability. Computer simulations are presented to test the performance of the estimation algorithm in the presence of noise, different types of lens geometric distortion, quantization and calibration errors.