Authors:
Sandro Magalhães
1
;
2
;
António Moreira
1
;
2
;
Filipe Santos
1
and
Jorge Dias
3
;
4
Affiliations:
1
INESC TEC, Porto, Portugal
;
2
FEUP, Porto, Portugal
;
3
ISR, University of Coimbra, Coimbra, Portugal
;
4
KUCARS, Khalifa University, Abu Dhabi, U.A.E.
Keyword(s):
Viewpoint Selection, 3D Position Estimation, Pose Estimation, Statistics, Kalman Filter, Active Perception, Active Sensing.
Abstract:
RGB-D sensors face multiple challenges operating under open-field environments because of their sensitivity to external perturbations such as radiation or rain. Multiple works are approaching the challenge of perceiving the three-dimensional (3D) position of objects using monocular cameras. However, most of these works focus mainly on deep learning-based solutions, which are complex, data-driven, and difficult to predict. So, we aim to approach the problem of predicting the three-dimensional (3D) objects’ position using a Gaussian viewpoint estimator named best viewpoint estimator (BVE), powered by an extended Kalman filter (EKF). The algorithm proved efficient on the tasks and reached a maximum average Euclidean error of about 32 mm. The experiments were deployed and evaluated in MATLAB using artificial Gaussian noise. Future work aims to implement the system in a robotic system.