An Behavior-based Robotics
Mobile Robot Localisation Using Active Vision
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Color-Based Probabilistic Tracking
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
A Humanoid Vision System for Versatile Interaction
BMVC '00 Proceedings of the First IEEE International Workshop on Biologically Motivated Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Active visual navigation using non-metric structure
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
A tutorial on particle filters for online nonlinear/non-GaussianBayesian tracking
IEEE Transactions on Signal Processing
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Enhancing a disparity map by color segmentation
Integrated Computer-Aided Engineering
Pedestrian detection in far infrared images
Integrated Computer-Aided Engineering
Hi-index | 0.00 |
In this paper, we propose a mobile robot architecture for person tracking, consisting of an active stereo vision module (ASVM) and a navigation module (NM). The first uses a stereo head equipped with a pan-tilt mechanism to track a moving target (selected by an operator) and keep it centered in the visual field. Its output, i.e. the 3D position of the person, is fed to the NM, which drives the robot towards the target while avoiding obstacles. For this, a hybrid navigation algorithm is adopted with a reactive part that efficiently reacts to the most recent sensor data, and a deliberative part that generates a globally optimal path to a target destination, such as the person's location. As a peculiarity of the system, there is no feedback from the NM or the robot motion controller (RMC) to the ASVM. While this imparts flexibility in combining the ASVM with a wide range of robot platforms, it puts considerable strain on the ASVM. Indeed, besides the changes in the target dynamics, it has to cope with the robot motion during obstacle avoidance. These disturbances are accommodated via a suitable stochastic dynamic model for the stereo head-target system. Robust tracking is achieved by combining a color-based particle filter with a method to update the color model of the target under changing illumination conditions. The main contributions of this paper lie in (1) devising a robust color-based 3D target tracking method, (2) proposing a hybrid deliberative/reactive navigation scheme, and (3) integrating them on a wheelchair platform for the final goal of person following. Experimental results are presented for ASVM separately and in combination with a wheelchair platform-based implementation of the NM.