A data fusion scheme for visual object identification and tracking by autonomous vehicles is recommended. Image motion vectors fields, color features, visual disparity depth information and camera motion parameters are fused together to identify the target 3D (Three-Dimensional) visual and dynamic features. A detailed description of the 3D target tracking algorithm using an extended Kalman Filter with a constant velocity dynamic model is presented. Performance of the proposed scheme is discussed through experimental results.
Camera motion and visual information fusion for 3D target tracking
Fusion der Kamerabewegung und der visuellen Informationen für die dreidimensionale Zielverfolgung
2004
6 Seiten, 10 Quellen
Conference paper
English
Visual target motion analysis using controlled camera motion
TIBKAT | 1994
|Motion priors for multiple target visual tracking
British Library Online Contents | 2015
|Multi-vessel target tracking with camera fusion for unmanned surface vehicles
DOAJ | 2024
|Multi-vessel target tracking with camera fusion for unmanned surface vehicles
Elsevier | 2024
|