An adaptive observer framework for accurate feature depth estimation using an uncalibrated monocular camera |
| |
| Affiliation: | 1. University of Bayreuth, Mathematical Institute, Germany;2. Ruhr-University Bochum, Institute of Automation and Computer Control, Germany;1. Control and Simulation Center, Harbin Institute of Technology, Room 303, Building-E1, Science Park, Harbin 150080, China;2. Department of Electrical and Electronics Engineering, Chiba University, Chiba, Japan;1. German Aerospace Center (DLR), Oberpfaffenhofen, Germany;2. AIRBUS Flight Control Systems, Toulouse, France;3. DEIMOS-SPACE S.L.U., Madrid, Spain (now with the University of Bristol) |
| |
| Abstract: | This paper presents a novel solution to the problem of depth estimation using a monocular camera undergoing known motion. Such problems arise in machine vision where the position of an object moving in three-dimensional space has to be identified by tracking motion of its projected feature on the two-dimensional image plane. The camera is assumed to be uncalibrated, and an adaptive observer yielding asymptotic estimates of focal length and feature depth is developed that precludes prior knowledge of scene geometry and is simpler than alternative designs. Experimental results using real camera imagery are obtained with the current scheme as well as the extended Kalman filter, and performance of the proposed observer is shown to be better than the extended Kalman filter-based framework. |
| |
| Keywords: | Feature depth estimation Uncalibrated camera Optic flow Focal length estimation Lyapunov analysis Adaptive observer |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
