Second order minimum energy filtering on SE3 with nonlinear measurement equations
Accurate camera motion estimation is a fundamental building block for many Computer Vision algorithms. For improved robustness, temporal consistency of translational and rotational camera velocity is often assumed by propagating motion information forward using stochastic filters. Classical stochast...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Chapter/Article |
| Language: | English |
| Published: |
28 April 2015
|
| In: |
Scale Space and Variational Methods in Computer Vision
Year: 2015, Pages: 397-409 |
| DOI: | 10.1007/978-3-319-18461-6_32 |
| Online Access: | Resolving-System, Volltext: http://dx.doi.org/10.1007/978-3-319-18461-6_32 Verlag, Volltext: https://link.springer.com/chapter/10.1007/978-3-319-18461-6_32 
|
| Author Notes: | Johannes Berger, Andreas Neufeld, Florian Becker, Frank Lenzen, Christoph Schnörr |
| Summary: | Accurate camera motion estimation is a fundamental building block for many Computer Vision algorithms. For improved robustness, temporal consistency of translational and rotational camera velocity is often assumed by propagating motion information forward using stochastic filters. Classical stochastic filters, however, use linear approximations for the non-linear observer model and for the non-linear structure of the underlying Lie Group SE_3 and have to approximate the unknown posteriori distribution. In this paper we employ a non-linear measurement model for the camera motion estimation problem that incorporates multiple observation equations. We solve the underlying filtering problem using a novel Minimum Energy Filter on SE_3 and give explicit expressions for the optimal state variables. Experiments on the challenging KITTI benchmark show that, although a simple motion model is only employed, our approach improves rotational velocity estimation and otherwise is on par with the state-of-the-art. |
|---|---|
| Item Description: | Im Titel ist die Ziffer 3 tiefgestellt Gesehen am 07.03.2019 |
| Physical Description: | Online Resource |
| ISBN: | 9783319184616 |
| DOI: | 10.1007/978-3-319-18461-6_32 |