A Monocular Indoor Localiser Based on an Extended Kalman Filter and Edge Images from a Convolutional Neural Network
- Publication Type:
- Conference Proceeding
- IEEE International Conference on Intelligent Robots and Systems, 2018, pp. 6335 - 6340
- Issue Date:
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is currently unavailable due to the publisher's embargo.
The embargo period expires on 1 Oct 2020
© 2018 IEEE. The main contribution of this paper is an extended Kalman filter (EKF)based algorithm for estimating the 6 DOF pose of a camera using monocular images of an indoor environment. In contrast to popular visual simultaneous localisation and mapping algorithms, the technique proposed relies on a pre-built map represented as an unsigned distance function of the ground plane edges. Images from the camera are processed using a Convolutional Neural Network (CNN)to extract a ground plane edge image. Pixels that belong to these edges are used in the observation equation of the EKF to estimate the camera location. Use of the CNN makes it possible to extract ground plane edges under significant changes to scene illumination. The EKF framework lends itself to use of a suitable motion model, fusing information from any other sensors such as wheel encoders or inertial measurement units, if available, and rejecting spurious observations. A series of experiments are presented to demonstrate the effectiveness of the proposed technique.
Please use this identifier to cite or link to this item: