Online Variational Bayesian Motion Averaging
In this paper, we propose a novel algorithm dedicated to online motion averaging for large scale problems. To this end, we design a filter that continuously approximates the posterior distribution of the estimated transformations. In order to deal with la
- PDF / 774,968 Bytes
- 17 Pages / 439.37 x 666.142 pts Page_size
- 14 Downloads / 212 Views
Abstract. In this paper, we propose a novel algorithm dedicated to online motion averaging for large scale problems. To this end, we design a filter that continuously approximates the posterior distribution of the estimated transformations. In order to deal with large scale problems, we associate a variational Bayesian approachwith a relative parametrization of the absolute transformations. Such an association allows our algorithm to simultaneously possess two features that are essential for an algorithm dedicated to large scale online motion averaging: (1) a low computational time, (2) the ability to detect wrong loop closure measurements. We extensively demonstrate on several applications (binocular SLAM, monocular SLAM and video mosaicking) that our approach not only exhibits a low computational time and detects wrong loop closures but also significantly outperforms the state of the art algorithm in terms of RMSE. Keywords: Variational Bayes · Motion averaging · Pose-graph · Lie group · Filtering · Relative parametrization · Large scale · Visual SLAM
1
Introduction
The motion averaging problem, also called “multiple rotation averaging” when dealing with 3D rotations or “pose-graph inference” when applied to camera poses, has been studied for more than fifteen years [6,14,16–19,24,31,32] and is still a very active area of research [4,5,7,8,10,12,20,29]. This generic problem arises in a large number of applications, such as video mosaicking [6,24], reconstruction of 3D scenes [10,27] or visual SLAM [13,14], where only the considered group of transformations changes: SE(3) for 3D euclidean motions, SL(3) for homographies, Sim(3) for 3D similarities. In fact, in all these applications, the task consists in estimating absolute transformations, between a “world” coordinate system and local coordinate systems, given noisy measurements corresponding to relative transformations between pairs of local coordinate systems. The noisy relative transformation measurements are usually obtained by processing a video stream, coming from an RGB or RGB-D camera, with two different modules: Electronic supplementary material The online version of this chapter (doi:10. 1007/978-3-319-46484-8 8) contains supplementary material, which is available to authorized users. c Springer International Publishing AG 2016 B. Leibe et al. (Eds.): ECCV 2016, Part VIII, LNCS 9912, pp. 126–142, 2016. DOI: 10.1007/978-3-319-46484-8 8
Online Variational Bayesian Motion Averaging
LOAM [33] (Lidar)
Visual odometry
COP-SLAM [12]
127
This paper
Fig. 1. Results for monocular visual SLAM (Sim(3)) on sequence KITTI 13. The ground truth is not available for that sequence. Thus, we reported the best result obtained using a Lidar [33].
– a visual odometry module that continuously computes the transformation between the current and the previous local coordinate system of the camera; – a loop closure module that detects when the camera comes back in a previously visited area and computes a relative transformation. The odometry measurements and loop closur
Data Loading...
