Inverse Depth Parametrization for Monocular SLAM

Abstract

Abstract-We present a new parametrization for point features within monocular simultaneous localization and mapping (SLAM) that permits efficient and accurate representation of uncertainty during undelayed initialization and beyond, all within the standard extended Kalman filter (EKF). The key concept is direct parametrization of the inverse depth of features relative to the camera locations from which they were first viewed, which produces measurement equations with a high degree of Manuscript received February 27, 2007; revised September 28, 2007 This paper has supplementary downloadable multimedia material available at http://ieeexplore.ieee.org provided by the author. This material includes the following video files. inverseDepth_indoor.avi (11.7 MB) shows simultaneous localization and mapping, from a hand-held camera observing an indoor scene. All the processing is automatic, the image sequence being the only sensorial information used as input. It is shown as a top view of the computed camera trajectory and 3-D scene map. Image sequence is acquired with a hand-held camera 320 £ 240 at 30 frames/second. Player information XviD MPEG-4. inverseDepth_outdoor.avi (12.4 MB) shows real-time simultaneous localization and mapping, from a hand-held camera observing an outdoor scene, including rather distant features. All the processing is automatic, the image sequence being the only sensorial information used as input. It is shown as a top view of the computed camera trajectory and 3-D scene map. Image sequence is acquired with a hand-held camera 320 £ 240 at 30 frames/second. The processing is done with a standard laptop. Player information XviD MPEG-4. inverseDepth_loopClosing.avi (10.2MB) shows simultaneous localization and mapping, from a hand-held camera observing a loop-closing indoor scene. All the processing is automatic, the image sequence being the only sensorial information used as input. It is shown as a top view of the computed camera trajectory and 3-D scene map. Image sequence is acquired with a hand-held camera 320 £ 240 at 30 frames/second. Player information XviD MPEG-4. inverseDepth_loopClosing_ID_to_XYZ_conversion.avi (10.1 MB) shows simultaneous localization and mapping, from a hand-held camera observing the same loop-closing indoor sequence as in inverseDepth loopClosing.avi, but switching from inverse depth to XYZ parameterization when necessary. All the processing is automatic, the image sequence being the only sensorial information used as input. It is shown as a top view of the computed camera trajectory and 3-D scene map. Image sequence is acquired with a hand-held camera 320 £ 240 at 30 frames/second.

Simple yet stable bearing‐only navigation

“…The papers (Julier and Uhlmann, 2001;Martinelli et al, 2005) indicate that due to errors introduced in linearization EKF methods might provide inconsistent results. Although the linearization process poses a significant threat to the consistency of the position estimation, it can be elegantly avoided using the inverse depth representation (Montiel et al, 2006;Civera et al, 2008).…”

An Inverse Perspective Mapping Approach using Monocular Camera of Pepper Humanoid Robot to Determine the Position of Other Moving Robot in Plane

“…(Laganiere, 2000) (Lin and Wang, 2012) and some of the assumptions in which the image is presented(here defined as a priori knowledge). Therefore, the IPM transform can be used in a structural environment in which, for example, the camera is placed in a static position or in situations where the caliber system and caliber can be obtained from another type of sensor (Yenikaya et al, 2013) (Guo et al, 2014) (Civera et al, 2008). In this case, we use the IPM to get a Pepper robot top-down view from the camera.…”

Mobile Visual Location Recognition

“…This special treatment of new features is generally undesirable, especially when taking into account that very distant features are highly reliable sources for measuring bearing. A remedy to this problem is the inverse depth parametrization proposed by [CDM08], which has since been adopted by the majority of authors. The key concept is that by initializing features in a coordinate system local to the camera position, and storing the inverse depth (1/depth) instead of the depth, the associated uncertainty more accurately resembles a Gaussian and can therefore be used in an EKF framework.…”