A New Strategy for Feature Initialization in Visual SLAM

Abstract : This paper presents a Visual EKF-SLAM process using an original and very efficient strategy for initializing landmarks. Usually, with Cartesian coordinates, new points are created along the line-of-sight with a large variance. However, this type of initialization is subject to significant linearization issues making landmarks diverge from their real position. The immediate consequence is a failure of the Visual SLAM process. We propose here a new strategy that avoids or drastically limits the linearization errors. The first part of this strategy takes place during the tracking process where a coherent window is needed in order to successfully follow a point and make it converge. The second part concerns the update step. Due to linearization errors, a landmark in front of the observer can be updated behind it. We compute a corrective of the Kalman gain in order to preserve the integrity. We applied this strategy to real data illustrating its efficiency.
Document type :
Conference papers
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.inria.fr/hal-01351394
Contributor : Guillaume Bresson <>
Submitted on : Wednesday, August 3, 2016 - 4:09:50 PM
Last modification on : Saturday, February 17, 2018 - 1:21:28 AM

File

2011-a_new_strategy_for_featur...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01351394, version 1

Citation

Guillaume Bresson, Thomas Féraud, Romuald Aufrère, Paul Checchin, Roland Chapuis. A New Strategy for Feature Initialization in Visual SLAM. IEEE/RSJ International Conference on Intelligent Robots and Systems Workshop on Perception and Navigation for Autonomous Vehicles in Human Environment, 2011, San Francisco, United States. ⟨hal-01351394⟩

Share

Metrics

Record views

45

Files downloads

23