Skip to Main content Skip to Navigation
Conference papers

A Dense Structure Model for Image Based Stereo SLAM

Abstract : In this paper a dense structure model is developed for stereo image based Simultaneous Localization And Mapping (SLAM). It is proposed to model dense environment structure incrementally by robustly integrating disparity maps from current and previous time instants. In this way disparities can be refined over time to favor consistent 3D structure over noise. The analytical search bounds for disparities are transferred into the current map to allow efficient re-localization. The cost function is image-based and it is minimized by combining Iteratively Reweighted Least-Squares (IRLS) with exhaustive search for finding motion and disparity parameters respectively.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01357370
Contributor : Andrew Comport <>
Submitted on : Monday, August 29, 2016 - 4:35:32 PM
Last modification on : Thursday, March 5, 2020 - 12:20:25 PM

Identifiers

  • HAL Id : hal-01357370, version 1

Collections

Citation

Tommy Tykkala, Andrew I. Comport. A Dense Structure Model for Image Based Stereo SLAM. IEEE International Conference on Robotics and Automation, 2011, Shanghai, China. ⟨hal-01357370⟩

Share

Metrics

Record views

150