Object-level data association and pose estimation play a fundamental role in
semantic SLAM, which remain unsolved due to the lack of robust and accurate
algorithms. In this work, we propose an ensemble data associate strategy for
integrating the parametric and nonparametric statistic tests. By exploiting the
nature of different statistics, our method can effectively aggregate the
information of different measurements, and thus significantly improve the
robustness and accuracy of data association. We then present an accurate object
pose estimation framework, in which an outliers-robust centroid and scale
estimation algorithm and an object pose initialization algorithm are developed
to help improve the optimality of pose estimation results. Furthermore, we
build a SLAM system that can generate semi-dense or lightweight object-oriented
maps with a monocular camera. Extensive experiments are conducted on three
publicly available datasets and a real scenario. The results show that our
approach significantly outperforms state-of-the-art techniques in accuracy and
robustness. The source code is available on:
https://github.com/yanmin-wu/EAO-SLAM.
%0 Generic
%1 wu2020eaoslam
%A Wu, Yanmin
%A Zhang, Yunzhou
%A Zhu, Delong
%A Feng, Yonghui
%A Coleman, Sonya
%A Kerr, Dermot
%D 2020
%K 3d_reconstruction object_oriented slam
%R 10.1109/IROS45743.2020.9341757
%T EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data
Association
%U http://arxiv.org/abs/2004.12730
%X Object-level data association and pose estimation play a fundamental role in
semantic SLAM, which remain unsolved due to the lack of robust and accurate
algorithms. In this work, we propose an ensemble data associate strategy for
integrating the parametric and nonparametric statistic tests. By exploiting the
nature of different statistics, our method can effectively aggregate the
information of different measurements, and thus significantly improve the
robustness and accuracy of data association. We then present an accurate object
pose estimation framework, in which an outliers-robust centroid and scale
estimation algorithm and an object pose initialization algorithm are developed
to help improve the optimality of pose estimation results. Furthermore, we
build a SLAM system that can generate semi-dense or lightweight object-oriented
maps with a monocular camera. Extensive experiments are conducted on three
publicly available datasets and a real scenario. The results show that our
approach significantly outperforms state-of-the-art techniques in accuracy and
robustness. The source code is available on:
https://github.com/yanmin-wu/EAO-SLAM.
@misc{wu2020eaoslam,
abstract = {Object-level data association and pose estimation play a fundamental role in
semantic SLAM, which remain unsolved due to the lack of robust and accurate
algorithms. In this work, we propose an ensemble data associate strategy for
integrating the parametric and nonparametric statistic tests. By exploiting the
nature of different statistics, our method can effectively aggregate the
information of different measurements, and thus significantly improve the
robustness and accuracy of data association. We then present an accurate object
pose estimation framework, in which an outliers-robust centroid and scale
estimation algorithm and an object pose initialization algorithm are developed
to help improve the optimality of pose estimation results. Furthermore, we
build a SLAM system that can generate semi-dense or lightweight object-oriented
maps with a monocular camera. Extensive experiments are conducted on three
publicly available datasets and a real scenario. The results show that our
approach significantly outperforms state-of-the-art techniques in accuracy and
robustness. The source code is available on:
https://github.com/yanmin-wu/EAO-SLAM.},
added-at = {2021-08-25T14:04:37.000+0200},
author = {Wu, Yanmin and Zhang, Yunzhou and Zhu, Delong and Feng, Yonghui and Coleman, Sonya and Kerr, Dermot},
biburl = {https://www.bibsonomy.org/bibtex/21bf2a803444d89e04118b29c42944633/shuncheng.wu},
description = {2004.12730.pdf},
doi = {10.1109/IROS45743.2020.9341757},
interhash = {e1ab809c34a932667e489bb4cbffec67},
intrahash = {1bf2a803444d89e04118b29c42944633},
keywords = {3d_reconstruction object_oriented slam},
note = {cite arxiv:2004.12730Comment: Accepted to IROS 2020. Project Page: https://yanmin-wu.github.io/project/eaoslam/; Code: https://github.com/yanmin-wu/EAO-SLAM},
timestamp = {2021-08-25T14:04:37.000+0200},
title = {EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data
Association},
url = {http://arxiv.org/abs/2004.12730},
year = 2020
}