Visual Place Recognition via Robust ℓ2-Norm Distance Based Holism and Landmark Integration
Visual place recognition is essential for large-scale simultaneous localization and mapping (SLAM). Long-term robot operations across different time of the days, months, and seasons introduce new challenges from significant environment appearance variations. In this paper, we propose a novel method...
Published in: | Proceedings of the AAAI Conference on Artificial Intelligence |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Association for the Advancement of Artificial Intelligence
2019
|
Subjects: | |
Online Access: | https://ojs.aaai.org/index.php/AAAI/article/view/4805 https://doi.org/10.1609/aaai.v33i01.33018034 |
id |
ftjaaai:oai:ojs.aaai.org:article/4805 |
---|---|
record_format |
openpolar |
spelling |
ftjaaai:oai:ojs.aaai.org:article/4805 2023-05-15T17:24:38+02:00 Visual Place Recognition via Robust ℓ2-Norm Distance Based Holism and Landmark Integration Liu, Kai Wang, Hua Han, Fei Zhang, Hao 2019-07-17 application/pdf https://ojs.aaai.org/index.php/AAAI/article/view/4805 https://doi.org/10.1609/aaai.v33i01.33018034 eng eng Association for the Advancement of Artificial Intelligence https://ojs.aaai.org/index.php/AAAI/article/view/4805/4683 https://ojs.aaai.org/index.php/AAAI/article/view/4805 doi:10.1609/aaai.v33i01.33018034 Copyright (c) 2019 Association for the Advancement of Artificial Intelligence Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 33 No. 01: AAAI-19, IAAI-19, EAAI-20; 8034-8041 2374-3468 2159-5399 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion 2019 ftjaaai https://doi.org/10.1609/aaai.v33i01.33018034 2022-07-02T23:12:41Z Visual place recognition is essential for large-scale simultaneous localization and mapping (SLAM). Long-term robot operations across different time of the days, months, and seasons introduce new challenges from significant environment appearance variations. In this paper, we propose a novel method to learn a location representation that can integrate the semantic landmarks of a place with its holistic representation. To promote the robustness of our new model against the drastic appearance variations due to long-term visual changes, we formulate our objective to use non-squared ℓ2-norm distances, which leads to a difficult optimization problem that minimizes the ratio of the ℓ2,1-norms of matrices. To solve our objective, we derive a new efficient iterative algorithm, whose convergence is rigorously guaranteed by theory. In addition, because our solution is strictly orthogonal, the learned location representations can have better place recognition capabilities. We evaluate the proposed method using two large-scale benchmark data sets, the CMU-VL and Nordland data sets. Experimental results have validated the effectiveness of our new method in long-term visual place recognition applications. Article in Journal/Newspaper Nordland Nordland Nordland AAAI Publications (Association for the Advancement of Artificial Intelligence) Proceedings of the AAAI Conference on Artificial Intelligence 33 8034 8041 |
institution |
Open Polar |
collection |
AAAI Publications (Association for the Advancement of Artificial Intelligence) |
op_collection_id |
ftjaaai |
language |
English |
description |
Visual place recognition is essential for large-scale simultaneous localization and mapping (SLAM). Long-term robot operations across different time of the days, months, and seasons introduce new challenges from significant environment appearance variations. In this paper, we propose a novel method to learn a location representation that can integrate the semantic landmarks of a place with its holistic representation. To promote the robustness of our new model against the drastic appearance variations due to long-term visual changes, we formulate our objective to use non-squared ℓ2-norm distances, which leads to a difficult optimization problem that minimizes the ratio of the ℓ2,1-norms of matrices. To solve our objective, we derive a new efficient iterative algorithm, whose convergence is rigorously guaranteed by theory. In addition, because our solution is strictly orthogonal, the learned location representations can have better place recognition capabilities. We evaluate the proposed method using two large-scale benchmark data sets, the CMU-VL and Nordland data sets. Experimental results have validated the effectiveness of our new method in long-term visual place recognition applications. |
format |
Article in Journal/Newspaper |
author |
Liu, Kai Wang, Hua Han, Fei Zhang, Hao |
spellingShingle |
Liu, Kai Wang, Hua Han, Fei Zhang, Hao Visual Place Recognition via Robust ℓ2-Norm Distance Based Holism and Landmark Integration |
author_facet |
Liu, Kai Wang, Hua Han, Fei Zhang, Hao |
author_sort |
Liu, Kai |
title |
Visual Place Recognition via Robust ℓ2-Norm Distance Based Holism and Landmark Integration |
title_short |
Visual Place Recognition via Robust ℓ2-Norm Distance Based Holism and Landmark Integration |
title_full |
Visual Place Recognition via Robust ℓ2-Norm Distance Based Holism and Landmark Integration |
title_fullStr |
Visual Place Recognition via Robust ℓ2-Norm Distance Based Holism and Landmark Integration |
title_full_unstemmed |
Visual Place Recognition via Robust ℓ2-Norm Distance Based Holism and Landmark Integration |
title_sort |
visual place recognition via robust ℓ2-norm distance based holism and landmark integration |
publisher |
Association for the Advancement of Artificial Intelligence |
publishDate |
2019 |
url |
https://ojs.aaai.org/index.php/AAAI/article/view/4805 https://doi.org/10.1609/aaai.v33i01.33018034 |
genre |
Nordland Nordland Nordland |
genre_facet |
Nordland Nordland Nordland |
op_source |
Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 33 No. 01: AAAI-19, IAAI-19, EAAI-20; 8034-8041 2374-3468 2159-5399 |
op_relation |
https://ojs.aaai.org/index.php/AAAI/article/view/4805/4683 https://ojs.aaai.org/index.php/AAAI/article/view/4805 doi:10.1609/aaai.v33i01.33018034 |
op_rights |
Copyright (c) 2019 Association for the Advancement of Artificial Intelligence |
op_doi |
https://doi.org/10.1609/aaai.v33i01.33018034 |
container_title |
Proceedings of the AAAI Conference on Artificial Intelligence |
container_volume |
33 |
container_start_page |
8034 |
op_container_end_page |
8041 |
_version_ |
1766115748680302592 |