Cargando…
Matching-range-constrained real-time loop closure detection with CNNs features
The loop closure detection (LCD) is an essential part of visual simultaneous localization and mapping systems (SLAM). LCD is capable of identifying and compensating the accumulation drift of localization algorithms to produce an consistent map if the loops are checked correctly. Deep convolutional n...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer Berlin Heidelberg
2016
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5028405/ https://www.ncbi.nlm.nih.gov/pubmed/27730029 http://dx.doi.org/10.1186/s40638-016-0047-x |
_version_ | 1782454364174024704 |
---|---|
author | Bai, Dongdong Wang, Chaoqun Zhang, Bo Yi, Xiaodong Tang, Yuhua |
author_facet | Bai, Dongdong Wang, Chaoqun Zhang, Bo Yi, Xiaodong Tang, Yuhua |
author_sort | Bai, Dongdong |
collection | PubMed |
description | The loop closure detection (LCD) is an essential part of visual simultaneous localization and mapping systems (SLAM). LCD is capable of identifying and compensating the accumulation drift of localization algorithms to produce an consistent map if the loops are checked correctly. Deep convolutional neural networks (CNNs) have outperformed state-of-the-art solutions that use traditional hand-crafted features in many computer vision and pattern recognition applications. After the great success of CNNs, there has been much interest in applying CNNs features to robotic fields such as visual LCD. Some researchers focus on using a pre-trained CNNs model as a method of generating an image representation appropriate for visual loop closure detection in SLAM. However, there are many fundamental differences and challenges involved in character between simple computer vision applications and robotic applications. Firstly, the adjacent images in the dataset of loop closure detection might have more resemblance than the images that form the loop closure. Secondly, real-time performance is one of the most critical demands for robots. In this paper, we focus on making use of the feature generated by CNNs layers to implement LCD in real environment. In order to address the above challenges, we explicitly provide a value to limit the matching range of images to solve the first problem; meanwhile we get better results than state-of-the-art methods and improve the real-time performance using an efficient feature compression method. |
format | Online Article Text |
id | pubmed-5028405 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2016 |
publisher | Springer Berlin Heidelberg |
record_format | MEDLINE/PubMed |
spelling | pubmed-50284052016-10-09 Matching-range-constrained real-time loop closure detection with CNNs features Bai, Dongdong Wang, Chaoqun Zhang, Bo Yi, Xiaodong Tang, Yuhua Robotics Biomim Research The loop closure detection (LCD) is an essential part of visual simultaneous localization and mapping systems (SLAM). LCD is capable of identifying and compensating the accumulation drift of localization algorithms to produce an consistent map if the loops are checked correctly. Deep convolutional neural networks (CNNs) have outperformed state-of-the-art solutions that use traditional hand-crafted features in many computer vision and pattern recognition applications. After the great success of CNNs, there has been much interest in applying CNNs features to robotic fields such as visual LCD. Some researchers focus on using a pre-trained CNNs model as a method of generating an image representation appropriate for visual loop closure detection in SLAM. However, there are many fundamental differences and challenges involved in character between simple computer vision applications and robotic applications. Firstly, the adjacent images in the dataset of loop closure detection might have more resemblance than the images that form the loop closure. Secondly, real-time performance is one of the most critical demands for robots. In this paper, we focus on making use of the feature generated by CNNs layers to implement LCD in real environment. In order to address the above challenges, we explicitly provide a value to limit the matching range of images to solve the first problem; meanwhile we get better results than state-of-the-art methods and improve the real-time performance using an efficient feature compression method. Springer Berlin Heidelberg 2016-09-19 2016 /pmc/articles/PMC5028405/ /pubmed/27730029 http://dx.doi.org/10.1186/s40638-016-0047-x Text en © The Author(s) 2016 Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. |
spellingShingle | Research Bai, Dongdong Wang, Chaoqun Zhang, Bo Yi, Xiaodong Tang, Yuhua Matching-range-constrained real-time loop closure detection with CNNs features |
title | Matching-range-constrained real-time loop closure detection with CNNs features |
title_full | Matching-range-constrained real-time loop closure detection with CNNs features |
title_fullStr | Matching-range-constrained real-time loop closure detection with CNNs features |
title_full_unstemmed | Matching-range-constrained real-time loop closure detection with CNNs features |
title_short | Matching-range-constrained real-time loop closure detection with CNNs features |
title_sort | matching-range-constrained real-time loop closure detection with cnns features |
topic | Research |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5028405/ https://www.ncbi.nlm.nih.gov/pubmed/27730029 http://dx.doi.org/10.1186/s40638-016-0047-x |
work_keys_str_mv | AT baidongdong matchingrangeconstrainedrealtimeloopclosuredetectionwithcnnsfeatures AT wangchaoqun matchingrangeconstrainedrealtimeloopclosuredetectionwithcnnsfeatures AT zhangbo matchingrangeconstrainedrealtimeloopclosuredetectionwithcnnsfeatures AT yixiaodong matchingrangeconstrainedrealtimeloopclosuredetectionwithcnnsfeatures AT tangyuhua matchingrangeconstrainedrealtimeloopclosuredetectionwithcnnsfeatures |