Combining Deep Learning and Robust Estimation for Outlier-Resilient Underwater Visual Graph SLAM
Visual Loop Detection (VLD) is a core component of any Visual Simultaneous Localization and Mapping (SLAM) system, and its goal is to determine if the robot has returned to a previously visited region by comparing images obtained at different time steps. This paper presents a new approach to visual...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/10/4/511 |
| _version_ | 1797410584665260032 |
|---|---|
| author | Antoni Burguera Francisco Bonin-Font Eric Guerrero Font Antoni Martorell Torres |
| author_facet | Antoni Burguera Francisco Bonin-Font Eric Guerrero Font Antoni Martorell Torres |
| author_sort | Antoni Burguera |
| collection | DOAJ |
| description | Visual Loop Detection (VLD) is a core component of any Visual Simultaneous Localization and Mapping (SLAM) system, and its goal is to determine if the robot has returned to a previously visited region by comparing images obtained at different time steps. This paper presents a new approach to visual Graph-SLAM for underwater robots that goes one step forward the current techniques. The proposal, which centers its attention on designing a robust VLD algorithm aimed at reducing the amount of false loops that enter into the pose graph optimizer, operates in three steps. In the first step, an easily trainable Neural Network performs a fast selection of image pairs that are likely to close loops. The second step carefully confirms or rejects these candidate loops by means of a robust image matcher. During the third step, all the loops accepted in the second step are subject to a geometric consistency verification process, being rejected those that do not fit with it. The accepted loops are then used to feed a Graph-SLAM algorithm. The advantages of this approach are twofold. First, the robustness in front of wrong loop detection. Second, the computational efficiency since each step operates only on the loops accepted in the previous one. This makes online usage of this VLD algorithm possible. Results of experiments with semi-synthetic data and real data obtained with an autonomous robot in several marine resorts of the Balearic Islands, support the validity and suitability of the approach to be applied in further field campaigns. |
| first_indexed | 2024-03-09T04:32:19Z |
| format | Article |
| id | doaj.art-ce7e91b32fb242559508217a2e1abdc1 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-09T04:32:19Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-ce7e91b32fb242559508217a2e1abdc12023-12-03T13:33:58ZengMDPI AGJournal of Marine Science and Engineering2077-13122022-04-0110451110.3390/jmse10040511Combining Deep Learning and Robust Estimation for Outlier-Resilient Underwater Visual Graph SLAMAntoni Burguera0Francisco Bonin-Font1Eric Guerrero Font2Antoni Martorell Torres3Systems, Robotics and Vision Group, Departament de Matemàtiques i Informàtica, Universitat de les Illes Balears, Carretera de Valldemossa Km. 7.5, 07122 Palma, SpainSystems, Robotics and Vision Group, Departament de Matemàtiques i Informàtica, Universitat de les Illes Balears, Carretera de Valldemossa Km. 7.5, 07122 Palma, SpainSystems, Robotics and Vision Group, Departament de Matemàtiques i Informàtica, Universitat de les Illes Balears, Carretera de Valldemossa Km. 7.5, 07122 Palma, SpainSystems, Robotics and Vision Group, Departament de Matemàtiques i Informàtica, Universitat de les Illes Balears, Carretera de Valldemossa Km. 7.5, 07122 Palma, SpainVisual Loop Detection (VLD) is a core component of any Visual Simultaneous Localization and Mapping (SLAM) system, and its goal is to determine if the robot has returned to a previously visited region by comparing images obtained at different time steps. This paper presents a new approach to visual Graph-SLAM for underwater robots that goes one step forward the current techniques. The proposal, which centers its attention on designing a robust VLD algorithm aimed at reducing the amount of false loops that enter into the pose graph optimizer, operates in three steps. In the first step, an easily trainable Neural Network performs a fast selection of image pairs that are likely to close loops. The second step carefully confirms or rejects these candidate loops by means of a robust image matcher. During the third step, all the loops accepted in the second step are subject to a geometric consistency verification process, being rejected those that do not fit with it. The accepted loops are then used to feed a Graph-SLAM algorithm. The advantages of this approach are twofold. First, the robustness in front of wrong loop detection. Second, the computational efficiency since each step operates only on the loops accepted in the previous one. This makes online usage of this VLD algorithm possible. Results of experiments with semi-synthetic data and real data obtained with an autonomous robot in several marine resorts of the Balearic Islands, support the validity and suitability of the approach to be applied in further field campaigns.https://www.mdpi.com/2077-1312/10/4/511visual SLAMvisual loop closingconvolutional neural network |
| spellingShingle | Antoni Burguera Francisco Bonin-Font Eric Guerrero Font Antoni Martorell Torres Combining Deep Learning and Robust Estimation for Outlier-Resilient Underwater Visual Graph SLAM Journal of Marine Science and Engineering visual SLAM visual loop closing convolutional neural network |
| title | Combining Deep Learning and Robust Estimation for Outlier-Resilient Underwater Visual Graph SLAM |
| title_full | Combining Deep Learning and Robust Estimation for Outlier-Resilient Underwater Visual Graph SLAM |
| title_fullStr | Combining Deep Learning and Robust Estimation for Outlier-Resilient Underwater Visual Graph SLAM |
| title_full_unstemmed | Combining Deep Learning and Robust Estimation for Outlier-Resilient Underwater Visual Graph SLAM |
| title_short | Combining Deep Learning and Robust Estimation for Outlier-Resilient Underwater Visual Graph SLAM |
| title_sort | combining deep learning and robust estimation for outlier resilient underwater visual graph slam |
| topic | visual SLAM visual loop closing convolutional neural network |
| url | https://www.mdpi.com/2077-1312/10/4/511 |
| work_keys_str_mv | AT antoniburguera combiningdeeplearningandrobustestimationforoutlierresilientunderwatervisualgraphslam AT franciscoboninfont combiningdeeplearningandrobustestimationforoutlierresilientunderwatervisualgraphslam AT ericguerrerofont combiningdeeplearningandrobustestimationforoutlierresilientunderwatervisualgraphslam AT antonimartorelltorres combiningdeeplearningandrobustestimationforoutlierresilientunderwatervisualgraphslam |