Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM
Modern visual SLAM (vSLAM) algorithms take advantage of computer vision developments in image processing and in interest point detectors to create maps and trajectories from camera images. Different feature detectors and extractors have been evaluated for this purpose in air and ground environments,...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/15/4343 |
| _version_ | 1797560349196550144 |
|---|---|
| author | Franco Hidalgo Thomas Bräunl |
| author_facet | Franco Hidalgo Thomas Bräunl |
| author_sort | Franco Hidalgo |
| collection | DOAJ |
| description | Modern visual SLAM (vSLAM) algorithms take advantage of computer vision developments in image processing and in interest point detectors to create maps and trajectories from camera images. Different feature detectors and extractors have been evaluated for this purpose in air and ground environments, but not extensively for underwater scenarios. In this paper (I) we characterize underwater images where light and suspended particles alter considerably the images captured, (II) evaluate the performance of common interest points detectors and descriptors in a variety of underwater scenes and conditions towards vSLAM in terms of the number of features matched in subsequent video frames, the precision of the descriptors and the processing time. This research justifies the usage of feature detectors in vSLAM for underwater scenarios and present its challenges and limitations. |
| first_indexed | 2024-03-10T17:58:56Z |
| format | Article |
| id | doaj.art-cc5d7a6defb543968494a363593b5ff0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T17:58:56Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-cc5d7a6defb543968494a363593b5ff02023-11-20T09:02:02ZengMDPI AGSensors1424-82202020-08-012015434310.3390/s20154343Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAMFranco Hidalgo0Thomas Bräunl1Facultad de Ingeniería, Universidad San Ignacio de Loyola, La Molina, Lima 15024, PeruDepartment of Electrical, Electronic and Computer Engineering, The University of Western Australia, Perth, WA 6009, AustraliaModern visual SLAM (vSLAM) algorithms take advantage of computer vision developments in image processing and in interest point detectors to create maps and trajectories from camera images. Different feature detectors and extractors have been evaluated for this purpose in air and ground environments, but not extensively for underwater scenarios. In this paper (I) we characterize underwater images where light and suspended particles alter considerably the images captured, (II) evaluate the performance of common interest points detectors and descriptors in a variety of underwater scenes and conditions towards vSLAM in terms of the number of features matched in subsequent video frames, the precision of the descriptors and the processing time. This research justifies the usage of feature detectors in vSLAM for underwater scenarios and present its challenges and limitations.https://www.mdpi.com/1424-8220/20/15/4343vSLAMdetectordescriptorunderwater videomonocular underwaterunderwater robots |
| spellingShingle | Franco Hidalgo Thomas Bräunl Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM Sensors vSLAM detector descriptor underwater video monocular underwater underwater robots |
| title | Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM |
| title_full | Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM |
| title_fullStr | Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM |
| title_full_unstemmed | Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM |
| title_short | Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM |
| title_sort | evaluation of several feature detectors extractors on underwater images towards vslam |
| topic | vSLAM detector descriptor underwater video monocular underwater underwater robots |
| url | https://www.mdpi.com/1424-8220/20/15/4343 |
| work_keys_str_mv | AT francohidalgo evaluationofseveralfeaturedetectorsextractorsonunderwaterimagestowardsvslam AT thomasbraunl evaluationofseveralfeaturedetectorsextractorsonunderwaterimagestowardsvslam |