Automatic Hierarchical Classification of Kelps Using Deep Residual Features
Across the globe, remote image data is rapidly being collected for the assessment of benthic communities from shallow to extremely deep waters on continental slopes to the abyssal seas. Exploiting this data is presently limited by the time it takes for experts to identify organisms found in these im...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/2/447 |
| _version_ | 1811303225818611712 |
|---|---|
| author | Ammar Mahmood Ana Giraldo Ospina Mohammed Bennamoun Senjian An Ferdous Sohel Farid Boussaid Renae Hovey Robert B. Fisher Gary A. Kendrick |
| author_facet | Ammar Mahmood Ana Giraldo Ospina Mohammed Bennamoun Senjian An Ferdous Sohel Farid Boussaid Renae Hovey Robert B. Fisher Gary A. Kendrick |
| author_sort | Ammar Mahmood |
| collection | DOAJ |
| description | Across the globe, remote image data is rapidly being collected for the assessment of benthic communities from shallow to extremely deep waters on continental slopes to the abyssal seas. Exploiting this data is presently limited by the time it takes for experts to identify organisms found in these images. With this limitation in mind, a large effort has been made globally to introduce automation and machine learning algorithms to accelerate both classification and assessment of marine benthic biota. One major issue lies with organisms that move with swell and currents, such as kelps. This paper presents an automatic hierarchical classification method local binary classification as opposed to the conventional flat classification to classify kelps in images collected by autonomous underwater vehicles. The proposed kelp classification approach exploits learned feature representations extracted from deep residual networks. We show that these generic features outperform the traditional off-the-shelf CNN features and the conventional hand-crafted features. Experiments also demonstrate that the hierarchical classification method outperforms the traditional parallel multi-class classifications by a significant margin (90.0% vs. 57.6% and 77.2% vs. 59.0%) on Benthoz15 and Rottnest datasets respectively. Furthermore, we compare different hierarchical classification approaches and experimentally show that the sibling hierarchical training approach outperforms the inclusive hierarchical approach by a significant margin. We also report an application of our proposed method to study the change in kelp cover over time for annually repeated AUV surveys. |
| first_indexed | 2024-04-13T07:43:00Z |
| format | Article |
| id | doaj.art-e7fb29c027da4c23a9f17803beda23ed |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T07:43:00Z |
| publishDate | 2020-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e7fb29c027da4c23a9f17803beda23ed2022-12-22T02:55:48ZengMDPI AGSensors1424-82202020-01-0120244710.3390/s20020447s20020447Automatic Hierarchical Classification of Kelps Using Deep Residual FeaturesAmmar Mahmood0Ana Giraldo Ospina1Mohammed Bennamoun2Senjian An3Ferdous Sohel4Farid Boussaid5Renae Hovey6Robert B. Fisher7Gary A. Kendrick8Computer Science and Software Engineering, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Biological Sciences and Oceans Institute, The University of Western Australia, Crawley, WA 6009, AustraliaComputer Science and Software Engineering, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Bentley, WA 6845, AustraliaCollege of Science, Health, Engineering and Education Murdoch University, Murdoch, WA 6150, AustraliaElectrical, Electronic and Computer Engineering, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Biological Sciences and Oceans Institute, The University of Western Australia, Crawley, WA 6009, AustraliaSchool of Informatics, University of Edinburgh, Edinburgh EH8 9YL, UKSchool of Biological Sciences and Oceans Institute, The University of Western Australia, Crawley, WA 6009, AustraliaAcross the globe, remote image data is rapidly being collected for the assessment of benthic communities from shallow to extremely deep waters on continental slopes to the abyssal seas. Exploiting this data is presently limited by the time it takes for experts to identify organisms found in these images. With this limitation in mind, a large effort has been made globally to introduce automation and machine learning algorithms to accelerate both classification and assessment of marine benthic biota. One major issue lies with organisms that move with swell and currents, such as kelps. This paper presents an automatic hierarchical classification method local binary classification as opposed to the conventional flat classification to classify kelps in images collected by autonomous underwater vehicles. The proposed kelp classification approach exploits learned feature representations extracted from deep residual networks. We show that these generic features outperform the traditional off-the-shelf CNN features and the conventional hand-crafted features. Experiments also demonstrate that the hierarchical classification method outperforms the traditional parallel multi-class classifications by a significant margin (90.0% vs. 57.6% and 77.2% vs. 59.0%) on Benthoz15 and Rottnest datasets respectively. Furthermore, we compare different hierarchical classification approaches and experimentally show that the sibling hierarchical training approach outperforms the inclusive hierarchical approach by a significant margin. We also report an application of our proposed method to study the change in kelp cover over time for annually repeated AUV surveys.https://www.mdpi.com/1424-8220/20/2/447deep learninghierarchical classificationkelp coverkelpsmanual annotationbenthic marine population analysis |
| spellingShingle | Ammar Mahmood Ana Giraldo Ospina Mohammed Bennamoun Senjian An Ferdous Sohel Farid Boussaid Renae Hovey Robert B. Fisher Gary A. Kendrick Automatic Hierarchical Classification of Kelps Using Deep Residual Features Sensors deep learning hierarchical classification kelp cover kelps manual annotation benthic marine population analysis |
| title | Automatic Hierarchical Classification of Kelps Using Deep Residual Features |
| title_full | Automatic Hierarchical Classification of Kelps Using Deep Residual Features |
| title_fullStr | Automatic Hierarchical Classification of Kelps Using Deep Residual Features |
| title_full_unstemmed | Automatic Hierarchical Classification of Kelps Using Deep Residual Features |
| title_short | Automatic Hierarchical Classification of Kelps Using Deep Residual Features |
| title_sort | automatic hierarchical classification of kelps using deep residual features |
| topic | deep learning hierarchical classification kelp cover kelps manual annotation benthic marine population analysis |
| url | https://www.mdpi.com/1424-8220/20/2/447 |
| work_keys_str_mv | AT ammarmahmood automatichierarchicalclassificationofkelpsusingdeepresidualfeatures AT anagiraldoospina automatichierarchicalclassificationofkelpsusingdeepresidualfeatures AT mohammedbennamoun automatichierarchicalclassificationofkelpsusingdeepresidualfeatures AT senjianan automatichierarchicalclassificationofkelpsusingdeepresidualfeatures AT ferdoussohel automatichierarchicalclassificationofkelpsusingdeepresidualfeatures AT faridboussaid automatichierarchicalclassificationofkelpsusingdeepresidualfeatures AT renaehovey automatichierarchicalclassificationofkelpsusingdeepresidualfeatures AT robertbfisher automatichierarchicalclassificationofkelpsusingdeepresidualfeatures AT garyakendrick automatichierarchicalclassificationofkelpsusingdeepresidualfeatures |