Superpixel based sea ice segmentation with high-resolution optical images: analysis and evaluation.
By grouping pixels with visual coherence, superpixel algorithms provide an alternative representation of regular pixel grid for precise and efficient image segmentation. In this paper, a multi-stage model is used for sea ice segmentation from the high-resolution optical imagery, including the pre-pr...
Main Authors: | , , , , , |
---|---|
Other Authors: | , , , , |
Format: | Conference Object |
Language: | unknown |
Published: |
Springer
2022
|
Subjects: | |
Online Access: | https://doi.org/10.1007/978-981-19-0390-8_126 https://rgu-repository.worktribe.com/file/1654079/1/CHEN%202022%20Superpixel%20based%20sea%20%28AAM%29 https://rgu-repository.worktribe.com/output/1654079 |
id |
ftrobertguniv:oai:rgu-repository.worktribe.com:1654079 |
---|---|
record_format |
openpolar |
spelling |
ftrobertguniv:oai:rgu-repository.worktribe.com:1654079 2023-05-15T15:54:34+02:00 Superpixel based sea ice segmentation with high-resolution optical images: analysis and evaluation. Chen, Siyuan Yan, Yijun Ren, Jinchang Hwang, Byongjun Marshall, Stephen Durrani, Tariq Liang, Qilian Wang, Wei Liu, Xin Na, Zhenyu Zhang, Baoju 2022-03-30 https://doi.org/10.1007/978-981-19-0390-8_126 https://rgu-repository.worktribe.com/file/1654079/1/CHEN%202022%20Superpixel%20based%20sea%20%28AAM%29 https://rgu-repository.worktribe.com/output/1654079 unknown Springer https://rgu-repository.worktribe.com/output/1654079 doi:https://doi.org/10.1007/978-981-19-0390-8_126 https://rgu-repository.worktribe.com/file/1654079/1/CHEN%202022%20Superpixel%20based%20sea%20%28AAM%29 9789811903892 10.1007/978-981-19-0390-8_126 openAccess Sea ice segmentation Superpixel Satellite remote sensing Conference Proceeding acceptedVersion 2022 ftrobertguniv https://doi.org/10.1007/978-981-19-0390-8_126 2023-03-26T20:20:45Z By grouping pixels with visual coherence, superpixel algorithms provide an alternative representation of regular pixel grid for precise and efficient image segmentation. In this paper, a multi-stage model is used for sea ice segmentation from the high-resolution optical imagery, including the pre-processing to enhance the image contrast and suppress the noise, superpixel generation and classification, and post-processing to refine the segmented results. Four superpixel algorithms are evaluated within the framework, where the high-resolution imagery of the Chukchi sea is used for validation. Quantitative evaluation in terms of the segmentation quality and floe size distribution, and visual comparison for several selected regions of interest are presented. Overall, the model with TS-SLIC yields the best results, with a segmentation accuracy of 98.19% on average and adhering to the ice edges well. Conference Object Chukchi Chukchi Sea Sea ice OpenAIR@RGU (Robert Gordon University, Aberdeen) Chukchi Sea 1004 1012 |
institution |
Open Polar |
collection |
OpenAIR@RGU (Robert Gordon University, Aberdeen) |
op_collection_id |
ftrobertguniv |
language |
unknown |
topic |
Sea ice segmentation Superpixel Satellite remote sensing |
spellingShingle |
Sea ice segmentation Superpixel Satellite remote sensing Chen, Siyuan Yan, Yijun Ren, Jinchang Hwang, Byongjun Marshall, Stephen Durrani, Tariq Superpixel based sea ice segmentation with high-resolution optical images: analysis and evaluation. |
topic_facet |
Sea ice segmentation Superpixel Satellite remote sensing |
description |
By grouping pixels with visual coherence, superpixel algorithms provide an alternative representation of regular pixel grid for precise and efficient image segmentation. In this paper, a multi-stage model is used for sea ice segmentation from the high-resolution optical imagery, including the pre-processing to enhance the image contrast and suppress the noise, superpixel generation and classification, and post-processing to refine the segmented results. Four superpixel algorithms are evaluated within the framework, where the high-resolution imagery of the Chukchi sea is used for validation. Quantitative evaluation in terms of the segmentation quality and floe size distribution, and visual comparison for several selected regions of interest are presented. Overall, the model with TS-SLIC yields the best results, with a segmentation accuracy of 98.19% on average and adhering to the ice edges well. |
author2 |
Liang, Qilian Wang, Wei Liu, Xin Na, Zhenyu Zhang, Baoju |
format |
Conference Object |
author |
Chen, Siyuan Yan, Yijun Ren, Jinchang Hwang, Byongjun Marshall, Stephen Durrani, Tariq |
author_facet |
Chen, Siyuan Yan, Yijun Ren, Jinchang Hwang, Byongjun Marshall, Stephen Durrani, Tariq |
author_sort |
Chen, Siyuan |
title |
Superpixel based sea ice segmentation with high-resolution optical images: analysis and evaluation. |
title_short |
Superpixel based sea ice segmentation with high-resolution optical images: analysis and evaluation. |
title_full |
Superpixel based sea ice segmentation with high-resolution optical images: analysis and evaluation. |
title_fullStr |
Superpixel based sea ice segmentation with high-resolution optical images: analysis and evaluation. |
title_full_unstemmed |
Superpixel based sea ice segmentation with high-resolution optical images: analysis and evaluation. |
title_sort |
superpixel based sea ice segmentation with high-resolution optical images: analysis and evaluation. |
publisher |
Springer |
publishDate |
2022 |
url |
https://doi.org/10.1007/978-981-19-0390-8_126 https://rgu-repository.worktribe.com/file/1654079/1/CHEN%202022%20Superpixel%20based%20sea%20%28AAM%29 https://rgu-repository.worktribe.com/output/1654079 |
geographic |
Chukchi Sea |
geographic_facet |
Chukchi Sea |
genre |
Chukchi Chukchi Sea Sea ice |
genre_facet |
Chukchi Chukchi Sea Sea ice |
op_relation |
https://rgu-repository.worktribe.com/output/1654079 doi:https://doi.org/10.1007/978-981-19-0390-8_126 https://rgu-repository.worktribe.com/file/1654079/1/CHEN%202022%20Superpixel%20based%20sea%20%28AAM%29 9789811903892 10.1007/978-981-19-0390-8_126 |
op_rights |
openAccess |
op_doi |
https://doi.org/10.1007/978-981-19-0390-8_126 |
container_start_page |
1004 |
op_container_end_page |
1012 |
_version_ |
1766389816533975040 |