A few-shot oil spill segmentation network guided by multi-scale feature similarity modeling
Segmentation of oil spills with few-shot samples using UAV optical and SAR images is crucial for enhancing the efficiency of oil spill monitoring. Current oil spill semantic segmentation predominantly relies on SAR images, rendering it relatively data-dependent. We propose a flexible and scalable fe...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-12-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2024.1481028/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846128344760844288 |
|---|---|
| author | Lingfei Shi Lingfei Shi Xianhu Wei Xianhu Wei Kun Yang Kun Yang Gong Chen Gong Chen |
| author_facet | Lingfei Shi Lingfei Shi Xianhu Wei Xianhu Wei Kun Yang Kun Yang Gong Chen Gong Chen |
| author_sort | Lingfei Shi |
| collection | DOAJ |
| description | Segmentation of oil spills with few-shot samples using UAV optical and SAR images is crucial for enhancing the efficiency of oil spill monitoring. Current oil spill semantic segmentation predominantly relies on SAR images, rendering it relatively data-dependent. We propose a flexible and scalable few-shot oil spill segmentation network that transitions from UAV optical images to SAR images based on the image similarity of oil spill regions in both types of images. Specifically, we introduce an Adaptive Feature Enhancement Module (AFEM) between the support set branch and the query set branch. This module leverages the precise oil spill information from the UAV optical image support set to derive initial oil spill templates and subsequently refines and updates the query oil spill templates through training to guide the segmentation of SAR oil spills with limited samples. Additionally, to fully exploit information from both low and high-level features, we design a Feature Fusion Module (FFM) to merge these features. Finally, the experimental results demonstrate the effectiveness of our network in enhancing the performance of UAV optical-to-SAR oil spill segmentation with few samples. Notably, the SAR oil spill detection accuracy reaches 75.88% in 5-shot experiments, representing an average improvement of 5.3% over the optimal baseline model accuracy. |
| format | Article |
| id | doaj-art-bd2989df1c02454fbc0322f2e00336f3 |
| institution | Kabale University |
| issn | 2296-7745 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj-art-bd2989df1c02454fbc0322f2e00336f32024-12-11T04:32:45ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452024-12-011110.3389/fmars.2024.14810281481028A few-shot oil spill segmentation network guided by multi-scale feature similarity modelingLingfei Shi0Lingfei Shi1Xianhu Wei2Xianhu Wei3Kun Yang4Kun Yang5Gong Chen6Gong Chen7Faculty of Geography, Yunnan Normal University, Kunming, ChinaThe Engineering Research Center of GIS Technology in Western China of Ministry of Education of China, Yunnan Normal University, Kunming, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaSino-Africa Joint Research Center, Chinese Academy of Sciences, Wuhan, Hubei, ChinaFaculty of Geography, Yunnan Normal University, Kunming, ChinaThe Engineering Research Center of GIS Technology in Western China of Ministry of Education of China, Yunnan Normal University, Kunming, ChinaFaculty of Geography, Yunnan Normal University, Kunming, ChinaThe Engineering Research Center of GIS Technology in Western China of Ministry of Education of China, Yunnan Normal University, Kunming, ChinaSegmentation of oil spills with few-shot samples using UAV optical and SAR images is crucial for enhancing the efficiency of oil spill monitoring. Current oil spill semantic segmentation predominantly relies on SAR images, rendering it relatively data-dependent. We propose a flexible and scalable few-shot oil spill segmentation network that transitions from UAV optical images to SAR images based on the image similarity of oil spill regions in both types of images. Specifically, we introduce an Adaptive Feature Enhancement Module (AFEM) between the support set branch and the query set branch. This module leverages the precise oil spill information from the UAV optical image support set to derive initial oil spill templates and subsequently refines and updates the query oil spill templates through training to guide the segmentation of SAR oil spills with limited samples. Additionally, to fully exploit information from both low and high-level features, we design a Feature Fusion Module (FFM) to merge these features. Finally, the experimental results demonstrate the effectiveness of our network in enhancing the performance of UAV optical-to-SAR oil spill segmentation with few samples. Notably, the SAR oil spill detection accuracy reaches 75.88% in 5-shot experiments, representing an average improvement of 5.3% over the optimal baseline model accuracy.https://www.frontiersin.org/articles/10.3389/fmars.2024.1481028/fulloil spillUAVdeep learningfew-shotsegmentation |
| spellingShingle | Lingfei Shi Lingfei Shi Xianhu Wei Xianhu Wei Kun Yang Kun Yang Gong Chen Gong Chen A few-shot oil spill segmentation network guided by multi-scale feature similarity modeling Frontiers in Marine Science oil spill UAV deep learning few-shot segmentation |
| title | A few-shot oil spill segmentation network guided by multi-scale feature similarity modeling |
| title_full | A few-shot oil spill segmentation network guided by multi-scale feature similarity modeling |
| title_fullStr | A few-shot oil spill segmentation network guided by multi-scale feature similarity modeling |
| title_full_unstemmed | A few-shot oil spill segmentation network guided by multi-scale feature similarity modeling |
| title_short | A few-shot oil spill segmentation network guided by multi-scale feature similarity modeling |
| title_sort | few shot oil spill segmentation network guided by multi scale feature similarity modeling |
| topic | oil spill UAV deep learning few-shot segmentation |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2024.1481028/full |
| work_keys_str_mv | AT lingfeishi afewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT lingfeishi afewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT xianhuwei afewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT xianhuwei afewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT kunyang afewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT kunyang afewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT gongchen afewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT gongchen afewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT lingfeishi fewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT lingfeishi fewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT xianhuwei fewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT xianhuwei fewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT kunyang fewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT kunyang fewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT gongchen fewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling AT gongchen fewshotoilspillsegmentationnetworkguidedbymultiscalefeaturesimilaritymodeling |