An FSFS-Net Method for Occluded and Aggregated Fish Segmentation from Fish School Feeding Images
Smart feeding is essential for maximizing resource utilization, enhancing fish growth and welfare, and reducing environmental impact in intensive aquaculture. The image segmentation technique facilitates fish feeding behavior analysis to achieve quantitative decision making in smart feeding. Existin...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/10/6235 |
| _version_ | 1797601168891838464 |
|---|---|
| author | Ling Yang Yingyi Chen Tao Shen Daoliang Li |
| author_facet | Ling Yang Yingyi Chen Tao Shen Daoliang Li |
| author_sort | Ling Yang |
| collection | DOAJ |
| description | Smart feeding is essential for maximizing resource utilization, enhancing fish growth and welfare, and reducing environmental impact in intensive aquaculture. The image segmentation technique facilitates fish feeding behavior analysis to achieve quantitative decision making in smart feeding. Existing studies have largely focused on single-category object segmentation, ignoring issues like occlusion, overlap, and aggregation amongst individual fish in the fish feeding process. To address the above challenges, this paper presents research on fish school feeding behavior quantification and analysis using a semantic segmentation algorithm. We propose the use of the fish school feeding segmentation method (FSFS-Net), together with the shuffle polarized self-attention (SPSA) and lightweight multi-scale module (LMSM), to achieve two-class pixel-wise classification in fish feeding images. Specifically, the SPSA method proposed is designed to extract long-range dependencies between features in an image. Moreover, the use of LMSM techniques is proposed in order to learn contextual semantic information by expanding the receptive field to extract multi-scale features. The extensive experimental results demonstrate that the proposed method outperforms several state-of-the-art semantic segmentation methods such as U-Net, SegNet, FCN, DeepLab v3 plus, GCN, HRNet-w48, DDRNet, LinkNet, BiSeNet v2, DANet, and CCNet, achieving competitive performance and computational efficiency without data augmentation. It has a 79.62% mIoU score on annotated fish feeding datasets. Finally, a feeding video with 3 min clip is tested, and two index parameters are extracted to analyze the feeding intensity of the fish. Therefore, our proposed method and dataset provide promising opportunities for the urther analysis of fish school feeding behavior. |
| first_indexed | 2024-03-11T03:57:35Z |
| format | Article |
| id | doaj.art-51423807446b46ecb74bfd269bb52032 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T03:57:35Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-51423807446b46ecb74bfd269bb520322023-11-18T00:22:34ZengMDPI AGApplied Sciences2076-34172023-05-011310623510.3390/app13106235An FSFS-Net Method for Occluded and Aggregated Fish Segmentation from Fish School Feeding ImagesLing Yang0Yingyi Chen1Tao Shen2Daoliang Li3Yunnan Key Laboratory of Computer Technologies Application, Kunming University of Science and Technology, Kunming 650500, ChinaNational Innovation Center for Digital Fishery, China Agricultural University, Beijing 100083, ChinaYunnan Key Laboratory of Computer Technologies Application, Kunming University of Science and Technology, Kunming 650500, ChinaNational Innovation Center for Digital Fishery, China Agricultural University, Beijing 100083, ChinaSmart feeding is essential for maximizing resource utilization, enhancing fish growth and welfare, and reducing environmental impact in intensive aquaculture. The image segmentation technique facilitates fish feeding behavior analysis to achieve quantitative decision making in smart feeding. Existing studies have largely focused on single-category object segmentation, ignoring issues like occlusion, overlap, and aggregation amongst individual fish in the fish feeding process. To address the above challenges, this paper presents research on fish school feeding behavior quantification and analysis using a semantic segmentation algorithm. We propose the use of the fish school feeding segmentation method (FSFS-Net), together with the shuffle polarized self-attention (SPSA) and lightweight multi-scale module (LMSM), to achieve two-class pixel-wise classification in fish feeding images. Specifically, the SPSA method proposed is designed to extract long-range dependencies between features in an image. Moreover, the use of LMSM techniques is proposed in order to learn contextual semantic information by expanding the receptive field to extract multi-scale features. The extensive experimental results demonstrate that the proposed method outperforms several state-of-the-art semantic segmentation methods such as U-Net, SegNet, FCN, DeepLab v3 plus, GCN, HRNet-w48, DDRNet, LinkNet, BiSeNet v2, DANet, and CCNet, achieving competitive performance and computational efficiency without data augmentation. It has a 79.62% mIoU score on annotated fish feeding datasets. Finally, a feeding video with 3 min clip is tested, and two index parameters are extracted to analyze the feeding intensity of the fish. Therefore, our proposed method and dataset provide promising opportunities for the urther analysis of fish school feeding behavior.https://www.mdpi.com/2076-3417/13/10/6235fish feeding behaviorsemantic segmentationattention mechanismmulti-scale featureintensive aquaculture |
| spellingShingle | Ling Yang Yingyi Chen Tao Shen Daoliang Li An FSFS-Net Method for Occluded and Aggregated Fish Segmentation from Fish School Feeding Images Applied Sciences fish feeding behavior semantic segmentation attention mechanism multi-scale feature intensive aquaculture |
| title | An FSFS-Net Method for Occluded and Aggregated Fish Segmentation from Fish School Feeding Images |
| title_full | An FSFS-Net Method for Occluded and Aggregated Fish Segmentation from Fish School Feeding Images |
| title_fullStr | An FSFS-Net Method for Occluded and Aggregated Fish Segmentation from Fish School Feeding Images |
| title_full_unstemmed | An FSFS-Net Method for Occluded and Aggregated Fish Segmentation from Fish School Feeding Images |
| title_short | An FSFS-Net Method for Occluded and Aggregated Fish Segmentation from Fish School Feeding Images |
| title_sort | fsfs net method for occluded and aggregated fish segmentation from fish school feeding images |
| topic | fish feeding behavior semantic segmentation attention mechanism multi-scale feature intensive aquaculture |
| url | https://www.mdpi.com/2076-3417/13/10/6235 |
| work_keys_str_mv | AT lingyang anfsfsnetmethodforoccludedandaggregatedfishsegmentationfromfishschoolfeedingimages AT yingyichen anfsfsnetmethodforoccludedandaggregatedfishsegmentationfromfishschoolfeedingimages AT taoshen anfsfsnetmethodforoccludedandaggregatedfishsegmentationfromfishschoolfeedingimages AT daoliangli anfsfsnetmethodforoccludedandaggregatedfishsegmentationfromfishschoolfeedingimages AT lingyang fsfsnetmethodforoccludedandaggregatedfishsegmentationfromfishschoolfeedingimages AT yingyichen fsfsnetmethodforoccludedandaggregatedfishsegmentationfromfishschoolfeedingimages AT taoshen fsfsnetmethodforoccludedandaggregatedfishsegmentationfromfishschoolfeedingimages AT daoliangli fsfsnetmethodforoccludedandaggregatedfishsegmentationfromfishschoolfeedingimages |