RA-UNet: an intelligent fish phenotype segmentation method based on ResNet50 and atrous spatial pyramid pooling
Introduction: Changes in fish phenotypes during aquaculture must be monitored to improve the quality of fishery resources. Therefore, a method for segmenting and measuring phenotypes rapidly and accurately without harming the fish is essential. This study proposes an intelligent fish phenotype segme...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-09-01
|
| Series: | Frontiers in Environmental Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenvs.2023.1201942/full |
| _version_ | 1827819337814114304 |
|---|---|
| author | Jianyuan Li Jianyuan Li Chunna Liu Zuobin Yang Xiaochun Lu Bilang Wu |
| author_facet | Jianyuan Li Jianyuan Li Chunna Liu Zuobin Yang Xiaochun Lu Bilang Wu |
| author_sort | Jianyuan Li |
| collection | DOAJ |
| description | Introduction: Changes in fish phenotypes during aquaculture must be monitored to improve the quality of fishery resources. Therefore, a method for segmenting and measuring phenotypes rapidly and accurately without harming the fish is essential. This study proposes an intelligent fish phenotype segmentation method based on the residual network, ResNet50, and atrous spatial pyramid pooling (ASPP).Methods: A sufficient number of fish phenotypic segmentation datasets rich in experimental research was constructed, and diverse semantic segmentation datasets were developed. ResNet50 was then built as the backbone feature extraction network to prevent the loss of fish phenotypic feature information and improve the precision of fish phenotypic segmentation. Finally, an ASPP module was designed to improve the phenotypic segmentation accuracy of different parts of fish.Results: The test algorithm based on the collected fish phenotype segmentation datasets showed that the proposed algorithm (RA-UNet) yielded the best results among several advanced semantic segmentation models. The mean intersection over union (mIoU) and mean pixel accuracy (mPA) were 87.8% and 92.3%, respectively.Discussion: Compared with the benchmark UNet algorithm, RA-UNet demonstrated improvements in the mIoU and mPA by 5.0 and 1.8 percentage points, respectively. Additionally, RA-UNet exhibited superior fish phenotype segmentation performance, with a low false detection rate and clear and complete edge segmentation. Conclusively, the RA-UNet proposed in this study has high accuracy and edge segmentation ability and can, therefore, directly improve the efficiency of phenotypic monitoring in fish farming. |
| first_indexed | 2024-03-12T01:13:36Z |
| format | Article |
| id | doaj.art-48760919f7054fc5b96150cb4e961345 |
| institution | Directory Open Access Journal |
| issn | 2296-665X |
| language | English |
| last_indexed | 2024-03-12T01:13:36Z |
| publishDate | 2023-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Environmental Science |
| spelling | doaj.art-48760919f7054fc5b96150cb4e9613452023-09-13T20:28:13ZengFrontiers Media S.A.Frontiers in Environmental Science2296-665X2023-09-011110.3389/fenvs.2023.12019421201942RA-UNet: an intelligent fish phenotype segmentation method based on ResNet50 and atrous spatial pyramid poolingJianyuan Li0Jianyuan Li1Chunna Liu2Zuobin Yang3Xiaochun Lu4Bilang Wu5State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing, ChinaCollege of Hydraulic and Environmental Engineering, China Three Gorges University, Yichang, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing, ChinaHuaneng Yarlung Zangbo Hydropower Development Co., Ltd., Chengdu, ChinaCollege of Hydraulic and Environmental Engineering, China Three Gorges University, Yichang, ChinaState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower Research, Beijing, ChinaIntroduction: Changes in fish phenotypes during aquaculture must be monitored to improve the quality of fishery resources. Therefore, a method for segmenting and measuring phenotypes rapidly and accurately without harming the fish is essential. This study proposes an intelligent fish phenotype segmentation method based on the residual network, ResNet50, and atrous spatial pyramid pooling (ASPP).Methods: A sufficient number of fish phenotypic segmentation datasets rich in experimental research was constructed, and diverse semantic segmentation datasets were developed. ResNet50 was then built as the backbone feature extraction network to prevent the loss of fish phenotypic feature information and improve the precision of fish phenotypic segmentation. Finally, an ASPP module was designed to improve the phenotypic segmentation accuracy of different parts of fish.Results: The test algorithm based on the collected fish phenotype segmentation datasets showed that the proposed algorithm (RA-UNet) yielded the best results among several advanced semantic segmentation models. The mean intersection over union (mIoU) and mean pixel accuracy (mPA) were 87.8% and 92.3%, respectively.Discussion: Compared with the benchmark UNet algorithm, RA-UNet demonstrated improvements in the mIoU and mPA by 5.0 and 1.8 percentage points, respectively. Additionally, RA-UNet exhibited superior fish phenotype segmentation performance, with a low false detection rate and clear and complete edge segmentation. Conclusively, the RA-UNet proposed in this study has high accuracy and edge segmentation ability and can, therefore, directly improve the efficiency of phenotypic monitoring in fish farming.https://www.frontiersin.org/articles/10.3389/fenvs.2023.1201942/fullfish phenotypic segmentationRA-UNetfishery resourcesResnet50ASPP |
| spellingShingle | Jianyuan Li Jianyuan Li Chunna Liu Zuobin Yang Xiaochun Lu Bilang Wu RA-UNet: an intelligent fish phenotype segmentation method based on ResNet50 and atrous spatial pyramid pooling Frontiers in Environmental Science fish phenotypic segmentation RA-UNet fishery resources Resnet50 ASPP |
| title | RA-UNet: an intelligent fish phenotype segmentation method based on ResNet50 and atrous spatial pyramid pooling |
| title_full | RA-UNet: an intelligent fish phenotype segmentation method based on ResNet50 and atrous spatial pyramid pooling |
| title_fullStr | RA-UNet: an intelligent fish phenotype segmentation method based on ResNet50 and atrous spatial pyramid pooling |
| title_full_unstemmed | RA-UNet: an intelligent fish phenotype segmentation method based on ResNet50 and atrous spatial pyramid pooling |
| title_short | RA-UNet: an intelligent fish phenotype segmentation method based on ResNet50 and atrous spatial pyramid pooling |
| title_sort | ra unet an intelligent fish phenotype segmentation method based on resnet50 and atrous spatial pyramid pooling |
| topic | fish phenotypic segmentation RA-UNet fishery resources Resnet50 ASPP |
| url | https://www.frontiersin.org/articles/10.3389/fenvs.2023.1201942/full |
| work_keys_str_mv | AT jianyuanli raunetanintelligentfishphenotypesegmentationmethodbasedonresnet50andatrousspatialpyramidpooling AT jianyuanli raunetanintelligentfishphenotypesegmentationmethodbasedonresnet50andatrousspatialpyramidpooling AT chunnaliu raunetanintelligentfishphenotypesegmentationmethodbasedonresnet50andatrousspatialpyramidpooling AT zuobinyang raunetanintelligentfishphenotypesegmentationmethodbasedonresnet50andatrousspatialpyramidpooling AT xiaochunlu raunetanintelligentfishphenotypesegmentationmethodbasedonresnet50andatrousspatialpyramidpooling AT bilangwu raunetanintelligentfishphenotypesegmentationmethodbasedonresnet50andatrousspatialpyramidpooling |