FCFormer: fish density estimation and counting in recirculating aquaculture system
In intelligent feeding recirculating aquaculture system, accurately estimating fish population and density is pivotal for management practices and survival rate assessments. However, challenges arise due to mutual occlusion among fish, rapid movement, and complex breeding environments. Traditional o...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-03-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2024.1370786/full |
| _version_ | 1797253694825168896 |
|---|---|
| author | Kaijie Zhu Kaijie Zhu Kaijie Zhu Kaijie Zhu Xinting Yang Xinting Yang Xinting Yang Caiwei Yang Caiwei Yang Caiwei Yang Tingting Fu Tingting Fu Tingting Fu Pingchuan Ma Pingchuan Ma Pingchuan Ma Pingchuan Ma Weichen Hu Weichen Hu Weichen Hu |
| author_facet | Kaijie Zhu Kaijie Zhu Kaijie Zhu Kaijie Zhu Xinting Yang Xinting Yang Xinting Yang Caiwei Yang Caiwei Yang Caiwei Yang Tingting Fu Tingting Fu Tingting Fu Pingchuan Ma Pingchuan Ma Pingchuan Ma Pingchuan Ma Weichen Hu Weichen Hu Weichen Hu |
| author_sort | Kaijie Zhu |
| collection | DOAJ |
| description | In intelligent feeding recirculating aquaculture system, accurately estimating fish population and density is pivotal for management practices and survival rate assessments. However, challenges arise due to mutual occlusion among fish, rapid movement, and complex breeding environments. Traditional object detection methods based on convolutional neural networks (CNN) often fall short in fully addressing the detection demands for fish schools, especially for distant and small targets. In this regard, we introduce a detection framework dubbed FCFormer (Fish Count Transformer). Specifically, the Twins-SVT backbone network is employed first to extract global features of fish schools. To further enhance feature extraction, especially in the fusion of features at different levels, a Bi-FPN aggregation network model with a CAM Count module is incorporated (BiCC). The CAM module aids in focusing more on critical region features, thus rendering feature fusion more cohesive and effective. Furthermore, to precisely predict density maps and elevate the accuracy of fish counting, we devised an adaptive feature fusion regression head: CRMHead. This approach not only optimizes the feature fusion process but also ensures superior counting precision. Experimental results shown that the proposed FCFormer network achieves an accuracy of 97.06%, with a mean absolute error (MAE) of 6.37 and a root mean square error (MSE) of 8.69. Compared to the Twins transformer, there's a 2.02% improvement, outperforming other transformer-based architectures like CCTrans and DM_Count. The presented FCFormer algorithm can be effectively applied to fish density detection in intelligent feeding recirculating aquaculture system, offering valuable input for the development of intelligent breeding management systems. |
| first_indexed | 2024-04-24T21:38:08Z |
| format | Article |
| id | doaj.art-32f7373504644cee85a50cf27a654524 |
| institution | Directory Open Access Journal |
| issn | 2296-7745 |
| language | English |
| last_indexed | 2024-04-24T21:38:08Z |
| publishDate | 2024-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj.art-32f7373504644cee85a50cf27a6545242024-03-21T12:39:56ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452024-03-011110.3389/fmars.2024.13707861370786FCFormer: fish density estimation and counting in recirculating aquaculture systemKaijie Zhu0Kaijie Zhu1Kaijie Zhu2Kaijie Zhu3Xinting Yang4Xinting Yang5Xinting Yang6Caiwei Yang7Caiwei Yang8Caiwei Yang9Tingting Fu10Tingting Fu11Tingting Fu12Pingchuan Ma13Pingchuan Ma14Pingchuan Ma15Pingchuan Ma16Weichen Hu17Weichen Hu18Weichen Hu19School of Mechanical Engineering, Guangxi University, Nanning, ChinaNational Engineering Laboratory for Agri-product Quality Traceability, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Laboratory for Agri-product Quality Traceability, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Laboratory for Agri-product Quality Traceability, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Laboratory for Agri-product Quality Traceability, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaSchool of Mechanical Engineering, Guangxi University, Nanning, ChinaNational Engineering Laboratory for Agri-product Quality Traceability, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Laboratory for Agri-product Quality Traceability, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaResearch Center of Information Technology, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaNational Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agriculture and Forestry Sciences, Beijing, ChinaIn intelligent feeding recirculating aquaculture system, accurately estimating fish population and density is pivotal for management practices and survival rate assessments. However, challenges arise due to mutual occlusion among fish, rapid movement, and complex breeding environments. Traditional object detection methods based on convolutional neural networks (CNN) often fall short in fully addressing the detection demands for fish schools, especially for distant and small targets. In this regard, we introduce a detection framework dubbed FCFormer (Fish Count Transformer). Specifically, the Twins-SVT backbone network is employed first to extract global features of fish schools. To further enhance feature extraction, especially in the fusion of features at different levels, a Bi-FPN aggregation network model with a CAM Count module is incorporated (BiCC). The CAM module aids in focusing more on critical region features, thus rendering feature fusion more cohesive and effective. Furthermore, to precisely predict density maps and elevate the accuracy of fish counting, we devised an adaptive feature fusion regression head: CRMHead. This approach not only optimizes the feature fusion process but also ensures superior counting precision. Experimental results shown that the proposed FCFormer network achieves an accuracy of 97.06%, with a mean absolute error (MAE) of 6.37 and a root mean square error (MSE) of 8.69. Compared to the Twins transformer, there's a 2.02% improvement, outperforming other transformer-based architectures like CCTrans and DM_Count. The presented FCFormer algorithm can be effectively applied to fish density detection in intelligent feeding recirculating aquaculture system, offering valuable input for the development of intelligent breeding management systems.https://www.frontiersin.org/articles/10.3389/fmars.2024.1370786/fullrecirculating aquaculture systemsdensity estimationfish countingtransformerdeep learning |
| spellingShingle | Kaijie Zhu Kaijie Zhu Kaijie Zhu Kaijie Zhu Xinting Yang Xinting Yang Xinting Yang Caiwei Yang Caiwei Yang Caiwei Yang Tingting Fu Tingting Fu Tingting Fu Pingchuan Ma Pingchuan Ma Pingchuan Ma Pingchuan Ma Weichen Hu Weichen Hu Weichen Hu FCFormer: fish density estimation and counting in recirculating aquaculture system Frontiers in Marine Science recirculating aquaculture systems density estimation fish counting transformer deep learning |
| title | FCFormer: fish density estimation and counting in recirculating aquaculture system |
| title_full | FCFormer: fish density estimation and counting in recirculating aquaculture system |
| title_fullStr | FCFormer: fish density estimation and counting in recirculating aquaculture system |
| title_full_unstemmed | FCFormer: fish density estimation and counting in recirculating aquaculture system |
| title_short | FCFormer: fish density estimation and counting in recirculating aquaculture system |
| title_sort | fcformer fish density estimation and counting in recirculating aquaculture system |
| topic | recirculating aquaculture systems density estimation fish counting transformer deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2024.1370786/full |
| work_keys_str_mv | AT kaijiezhu fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT kaijiezhu fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT kaijiezhu fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT kaijiezhu fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT xintingyang fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT xintingyang fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT xintingyang fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT caiweiyang fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT caiweiyang fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT caiweiyang fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT tingtingfu fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT tingtingfu fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT tingtingfu fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT pingchuanma fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT pingchuanma fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT pingchuanma fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT pingchuanma fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT weichenhu fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT weichenhu fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem AT weichenhu fcformerfishdensityestimationandcountinginrecirculatingaquaculturesystem |