DASNet a dual branch multi level attention sheep counting network
Abstract Grassland sheep counting is essential for both animal husbandry and ecological balance. Accurate population statistics help optimize livestock management and sustain grassland ecosystems. However, traditional counting methods are time–consuming and costly, especially for dense sheep herds....
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-97929-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849238566355337216 |
|---|---|
| author | Yini Chen Ronghua Gao Qifeng Li Hongtao Zhao Rong Wang Luyu Ding Xuwen Li |
| author_facet | Yini Chen Ronghua Gao Qifeng Li Hongtao Zhao Rong Wang Luyu Ding Xuwen Li |
| author_sort | Yini Chen |
| collection | DOAJ |
| description | Abstract Grassland sheep counting is essential for both animal husbandry and ecological balance. Accurate population statistics help optimize livestock management and sustain grassland ecosystems. However, traditional counting methods are time–consuming and costly, especially for dense sheep herds. Computer vision offers a cost–effective and labor–efficient alternative, but existing methods still face challenges. Object detection–based counting often leads to overcounts or missed detections, while instance segmentation requires extensive annotation efforts. To better align with the practical task of counting sheep on grasslands, we collected the Sheep1500 UAV Dataset using drones in real–world settings. The varying flight altitudes, diverse scenes, and different density levels captured by the drones endow our dataset with a high degree of diversity. To address the challenge of inaccurate counting caused by background object interference in this dataset, we propose a dual–branch multi–level attention network based on density map regression. DASNet is built on a modified VGG–19 architecture, where a dual-branch structure is employed to integrate both shallow and deep features. A Conv Convolutional Block Attention Layer (CCBL) is incorporated into the network to more effectively focus on sheep regions, alongside a Multi–Level Attention Module (MAM) in the deep feature branch. The MAM, consisting of three Light Channel and Pixel Attention Modules (LCPM), is designed to refine feature representation at both the channel and pixel levels, improving the accuracy of density map generation for sheep counting. In addition, a residual structure connects each module, facilitating feature fusion across different levels and offering increased flexibility in handling diverse information. The LCPM leverages the advantages of attention mechanisms to more effectively extract multi-scale global features of the sheep regions, thereby helping the network to reduce the loss of deep feature information. Experiments conducted on our Sheep1500 UAV Dataset have demonstrated that DASNet significantly outperforms the baseline MAN network, with a Mean Absolute Error (MAE) of 3.95 and a Mean Squared Error (MSE) of 4.87, compared to the baseline’s MAE of 5.39 and MSE of 6.50. DASNet is shown to be effective in handling challenging scenarios, such as dense flocks and background noise, due to its dual–branch feature enhancement and global multi–level feature fusion. DASNet has shown promising results in accuracy and computational efficiency, making it an ideal solution for practical sheep counting in precision agriculture. |
| format | Article |
| id | doaj-art-b594053e490d4b22bc664719e82242b4 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-b594053e490d4b22bc664719e82242b42025-08-20T04:01:34ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-97929-wDASNet a dual branch multi level attention sheep counting networkYini Chen0Ronghua Gao1Qifeng Li2Hongtao Zhao3Rong Wang4Luyu Ding5Xuwen Li6Information Technology Research Center, Beijing Academy of Agriculture and Forestry SciencesInformation Technology Research Center, Beijing Academy of Agriculture and Forestry SciencesInformation Technology Research Center, Beijing Academy of Agriculture and Forestry SciencesDepartment of Mathematics And Physics, North China Electric Power UniversityInformation Technology Research Center, Beijing Academy of Agriculture and Forestry SciencesInformation Technology Research Center, Beijing Academy of Agriculture and Forestry SciencesInformation Technology Research Center, Beijing Academy of Agriculture and Forestry SciencesAbstract Grassland sheep counting is essential for both animal husbandry and ecological balance. Accurate population statistics help optimize livestock management and sustain grassland ecosystems. However, traditional counting methods are time–consuming and costly, especially for dense sheep herds. Computer vision offers a cost–effective and labor–efficient alternative, but existing methods still face challenges. Object detection–based counting often leads to overcounts or missed detections, while instance segmentation requires extensive annotation efforts. To better align with the practical task of counting sheep on grasslands, we collected the Sheep1500 UAV Dataset using drones in real–world settings. The varying flight altitudes, diverse scenes, and different density levels captured by the drones endow our dataset with a high degree of diversity. To address the challenge of inaccurate counting caused by background object interference in this dataset, we propose a dual–branch multi–level attention network based on density map regression. DASNet is built on a modified VGG–19 architecture, where a dual-branch structure is employed to integrate both shallow and deep features. A Conv Convolutional Block Attention Layer (CCBL) is incorporated into the network to more effectively focus on sheep regions, alongside a Multi–Level Attention Module (MAM) in the deep feature branch. The MAM, consisting of three Light Channel and Pixel Attention Modules (LCPM), is designed to refine feature representation at both the channel and pixel levels, improving the accuracy of density map generation for sheep counting. In addition, a residual structure connects each module, facilitating feature fusion across different levels and offering increased flexibility in handling diverse information. The LCPM leverages the advantages of attention mechanisms to more effectively extract multi-scale global features of the sheep regions, thereby helping the network to reduce the loss of deep feature information. Experiments conducted on our Sheep1500 UAV Dataset have demonstrated that DASNet significantly outperforms the baseline MAN network, with a Mean Absolute Error (MAE) of 3.95 and a Mean Squared Error (MSE) of 4.87, compared to the baseline’s MAE of 5.39 and MSE of 6.50. DASNet is shown to be effective in handling challenging scenarios, such as dense flocks and background noise, due to its dual–branch feature enhancement and global multi–level feature fusion. DASNet has shown promising results in accuracy and computational efficiency, making it an ideal solution for practical sheep counting in precision agriculture.https://doi.org/10.1038/s41598-025-97929-w |
| spellingShingle | Yini Chen Ronghua Gao Qifeng Li Hongtao Zhao Rong Wang Luyu Ding Xuwen Li DASNet a dual branch multi level attention sheep counting network Scientific Reports |
| title | DASNet a dual branch multi level attention sheep counting network |
| title_full | DASNet a dual branch multi level attention sheep counting network |
| title_fullStr | DASNet a dual branch multi level attention sheep counting network |
| title_full_unstemmed | DASNet a dual branch multi level attention sheep counting network |
| title_short | DASNet a dual branch multi level attention sheep counting network |
| title_sort | dasnet a dual branch multi level attention sheep counting network |
| url | https://doi.org/10.1038/s41598-025-97929-w |
| work_keys_str_mv | AT yinichen dasnetadualbranchmultilevelattentionsheepcountingnetwork AT ronghuagao dasnetadualbranchmultilevelattentionsheepcountingnetwork AT qifengli dasnetadualbranchmultilevelattentionsheepcountingnetwork AT hongtaozhao dasnetadualbranchmultilevelattentionsheepcountingnetwork AT rongwang dasnetadualbranchmultilevelattentionsheepcountingnetwork AT luyuding dasnetadualbranchmultilevelattentionsheepcountingnetwork AT xuwenli dasnetadualbranchmultilevelattentionsheepcountingnetwork |