Development of a Lightweight Model for Rice Plant Counting and Localization Using UAV-Captured RGB Imagery
Accurately obtaining both the number and the location of rice plants plays a critical role in agricultural applications, such as precision fertilization and yield prediction. With the rapid development of deep learning, numerous models for plant counting have been proposed. However, many of these mo...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Agriculture |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0472/15/2/122 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589473247920128 |
|---|---|
| author | Haoran Sun Siqiao Tan Zhengliang Luo Yige Yin Congyin Cao Kun Zhou Lei Zhu |
| author_facet | Haoran Sun Siqiao Tan Zhengliang Luo Yige Yin Congyin Cao Kun Zhou Lei Zhu |
| author_sort | Haoran Sun |
| collection | DOAJ |
| description | Accurately obtaining both the number and the location of rice plants plays a critical role in agricultural applications, such as precision fertilization and yield prediction. With the rapid development of deep learning, numerous models for plant counting have been proposed. However, many of these models contain a large number of parameters, making them unsuitable for deployment in agricultural settings with limited computational resources. To address this challenge, we propose a novel pruning method, Cosine Norm Fusion (CNF), and a lightweight feature fusion technique, the Depth Attention Fusion Module (DAFM). Based on these innovations, we modify the existing P2PNet network to create P2P-CNF, a lightweight model for rice plant counting. The process begins with pruning the trained network using CNF, followed by the integration of our lightweight feature fusion module, DAFM. To validate the effectiveness of our method, we conducted experiments using rice datasets, including the RSC-UAV dataset, captured by UAV. The results demonstrate that our method achieves a MAE of 3.12 and an RMSE of 4.12 while utilizing only 33% of the original network parameters. We also evaluated our method on other plant counting datasets, and the results show that our method achieves a high counting accuracy while maintaining a lightweight architecture. |
| format | Article |
| id | doaj-art-67f45ef1de1b4786a5f0289c082b509d |
| institution | Kabale University |
| issn | 2077-0472 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agriculture |
| spelling | doaj-art-67f45ef1de1b4786a5f0289c082b509d2025-01-24T13:15:46ZengMDPI AGAgriculture2077-04722025-01-0115212210.3390/agriculture15020122Development of a Lightweight Model for Rice Plant Counting and Localization Using UAV-Captured RGB ImageryHaoran Sun0Siqiao Tan1Zhengliang Luo2Yige Yin3Congyin Cao4Kun Zhou5Lei Zhu6College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaYueLuShan Labortory, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaYueLuShan Labortory, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaAccurately obtaining both the number and the location of rice plants plays a critical role in agricultural applications, such as precision fertilization and yield prediction. With the rapid development of deep learning, numerous models for plant counting have been proposed. However, many of these models contain a large number of parameters, making them unsuitable for deployment in agricultural settings with limited computational resources. To address this challenge, we propose a novel pruning method, Cosine Norm Fusion (CNF), and a lightweight feature fusion technique, the Depth Attention Fusion Module (DAFM). Based on these innovations, we modify the existing P2PNet network to create P2P-CNF, a lightweight model for rice plant counting. The process begins with pruning the trained network using CNF, followed by the integration of our lightweight feature fusion module, DAFM. To validate the effectiveness of our method, we conducted experiments using rice datasets, including the RSC-UAV dataset, captured by UAV. The results demonstrate that our method achieves a MAE of 3.12 and an RMSE of 4.12 while utilizing only 33% of the original network parameters. We also evaluated our method on other plant counting datasets, and the results show that our method achieves a high counting accuracy while maintaining a lightweight architecture.https://www.mdpi.com/2077-0472/15/2/122rice plant countingpruninglightweight architecturedeep learningUAV |
| spellingShingle | Haoran Sun Siqiao Tan Zhengliang Luo Yige Yin Congyin Cao Kun Zhou Lei Zhu Development of a Lightweight Model for Rice Plant Counting and Localization Using UAV-Captured RGB Imagery Agriculture rice plant counting pruning lightweight architecture deep learning UAV |
| title | Development of a Lightweight Model for Rice Plant Counting and Localization Using UAV-Captured RGB Imagery |
| title_full | Development of a Lightweight Model for Rice Plant Counting and Localization Using UAV-Captured RGB Imagery |
| title_fullStr | Development of a Lightweight Model for Rice Plant Counting and Localization Using UAV-Captured RGB Imagery |
| title_full_unstemmed | Development of a Lightweight Model for Rice Plant Counting and Localization Using UAV-Captured RGB Imagery |
| title_short | Development of a Lightweight Model for Rice Plant Counting and Localization Using UAV-Captured RGB Imagery |
| title_sort | development of a lightweight model for rice plant counting and localization using uav captured rgb imagery |
| topic | rice plant counting pruning lightweight architecture deep learning UAV |
| url | https://www.mdpi.com/2077-0472/15/2/122 |
| work_keys_str_mv | AT haoransun developmentofalightweightmodelforriceplantcountingandlocalizationusinguavcapturedrgbimagery AT siqiaotan developmentofalightweightmodelforriceplantcountingandlocalizationusinguavcapturedrgbimagery AT zhengliangluo developmentofalightweightmodelforriceplantcountingandlocalizationusinguavcapturedrgbimagery AT yigeyin developmentofalightweightmodelforriceplantcountingandlocalizationusinguavcapturedrgbimagery AT congyincao developmentofalightweightmodelforriceplantcountingandlocalizationusinguavcapturedrgbimagery AT kunzhou developmentofalightweightmodelforriceplantcountingandlocalizationusinguavcapturedrgbimagery AT leizhu developmentofalightweightmodelforriceplantcountingandlocalizationusinguavcapturedrgbimagery |