Development of a Lightweight Model for Rice Plant Counting and Localization Using UAV-Captured RGB Imagery

Haoran Sun, Siqiao Tan, Zhengliang Luo, Yige Yin, Congyin Cao, Kun Zhou () and Lei Zhu ()
Additional contact information
Haoran Sun: College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, China
Siqiao Tan: College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, China
Zhengliang Luo: YueLuShan Labortory, Changsha 410128, China
Yige Yin: College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, China
Congyin Cao: College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, China
Kun Zhou: YueLuShan Labortory, Changsha 410128, China
Lei Zhu: College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, China

Agriculture, 2025, vol. 15, issue 2, 1-24

Abstract: 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.

Keywords: rice plant counting; pruning; lightweight architecture; deep learning; UAV (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/15/2/122/pdf (application/pdf)
https://www.mdpi.com/2077-0472/15/2/122/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:15:y:2025:i:2:p:122-:d:1562117

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().