RPNet: Rice plant counting after tillering stage based on plant attention and multiple supervision network

作     者：Xiaodong Bai Susong Gu Pichao Liu Aiping Yang Zhe Cai Jianjun Wang Jianguo Yao Xiaodong Bai;Susong Gu;Pichao Liu;Aiping Yang;Zhe Cai;Jianjun Wang;Jianguo Yao

作者机构：School of Computer Science and TechnologyHainan UniversityHaikou 570228HainanChina Institute of Advanced TechnologyNanjing University of Posts and TelecommunicationsNanjing 210003JiangsuChina Agricultural Meteorological CenterJiangxi Meteorological BureauNanchang 330045JiangxiChina 

出 版 物：《作物学报:英文版》 (The Crop Journal)

年 卷 期：2023年第11卷第5期

页      面：1586-1594页

核心收录：

学科分类：0710[理学-生物学] 09[农学] 0901[农学-作物学] 

基　　金：supported by the National Natural Science Foundation of China (61701260 and 62271266) the Postgraduate Research&Practice Innovation Program of Jiangsu Province (SJCX21_0255) the Postdoctoral Research Program of Jiangsu Province(2019K287) 

主　　题：Rice Precision agriculture Plant counting Deep learning Attention mechanism 

摘      要：Rice is a major food crop and is planted worldwide. Climatic deterioration, population growth, farmland shrinkage, and other factors have necessitated the application of cutting-edge technology to achieve accurate and efficient rice production. In this study, we mainly focus on the precise counting of rice plants in paddy field and design a novel deep learning network, RPNet, consisting of four modules: feature encoder, attention block, initial density map generator, and attention map generator. Additionally, we propose a novel loss function called RPloss. This loss function considers the magnitude relationship between different sub-loss functions and ensures the validity of the designed network. To verify the proposed method, we conducted experiments on our recently presented URC dataset, which is an unmanned aerial vehicle dataset that is quite challenged at counting rice plants. For experimental comparison, we chose some popular or recently proposed counting methods, namely MCNN, CSRNet, SANet, TasselNetV2, and FIDTM. In the experiment, the mean absolute error(MAE), root mean squared error(RMSE), relative MAE(rMAE) and relative RMSE(rRMSE) of the proposed RPNet were 8.3, 11.2, 1.2% and 1.6%, respectively,for the URC dataset. RPNet surpasses state-of-the-art methods in plant counting. To verify the universality of the proposed method, we conducted experiments on the well-know MTC and WED datasets. The final results on these datasets showed that our network achieved the best results compared with excellent previous approaches. The experiments showed that the proposed RPNet can be utilized to count rice plants in paddy fields and replace traditional methods.