RPNet: Rice plant counting after tillering stage based on plant attention and multiple supervision network
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...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2023-10-01
|
| Series: | Crop Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214514123000557 |
| _version_ | 1827793579588714496 |
|---|---|
| author | Xiaodong Bai Susong Gu Pichao Liu Aiping Yang Zhe Cai Jianjun Wang Jianguo Yao |
| author_facet | Xiaodong Bai Susong Gu Pichao Liu Aiping Yang Zhe Cai Jianjun Wang Jianguo Yao |
| author_sort | Xiaodong Bai |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-11T18:19:31Z |
| format | Article |
| id | doaj.art-d92850be09974cfbbb13ac27c9d59a7e |
| institution | Directory Open Access Journal |
| issn | 2214-5141 |
| language | English |
| last_indexed | 2024-03-11T18:19:31Z |
| publishDate | 2023-10-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Crop Journal |
| spelling | doaj.art-d92850be09974cfbbb13ac27c9d59a7e2023-10-16T04:12:25ZengKeAi Communications Co., Ltd.Crop Journal2214-51412023-10-0111515861594RPNet: Rice plant counting after tillering stage based on plant attention and multiple supervision networkXiaodong Bai0Susong Gu1Pichao Liu2Aiping Yang3Zhe Cai4Jianjun Wang5Jianguo Yao6School of Computer Science and Technology, Hainan University, Haikou 570228, Hainan, ChinaInstitute of Advanced Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, Jiangsu, China; Corresponding author.Institute of Advanced Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, Jiangsu, ChinaAgricultural Meteorological Center, Jiangxi Meteorological Bureau, Nanchang 330045, Jiangxi, ChinaAgricultural Meteorological Center, Jiangxi Meteorological Bureau, Nanchang 330045, Jiangxi, ChinaAgricultural Meteorological Center, Jiangxi Meteorological Bureau, Nanchang 330045, Jiangxi, ChinaInstitute of Advanced Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, Jiangsu, ChinaRice 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.http://www.sciencedirect.com/science/article/pii/S2214514123000557RicePrecision agriculturePlant countingDeep learningAttention mechanism |
| spellingShingle | Xiaodong Bai Susong Gu Pichao Liu Aiping Yang Zhe Cai Jianjun Wang Jianguo Yao RPNet: Rice plant counting after tillering stage based on plant attention and multiple supervision network Crop Journal Rice Precision agriculture Plant counting Deep learning Attention mechanism |
| title | RPNet: Rice plant counting after tillering stage based on plant attention and multiple supervision network |
| title_full | RPNet: Rice plant counting after tillering stage based on plant attention and multiple supervision network |
| title_fullStr | RPNet: Rice plant counting after tillering stage based on plant attention and multiple supervision network |
| title_full_unstemmed | RPNet: Rice plant counting after tillering stage based on plant attention and multiple supervision network |
| title_short | RPNet: Rice plant counting after tillering stage based on plant attention and multiple supervision network |
| title_sort | rpnet rice plant counting after tillering stage based on plant attention and multiple supervision network |
| topic | Rice Precision agriculture Plant counting Deep learning Attention mechanism |
| url | http://www.sciencedirect.com/science/article/pii/S2214514123000557 |
| work_keys_str_mv | AT xiaodongbai rpnetriceplantcountingaftertilleringstagebasedonplantattentionandmultiplesupervisionnetwork AT susonggu rpnetriceplantcountingaftertilleringstagebasedonplantattentionandmultiplesupervisionnetwork AT pichaoliu rpnetriceplantcountingaftertilleringstagebasedonplantattentionandmultiplesupervisionnetwork AT aipingyang rpnetriceplantcountingaftertilleringstagebasedonplantattentionandmultiplesupervisionnetwork AT zhecai rpnetriceplantcountingaftertilleringstagebasedonplantattentionandmultiplesupervisionnetwork AT jianjunwang rpnetriceplantcountingaftertilleringstagebasedonplantattentionandmultiplesupervisionnetwork AT jianguoyao rpnetriceplantcountingaftertilleringstagebasedonplantattentionandmultiplesupervisionnetwork |