A point-supervised algorithm with multiscale semantic enhancement for counting multiple crop plants from aerial imagery
文献类型： 外文期刊
作者： Li, Huibin 1 ; Liu, Huaiyang 2 ; Wang, Wenbo 2 ; Wang, Haozhou 3 ; Yu, Qiangyi 1 ; Qian, Jianping 1 ; Wu, Wenbin 1 ; Shi, Yun 1 ; Geng, Changxing 2 ;
作者机构： 1.Chinese Acad Agr Sci, Inst Agr Resources & Reg Planning, State Key Lab Efficient Utilizat Arid & Semiarid A, Beijing 100086, Peoples R China
2.Soochow Univ, Sch Mech & Elect Engn, Suzhou 215000, Peoples R China
3.Univ Tokyo, Grad Sch Agr & Life Sci, Tokyo 1880002, Japan
4.Suzhou Zhongnong Digital Intelligence Technol Co L, Suzhou 215000, Peoples R China
关键词： Plant counting; Point supervision; Aerial imagery; Semantic enhancement; Density map
期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：8.9； 五年影响因子：9.3 ）
ISSN： 0168-1699
年卷期： 2025 年 234 卷
页码：
收录情况： SCI
摘要： Counting crop plants is important for agricultural activities such as crop breeding and yield prediction. Numerous studies have developed methods for counting individual crop plants or those with similar morphological characteristics. However, these methods often face challenges of low accuracy and poor generalization when counting multiple crop plants with significant scale variations in complex backgrounds. Hence, we proposed MCPCNet, a point-supervised algorithm that enhances multiscale semantics for counting multiple crop plants from aerial imagery. We also constructed the first dataset of multicategory crop plant counting (MCPCDataset). We developed a concurrent spatial group enhancement module, a residual dynamic dilated convolution module, and introduced the contextual transformer module with self-attention mechanism. These modules can reduce the impact of background, adapt to scale variations of multiple crops, and enhance the robustness of our algorithm, respectively. The experiment results on the MCPC-Dataset indicate that MCPCNet achieves excellent performance, with a mean absolute error (MAE) of 2.577, a mean square error (MSE) of 14.289, and a coefficient of determination (R2) of 0.991. MCPCNet also has a clear advantage over the state-of-the-art (SOTA) pointsupervised counting algorithm. In conclusion, MCPCNet provides a robust solution for high-precision counting of multiple crop plants and is a vital reference for future related research.
- 相关文献
作者其他论文 更多>>
-
Dynamic multi-objective time-temperature management for climacteric fruit cold storage considering ripeness windows and energy consumption
作者：Chen, Qian;Qian, Jianping;Li, Huibin;Lin, Xintao;Li, Jiali;Chen, Qian;Qian, Jianping;Li, Huibin;Lin, Xintao;Li, Jiali;Liu, Zihan;Zhao, Zhiyao
关键词：Climacteric fruit; Cold storage; Dynamic multi-objective optimization; Time-temperature management; Sustainability
-
Extreme surface solar ultraviolet radiation events reduce maize yields in China
作者：Guan, Haixiang;Huang, Jianxi;Li, Xuecao;Zeng, Yelu;Su, Wei;Miao, Shuangxi;Zhu, Peng;Huang, Jianxi;Huang, Jianxi;Li, Xuecao;Zeng, Yelu;Su, Wei;Miao, Shuangxi;Jin, Zhenong;Ma, Yuyang;Wu, Wenbin;Wu, Wenbin;Wu, Bingfang;Wu, Bingfang
关键词：
-
Field-scale irrigated winter wheat mapping using a novel cross-region slope length index in 3D canopy hydrothermal and spectral feature space
作者：Zhang, Youming;Yang, Guijun;Li, Zhenhong;Liu, Miao;Zhang, Jing;Gao, Meiling;Zhu, Wu;Zhang, Youming;Yang, Guijun;Yang, Xiaodong;Song, Xiaoyu;Long, Huiling;Liu, Miao;Meng, Yang;Thenkabail, Prasad S.;Wu, Wenbin;Zuo, Lijun;Meng, Yang
关键词：Winter wheat; Irrigation mapping; Hydrothermal and spectral feature; Cross-region; Rainfed line; Slope Length Index
-
Optimizing plant density to improve the soil microenvironment and enhance crop productivity in cotton/cumin intercropping systems
作者：Zhang, Humei;Li, Nannan;Shi, Xiaojuan;Shi, Feng;Tian, Yu;Luo, Honghai;Zhang, Humei;Tian, Liwen;Hao, Xianzhe;Wang, Wenbo
关键词：cotton/cumin intercropping; density; soil environment; crop productivity; nonfilm cotton
-
Customized crop feature construction using genetic programming for early-and in-season crop mapping☆
作者：Wen, Caiyun;Lu, Miao;Xia, Lang;Sun, Jing;Shi, Yun;Wei, Yanbing;Wu, Wenbin;Lu, Miao;Bi, Ying;Bi, Ying
关键词：Remote Sensing; Crop mapping; Genetic Programming; Feature Construction; Customized feature
-
Integrating Historical Crop Rotation Changes Into Soil Organic Matter Mapping in the Cropland of Southeastern China
作者：Zhou, Furong;Xue, Jie;Wang, Zheng;Jin, Wuze;Shi, Zhou;Zhou, Lianqing;Chen, Songchao;Zhou, Furong;Xue, Jie;Wang, Zheng;Jin, Wuze;Shi, Zhou;Zhou, Lianqing;Chen, Songchao;Shi, Zhou;Yu, Qiangyi
关键词：digital soil mapping; soil organic matter; crop rotation changes; remote sensing; machine learning
-
Identify Tea Plantations Using Multidimensional Features Based on Multisource Remote Sensing Data: A Case Study of the Northwest Mountainous Area of Hubei Province
作者：Xiao, Pengnan;Qian, Jianping;Yu, Qiangyi;Lin, Xintao;Xu, Jie;Liu, Yujie
关键词：Google Earth Engine; tea plantation; Sentinel-1; Sentinel-2; feature selection
