Segmentation and Fractional Coverage Estimation of Soil, Illuminated Vegetation, and Shaded Vegetation in Corn Canopy Images Using CCSNet and UAV Remote Sensing
文献类型： 外文期刊
作者： Zhang, Shanxin 1 ; Yue, Jibo 1 ; Wang, Xiaoyan 3 ; Feng, Haikuan 4 ; Liu, Yang 6 ; Shu, Meiyan 1 ;
作者机构： 1.Henan Agr Univ, Coll Informat & Management Sci, Zhengzhou 450002, Peoples R China
2.Beijing Forestry Univ, Sch Informat Sci & Technol, Beijing 100083, Peoples R China
3.China Ctr Resources Satellite Data & Applicat, Beijing 100094, Peoples R China
4.Beijing Acad Agr & Forestry Sci, Informat Technol Res Ctr, Key Lab Quantitat Remote Sensing Agr, Minist Agr & Rural Affairs, Beijing 100097, Peoples R China
5.Nanjing Agr Univ, Coll Agr, Nanjing 210095, Peoples R China
6.China Agr Univ, Key Lab Smart Agr Syst, Minist Educ, Beijing 100083, Peoples R China
关键词： segmentation; digital camera; corn; deep learning
期刊名称：AGRICULTURE-BASEL （ 影响因子：3.6； 五年影响因子：3.8 ）
ISSN：
年卷期： 2025 年 15 卷 12 期
页码：
收录情况： SCI
摘要： The accurate estimation of corn canopy structure and light conditions is essential for effective crop management and informed variety selection. This study introduces CCSNet, a deep learning-based semantic segmentation model specifically developed to extract fractional coverages of soil, illuminated vegetation, and shaded vegetation from high-resolution corn canopy images acquired by UAVs. CCSNet improves segmentation accuracy by employing multi-level feature fusion and pyramid pooling to effectively capture multi-scale contextual information. The model was evaluated using Pixel Accuracy (PA), mean Intersection over Union (mIoU), and Recall, and was benchmarked against U-Net, PSPNet and UNetFormer. On the test set, CCSNet utilizing a ResNet50 backbone achieved the highest accuracy, with an mIoU of 86.42% and a PA of 93.58%. In addition, its estimation of fractional coverage for key canopy components yielded a root mean squared error (RMSE) ranging from 3.16% to 5.02%. Compared to lightweight backbones (e.g., MobileNetV2), CCSNet exhibited superior generalization performance when integrated with deeper backbones. These results highlight CCSNet's capability to deliver high-precision segmentation and reliable phenotypic measurements. This provides valuable insights for breeders to evaluate light-use efficiency and facilitates intelligent decision-making in precision agriculture.
- 相关文献
作者其他论文 更多>>
-
Genotyping Identification of Maize Based on Three-Dimensional Structural Phenotyping and Gaussian Fuzzy Clustering
作者：Xu, Bo;Zhao, Chunjiang;Xu, Bo;Zhao, Chunjiang;Yang, Guijun;Zhang, Yuan;Liu, Changbin;Feng, Haikuan;Yang, Xiaodong;Yang, Hao;Xu, Bo;Zhao, Chunjiang;Yang, Guijun;Zhang, Yuan;Liu, Changbin;Feng, Haikuan;Yang, Xiaodong;Yang, Hao
关键词：tassel; 3D phenotyping; TreeQSM; genotyping; clustering
-
Sensitivity Analysis of AquaCrop Model Parameters for Winter Wheat under Different Meteorological Conditions Based on the EFAST Method
作者：Xing, Huimin;Sun, Qi;Li, Zhiguo;Wang, Zhen;Xing, Huimin;Wang, Zhen;Xing, Huimin;Sun, Qi;Wang, Zhen;Li, Zhiguo;Feng, Haikuan
关键词：winter wheat; biomass; sensitivity analysis; AquaCrop model
-
Estimation of Leaf Chlorophyll Content of Maize from Hyperspectral Data Using E2D-COS Feature Selection, Deep Neural Network, and Transfer Learning
作者：Chen, Riqiang;Feng, Haikuan;Hu, Haitang;Chen, Riqiang;Ren, Lipeng;Yang, Guijun;Cheng, Zhida;Zhao, Dan;Zhang, Chengjian;Feng, Haikuan;Hu, Haitang;Yang, Hao;Chen, Riqiang;Zhang, Chengjian;Ren, Lipeng;Feng, Haikuan
关键词：maize; chlorophyll; radiative transfer model; feature selection; transfer learning
-
Combining UAV Remote Sensing with Ensemble Learning to Monitor Leaf Nitrogen Content in Custard Apple (Annona squamosa L.)
作者：Jiang, Xiangtai;Xu, Xingang;Wu, Wenbiao;Yang, Guijun;Meng, Yang;Feng, Haikuan;Li, Yafeng;Xue, Hanyu;Chen, Tianen;Jiang, Xiangtai;Xu, Xingang;Gao, Lutao
关键词：canopy nitrogen content; UAV remote sensing; ensemble learning; Lasso model
-
Retrieving the chlorophyll content of individual apple trees by reducing canopy shadow impact via a 3D radiative transfer model and UAV multispectral imagery
作者：Zhang, Chengjian;Chen, Zhibo;Chen, Riqiang;Zhang, Wenjie;Zhang, Chengjian;Chen, Riqiang;Zhang, Wenjie;Zhao, Dan;Yang, Guijun;Xu, Bo;Feng, Haikuan;Yang, Hao
关键词：Chlorophyll content; Shadows; Vegetation index (VI); Radiative transfer models (RTMs); Hybrid inversion model; Individual apple tree crown
-
Enhancing potato leaf protein content, carbon-based constituents, and leaf area index monitoring using radiative transfer model and deep learning
作者：Feng, Haikuan;Fan, Yiguang;Ma, Yanpeng;Liu, Yang;Chen, Riqiang;Bian, Mingbo;Fan, Jiejie;Yang, Guijun;Zhao, Chunjiang;Feng, Haikuan;Zhao, Chunjiang;Yue, Jibo;Fu, Yuanyuan;Leng, Mengdie;Jin, Xiuliang;Zhao, Yu
关键词：Potato; Deep learning; Radiative transfer model; Transfer learning; Leaf protein content
-
Winter wheat harvest detection via Sentinel-2 MSI images
作者：Yue, Jibo;Yao, Yihan;Shen, Jianing;Li, Ting;Wei, Yihao;Xu, Xin;Guo, Wei;Fu, Yuanyuan;Qiao, Hongbo;Ma, Xinming;Wang, Jian;Xu, Nianxu;Feng, Haikuan;Feng, Haikuan;Lin, Yinghao;Lin, Yinghao
关键词：Wheat; maturity; harvest; monitoring; vegetation index
