RCTUnet：一种用于作物-残茬-土壤图像分割与秸秆覆盖度提取的深度学习模型

李婷; 刘杨; 冯海宽; 束美艳; 杨浩; 付元元; 许鑫; 林英豪; 乔红波; 郭伟; 马新明; 时雷; 岳继博

doi:10.1631/jzus.B2500451

Your Location：

Home >

Browse articles >

RCTUnet：一种用于作物-残茬-土壤图像分割与秸秆覆盖度提取的深度学习模型

Scan QR Code

文章被引用时，请邮件提醒。

Submit

Research Article | Updated：2026-05-15

RCTUnet：一种用于作物-残茬-土壤图像分割与秸秆覆盖度提取的深度学习模型
RCTUnet: a deep learning model for crop-residue-soil image segmentation and crop residue cover extraction
浙江大学学报（英文版）（B辑：生物医学和生物技术） 2026年27卷第5期页码：517-536
Affiliations：

1.College of Information and Management Science, Henan Agricultural University, Zhengzhou 450046, China
2.Institute of Quantitative Remote Sensing and Smart Agriculture, Henan Polytechnic University, Jiaozuo 454000, China
3.Key Laboratory of Quantitative Remote Sensing in Agriculture, Ministry of Agriculture and Rural Affairs, Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing 100097, China
4.Shenzhen Research Institute of Henan University, Shenzhen 450046, China
5.Henan Key Laboratory of Big Data Analysis and Processing, School of Computer and Information Engineering, Henan University, Kaifeng 475001, China
Funds：

the National Natural Science Foundation of China(42101362);the Natural Science Foundation of Henan Province(252300421158);the Shenzhen Science and Technology Program(JCYJ20220530162001003);the Science and Technology Development Program of Henan Province(242300421639)
DOI：10.1631/jzus.B2500451
中图分类号：
CSTR：
收稿：2025-07-29，

修回：2025-11-25，

纸质出版：2026-05-15
Accepted：

李婷,刘杨,冯海宽等.RCTUnet：一种用于作物-残茬-土壤图像分割与秸秆覆盖度提取的深度学习模型[J].浙江大学学报（英文版）（B辑：生物医学和生物技术）,2026,27(05):517-536.

Ting LI, Yang LIU, Haikuan FENG, et al. RCTUnet: a deep learning model for crop-residue-soil image segmentation and crop residue cover extraction[J]. Journal of Zhejiang University-SCIENCE B, 2026, 27(5): 517-536.
李婷,刘杨,冯海宽等.RCTUnet：一种用于作物-残茬-土壤图像分割与秸秆覆盖度提取的深度学习模型[J].浙江大学学报（英文版）（B辑：生物医学和生物技术）,2026,27(05):517-536. DOI： 10.1631/jzus.B2500451.

Ting LI, Yang LIU, Haikuan FENG, et al. RCTUnet: a deep learning model for crop-residue-soil image segmentation and crop residue cover extraction[J]. Journal of Zhejiang University-SCIENCE B, 2026, 27(5): 517-536. DOI： 10.1631/jzus.B2500451.

摘要

作物残茬覆盖度（crop residue cover

CRC）的准确量化对监测与评价保护性耕作至关重要，但面临图像分割难题。破碎残茬与土壤间细微的视觉差异，叠加田间图像中光照和阴影的变化干扰，常导致分割效果不佳。为突破上述局限，本研究提出了RCTUnet——一种专为作物-残茬-土壤稳健分割与精准CRC估算设计的新型深度学习架构。RCTUnet架构深度融合了三个关键模块：（1）ResNet50骨干网络用于深度多尺度特征提取；（2）卷积注意力模块（CBAM）实现通道和空间维度的显著残茬特征自适应聚焦；（3）基于transformer的全局上下文融合模块建模长距离空间依赖性，这对理解异质残茬分布模式至关重要。本研究在1220幅包含四种典型轮作模式的田间图像数据集上评估了RCTUnet模型。实验结果表明，相较传统模型（包括Unet、Unet++、DeepLabV3、SegNet和FCN）：（1）RCTUnet的作物-残茬-土壤分割精度优越性显著，整体准度分别提升3.24%、3.42%、4.88%、8.28%和6.05%；（2）RCTUnet在残茬-土壤分割性能上表现更优，残茬召回率分别提高7.67%、7.37%、14.09%、27.05%和16.91%；（3）RCTUnet显示出最强的CRC估算能力，均方根误差（RMSE）为4.875，较Unet（RMSE=8.941）提高了45.5%。这些结果验证了本研究提出的融合深度层次特征、双域注意力和全局上下文建模的混合架构的有效性。RCTUnet为自动化CRC评估提供了一种稳健可靠的工具，有助于提升田间农业监测能力。

Abstract

Accurate quantification of crop residue cover (CRC) is crucial for monitoring and evaluating conservation tillage practices

yet it poses a significant image segmentation challenge. The subtle visual distinctions between fragmented residue and soil

compounded by variable illumination and shadows in field imagery

often lead to poor segmentation performance. To overcome these limitations

we introduce RCTUnet

a novel deep learning architecture designed for robust crop-residue-soil segmentation and precise CRC estimation. RCTUnet’s architecture synergistically integrates three key components: (1) a ResNet50 backbone for deep

multi-scale feature extraction; (2) a convolutional block attention module (CBAM) to adaptively focus on salient residue features across both channel and spatial dimensions; and (3) a transformer-based global context fusion module (GCFM) to model long-range spatial dependencies

which is critical for interpreting heterogeneous residue patterns. We evaluated RCTUnet on a dataset of 1220 field-acquired images spanning four typical crop rotations. Experimental results show that

compared to traditional models: (1) RCTUnet achieves significantly higher crop-residue-soil segmentation accuracy than classic models including Unet

Unet++

DeepLabV3

segmentation network (SegNet)

and fully convolutional network (FCN)

with improvements of 3.24%

3.42%

4.88%

8.28%

and 6.05% in overall accuracy

respectively; (2) RCTUnet yields superior residue-soil segmentation performance

with increases in residue recall of 7.67%

7.37%

14.09%

27.05%

and 16.91%

respectively; (3) RCTUnet shows enhanced CRC estimation accuracy

achieving a root mean square error (RMSE) of 4.875

representing a 45.5% improvement over Unet (RMSE=8.941). These results demonstrate the efficacy of our hybrid approach

which combines deep hierarchical features

dual-domain attention

and global context modeling. RCTUnet provides a robust and reliable tool for automated CRC assessment

advancing the capabilities of in-field agricultural monitoring.

关键词

Keywords

references

Beeche C , Singh JP , Leader JK , et al. , 2022 . Super U-Net: a modularized generalizable architecture . Pattern Recognit , 128 : 108669 . https://doi.org/10.1016/j.patcog.2022.108669 https://doi.org/10.1016/j.patcog.2022.108669

Brosch T , Tang LYW , Yoo Y , et al. , 2016 . Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation . IEEE Trans Med Imaging 35 ( 5 ): 1229 - 1239 . https://doi.org/10.1109/TMI.2016.2528821 https://doi.org/10.1109/TMI.2016.2528821

Delandmeter M , Colinet G , Pierreux J , et al. , 2024 . Combining field measurements and process-based modelling to ana lyse soil tillage and crop residues management impacts on crop production and carbon balance in temperate areas. Soil Use Manage , 40 ( 3 ): e13098 . https://doi.org/10.1111/sum.13098 https://doi.org/10.1111/sum.13098

de Obade Paul Obade V , Gaya C , 2020 . Mapping tillage practices using spatial information techniques . Environ Manage , 66 ( 4 ): 722 - 731 . https://doi.org/10.1007/s00267-020-01335-z https://doi.org/10.1007/s00267-020-01335-z

Ding YL , Zhang HY , Wang ZQ , et al , 2020 . A comparison of estimating crop residue cover from Sentinel-2 data using empirical regressions and machine learning methods . Remote Sens , 12 ( 9 ): 1470 . https://doi.org/10.3390/rs12091470 https://doi.org/10.3390/rs12091470

Du L , Lu ZC , Li DL , 2022 . Broodstock breeding behaviour recognition based on Resnet50-LSTM with CBAM attention mechanism . Comput Electron Agric , 202 : 107404 . https://doi.org/10.1016/j.compag.2022.107404 https://doi.org/10.1016/j.compag.2022.107404

Feng YG , Han B , Wang XC , et al. , 2024 . Self-supervised transformers for unsupervised SAR complex interference detection using canny edge detector . Remote Sens , 16 ( 2 ): 306 . https://doi.org/10.3390/rs16020306 https://doi.org/10.3390/rs16020306

Gao GF , Zhang SX , Shen JN , et al. , 2024 . Segmentation and proportion extraction of crop, crop residues, and soil using digital images and deep learning . Agriculture , 14 ( 12 ): 2240 . https://doi.org/10.3390/agriculture14122240 https://doi.org/10.3390/agriculture14122240

Gao LL , Zhang C , Yun WJ , et al. , 2022 . Mapping crop residue cover using Adjust Normalized Difference Residue Index based on Sentinel-2 MSI data . Soil Tillage Res , 220 : 105374 . https://doi.org/10.1016/j.still.2022.105374 https://doi.org/10.1016/j.still.2022.105374

Gao PP , Song Y , Song MH , et al. , 2022 . Extract nanoporous gold ligaments from SEM images by combining fully convolutional network and Sobel operator edge detection algorithm . Scr Mater , 213 : 114627 . https://doi.org/10.1016/j.scriptamat.2022.114627 https://doi.org/10.1016/j.scriptamat.2022.114627

Han XJ , Cheng QB , Chen QZ , et al. , 2025 . Deep learning-based multi-category disease semantic image segmentation detection for concrete structures using the Res-Unet model . J Civil Struct Health Monit , 15 ( 5 ): 1369 - 1380 . https://doi.org/10.1007/s13349-024-00893-8 https://doi.org/10.1007/s13349-024-00893-8

Hively WD , Lamb BT , Daughtry CST , et al. , 2018 . Mapping crop residue and tillage intensity using WorldView-3 satellite shortwave infrared residue indices . Remote Sens , 10 ( 10 ): 1657 . https://doi.org/10.3390/rs10101657 https://doi.org/10.3390/rs10101657

Jin ZY , Hong WJ , Wang YR , et al. , 2025 . A transformer-based symmetric diffusion segmentation network for wheat growth monitoring and yield counting . Agriculture , 15 ( 7 ): 670 . https://doi.org/10.3390/agriculture15070670 https://doi.org/10.3390/agriculture15070670

Laamrani A , Pardo Lara R , Berg AA , et al. , 2018 . Using a mobile device “app” and proximal remote sensing technologies to assess soil cover fractions on agricultural fields . Sensors , 18 ( 3 ): 708 . https://doi.org/10.3390/s18030708 https://doi.org/10.3390/s18030708

Li K , Zhang YJ , Wang TF , et al. , 2025 . FreqUNet: a lightweight dual-branch network with frequency-aware decomposition for retinal vessel segmentation . Expert Syst Appl , 287 : 128124 . https://doi.org/10.1016/j.eswa.2025.128124 https://doi.org/10.1016/j.eswa.2025.128124

Li L , Li J , Lv CX , et al. , 2021 . Maize residue segmentation using Siamese domain transfer network . Comput Electron Agric , 187 : 106261 . https://doi.org/10.1016/j.compag.2021.106261 https://doi.org/10.1016/j.compag.2021.106261

Li YW , Zhao HS , Qi XJ , et al. , 2023 . Fully convolutional networks for panoptic segmentation with point-based supervision . IEEE Trans Pattern Anal Mach Intell , 45 ( 4 ): 4552 - 4568 . https://doi.org/10.1109/tpami.2022.3200416 https://doi.org/10.1109/tpami.2022.3200416

Liu J , Qiu TY , Peñuelas J , et al. , 2023 . Crop residue return sustains global soil ecological stoichiometry balance . Global Change Biol , 29 ( 8 ): 2203 - 2226 . https://doi.org/10.1111/gcb.16584 https://doi.org/10.1111/gcb.16584

Luo CH , Chen JP , Guo SX , et al. , 2022 . Development and application of a remote monitoring system for agricultural machinery operation in conservation tillage . Agriculture , 12 ( 9 ): 1460 . https://doi.org/10.3390/agriculture12091460 https://doi.org/10.3390/agriculture12091460

Mahmood MT , Ucan ON , 2025 . Data and image processing for intelligent glaucoma detection and optic disc segmentation using deep convolutional neural network architecture . Discov Comput , 28 : 73 . https://doi.org/10.1007/s10791-025-09587-1 https://doi.org/10.1007/s10791-025-09587-1

Pacheco A , McNairn H , 2010 . Evaluating multispectral remote sensing and spectral unmixing analysis for crop residue mapping . Remote Sens Environ , 114 ( 10 ): 2219 - 2228 . https://doi.org/10.1016/j.rse.2010.04.024 https://doi.org/10.1016/j.rse.2010.04.024

Qiang J , Liu WJ , Li XX , et al. , 2023 . Detection of citrus pests in double backbone network based on single shot multibox detector . Comput Electron Agric , 212 : 108158 . https://doi.org/10.1016/j.compag.2023.108158 https://doi.org/10.1016/j.compag.2023.108158

Serbin G , Hunt Jr ER , Daughtry CST , et al. , 2009 . An improved ASTER index for remote sensing of crop residue . Remote Sens , 1 ( 4 ): 971 - 991 . https://doi.org/10.3390/rs1040971 https://doi.org/10.3390/rs1040971

Shahi TB , Dahal S , Sitaula C , et al. , 2023 . Deep learning-based weed detection using UAV images: a comparative study . Drones , 7 ( 10 ): 624 . https://doi.org/10.3390/drones7100624 https://doi.org/10.3390/drones7100624

Shang CJ , Zhang D , Yang Y , 2021 . A gradient-based method for multilevel thresholding . Expert Syst Appl , 175 : 114845 . https://doi.org/10.1016/j.eswa.2021.114845 https://doi.org/10.1016/j.eswa.2021.114845

She QS , Sun SK , Ma YL , et al. , 2025 . LUCF-Net: lightweight U-shaped cascade fusion network for medical image segmentation . IEEE J Biomed Health Inform , 29 ( 3 ): 2088 - 2099 . https://doi.org/10.1109/jbhi.2024.3506829 https://doi.org/10.1109/jbhi.2024.3506829

Shi JF , Ji SS , Jin HY , et al. , 2025 . Multi-feature lightweight DeeplabV3+ network for polarimetric SAR image classification with attention mechanism . Remote Sens , 17 ( 8 ): 1422 . https://doi.org/10.3390/rs17081422 https://doi.org/10.3390/rs17081422

Song HH , Wang JQ , Bei JL , et al. , 2024 . Modified snake optimizer based multi-level thresholding for color image segmentation of agricultural diseases . Expert Syst Appl , 255 : 124624 . https://doi.org/10.1016/j.eswa.2024.124624 https://doi.org/10.1016/j.eswa.2024.124624

Song WY , Nie FX , Wang C , et al. , 2024 . Unsupervised multi-scale hybrid feature extraction network for semantic segmentation of high-resolution remote sensing images . Remote Sens , 16 ( 20 ): 3774 . https://doi.org/10.3390/rs16203774 https://doi.org/10.3390/rs16203774

Tao WC , Xie ZX , Zhang Y , et al. , 2021 . Corn residue covered area mapping with a deep learning method using Chinese GF-1 B/D high resolution remote sensing images . Remote Sens , 13 ( 15 ): 2903 . https://doi.org/10.3390/rs13152903 https://doi.org/10.3390/rs13152903

Wang FY , Lv CX , Jiang HL , et al. , 2025 . Efficient detection of corn straw coverage in complex agricultural scenarios . Comput Electron Agric , 235 : 110338 . https://doi.org/10.1016/j.compag.2025.110338 https://doi.org/10.1016/j.compag.2025.110338

Wang GD , Bai D , Lin HF , et al. , 2024 . FireViTNet: a hybrid model integrating ViT and CNNs for forest fire segmentation . Comput Electron Agric , 218 : 108722 . https://doi.org/10.1016/j.compag.2024.108722 https://doi.org/10.1016/j.compag.2024.108722

Wang GZ , Wang JP , Zou XY , et al. , 2019 . Estimating the fractional cover of photosynthetic vegetation, non-photosynthetic vegetation and bare soil from MODIS data: assessing the applicability of the NDVI-DFI model in the typical Xilingol grasslands . Int J Appl Earth Obs Geoinf , 76 : 154 - 166 . https://doi.org/10.1016/j.jag.2018.11.006 https://doi.org/10.1016/j.jag.2018.11.006

Wang YY , Gao XB , Sun Y , et al. , 2025 . Semantic segmentation-based conservation tillage corn straw return cover type recognition . Comput Electron Agric , 229 : 109792 . https://doi.org/10.1016/j.compag.2024.109792 https://doi.org/10.1016/j.compag.2024.109792

Xie EZ , Wang WH , Yu ZD , et al. , 2021 . SegFormer: simple and efficient design for semantic segmentation with Transformers . Advances in Neural Information Processing Systems , 34 : 12077 - 12090 . https://doi.org/10.48550/arXiv.2105.15203 https://doi.org/10.48550/arXiv.2105.15203

Xu JY , Zhou SY , Xu AJ , et al. , 2022 . Automatic scoring of postures in grouped pigs using depth image and CNN-SVM . Comput Electron Agric , 194 : 106746 . https://doi.org/10.1016/j.compag.2022.106746 https://doi.org/10.1016/j.compag.2022.106746

Yang H , Sun H , Wang K , et al. , 2025 . Enhanced farmland extraction from Gaofen-2: multi-scale segmentation, SVM integration, and multi-temporal analysis . Agriculture , 15 ( 10 ): 1073 . https://doi.org/10.3390/agriculture15101073 https://doi.org/10.3390/agriculture15101073

Yu FH , Bai JC , Fang JY , et al , 2024 . Integration of a parameter combination discriminator improves the accuracy of chlorophyll inversion from spectral imaging of rice . Agric Commun , 2 ( 3 ): 100055 . https://doi.org/10.1016/j.agrcom.2024.100055 https://doi.org/10.1016/j.agrcom.2024.100055

Yue JB , Tian QJ , 2020 . Estimating fractional cover of crop, crop residue, and soil in cropland using broadband remote sensing data and machine learning . Int J Appl Earth Obs Geoinf , 89 : 102089 . https://doi.org/10.1016/j.jag.2020.102089 https://doi.org/10.1016/j.jag.2020.102089

Yue JB , Tian QJ , Tang SF , et al. , 2019 . A dynamic soil endmember spectrum selection approach for soil and crop residue linear spectral unmixing analysis . Int J Appl Earth Obs Geoinf , 78 : 306 - 317 . https://doi.org/10.1016/j.jag.2019.02.001 https://doi.org/10.1016/j.jag.2019.02.001

Yue JB , Tian QJ , Liu Y , et al. , 2023 . Mapping cropland rice residue cover using a radiative transfer model and deep learning . Comput Electron Agric , 215 : 108421 . https://doi.org/10.1016/j.compag.2023.108421 https://doi.org/10.1016/j.compag.2023.108421

Yue JB , Li T , Feng HK , et al. , 2024 . Enhancing field soil moisture content monitoring using laboratory-based soil spectral measurements and radiative transfer models . Agric Commun , 2 ( 4 ): 100060 . https://doi.org/10.1016/j.agrcom.2024.100060 https://doi.org/10.1016/j.agrcom.2024.100060

Zhang TT , Hu DN , Wu CX , et al. , 2023 . Large-scale apple orchard mapping from multi-source data using the semantic segmentation model with image-to-image translation and transfer learning . Comput Electron Agric , 213 : 108204 . https://doi.org/10.1016/j.compag.2023.108204 https://doi.org/10.1016/j.compag.2023.108204

Zhang WQ , Li WJ , Wang C , et al. , 2025 . A novel index for mapping crop residue covered cropland using remote sensing data . Comput Electron Agric , 231 : 109995 . https://doi.org/10.1016/j.compag.2025.109995 https://doi.org/10.1016/j.compag.2025.109995

Zhao JL , Li Z , Lei Y , et al. , 2023 . Application of UAV RGB images and improved PSPNet network to the identification of wheat lodging areas . Agronomy , 13 ( 5 ): 1309 . https://doi.org/10.3390/agronomy13051309 https://doi.org/10.3390/agronomy13051309

Zheng XX , Cao F , Ou JY , et al. , 2024 . RSU-Net: a new method for fine classification of corn residue coverage in black soil area using Chinese GF-1B PMS image . Ecol Front , 44 ( 6 ): 1259 - 1268 . https://doi.org/10.1016/j.ecofro.2024.08.001 https://doi.org/10.1016/j.ecofro.2024.08.001

Zhou DY , Li M , Li Y , et al. , 2020 . Detection of ground straw coverage under conservation tillage based on deep learning . Comput Electron Agric , 172 : 105369 . https://doi.org/10.1016/j.compag.2020.105369 https://doi.org/10.1016/j.compag.2020.105369

Zhu QL , Wang K , Liang D , et al. , 2025 . WLUSNet: a lightweight wheat lodging segmentation network based on UAV image . Comput Electron Agric , 237 : 110587 . https://doi.org/10.1016/j.compag.2025.110587 https://doi.org/10.1016/j.compag.2025.110587

浏览量

Downloads

CSCD

工具集

关联资源

Deep learning-based phenology extraction and crop classification in arid oasis using Sentinel-2 time series

Improved lightweight convolutional neural network models for the detection and evaluation of Fusarium head blight in wheat

Recent advances in antibody optimization based on deep learning methods

表皮更新过程中的细胞增殖与分化

屈光手术患者TGFBI突变多重qPCR检测体系的建立