文献类型： 外文期刊

作者： Gao, Guangfu ¹ ; Zhang, Shanxin ² ; Shen, Jianing ¹ ; Hu, Kailong ³ ; Tian, Jia ⁴ ; Yao, Yihan ¹ ; Tian, Qingjiu ⁵ ; Fu, Yuanyuan ¹ ; Feng, Haikuan ⁶ ; Liu, Yang ⁶ ; Yue, Jibo 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.Minist Emergency Management, Key Lab Emergency Satellite Engn & Applicat, Beijing 100124, Peoples R China

4.Beihang Univ, Sch Instrumentat & Optoelect Engn, Beijing 100191, Peoples R China

5.Nanjing Univ, Int Inst Earth Syst Sci, Nanjing 210023, Peoples R China

6.Minist Agr, Beijing Res Ctr Informat Technol Agr, Key Lab Quantitat Remote Sensing Agr, Beijing 100097, Peoples R China

7.China Agr Univ, Key Lab Smart Agr Syst, Minist Educ, Beijing 100083, Peoples R China

关键词： image segmentation; proportion extraction; deep learning; crop residue coverage

期刊名称：AGRICULTURE-BASEL （ 影响因子：3.6； 五年影响因子：3.8 ）

ISSN：

年卷期： 2024 年 14 卷 12 期

页码：

收录情况： SCI

摘要： Conservation tillage involves covering the soil surface with crop residues after harvest, typically through reduced or no-tillage practices. This approach increases the soil organic matter, improves the soil structure, prevents erosion, reduces water loss, promotes microbial activity, and enhances root development. Therefore, accurate information on crop residue coverage is critical for monitoring the implementation of conservation tillage practices. This study collected "crop-crop residues-soil" images from wheat-soybean rotation fields using mobile phones to create calibration, validation, and independent validation datasets. We developed a deep learning model named crop-crop residue-soil segmentation network (CCRSNet) to enhance the performance of cropland "crop-crop residues-soil" image segmentation and proportion extraction. The model enhances the segmentation accuracy and proportion extraction by extracting and integrating shallow and deep image features and attention modules to capture multi-scale contextual information. Our findings indicated that (1) lightweight models outperformed deeper networks for "crop-crop residues-soil" image segmentation. When CCRSNet employed a deep network backbone (ResNet50), its feature extraction capability was inferior to that of lighter models (VGG16). (2) CCRSNet models that integrated shallow and deep features with attention modules achieved a high segmentation and proportion extraction performance. Using VGG16 as the backbone, CCRSNet achieved an mIoU of 92.73% and a PA of 96.23% in the independent validation dataset, surpassing traditional SVM and RF models. The RMSE for the proportion extraction accuracy ranged from 1.05% to 3.56%. These results demonstrate the potential of CCRSNet for the accurate, rapid, and low-cost detection of crop residue coverage. However, the generalizability and robustness of deep learning models depend on the diversity of calibration datasets. Further experiments across different regions and crops are required to validate this method's accuracy and applicability for "crop-crop residues-soil" image segmentation and proportion extraction.