农业机械学报2026，Vol.57Issue(9)：289-298,10.DOI:10.6041/j.issn.1000-1298.2026.09.027
基于先验嵌入与多尺度特征融合的耕后水稻单根秸秆语义分割方法
Semantic Segmentation of Individual Straw Stalks after Plowing Based on Prior Embedding and Multi-scale Feature Fusion
摘要
Abstract
Straw coverage on the soil surface after tillage is a key parameter for evaluating the quality of straw return to the field.Existing methods struggle to effectively identify individual rice straw stalks.To address this,a semantic segmentation method that integrated prior embedding with multi-scale feature fusion was proposed to achieve accurate recognition of individual rice straw stalks.A fixed-threshold segmentation method based on color distance was employed to preprocess the original image and generate a prior map,providing prior information input for subsequent recognition tasks while suppressing background interference.An enhanced U-Net model,MRCF-DA-CDPE,was designed.It employed parallel multi-scale convolutions to capture information features across scales-from fragmented straw fragments to large straw clusters-while utilizing channel and spatial attention to select key features and suppress disturbances like soil bright spots.Continuous distance information from preprocessing was embedded into the network as an additional input channel,providing physical guidance for segmentation.Image preprocessing strategies demonstrated that this approach enhanced the average accuracy of each base model by 2～4 percentage points,with U-Net achieving the highest recognition accuracy.Validation tests of the improved model demonstrated that the MRCF-DA-CDPE model achieved 86.93％average intersection-over-union ratio(IOU),94.89％average precision,and 0.850 2 Kappa coefficient,representing improvements of 2.72,2.98 percentage points and 0.056 7 respectively over the baseline U-Net model.This method achieved precise recognition of individual straw stalks,providing technical support for straw return quality inspection and tillage effectiveness evaluation.关键词
水稻秸秆识别/语义分割/图像分割/深度学习/U-NetKey words
rice straw recognition/semantic segmentation/image segmentation/deep learning/U-Net分类
信息技术与安全科学引用本文复制引用
王昱,奚小波,丁杰源,韩连杰,邹贇涵,沈辉,张瑞宏..基于先验嵌入与多尺度特征融合的耕后水稻单根秸秆语义分割方法[J].农业机械学报,2026,57(9):289-298,10.基金项目
国家重点研发计划项目(2022YFD1500404)、江苏省重点研发计划项目(BE2022338)、江苏省农业科技自主创新资金项目(CX(24)1026)、江苏省现代农机装备与技术示范推广项目(NJ2025-02)和扬州大学"高端人才支持计划"项目 （2022YFD1500404）
