改进DeepLab v3+模型下的梯田遥感提取研究  

Remote Sensing Extraction Method of Terraced Fields Based on Improved DeepLab v3+

作　　者：张俊[1] 陈雨艳 秦震宇 张梦瑶 张军[1] ZHANG Jun;CHEN Yuyan;QIN Zhenyu;ZHANG Mengyao;ZHANG Jun(School of Earth Sciences,Yunnan University,Kunming 650500,China;Institute of International Rivers and Eco-security,Yunnan University,Kunming 650500,China)

机构地区：[1]云南大学地球科学学院,云南昆明650500 [2]云南大学国际河流与生态安全研究院,云南昆明650500

出　　处：《智慧农业（中英文）》2024年第3期46-57,共12页Smart Agriculture

基　　金：国防科技工业局高分专项云南省政府综合治理深度应用与规模化产业化示范项目(89-Y50G31-9001-22/23);云南大学研究生科研创新基金(KC-22222840)。

摘　　要：[目的与意义]梯田作为农业生产的关键要素之一,其面积估算对于农业政策制定、土地规划和资源管理至关重要。为解决复杂的地形条件、种植环境导致传统遥感数据和监测方法难以开展梯田自动化提取问题,探索一种利用深度学习技术在高分辨率遥感影像中精准提取梯田面积的方法。[方法]以休耕期梯田高分六号影像构建语义分割数据集,同时提出一种改进的DeepLab v3+模型。该模型使用轻量级网络MobileNet v2作为骨干网络,为了同时兼顾局部细节和全局语境,使用多尺度特征融合(Multi-scale Feature Fusion module,MSFF)模块代替空洞空间金字塔池化(Atrous Spatial Pyramid Pooling,ASPP)模块,利用扩张率依次增大的空洞卷积级联模式改善信息丢失的问题。此外,对浅层特征和深层特征使用坐标注意力机制以加强网络对于目标的学习。[结果与讨论]利用红、绿和近红外波段组合方式在梯田提取的精度和效果上表现最佳。相比于原始DeepLab v3+网络,精确率、召回率、F_(1)评分和交并比指标分别提升4.62%、2.61%、3.81%和2.81%。此外,与UNet和原始DeepLab v3+相比,改进的DeepLab v3+在参数量上和浮点运算数有着更为优越的性能,其参数量仅为UNet的28.6%和原始DeepLab v3+的19.5%,同时浮点运算数仅为UNet和DeepLab v3+的1/5。这不仅提高了计算效率,也使得改进后的模型更适用于资源有限或计算能力较低的环境中。[结论]深度学习在高分辨率遥感影像梯田识别中具有较高的精度,有利于为梯田精细化监测和管理提供参考依据。[Objective]The accurate estimation of terraced field areas is crucial for addressing issues such as slope erosion control,water retention,soil conservation,and increasing food production.The use of high-resolution remote sensing imagery for terraced field informa‐tion extraction holds significant importance in these aspects.However,as imaging sensor technologies continue to advance,traditional methods focusing on shallow features may no longer be sufficient for precise and efficient extraction in complex terrains and environ‐ments.Deep learning techniques offer a promising solution for accurately extracting terraced field areas from high-resolution remote sensing imagery.By utilizing these advanced algorithms,detailed terraced field characteristics with higher levels of automation can be better identified and analyzed.The aim of this research is to explore a proper deep learning algorithm for accurate terraced field area extraction in high-resolution remote sensing imagery.[Methods]Firstly,a terraced dataset was created using high-resolution remote sensing images captured by the Gaofen-6 satellite dur‐ing fallow periods.The dataset construction process involved data preprocessing,sample annotation,sample cropping,and dataset par‐titioning with training set augmentation.To ensure a comprehensive representation of terraced field morphologies,14 typical regions were selected as training areas based on the topographical distribution characteristics of Yuanyang county.To address misclassifica‐tions near image edges caused by limited contextual information,a sliding window approach with a size of 256 pixels and a stride of 192 pixels in each direction was utilized to vary the positions of terraced fields in the images.Additionally,geometric augmentation techniques were applied to both images and labels to enhance data diversity,resulting in a high-resolution terraced remote sensing da‐taset.Secondly,an improved DeepLab v3+model was proposed.In the encoder section,a lightweight MobileNet v2 was utilized in�

关 键 词：梯田提取 遥感 卷积神经网络 高分六号卫星 DeepLab v3+ 

分 类 号：S127[农业科学—农业基础科学]