摘要
传统方法提取细小水体的效果差、精度低,难以满足实际需求,该文以洱海流域的吉林一号国产高分卫星影像为数据源,提出一种改进DeepLabV3plus的深度学习语义分割方法,将编码结构ResNet101替换成EfficientNet-B4,创新性地将二元交叉熵损失(binary cross-entropy loss,BCE Loss)和Dice Loss损失函数进行联合,筛选出了洱海流域精细提取水体的最优方法。结果表明:(1)改进DeepLabV3plus模型较传统方法提取的水体边界效果更佳,更能准确识别主要水体,尤其在细小溪流的提取上表现优于传统方法;(2)改进DeepLabV3plus模型在精确率(98.87%)、召回率(99.30%)和F1分数(99.08%)上均高于归一化差异水体指数(normalized difference water index,NDWI)和面向对象法;(3)在细节对比中,改进的DeepLabV3plus能够有效抑制建筑物阴影、植被遮挡以及复杂地物的影响,提升了细小水体和复杂边缘区域的提取效果。此外,消融实验表明,联合损失函数与复合缩放策略的引入分别将平均交并比提升了0.62和3.07百分点,显著提高了模型的分割精度与对多尺度语义信息的提取能力。
Traditional methods for information extraction of small water bodies suffer from poor performance and low accuracy,failing to meet actual needs.Using the high-resolution images of the Erhai Lake basin from the Jilin-1 domestic satellite as the data source,this study proposed a deep learning-based semantic segmentation method using an improved DeepLabV3plus model.Replacing the ResNet-101 encoder with EfficientNet-B4,this study innovatively combined the BCE Loss and Dice Loss functions,identifying the optimal method for fine-scale information extraction of water bodies in the Erhai Lake Basin.The results indicate that compared to traditional methods,the improved DeepLabV3plus model performed better in the information extraction of water boundaries,enabling accurate identification of main water bodies,especially small streams.The improved DeepLabV3plus model exhibited higher precision(98.87%),recall(99.30%),and F1-Score(99.08%)than the normalized difference water index(NDWI)and object-oriented methods.Regarding comparison of details,the improved DeepLabV3plus model can effectively suppress the influence of building shadows,vegetation occlusion,and complex surface features,improving the information extraction effects of small water bodies and complex edge areas.In addition,ablation experiments show that the introduction of the combined loss functions and compound scaling strategy increased mIoU by 0.62%and 3.07%,respectively,significantly enhancing the model's segmentation accuracy and ability to extract multi-scale semantic information.
作者
张莹
陈运春
郭晓飞
吴晓聪
陈凤林
曾维军
ZHANG Ying;CHEN Yunchun;GUO Xiaofei;WU Xiaocong;CHEN Fenglin;ZENG Weijun(College of Water Conservancy,Yunnan Agricultural University,Kunming 650201,China;Green Smart Agricultural Field and Carbon Emission Reduction Engineering Research Center of University in Yunnan Province,Kunming 650201,China;International Joint Research and Development Centre for Smart Agriculture and Water Security in Yunnan,Kunming 650201,China;Field Scientific Observation and Research Station of Yunnan Intermountain Basin Land Utilization of Ministry of Natural Resources,Kunming 650201,China)
出处
《自然资源遥感》
北大核心
2025年第6期201-210,共10页
Remote Sensing for Natural Resources
基金
国家自然科学基金项目“洱海典型流域水系网络-布局时空演化机理及其生态调控”(编号:42361043)
云南省教育厅科学研究基金项目“基于DeepLabV3plus模型和吉林一号高分影像的洱海水体精细提取方法研究”(编号:2025Y0528)共同资助。
关键词
改进DeepLabV3plus
高分遥感影像
语义分割
洱海流域
水体提取
improved DeepLabV3plus
high-resolution remote sensing image
semantic segmentation
Erhai Lake Basin
water body information extraction
