基于Vision Transformer-LSTM(ViTL)的多时序遥感影像农作物分类方法OACSTPCD
A crop classification method based on vision Transformer-LSTM(ViTL)for multi-temporal remote sensing images
针对当前遥感农作物分类研究中深度学习模型对光谱时间和空间信息特征采样不足,农作物提取仍然存在边界模糊、漏提、误提的问题,提出了一种名为视觉Transformer-长短期记忆递归神经网络(Vision Transformer-long short term memory,ViTL)的深度学习模型,ViTL模型集成了双路Vision-Transformer特征提取、时空特征融合和长短期记忆递归神经网络(LSTM)时序分类等3个关键模块,双路Visio…查看全部>>
For the current research in remote sensing crop classification using deep learning models,there exists an inadequacy in sampling temporal and spatial information features,leads to challenges in accurately extracting crops due to issues such as boundary fuzziness,omissions,and misclassifications.In this study,we propose a deep learning model called Vision Transformer-long short term memory(ViTL)to addresses these challenges.The ViTL model integrated three key…查看全部>>
张青云;杨辉;李兴伍;武永闯
安徽大学资源与环境工程学院,合肥 230601安徽大学物质科学与信息技术研究院,合肥 230601安徽大学人工智能学院,合肥 230601安徽大学人工智能学院,合肥 230601
农业科学
农作物分类Vision Transformer(ViT)LSTM深度学习遥感监测
crop classificationvision transformer(ViT)LSTMdeep learningremote sensing monitoring
《安徽农业大学学报》 2024 (5)
888-898,11
国家自然科学基金(42101381)和安徽省重点研发国际合作项目(202104b11020022)共同资助.
评论