全部
图书
期刊
学位论文
会议论文
报纸
图片
视频
新闻
关键词
- EGMT-CD: Edge-Guided Multimodal Transformers Change Detection from Satellite and Aerial Images
- 作者： Yunfan Xiang Xiangyu Tian Yue Xu Xiaokun Guan Zhengchao Chen 来源： Remote Sensing 年份： 2023 文献类型 ： 期刊 关键词： sensing detection images edge Transformer feature change remote alignment heterogeneous
- 描述： Change detection from heterogeneous satellite and aerial images plays a progressively important role in many fields, including disaster assessment, urban construction, and land use monitoring. Currently, researchers have mainly devoted their attention to change detection using homologous image pairs and achieved many remarkable results. It is sometimes necessary to use heterogeneous images for change detection in practical scenarios due to missing images, emergency situations, and cloud and fog occlusion. However, heterogeneous change detection still faces great challenges, especially using satellite and aerial images. The main challenges in satellite and aerial image change detection are related to the resolution gap and blurred edge. Previous studies used interpolation or shallow feature alignment before traditional homologous change detection methods, which ignored the high-level feature interaction and edge information. Therefore, we propose a new heterogeneous change detection model based on multimodal transformers combined with edge guidance. In order to alleviate the resolution gap between satellite and aerial images, we design an improved spatially aligned transformer (SP-T) with a sub-pixel module to align the satellite features to the same size of the aerial ones supervised by a token loss. Moreover, we introduce an edge detection branch to guide change features using the object edge with an auxiliary edge-change loss. Finally, we conduct considerable experiments to verify the effectiveness and superiority of our proposed model (EGMT-CD) on a new satellite–aerial heterogeneous change dataset, named SACD. The experiments show that our method (EGMT-CD) outperforms many previously superior change detection methods and fully demonstrates its potential in heterogeneous change detection from satellite–aerial images.
- EGMT-CD: Edge-Guided Multimodal Transformers Change Detection from Satellite and Aerial Images
- 作者： Yunfan Xiang Xiangyu Tian Yue Xu Xiaokun Guan Zhengchao Chen 来源： Remote Sensing 年份： 2023 文献类型 ： 期刊 关键词： sensing detection images edge Transformer feature change remote alignment heterogeneous
- 描述： Change detection from heterogeneous satellite and aerial images plays a progressively important role in many fields, including disaster assessment, urban construction, and land use monitoring. Currently, researchers have mainly devoted their attention to change detection using homologous image pairs and achieved many remarkable results. It is sometimes necessary to use heterogeneous images for change detection in practical scenarios due to missing images, emergency situations, and cloud and fog occlusion. However, heterogeneous change detection still faces great challenges, especially using satellite and aerial images. The main challenges in satellite and aerial image change detection are related to the resolution gap and blurred edge. Previous studies used interpolation or shallow feature alignment before traditional homologous change detection methods, which ignored the high-level feature interaction and edge information. Therefore, we propose a new heterogeneous change detection model based on multimodal transformers combined with edge guidance. In order to alleviate the resolution gap between satellite and aerial images, we design an improved spatially aligned transformer (SP-T) with a sub-pixel module to align the satellite features to the same size of the aerial ones supervised by a token loss. Moreover, we introduce an edge detection branch to guide change features using the object edge with an auxiliary edge-change loss. Finally, we conduct considerable experiments to verify the effectiveness and superiority of our proposed model (EGMT-CD) on a new satellite–aerial heterogeneous change dataset, named SACD. The experiments show that our method (EGMT-CD) outperforms many previously superior change detection methods and fully demonstrates its potential in heterogeneous change detection from satellite–aerial images.
- 基于神经网络的遥感图像飞机实时检测算法
- 作者： 刘志 杨江涛 许新云 来源： 工业控制计算机 年份： 2024 文献类型 ： 期刊 关键词： 遥感图像 注意力机制 YOLOv4 MobileNetv3 深度可分离卷积
- 描述： 情况下，减少参数量；同时在路聚合网络（PANet）中使用深度可分离卷积代替传统卷积；在主干网络中引入BAM注意力机制，提高整体模型的泛化能力。然后对NMS网络进行了优化，以提升模型的最终识别精度。最后在
- 基于BiGRU-Attention改进的航空设备故障知识图谱构建
- 作者： 陈勇刚 刘康妮 王帅 来源： 航空学报 年份： 2024 文献类型 ： 期刊 关键词： 注意力机制 双向门控循环神经网络 故障诊断 航空设备故障 知识图谱
- 描述： 针对航空设备故障数据量庞大且传统故障诊断方法低效的问题，利用知识图谱技术构建高性能图数据库来替代传统民机所用的关系数据库以提高故障诊断决策效率，并通过一种以注意力机制（Attention）结合
- 一种基于TCN-LGBM的航空发动机气路故障诊断方法
- 作者： 吕卫民 孙晨峰 任立坤 赵杰 李永强 来源： 兵工学报 年份： 2024 文献类型 ： 期刊 关键词： 轻量级梯度提升机 注意力机制 航空发动机 故障诊断 时间卷积神经网络
- 描述： 分为故障特征提取和分类诊断两个过程：引入TCN框架，在保证故障数据训练时序逻辑的基础上，实现对远层历史信息和当前层信息的特征融合构建，融合通道注意力机制增强了高质量特征的权重；基于LGBM模型实现对特征
- 基于深度学习方法的航空发动机寿命预测模型
- 作者： 郭晓静 贠玉晶 徐晓慧 来源： 振动.测试与诊断 年份： 2024 文献类型 ： 期刊 关键词： 注意力机制 长短期记忆网络 航空发动机 剩余寿命预测 协方差分析
- 描述： 为提高航空发动机剩余寿命（remaining useful life，简称RUL）预测能力，构建了一种注意力机制与长短期记忆网络（long short-term memory，简称LSTM）融合
- 飞机结构X射线裂纹图像智能评定
- 作者： 贾文博 汪洪量 奚之飞 樊俊铃 杨胜春 张伟 赵延广 来源： 航空工程进展 年份： 2024 文献类型 ： 期刊 关键词： 注意力机制 智能评定 裂纹图像 高效层聚合网络 X射线
- 描述： 飞机结构X射线图像评定过程存在复杂背景下裂纹分割不准确、检出难等问题。基于高效层聚合网络提出一种飞机结构X射线裂纹图像智能评定模型（ELAN-Seg），将ELAN-Seg模型和DeepLabv3+模型的射线图像裂纹分割能力进行对比，结合图像处理技术对模型分割的裂纹长度进行评估，利用飞机强度试验及外场维护过程采集的X射线图像对模型进行验证。结果表明：分割的最小裂纹长度约为3 mm,ELAN-Seg模型对复杂背景射线图像裂纹分割更加准确，裂纹漏检率小于3.8%，该模型具有工程适用性。
- 基于注意力Seq2Seq模型的终端区航空器航迹预测
- 作者： 卢婷婷 刘博 李纯柱 来源： 科学技术与工程 年份： 2024 文献类型 ： 期刊 关键词： 注意力机制 终端区 序列到序列框架 航空运输 航迹预测
- 描述： %、38.16%和20.57%,同时，上述4种预测时长下所提出方法预测结果的均值和方差最小，表明随着预测时长的增加，模型预测结果的稳定性最好。此外，引入的注意力机制与指数衰减采样方法对有效捕捉航迹时间依赖性、提高模型泛化性均具有积极的贡献。