地图匹配+目标定位

1. 思路

• 掌握飞机位姿和吊舱位姿
• 解算目标粗略GPS
• 根据该GPS调用在线或离线卫星图
• 将吊舱图像和卫星图进行匹配
  • 匹配应当考虑到，吊舱在不同焦距下的视野大小不同，此时与之对应的地图匹配能力大相径庭，因此可以考虑【解算】和【推理】两种方式的匹配，前者可以尽快找到合适的一块卫星图，后者可以准确完成任务
  • 无人机吊舱拍摄的pitch角先控制在(-30, +30)度之间
• 通过解算对目标进行精确定位，就很简单了

调用卫星图	匹配

2. 高权值区

2.1 Cross-View Object Geo-Localization in a Local Region With Satellite Imagery

• 目标定位
• 有github链接

2.2 Joint Representation Learning and Keypoint Detection for Cross-view Geo-localization

• 有github链接
• 思路一致
  

2.3 A Novel Geo-Localization Method for UAV and Satellite Images Using Cross-View Consistent Attention

• 有github链接
• 修改UAV获取图像的配色

Column 1	Column 2

2.4 Learning Visual Representation Clusters for Cross-View Geo-Location

• 有github链接
• 不甚理解
  

2.5 Style Alignment-Based Dynamic Observation Method for UAV-View Geo-Localization

• 有github链接
  

2.6 A Part-aware Attention Neural Network for Cross-view Geo-localization between UAV and Satellite.pdf

• 给出一组图像来做选择题？
• 无github链接
  

2.7 A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization.pdf

• 用到Transformer，需要进一步确定推理时间
• 无github链接

Column 1	Column 2

2.8 Sequence Matching for Image-Based UAV-to-Satellite Geolocalization

• 无github链接
• image sequence很有意思，可以继续往前探索

(a) One-to-all retrieval	(b) Sequence matching

3. 中间区

Learning to Find the Optimal Correspondence Between SAR and Optical Image Patches
把SAR图像和卫星图进行匹配，很有特色！

Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments
UAV视觉自定位

A Multi-Temporal Dataset for Remote Sensing Image Geo-Localization
主要用来地理匹配而不是定位，可以再看看

4. 低权值区

The First Experimental Study of Monocular Visual Localization for Train using Deep Learning Method
–卫星图和行人视角，思路不一致

Co-Visual Pattern-Augmented Generative Transformer Learning for Automobile Geo-Localization
–卫星图和车载视角，思路不一致

A Cross-View Image Matching Method with Feature Enhancement
–卫星图和车载视角，思路不一致

A cross-modal automatic visual geo-localization framework for a natural environment without GNSS information.pdf
–关注自然风景画面，与主题无关

下载不了View Distribution Alignment with Progressive Adversarial Learning for UAV Visual Geo-Localization

下载不了A cross-view geo-localization method guided by relation-aware global attention