期刊
1. IEEE Transactions on Geoscience and Remote Sensing
2. ISPRS Journal of Photogrammetry and Remote Sensing(Elsevier)
3. Remote Sensing of Environment(Elsevier)
1. GeoChat: Grounded Large Vision-Language Model for Remote Sensing(CVPR2024)
code:https://github.com/mbzuai-oryx/geochathttps://github.com/mbzuai-oryx/geochat
2. SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery(CVPR2024)
code:未公开
3. 3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions(CVPR2024)
code: https://github.com/opendatalab/MLS-BRNhttps://github.com/opendatalab/MLS-BRN
4. Poly Kernel Inception Network for Remote Sensing Detection(CVPR2024)
5. Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening(CVPR2024)
code:https://github.com/duanyll/CANConvhttps://github.com/duanyll/CANConv
6. Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation(CVPR2024)
code:http://https: //github.com/Lsan2401/RMSINhttp://https//github.com/Lsan2401/RMSIN
7. Bridging Remote Sensors with Multisensor Geospatial Foundation Models(CVPR2024)
8. S2MAE: A Spatial-Spectral Pretraining Foundation Model for Spectral Remote Sensing Data(CVPR2024)
code:未公开
9. Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery(CVPR2024)
code:https://github.com/techmn/satmae_pphttps://github.com/techmn/satmae_pp
10. Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery(CVPR2024)
code:https://github.com/zyqz97/Aerial_liftinghttps://github.com/zyqz97/Aerial_lifting
11. Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion(CVPR2024)
code:未公开
12. SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation(CVPR2024)
code:http://https: //github.com/yejy53/SG-BEVhttp://https//github.com/yejy53/SG-BEV
13. WildlifeMapper: Aerial Image Analysis for Multi-Species Detection and Identification(CVPR2024)
code:https://github.com/UCSB-VRL/WildlifeMapperhttps://github.com/UCSB-VRL/WildlifeMapper
14. Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?(CVPR2024)
15. Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans(CVPR2024)
16. Multiplane Prior Guided Few-Shot Aerial Scene Rendering(CVPR2024)
code:未公开
17. SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation(CVPR2024)
code:未公开
18. EarthLoc: Astronaut Photography Localization by Indexing Earth from Space(CVPR2024)
19. ShadowSense: Unsupervised Domain Adaptation and Feature Fusion for Shadow-Agnostic Tree Crown Detection from RGB-Thermal Drone Imagery (WACV2024)
paper:https://openaccess.thecvf.com/content/WACV2024/papers/Kapil_ShadowSense_Unsupervised_Domain_Adaptation_and_Feature_Fusion_for_Shadow-Agnostic_Tree_WACV_2024_paper.pdfhttps://openaccess.thecvf.com/content/WACV2024/papers/Kapil_ShadowSense_Unsupervised_Domain_Adaptation_and_Feature_Fusion_for_Shadow-Agnostic_Tree_WACV_2024_paper.pdfcode:GitHub - rudrakshkapil/ShadowSense: Official code implementation for WACV 2024 paper "ShadowSense: Unsupervised Domain Adaptation and Feature Fusion for Shadow-Agnostic Tree Crown Detection from RGB-Thermal Drone Imagery"Official code implementation for WACV 2024 paper "ShadowSense: Unsupervised Domain Adaptation and Feature Fusion for Shadow-Agnostic Tree Crown Detection from RGB-Thermal Drone Imagery" - rudrakshkapil/ShadowSense
https://github.com/rudrakshkapil/ShadowSense
20. Vision Transformer for Multispectral Satellite Imagery: Advancing Landcover Classification*(WACV2024)
21. UOW-Vessel: A Benchmark Dataset of High-Resolution Optical Satellite Images for Vessel Detection and Segmentation(WACV2024)
paper:https://openaccess.thecvf.com/content/WACV2024/papers/Bui_UOW-Vessel_A_Benchmark_Dataset_of_High-Resolution_Optical_Satellite_Images_for_WACV_2024_paper.pdfhttps://openaccess.thecvf.com/content/WACV2024/papers/Bui_UOW-Vessel_A_Benchmark_Dataset_of_High-Resolution_Optical_Satellite_Images_for_WACV_2024_paper.pdfcode:University of Wollongong – UOW - A world-class UniversityUOW is one of the world's top modern universities, offering excellence in teaching, learning, and research, and an unparalleled student experience.
https://documents.uow.edu.au/%E2%88%BCphung/UOW-Vessel.html
22. SICKLE: A Multi-Sensor Satellite Imagery Dataset Annotated with Multiple Key Cropping Parameters(WACV2024)
paper:https://openaccess.thecvf.com/content/WACV2024/papers/Sani_SICKLE_A_Multi-Sensor_Satellite_Imagery_Dataset_Annotated_With_Multiple_Key_WACV_2024_paper.pdfhttps://openaccess.thecvf.com/content/WACV2024/papers/Sani_SICKLE_A_Multi-Sensor_Satellite_Imagery_Dataset_Annotated_With_Multiple_Key_WACV_2024_paper.pdfcode:https://sites.google.com/iiitd.ac.in/sickle/home
https://sites.google.com/iiitd.ac.in/sickle/home
23. Revolutionize the Oceanic Drone RGB Imagery with Pioneering Sun Glint Detection and Removal Techniques(WACV2024)
24. Prototypical Contrastive Network for Imbalanced Aerial Image Segmentation(WACV2024)
paper:https://openaccess.thecvf.com/content/WACV2024/papers/Nogueira_Prototypical_Contrastive_Network_for_Imbalanced_Aerial_Image_Segmentation_WACV_2024_paper.pdfhttps://openaccess.thecvf.com/content/WACV2024/papers/Nogueira_Prototypical_Contrastive_Network_for_Imbalanced_Aerial_Image_Segmentation_WACV_2024_paper.pdfcode:https://github.com/keillernogueira/proto_ contrastive_net_imbalanced
https://github.com/keillernogueira/proto_%20contrastive_net_imbalanced
25. C2AIR: Consolidated Compact Aerial Image Haze Removal(WACV2024)
paper:https://openaccess.thecvf.com/content/WACV2024/papers/Kulkarni_C2AIR_Consolidated_Compact_Aerial_Image_Haze_Removal_WACV_2024_paper.pdfhttps://openaccess.thecvf.com/content/WACV2024/papers/Kulkarni_C2AIR_Consolidated_Compact_Aerial_Image_Haze_Removal_WACV_2024_paper.pdfcode:http://https: //github.com/AshutoshKulkarni4998/C2AIR
http://https//github.com/AshutoshKulkarni4998/C2AIR
26. MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition(WACV2024)
paper:https://openaccess.thecvf.com/content/WACV2024/papers/Xian_MITFAS_Mutual_Information_Based_Temporal_Feature_Alignment_and_Sampling_for_WACV_2024_paper.pdfhttps://openaccess.thecvf.com/content/WACV2024/papers/Xian_MITFAS_Mutual_Information_Based_Temporal_Feature_Alignment_and_Sampling_for_WACV_2024_paper.pdfcode:GitHub - Ricky-Xian/MITFAS: This is the official implementation of MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition(https://arxiv.org/abs/2303.02575).This is the official implementation of MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition(https://arxiv.org/abs/2303.02575). - Ricky-Xian/MITFAS
https://github.com/Ricky-Xian/MITFAS
27. Multi-Class Segmentation from Aerial Views using Recursive Noise Diffusion(WACV2024)
paper:https://openaccess.thecvf.com/content/WACV2024/papers/Kolbeinsson_Multi-Class_Segmentation_From_Aerial_Views_Using_Recursive_Noise_Diffusion_WACV_2024_paper.pdfhttps://openaccess.thecvf.com/content/WACV2024/papers/Kolbeinsson_Multi-Class_Segmentation_From_Aerial_Views_Using_Recursive_Noise_Diffusion_WACV_2024_paper.pdfcode:https://github.com/ benediktkol/recursive-noise-diffusion
https://github.com/%20benediktkol/recursive-noise-diffusion
28. NOMAD: A Natural, Occluded, Multi-scale Aerial Dataset, for Emergency Response Scenarios(WACV2024)
29. CHAI: Craters in Historical Aerial Images(WACV2024)
数据集
Dataset for Object deTection in Aerial images(DOTA数据集)
- DOTA数据集论文介绍:https://arxiv.org/pdf/1711.10398.pdf
- 数据集官网:https://captain-whu.github.io/DOTA/dataset.html
图片尺寸800×800~20000×20000
DOTAV1.0(2018)
类别数目:15
类别名称:plane, ship, storage tank, baseball diamond, tennis court, basketball court, ground track field, harbor, bridge, large vehicle, small vehicle, helicopter, roundabout, soccer ball field , swimming pool
DOTAV1.5(2019)
类别数目:16
类别名称:plane, ship, storage tank, baseball diamond, tennis court, basketball court, ground track field, harbor, bridge, large vehicle, small vehicle, helicopter, roundabout, soccer ball field, swimming pool , container crane
DOTAV2.0(2021)
类别数目:18
类别名称:plane, ship, storage tank, baseball diamond, tennis court, basketball court, ground track field, harbor, bridge, large vehicle, small vehicle, helicopter, roundabout, soccer ball field, swimming pool, container crane, airport , helipad
标注方式:oriented bounding box(定向边界框,即旋转边界框)
标签:x1~y4一个矩形框四个角的坐标,category表示对象类别,difficult表示识别难易程度,0表示简单,1表示困难。
x1, y1, x2, y2, x3, y3, x4, y4, category, difficult
x1, y1, x2, y2, x3, y3, x4, y4, category, difficult
...
DIOR/DIOR-R数据集
- DIOR数据集论文介绍:https://arxiv.org/ftp/arxiv/papers/1909/1909.00133.pdf
- 数据集官网:http://www.escience.cn/people/gongcheng/DIOR.html
- DIOR-R数据集论文介绍:https://arxiv.org/pdf/2110.01931.pdf
- 数据集官网:https://github.com/jbwang1997/AOPG
DIOR数据集(水平边界框):20个类--飞机、机场、棒球场、篮球场、桥梁、烟囱、水坝、高速公路服务区、高速公路收费站、港口、高尔夫球场、地面田径场、天桥、船舶、体育场、储罐、网球场、火车站、车辆和风磨。由23463张遥感图像和190288个目标实例组成,图像大小为800×800。
DIOR-R数据集(旋转边界框):在DIOR数据集的基础上,对目标实例重新标注边框,采用旋转框标注,这样避免了水平框的重叠问题。数据集格式需要转换成DOTA格式。