多年来，数据增强在计算机视觉中已展现出显著进展，可提升模型性能，尤其是在数据有限和不足的场景中。当前，在包括目标检测在内的各种任务中，大多数研究集中于调整图像或其特征，以在训练期间扩展样本的规模、质量和多样性。然而，我们认为有必要研究将边界框变换作为一种数据增强技术，而非图像级变换；由于航空图像中可能存在不一致的边界框标注，这一点尤其重要。因此，本通讯针对遥感目标检测，从缩放、旋转和平移三个方面对边界框变换进行了全面研究。我们将这种增强策略称为 NBBOX（Noise Injection into Bounding Box，向边界框注入噪声）。我们在 DOTA 和 DIOR-R 上开展了大量实验；这两个知名数据集包含航空图像中多种旋转的通用目标。实验结果表明，我们的方法无需复杂附加设计即可显著改进遥感目标检测，并且比其他最先进的增强策略更节省时间。
英文摘要：
Data augmentation has shown significant advancements in computer vision to improve model performance over the years, particularly in scenarios with limited and insufficient data. Currently, most studies focus on adjusting the image or its features to expand the size, quality, and variety of samples during training in various tasks including object detection. However, we argue that it is necessary to investigate bounding box transformations as a data augmentation technique rather than image-level transformations, especially in aerial imagery due to potentially inconsistent bounding box annotations. Hence, this letter presents a thorough investigation of bounding box transformation in terms of scaling, rotation, and translation for remote sensing object detection. We call this augmentation strategy NBBOX (Noise Injection into Bounding Box). We conduct extensive experiments on DOTA and DIOR-R, both well-known datasets that include a variety of rotated generic objects in aerial images. Experimental results show that our approach significantly improves remote sensing object detection without whistles and bells and it is more time-efficient than other state-of-the-art augmentation strategies.
ReCon1M:A Large-scale Benchmark Dataset for Relation Comprehension in Remote Sensing Imagery
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences（中国科学院大学电子电气与通信工程学院）
X-LineNet: Detecting Aircraft in Remote Sensing Images by a pair of Intersecting Line Segments
Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences（中国科学院大学电子电气与通信工程学院）；Unit 31008 of the PLA（中国人民解放军31008部队）
OBSeg: Accurate and Fast Instance Segmentation Framework Using Segmentation Foundation Models with Oriented Bounding Box Prompts
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）
OBBStacking: An Ensemble Method for Remote Sensing Object Detection
Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences（中国科学院光电信息处理重点实验室）；Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences（中国科学院机器人与智能制造创新研究院）
包围方法是一种可靠的方法来结合几个模型，以实现卓越的性能。然而，集成方法在遥感目标检测中的应用研究却很少。出现了两个问题。首先，遥感目标检测的一个独特的特点是目标的有向包围盒（OBB）和多个OBB的融合需要进一步的研究关注。其次，广泛使用的深度学习对象检测器为每个检测到的对象提供分数作为置信度的指标，但如何在集成方法中有效地使用这些指标仍然是一个问题。试图解决这些问题，本文提出了OBB堆叠，集成方法，是兼容OBB和结合的检测结果，在一个学习的方式。这种集成方法有助于在挑战赛赛道\textit{Fine-grained Object Recognition in High-Resolution Optical Images}中获得第一名，该赛道曾在\textit{2021 Gaofen Challenge on Automated High-Resolution Earth Observation Image Interpretation}中展出。在DOTA数据集和FAIR1M数据集上的实验证明了OBBStacking的性能改进，并分析了OBBStacking的特点。
PolyBuild: An End-to-End Method for Polygonal Building Contour Extraction from High-Resolution Remote Sensing Images
China University of Petroleum (East China)（中国石油大学（华东））；South Surveying&Mapping Instrument Co.,Ltd.（南方测绘仪器有限公司）；China Railway Design Corporation（中国铁路设计集团有限公司）
LO-Det: Lightweight Oriented Object Detection in Remote Sensing Images
Beijing Institute of Technology（北京理工大学）；University of Delaware（特拉华大学）；The Aviation Industry Corporation of China, Ltd.（中国航空工业集团有限公司）；Luoyang Institute of Electro-Optical Equipment（洛阳电光设备研究所）
Optimization for Arbitrary-Oriented Object Detection via Representation Invariance Loss
School of Automation, Beijing Institute of Technology（北京理工大学自动化学院）；Department of Computer Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程系）
The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shot
University of Western São Paulo (UNOESTE)（圣保罗西部大学）；University of Tennessee（田纳西大学）；Federal University of Mato Grosso do Sul (UFMS)（南马托格罗索联邦大学）；São Paulo State University (UNESP)（圣保罗州立大学）；University of Waterloo（滑铁卢大学）
本文探索了 Meta AI 的 Segment Anything Model (SAM) 在遥感图像分割中的应用，通过结合文本提示与单样本训练的自动化技术提升了多尺度数据上的分割精度，并开源代码以推动 SAM 在遥感领域的进一步适配。
LEVIRDet: A Million-Scale 159-Category Dataset and Foundation Model for Universal Remote Sensing Object Detection
Shen Yuan Honors College, Beihang University（北京航空航天大学沈元荣誉学院）；State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室）；Qian Xuesen Laboratory of Space Technology, China Academy of Space Technology（中国空间技术研究院钱学森空间技术实验室）
HiT: Building Mapping with Hierarchical Transformers
State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北京航空航天大学虚拟现实技术与系统国家重点实验室）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection
School of Automation, Southeast University（东南大学自动化学院）；Shanghai Jiao Tong University（上海交通大学）；School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院）；Wuhan University（武汉大学）；School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Science（中国科学院大学电子电气与通信工程学院）
Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution
Zhejiang University（浙江大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；The Second Affiliated Hospital Zhejiang University School of Medicine（浙江大学医学院附属第二医院）；The Hong Kong Polytechnic University（香港理工大学）
RSGen: Enhancing Layout-Driven Remote Sensing Image Generation with Diverse Edge Guidance
School of Future Science and Engineering, Soochow University, Suzhou, China（未来科学与工程学院，苏州大学）；D-Robotics, Beijing, China（北京D-机器人）；Fraunhofer Institute for Applied Information Technology, Sankt Augustin, Germany（弗劳恩霍夫应用信息技术研究所）；School of Mathematical and Computing Sciences, Heriot-Watt University Malaysia, Putrajaya, Malaysia（数学与计算科学学院，赫瑞-瓦德大学马来西亚分校）；Institute of Automation, Chinese Academy of Sciences, Beijing, China（自动化研究所，中国科学院北京分院）
GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding
Nanyang Technological University（南洋理工大学）；University of Reading（阅读大学）；Shanghai Jiao Tong University（上海交通大学）；Harbin Institute of Technology（哈尔滨工业大学）；SenseTime Research（商汤科技研究院）
SCRDet: Towards More Robust Detection for Small, Cluttered and Rotated Objects
Institute of Electronics, Chinese Academy of Sciences（中国科学院电子学研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Shanghai Jiao Tong University（上海交通大学）
Duke University（杜克大学）；Duke Kunshan University（昆山杜克大学）；Nicholas Institute for Energy, Environment & Sustainability, Duke University（杜克大学尼古拉斯能源、环境与可持续发展研究所）；University of Montana（蒙大拿大学）
