Journal of National University of Defense Technology 1001-2486 2026 48 2 29 47 10.11887/j.issn.1001-2486.25120033 article Survey on absolute visual localization techniques for low-altitude unmanned aerial vehicles 针对低空无人飞行器在全球卫星导航系统（global navigation satellite system，GNSS）拒止环境下自主定位的迫切需求，系统综述了基于“检索—匹配—位姿解算”框架的飞行器绝对视觉定位技术。讨论了低空观测带来的成像差异、场景尺度变化和地物遮挡等问题，阐明了该分层定位框架在解决大范围、长航时定位问题上的技术优势。在此基础上，分别从跨视角图像检索、像素级特征匹配及飞行器位姿解算三个核心模块，系统梳理了从传统手工特征到深度学习范式的技术发展趋势与研究现状。结合机载边缘计算平台的部署需求，分析了现有技术局限并展望了未来研究方向。本综述可为低空飞行器绝对视觉定位的技术研究与工程应用提供参考。 To address the critical need for autonomous navigation of low-altitude UAVs (unmanned aerial vehicles) in GNSS (global navigation satellite system)-denied environments, a comprehensive survey was presented on absolute visual localization techniques based on a "retrieval-matching-pose estimation" framework. Key challenges inherent to low-altitude UAV observations—including significant imaging disparities, scale variations, and object occlusions—were analyzed, thereby elucidating the advantages of this hierarchical framework for large-scale, long-endurance localization tasks. Subsequently, the technological evolution and state-of-the-art advancements across three core components (cross-view image retrieval, pixel-level feature matching, and UAV pose estimation) were systematically reviewed, tracing the progression from traditional handcrafted features to deep learning paradigms. Finally, considering the deployment requirements of onboard edge computing platforms, the limitations of existing technologies were discussed, and promising future research directions were outlined. This survey is intended to serve as a valuable reference for both research and practical applications in absolute visual localization for low-altitude UAVs. 低空无人飞行器；视觉定位；跨视角图像检索；跨视角图像匹配；位姿解算；GNSS拒止环境 low-altitude UAV； visual localization； cross-view image retrieval； cross-view image matching； pose estimation； GNSS-denied environments 叶熠彬,陈硕,滕锡超,李璋,杨鸿睿,宋潇铠,于起峰 YE Yibin, CHEN Shuo, TENG Xichao, LI Zhang, YANG Hongrui, SONG Xiaokai, YU Qifeng 1.国防科技大学 空天科学学院, 湖南 长沙 410073 ； 2.图像测量与视觉导航湖南省重点实验室， 湖南 长沙 410073 1.College of Aerospace Science and Engineering, National University of Defense Technology, Changsha 410073 , China ； 2.Hunan Key Laboratory of Image Measurement and Vision Navigation, Changsha 410073 , China http://journal.nudt.edu.cn/gfkjdxxb/article/abstract/20260202