支持场景表观差异的无人机图像视觉定位方法  

Visual Localization of UAV Images with Scene Appearance Change

作　　者：王骞仟 熊源 姜涵[1,2] 周忠 WANG Qianqian;XIONG Yuan;JIANG Han;ZHOU Zhong(Beihang University,Beijing 100091,China;National Key Laboratory of Science and Technology on Virtual Reality and Simulation System,Beijing 100091,China)

机构地区：[1]北京航空航天大学,北京100191 [2]虚拟现实技术与系统全国重点实验室,北京100191

出　　处：《空间控制技术与应用》2024年第1期56-67,共12页Aerospace Control and Application

基　　金：国家重点研发计划资助项目(2022YFC3803600);城市信息模型(CIM)数据结构化治理关键技术资助项目

摘　　要：视觉定位是计算机视觉中的基本任务,在无人机测控、视频监控和遥感分析等领域有着广泛应用.在GNSS拒止情况下,利用图像进行视觉定位是重要的导航替代方法.然而,由于室外场景易受天气、季节和光照等变化影响,细节的表观差异方差大,无人机视觉定位的鲁棒性与精度在近地面时难以保证.提出一种基于虚拟图像合成的视觉定位框架.设计阴影映射和深度卷积图像填补网络来合成具有大表观差异和大视差的虚拟图像集,以提高2D-3D配准质量从而提升视觉定位的鲁棒性.实验数据表明,与国际同类方法相比,本方法合成的图像质量在视觉效果、匹配点数量、置信度和视觉定位的精度等指标上都获得了明显的提升,可以支持大表观差异下的无人机视觉定位.Visual localization is a fundamental task in computer vision,which is widely used in UAV control,surveillance system and remote sensing.In GNSS denied cases,visual localization using existing image references is an alternative navigation method for UAVs.However,due to the scene differences caused by changes of weather,season and illumination,the accuracy of visual localization of UAV images can hardly be guaranteed,especially when the UAV is flying close to the ground.In this paper,a visual localization framework with image synthesis is proposed to solve these problems.The proposed framework combines shadow mapping-based texture fusion and deep convolutional inpainting network to synthesize novel view images.These synthesized images can be used as additional reference data to solve the appearance change and large parallax problem,by improving the accuracy of 2D-3D feature mapping and registration in the stage of pose estimation.Experimental results show that the performance of proposed image synthesis is better than traditional stitching methods,in terms of visualization,number of matches,confidence and localization accuracy.It is proved that the proposed method can support UVA visual localization with large appearance changes.

关 键 词：视觉定位 无人机 图像合成 三维重建 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]