特征法视觉SLAM逆深度滤波的三维重建  

3D reconstruction with inverse depth filter of feature-based visual SLAM

作　　者：张一[1] 姜挺[1] 江刚武[1] 余岸竹[1] 于英[1] ZHANG Yi;JIANG Ting;JIANG Gangwu;YU Anzhu;YU Ying(Institute of Surveying and Mapping,Information Engineering University,Zhengzhou 450001,China)

机构地区：[1]信息工程大学地理空间信息学院

出　　处：《测绘学报》2019年第6期708-717,共10页Acta Geodaetica et Cartographica Sinica

基　　金：国家自然科学基金(41501482;41471387;41801388)~~

摘　　要：针对现有特征法视觉SLAM只能重建稀疏点云、非关键帧对地图点深度估计无贡献等问题,本文提出一种特征法视觉SLAM逆深度滤波的三维重建方法,可利用视频序列影像实时、增量式地构建相对稠密的场景结构.具体来说,设计了一种基于运动模型的关键帧追踪流程,能够提供精确的相对位姿关系;采用一种基于概率分布的逆深度滤波器,地图点通过多帧信息累积、更新得到,而不再由两帧三角化直接获取;提出一种基于特征法与直接法的后端混合优化框架,以及基于平差约束的地图点筛选策略,可以准确、高效解算相机位姿与场景结构.试验结果表明,与现有方法相比,本文方法具有更高的计算效率和位姿估计精度,而且能够重建出全局一致的较稠密点云地图.Aiming at the problem that the current feature-based visual SLAM can only reconstruct a sparse point cloud and the ordinary frame does not contribute to point depth estimation, a novel 3D reconstruction method with inverse depth filter of feature-based visual SLAM is proposed, which utilizes video sequence to incrementally build a denser scene structure in real-time. Specifically, a motion model based keyframe tracking approach is designed to provide accurate relative pose relationship. The map point is no longer calculated directly by two-frame-triangulation, instead it is accumulated and updated by information of several frames with an inverse depth filter based on probability distribution. A back-end hybrid optimization framework composed of feature and direct method is introduced, as well as an adjustment constraint based point screening strategy, which can precisely and efficiently solve camera pose and structure. The experimental results demonstrate the superiority of proposed method on computational speed and pose estimation accuracy compared with existing methods. Meanwhile, it is shown that our method can reconstruct a denser globally consistent point cloud map.

关 键 词：视觉即时定位与地图构建 三维重建 逆深度滤波器 运动模型 后端混合优化框架 

分 类 号：P231[天文地球—摄影测量与遥感]