基于NCC动态调整协方差的视觉惯性里程计定位方法  

Visual-inertial odometry localization method based on NCC dynamic covariance adjustment

作　　者：隋心[1] 白建洲 王长强[1] 史政旭 高嵩 赵宏超 SUI Xin;BAI Jianzhou;WANG Changqiang;SHI Zhengxu;GAO Song;ZHAO Hongchao(School of Geomatics,Liaoning Technical University,Fuxin 123000,China)

机构地区：[1]辽宁工程技术大学测绘与地理科学学院,辽宁阜新123000

出　　处：《测绘通报》2025年第4期1-8,共8页Bulletin of Surveying and Mapping

基　　金：国家自然科学基金(42404045);辽宁省自然科学基金计划博士科研启动项目(2024-BS-256);2024年度辽宁省教育厅基本科研项目(LJ212410147093)。

摘　　要：视觉惯性里程计(VIO)在无人机和机器人导航中具有广泛的应用。然而,现有VIO系统在应对特征点匹配质量不一致的情况时稳健性较差。大多数VIO算法通常假设观测模型的噪声项协方差矩阵为常量,忽略了不同特征点匹配质量的差异。针对此问题,本文基于多状态约束卡尔曼滤波(MSCKF)提出了一种利用归一化互相关(NCC)动态调整协方差的VIO定位方法。该方法通过构建一种新的观测模型,在像素值上引入特征点的跟踪误差,将NCC作为量化特征点之间匹配质量的指标,通过计算特征点匹配的NCC反映特征点的跟踪误差,从而动态调整观测噪声项的协方差矩阵,以适应特征点匹配质量的变化。该方法能够在特征点匹配质量差异显著的复杂环境中,获得更准确、稳健的匹配结果。在EuRoC开源数据集和地下停车场实测数据集上进行对比试验,试验结果表明,与传统MSCKF算法相比,本文方法在平面均方根误差上分别降低了41.8%和33.8%;与VINS-MONO算法相比,本文方法在平面均方根误差上分别降低了26.3%和24.7%,显著提高了VIO系统在特征点匹配质量不佳情况下的稳健性和定位精度。Visual-inertial odometry(VIO)is widely applied in UAV and robotics navigation.However,existing VIO systems often struggle with robustness when feature point matching quality is inconsistent.Most VIO algorithms assume a constant covariance matrix for the noise term in the observation model,overlooking variations in feature point matching quality.To address this issue,this paper proposes a VIO localization method based on the multi-state constraint Kalman filter(MSCKF),incorporating normalized cross-correlation(NCC)for dynamic covariance adjustment.This method constructs a new observation model by introducing tracking errors for feature points at the pixel level,with NCC employed as a metric for quantifying feature point matching quality.By calculating the NCC of the feature matches,the method adjusts the covariance matrix of the observation noise dynamically to reflect variations in the matching quality.This approach leads to more accurate and robust results,especially in complex environments with significant differences in feature point matching quality.Comparative experiments conducted on the EuRoC open dataset and a real-world underground parking lot dataset demonstrate that,compared to the traditional MSCKF algorithm,the proposed method reduces planar root mean square error(RMSE)by 41.8%and 33.8%,respectively.Furthermore,compared to the VINS-MONO algorithm,the proposed method reduces planar RMSE by 26.3%and 24.7%,respectively.These results demonstrate a significant improvement in both the robustness and localization accuracy of VIO systems under challenging feature matching conditions.

关 键 词：VIO 多状态约束卡尔曼滤波 归一化互相关 匹配质量 观测噪声 

分 类 号：P228[天文地球—大地测量学与测量工程]