Due to the advantages of high computational efficiency and small memory requirements, filter-based visual inertial odometry (VIO) has a good application prospect in miniaturized and payload-constrained embedded systems. However, the filter-based method has the problem of insufficient accuracy. To this end, we propose the State transformation and Pose-only VIO (SP-VIO) by rebuilding the state and measurement models, and considering further visual deprived conditions. In detail, we first proposed a system model based on the double state transformation extended Kalman filter (DST-EKF), which has been proven to have better observability and consistency than the models based on extended Kalman filter (EKF) and state transformation extended Kalman filter (ST-EKF). Secondly, to reduce the influence of linearization error caused by inaccurate 3D reconstruction, we adopt the Pose-only (PO) theory to decouple the measurement model from 3D features. Moreover, to deal with visual deprived conditions, we propose a double state transformation Rauch-Tung-Striebel (DST-RTS) backtracking method to optimize motion trajectories during visual interruption. Experiments on public (EuRoC, Tum-VI, KITTI) and personal datasets show that SP-VIO has better accuracy and efficiency than state-of-the-art (SOTA) VIO algorithms, and has better robustness under visual deprived conditions.

翻译：由于计算效率高和内存需求小的优势，滤波式视觉惯性里程计（VIO）在小型化和载荷受限的嵌入式系统中具有良好的应用前景。然而，基于滤波的方法存在精度不足的问题。为此，我们通过重构状态与观测模型，并进一步考虑视觉受限条件，提出了状态转换与纯位姿视觉惯性里程计（SP-VIO）。具体而言，我们首先提出了一种基于双状态转换扩展卡尔曼滤波器（DST-EKF）的系统模型，该模型已被证明比基于扩展卡尔曼滤波器（EKF）和状态转换扩展卡尔曼滤波器（ST-EKF）的模型具有更好的可观测性与一致性。其次，为减少因三维重建不准确引起的线性化误差影响，我们采用纯位姿（PO）理论将观测模型与三维特征解耦。此外，为应对视觉受限条件，我们提出了一种双状态转换Rauch-Tung-Striebel（DST-RTS）回溯方法，以优化视觉中断期间的运动轨迹。在公开数据集（EuRoC、Tum-VI、KITTI）及自采数据集上的实验表明，SP-VIO相比当前最先进的VIO算法具有更高的精度与效率，且在视觉受限条件下表现出更好的鲁棒性。