单目视觉里程计位姿解算质量评估因素分析

近年来，弹性PNT和综合PNT不断发展，多源传感器的弹性融合机制受到广泛关注。针对多源组合导航中视觉传感器的测量精度和可靠性受环境影响大，对精度的影响程度难以单独评估等问题，通过研究单目视觉里程计位姿解算质量的评估因素，体现多源传感器融合系统中视觉传感器的测量质量，提出基于李代数推导的反应空间点构型对相机位姿恢复精度影响的精度衰减因子Visual-DOP,设计了单目视觉里程计位姿解算质量评估算法，并在视觉里程计权威数据集KITTI上做了验证，通过控制变量的方法解耦每一个评估因素与定位定姿精度的关系，结果显示采用的位姿解算质量评估因素能够正确反应单目视觉里程计的导航精度受视觉测量质量的影响程度。

Analysis of pose calculation quality evaluation factors of monocular visual odometry

In recent years, with the continuous development of resilient PNT and integrated PNT, the elastic fusion mechanism of multi-source sensors has attracted wide attention. Aiming at the problem that the measurement accuracy and reliability of visual sensors in multi-source integrated navigation are greatly affected by the environment, and the degree of influence on the accuracy is difficult to be evaluated independently. The evaluation factors of the pose calculation quality of monocular visual odometry were analyzed to reflect the measurement quality of visual sensors in multi-source sensor fusion system. A precision attenuation factor Visual-DOP based on the influence of the configuration of the reaction space point on the pose recovery accuracy of the camera was proposed. Further, the pose calculation quality evaluation algorithm of monocular visual odometry was designed, and it was verified on the visual odometry authoritative data set KITTI. The connection between each evaluation factor and the positioning accuracy was decoupled by the method of control variables. The results indicate that the pose calculation quality evaluation factors can correctly reflect the influence of visual measurement quality on the navigation accuracy of monocular visual odometer.