Multi-Feature Nonlinear Optimization Motion Estimation Based on RGB-D and Inertial Fusion

Abstract

To achieve a high precision estimation of indoor robot motion, a tightly coupled RGB-D visual-inertial SLAM system is proposed herein based on multiple features. Most of the traditional visual SLAM methods only rely on points for feature matching and they often underperform in low textured scenes. Besides point features, line segments can also provide geometrical structure information of the environment. This paper utilized both points and lines in low-textured scenes to increase the robustness of RGB-D SLAM system. In addition, we implemented a fast initialization process based on the RGB-D camera to improve the real-time performance of the proposed system and designed a new backend nonlinear optimization framework. By minimizing the cost function formed by the pre-integrated IMU residuals and re-projection errors of points and lines in sliding windows, the state vector is optimized. The experiments evaluated on public datasets show that our system achieves higher accuracy and robustness on trajectories and in pose estimation compared with several state-of-the-art visual SLAM systems.

Differences in Tridimensional Shoulder Kinematics between Asymptomatic Subjects and Subjects Suffering from Rotator Cuff Tears by Means of Inertial Sensors: A Cross-Sectional Study

“…As patients from the present study were on a waiting list for RCT surgery, the present measures could be used to give priority to subjects who present a greater alteration in the kinematics and function of the shoulder. On the other hand, while this study focuses on kinematic data captured by an inertial sensor, these instruments can be used as a complement to other devices, such as RGB-D cameras to achieve higher accuracy [ 37 ], optimizing their advantages [ 38 ]. In addition, data from inertial sensors can be used to develop a hybrid deep learning (HDL) system to facilitate the rehabilitation process [ 39 ].…”