Vision-Based Ground Moving Object Tracking for Micro Air Vehicles

Abstract

In recent years, vision-based ground moving object tracking has become a very active field of research for macro aerial vehicles (MAVs), which contains two main problems: pose estimation for MAVs and robust object tracking. A tightly-coupled visual-inertial odometry based on the sliding window is proposed. In practical applications, the sliding window of the most recent visual and inertial measurements are used, thus good real-time performance can be achieved. Simultaneously, historical measurements in the sliding window can improve the accuracy of pose estimation and make the estimated trajectory more smoothly. The object tracking can be used to estimate the location of the object in continuous frames. Finally, the position of the ground moving object in three-dimensional (3D) space can be solved. The experiments are performed on the MAV platform, and the experimental results validate the effectiveness of the proposed algorithms.