Скачать или смотреть Detecting and Tracking 6-DoF Motion of Unknown Dynamic Objects Using Stereo Visual Sensing

Abstract：In this work, we studied the problem of detecting and tracking the six-degree-of-freedom (6-DoF) motion of unknown moving objects with a stereo camera only. The fundamental idea of our approach is to estimate the positions of map points at each timestamp and model their uncertainty in position, such that the correlation between map points can be found by segmenting point clouds that are parts of moving objects into different groups. By analyzing the correlation between map points, we can detect the dynamic objects in the scene without making any assumptions about the type of objects. Thus, this approach allows for tracking both regular and irregular moving objects such as a robot carrier with stacked luggage. It outperforms the existing appearance-based methods because the latter does not perform well for irregular objects. We have conducted extensive experiments in real-world indoor and outdoor environments to demonstrate the robustness and accuracy of our algorithm. The results showcase that our method outperforms state-of-the-art visual sensing methods, establishing its superiority in terms of accuracy and reliability.