Xie Xiuchuan, Yang Tao, Ning Yajia, Zhang Fangbing, Zhang Yanning
National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science, Northwestern Polytechnical University, Xi'an 710072, China.
Sensors (Basel). 2021 May 13;21(10):3394. doi: 10.3390/s21103394.
With the extensive application of robots, such as unmanned aerial vehicle (UAV) in exploring unknown environments, visual odometry (VO) algorithms have played an increasingly important role. The environments are diverse, not always textured, or low-textured with insufficient features, making them challenging for mainstream VO. However, for low-texture environment, due to the structural characteristics of man-made scene, the lines are usually abundant. In this paper, we propose a virtual-real hybrid map based monocular visual odometry algorithm. The core idea is that we reprocess line segment features to generate the virtual intersection matching points, which can be used to build the virtual map. Introducing virtual map can improve the stability of the visual odometry algorithm in low-texture environment. Specifically, we first combine unparallel matched line segments to generate virtual intersection matching points, then, based on the virtual intersection matching points, we triangulate to get a virtual map, combined with the real map built upon the ordinary point features to form a virtual-real hybrid 3D map. Finally, using the hybrid map, the continuous camera pose estimation can be solved. Extensive experimental results have demonstrated the robustness and effectiveness of the proposed method in various low-texture scenes.
随着机器人的广泛应用，如无人飞行器（UAV）用于探索未知环境，视觉里程计（VO）算法发挥着越来越重要的作用。环境多种多样，并不总是有纹理的，或者纹理较少且特征不足，这使得主流的视觉里程计面临挑战。然而，对于低纹理环境，由于人造场景的结构特征，线条通常很丰富。在本文中，我们提出了一种基于虚实混合地图的单目视觉里程计算法。核心思想是对线段特征进行再处理以生成虚拟交点匹配点，这些点可用于构建虚拟地图。引入虚拟地图可以提高视觉里程计算法在低纹理环境中的稳定性。具体来说，我们首先将不平行的匹配线段组合以生成虚拟交点匹配点，然后基于虚拟交点匹配点进行三角测量以得到虚拟地图，再结合基于普通点特征构建的真实地图形成虚实混合3D地图。最后，利用混合地图可以求解连续的相机位姿估计。大量实验结果证明了所提方法在各种低纹理场景中的鲁棒性和有效性。
