基于深度视觉的多旋翼无人机障碍物检测研究

Research on Obstacle Detection of Multi Rotor Unmanned Aerial Vehicles Based on Depth Vision

摘要: 随着多旋翼无人机的智能化发展，在无人机执行任务过程中，无论是对动态还是静态障碍物都要进行感知和规避，而且感知系统作为无人机自主飞行过程中的第一步，也是极其重要的部分。针对这个问题，本文主要研究了无人机对动、静态障碍物的检测。首先，使用目标检测算法实时地检测图像中障碍物，并确定其在像素级别上的位置，结合立体匹配算法估计障碍物的深度信息，从而得到障碍物的三维坐标；实现了基于深度视觉的障碍物检测。本文的研究内容可以为无人机及其它机器人在复杂、动态的环境中安全运行提供重要的方法论指导，具有重要的工程实践意义。

Abstract: With the intelligent development of multi-rotor UAV, both dynamic and static obstacles need to be perceived and avoided during the task execution process. Moreover, the perception system, as the first step in the autonomous flight process of unmanned aerial vehicles, is also an extremely important part. In response to this issue, this article mainly studies the detection of dynamic and static obstacles by drones. Firstly, real time detection of obstacles in images using object detection algorithms and determining their position at the pixel level, combined with stereo matching algorithms to estimate the depth information of obstacles, thus obtaining the three-dimensional coordinates of obstacles; Implemented obstacle detection based on depth vision. The research content of this article can provide important methodological guidance for the safe operation of drones and other robots in complex and dynamic environments, and has important engineering practical significance.