针对存在障碍物农田区域的植保无人机避障问题，提出了一种基于结构光视觉的植保无人机障碍物检测方法。本文基于激光三角测量原理，通过半导体激光器与CCD 传感器间特殊的光路，设计了可探测前方障碍物信息的光学检测系统。激光器发出的线结构光经障碍物表面的反射，成像于CCD 靶面上，通过图像采集、处理和计算提取出前方障碍物距离、方位角和宽度等参数信息。实验表明，该方法能够有效检测出未知环境下障碍物的距离、方位角和宽度，并且距离检测误差小于0.06 m。

To solve the obstacle avoidance problem in plant protection UAV in operation, especially for farmland areas, a technology based on structured light vision was proposed. Based on the laser triangulation principle, through the special optical path design between the semiconductor laser and CCD sensor, an optical detection system to detect front obstacle information was designed. The line structured light emitted by the laser was reflected by the surface of the obstacle and was imaged on the CCD target surface. Through the image acquisition, processing and calculation, the distance, azimuth, width and other parameter information of front obstacle were extracted. Experiments show that this method can effectively detect the distance, azimuth and width of the obstacle in the unknown environment. The deviation of distance detection is less than 0.06 m.