Aiming at the application scenario of autonomous landing of fixed wing UAVs in complex electromagnetic interferences and blocking environments,a visual landing location algorithm of UAVs based on line segment detector(LSD)is proposed.The UAV is located by detecting the left and right edges of the runway and the starting line.According to the morphological features of the air-port runway,the airport runway data model is constructed,and the camera used in the experiment is calibrated.The gray scale and Gaussian filter are used to preprocess the acquired images.The LSD linear detection algorithm is used to extract the linear features of the runway,and the geometric filtering strategy is designed to extract three edge lines of the runway from the linear features.The an-ti-interference ability of detection algorithm is improved by using the nask technology;Based on the principle of camera imaging,the PNP positioning algorithm based on line detection is derived.The 3D position of the aircraft relative to the runway is obtained through the detected position information of the airport runway line in the pixel coordinate system.The detection and positioning solutions are carried out in the visual simulation environment and real airport environment,respectively.The experimental results show that the designed algorithm meets the real-time and accuracy requirements of UAV landing location,and it verifies the effectiveness of visual landing location algorithm.
关键词
LSD检测/跑道线检测/PNP定位算法/视觉着陆/位姿估计
Key words
LSD detection algorithm/runway line detection/PNP positioning algorithm/visual landing/pose estimation
维普
万方数据