一种消除局部强光影响的跑道特征提取方法  

Extraction Method of Runway Feature to Eliminate the Influence of Local Strong Light

作　　者：冯志斌 刘延飞 杨爱涛 FENG Zhi-bin;LIU Yan-fei;YANG Ai-tao(Rocket Forces Engineering University,Xi'an Shanxi 710025,China)

机构地区：[1]火箭军工程大学,陕西西安710025

出　　处：《计算机仿真》2022年第11期38-41,124,共5页Computer Simulation

基　　金：国家自然科学基金重点项目(61834004);国家自然科学基金项目(61701505)。

摘　　要：针对因局部的强光干扰导致小型无人机降落时可能出现跑道图像特征提取失败,同时传统方法难以运用在小型嵌入式系统的问题,提出一种复杂度较低的消除局部强光影响的图像处理算法。通过Sobel边缘检测算子处理原始图像,再将处理后的图像与原始图像的像素点对应相除,与阈值分割方法处理后的原始图像相互叠加,得到抑制局部强光影响的跑道特征图像。仿真结果表明,在局部强光的条件下,与传统单尺度Retinex算法相比,上述方法对跑道特征的提取效果更好,同时算法运行效率提高40%左右。Aiming at the problem that runway image feature extraction may fail when small UAVs land due to local strong light interference,and that traditional methods are difficult to apply in small embedded systems,an image processing algorithm with low complexity to eliminate the influence of local strong light is proposed.The original image is processed by Sobel edge detection operator,and then the processed image is divided from the corresponding pixel points of the original image,which is superposed with the original image processed by the threshold segmentation method to obtain the runway feature image that can suppress the influence of local strong light.The simulation results show that compared with the traditional single-scale Retinex algorithm,the proposed algorithm has a better performance in the extraction of runway features under local strong light conditions,and the operating efficiency of the algorithm is increased by about 40%.

关 键 词：局部强光 阈值分割 图像处理 边缘提取算子 

分 类 号：TN911.73[电子电信—通信与信息系统] TP391.9[电子电信—信息与通信工程]