基于直线特征的航拍图像机场跑道自动识别算法  

Runway recognition algorithm in aerial image based on straight line characteristics

作　　者：董银文[1] 苑秉成[2] 石钊铭[1] 王航宇[3] 

机构地区：[1]海军工程大学电子工程学院,湖北武汉430033 [2]海军工程大学兵器工程系,湖北武汉430033 [3]海军工程大学科研部,湖北武汉430033

出　　处：《系统工程与电子技术》2013年第4期876-879,共4页Systems Engineering and Electronics

基　　金：湖北省自然科学基金(2011CDC023);总装预研基金(9140A06040111JB11)资助课题

摘　　要：针对航拍图像中机场跑道的区域灰度特征和边界直线特征,提出了一种基于直线特征的机场跑道自动识别算法。首先对航拍图像进行边缘检测;然后在归一化的边缘检测幅度图像中进行直线提取,并对提取的直线进行三次连接;再进行机场跑道边界平行直线对的提取;最后根据区域灰度特征对机场跑道区域进行验证,完成机场跑道的识别和定位。大量实验结果表明,本算法对云层遮挡等具有较强的鲁棒性,并且定位准确,是一种有效的机场跑道识别算法。Aiming at the characteristics of area grey and edge line of runway, an algorithm for recognizing runway based on straight line characteristics is presented to achieve runway recognition correctly. Firstly, the edge detectors are used to get a edge image which has been number normalized, and straight lines are extracted in the edge image. Then the straight lines are connected three times and the parallel straight lines couple is ex tracted. Finally, the runway of airport is validated according to the characteristics of area grey. Many experiments show that this method can find the runway of airport exactly and quickly in aerial images, and is robust for the influence of cloud cover and noise. Experimental results verify the effectiveness of the proposed algorithm.

关 键 词：航拍图像 跑道识别 直线提取 直线连接 边缘检测 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]