基于数学形态学和支持向量机的跑道检测方法  

A Runway Detection Method based on Mathematical Morphology and Support Vector Machine

作　　者：张珍[1] 曹云峰[2] 丁萌[1] 冯成涛[1] 

机构地区：[1]南京航空航天大学自动化学院,江苏南京210016 [2]南京航空航天大学高新技术研究院,江苏南京210016

出　　处：《火力与指挥控制》2009年第9期147-149,153,共4页Fire Control & Command Control

基　　金："973"基金(51308);总装预研基金资助项目(9140A25040106AK02)

摘　　要：提出了一种基于数学形态学和支持向量机的跑道检测方法。首先采用Otsu法对原始图像进行全局阈值化处理,并利用灰度形态学边缘检测算法对所得图像进行边缘检测;然后利用Hough变换提取线段,若线段超过一定长度,则判定其所在区域为跑道的候选区域;最后选择8个分量组成跑道候选区域的纹理特征向量,用支持向量机作为分类函数,对候选区域的纹理特征向量进行分类,判别出跑道。实验表明,该算法对跑道定位准确,误检率低。A runway detection method based on Mathematical Morphology and Support Vector Machine （SVM）is presented. Firstly, the global thresholding method of Otsu is used to inspect image. Secondly, Mathematical Morphology is used to detect edges. Then the line is extracted with the Hough Transform. and so candidate region is determinated. Finally, SVM is used to classify the candidate regions of the runway and discriminate the runway. Experimental results show that the method can detect the runway exactly and the detection error rate is lower.

关 键 词：跑道检测 数学形态学 支持向量机 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]