基于无人机沙漠图像的道路检测  

Road Detection from Aerial Desert Images Based on UAV

作　　者：吕俊瑞[1] 

机构地区：[1]攀枝花学院数学与计算机学院,攀枝花617000

出　　处：《科学技术与工程》2013年第19期5702-5705,共4页Science Technology and Engineering

摘　　要：针对沙漠道路对比度低,遥感影像检测沙漠道路效果差的问题,提出一种基于无人机图像的沙漠道路检测方法。该方法首先采用直方图均衡化增强道路目标,再利用互惠最近邻聚类算法剔除噪声点,最后,通过最小二乘法拟合道路参数。经实验测试,该方法有较高的准确性和鲁棒性,具有较强的应用性。Aim at the problem that the effect on detection desert road from the remote sensing image is poor due to low contrast of road and background of desert, a road detection method from aerial desert images based on unmanned aerial vehicle is proposed. First histogram equalization is applied to enhance the characteristics of the road target , and then eliminate a large proportion of noise points by reciprocity nearest neighbor clustering algorithm, fi- nally, parameters on road are fitted through the path of least squares. Through experimental tests, this method has high accuracy and robustness, and has a wide range of applications.

关 键 词：无人机 沙漠图像 道路检测 互惠最近邻聚类 

分 类 号：TP391.76[自动化与计算机技术—计算机应用技术]