一种无人机电力巡检的影像匹配方法  

Image Matching Method for Power Inspection of Unmanned Aerial Vehicles

作　　者：靳渤文 杨耀权[1] 张明浩 JIN Bowen;YANG Yaoquan;ZHANG Minghao(School of Control and Computer Engineering,North China Electric Power University,Baoding 071003,China)

机构地区：[1]华北电力大学控制与计算机学院

出　　处：《山东电力技术》2019年第9期8-13,共6页Shandong Electric Power

摘　　要：针对无人机在电力巡检中拍摄条件复杂时图像匹配效果不佳、局部区域无法匹配等问题,提出应用Harris-Laplace特征检测算法与SIFT描述子结合改进无人机影像匹配方法。首先应用Harris-Laplace特征检测算法检测出无人机影像上的关键点,确定关键点的主方向及大小,生成特征点。然后应用SIFT算法对生产的特征点进行描述,最后使用多重约束的改进RANSAC算法,获得最优匹配集。实验结果表明,基于SIFT的匹配方法改进了RANSAC算法,此方法在控制匹配速度的情况下,提高了匹配精度。Aiming at image matching problem under complicated shooting conditions in the power inspection using the unmannde aerial vehicle(UAV), an application of Harris-Laplace feature detection algorithm and SIFT descriptor is proposed to improve the image matching method of drone.Firstly,the Harris-Laplace feature detection algorithm is used to detect the key points on the UAV image,and then the main direction and size of the key points are determined to generate feature points.Then the SIFT algorithm is used to describe the feature points of the production.Finally,the improved RANSAC algorithm with multiple constraints is used to obtain the optimal matching set.The experimental results show that the matching method based on SIFT improves the RANSAC algorithm,and the method improves the matching accuracy with little cost of matching speed.

关 键 词：无人机影像 Harris-Laplace特征 SIFT特征描述 基础矩阵 影像匹配 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]