测绘学报 ›› 2017, Vol. 46 ›› Issue (7): 900-909.doi: 10.11947/j.AGCS.2017.20160436

• 摄影测量学与遥感 • 上一篇    下一篇

颜色不变量与AKAZE特征相结合的无人机影像匹配算法

梁焕青1, 谢意1, 付四洲2   

  1. 1. 南宁市国土测绘地理信息中心, 广西 南宁 530021;
    2. 广西业恒勘测设计有限公司, 广西 南宁 530021
  • 收稿日期:2016-09-02 修回日期:2017-06-12 出版日期:2017-07-20 发布日期:2017-07-25
  • 作者简介:梁焕青(1990—),女,硕士,研究方向为无人机影像处理。

UAV Image Registration Algorithm Using Color Invariant and AKAZE Feature

LIANG Huanqing1, XIE Yi1, FU Sizhou2   

  1. 1. Nanning Land Surveying, Mapping and Geoinformation Center, Nanning 530021, China;
    2. Guangxi YeHeng Surveying Design Co. Ltd., Nanning 530021, China
  • Received:2016-09-02 Revised:2017-06-12 Online:2017-07-20 Published:2017-07-25

摘要: 基于特征的影像匹配方法是无人机影像匹配中较为实用的一类方法。针对传统特征匹配方法主要以灰度影像作为输入量,难以利用颜色特征高效区分同名点这一问题,本文结合颜色不变量,设计了一种运用AKAZE特征的匹配算法,克服了传统无人机影像匹配忽略彩色信息的缺点;然后通过灰度级变换,使特征点数目大量减少而又不失其可靠性。试验表明,该方法不仅能够准确识别同名点,而且还提高了运行效率。

关键词: 无人机影像, 颜色不变量, AKAZE特征检测算法, 灰度级变换, 影像匹配

Abstract: Image matching based on feature was one of practical methods in UAV image matching. Since the conventional methods of image registration mainly used gray image as input that it could not take color features into account to distinguish the identical point. To address this problem, this paper designed a matching algorithm combined color invariant with AKAZE feature, which overcame the shortcoming of ignoring color information in traditional UAV image matching. Then gray level transformation was utilized to reduce the number of feature points and remain its reliability. Experimental results demonstrate that the proposed method can find the identical point accurately and enhance the efficiency.

Key words: UAV image, color invariant, AKAZE feature extraction algorithm, gray level transformation, image matching

中图分类号: