激光与光电子学进展, 2019, 56 (19): 191004, 网络出版: 2019-10-12   

一种融合光照和彩色信息的图像匹配算法 下载: 941次

Image Matching Algorithm Based on Exposure and Color Information
作者单位
哈尔滨理工大学自动化学院, 黑龙江 哈尔滨 150080
摘要
针对传统SIFT算法很难兼顾匹配实时性与匹配准确率这一矛盾,提出一种融合彩色信息表征与光照补偿的Harris-SIFT算法。该算法在图像灰度化之前计算彩色信息补偿,并通过高斯权重函数得出光照补偿量,增强图像对比度,进而提高系统的匹配准确率。通过Harris角点检测算法与SIFT算法融合提高系统的快速性并剔除表征不好的特征点,改善系统的实时性。实验结果表明匹配算法在匹配准确率提高的同时,还提高了算法的实时性。
Abstract
This study proposes a Harris-SIFT algorithm that combines the color information representation and illumination compensation to resolve the contradiction between matching real time and matching accuracy of the traditional SIFT algorithm. The algorithm calculates the color information compensation before the image is grayed. By using the Gaussian weight function, the illumination compensation amount is obtained, the image contrast is enhanced, and the matching accuracy is improved. The Harris corner detection and SIFT algorithms are combined to improve the system rapidity and eliminate badly characterized feature points, improving the real-time system performance. Further, the experimental results denote that the proposed matching algorithm improves the real-time performance of the algorithm while improving the matching accuracy.

张庆鹏, 曹宇. 一种融合光照和彩色信息的图像匹配算法[J]. 激光与光电子学进展, 2019, 56(19): 191004. Qingpeng Zhang, Yu Cao. Image Matching Algorithm Based on Exposure and Color Information[J]. Laser & Optoelectronics Progress, 2019, 56(19): 191004.

本文已被 3 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!