J4 ›› 2010, Vol. 28 ›› Issue (06): 596-.

• 论文 • 上一篇    下一篇

基于特征点检测的重叠图像拼接算法

李原福|王学明|段金辉   

  1. 吉林铁道职业技术学院 铁道机车车辆系| 吉林 吉林 132002
  • 出版日期:2010-11-27 发布日期:2010-12-24
  • 通讯作者: 李原福(1973— ),男,吉林省吉林市人,吉林铁道职业技术学院副教授,主要从事铁道车辆构造、电气控制、图像信息处理研究,(Tel)86-13596245870 E-mail:lige2004@sina.com。
  • 作者简介:李原福(1973— )|男|吉林省吉林市人|吉林铁道职业技术学院副教授|主要从事铁道车辆构造、电气控制、图像信息处理研究|(Tel)86-13596245870(E-mail) lige2004@sina.com。
  • 基金资助:

    基于虚拟仪器的试验数据处理系统的研发基金资助项目(3R1095611419)

 Overlapping Image Mosaic Method Based on Feature Points Detection

LI Yuan-fu| WANG Xue-ming| DUAN Jin-hui   

  1. Department of Railway Vehicle, College of Jilin Railway Vocational and Technology|Jilin |132002, China
  • Online:2010-11-27 Published:2010-12-24

摘要:

为提高铁道车辆工程应用中自动监测与故障诊断的准确性,对5种常用的特征点检测方法进行了对比研究,采用 SIFT (ScaleInvariant Feature Transform)特征点检测实现重叠图像的拼接算法。在较宽松的条件下准确地匹配两幅图像。实验证明,该算法能有效地拼接普通相机拍摄的照片,消除图像扭曲、交叠和旋转对图像拼接的影响,并获得高分辨率的场景照片。

关键词: 重叠图像, 特征点检测, SIFT方法, 图像拼接

Abstract:

In order to improve the accuracy of automatic monitoring and fault diagnosis in the railway vehicles
and other engineering applications, the five methods of feature point detection are compared and researched in the paper. SIFT (ScaleInvariant Feature Transform) method is selected to detect feature points from the overlapping images, which can mosaic precisely the two images under most relaxed conditions. The experimental results demonstrate that the proposed method can mosaic effectively the overlapping images captured by ordinary camera and obtain high resolution image, eliminating the influences caused by image distortion, overlapping and rotation.

Key words: overlapping image, feature point detection, scale-invariant feature transform(SIFT) method, image mosaic

中图分类号: 

  • TP391.41