计算机工程 ›› 2019, Vol. 45 ›› Issue (10): 277-282.doi: 10.19678/j.issn.1000-3428.0052358

• 图形图像处理 • 上一篇    下一篇

基于点特征的SAR图像与可见光图像配准

秦杰, 纪则轩, 曹国   

  1. 南京理工大学 计算机科学与工程学院, 南京 210094
  • 收稿日期:2018-08-10 修回日期:2018-10-29 出版日期:2019-10-15 发布日期:2018-11-01
  • 作者简介:秦杰(1993-),男,硕士研究生,主研方向为图像配准、模式识别;纪则轩,副教授、博士;曹国,教授、博士。
  • 基金项目:
    国家自然科学基金(61371168)。

SAR Image and Optical Image Registration Based on Point Feature

QIN Jie, JI Zexuan, CAO Guo   

  1. School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
  • Received:2018-08-10 Revised:2018-10-29 Online:2019-10-15 Published:2018-11-01

摘要: 针对合成孔径雷达(SAR)图像与可见光图像配准精度低的问题,提出一种基于角点幅值与方向的点特征描述符HIOHC,用以改进Harris角点检测器。将检测器的响应函数从一阶项扩展为二阶项,提高其对SAR图像噪声的鲁棒性,同时构建一个组合像素空间及灰度信息的权值函数,提高角点检测的准确性。实验结果表明,与传统的Harris检测器相比,改进的检测器能够有效降低SAR图像噪声的影响,具有更高的配准精度。

关键词: 配准, Harris角点检测器, 合成孔径雷达图像, 可见光图像, 结构特征

Abstract: Aiming at the low registration accuracy of Synthetic Aperture Radar (SAR) images and optical images,a point feature descriptor HHIHC based on corner amplitude and orientation is proposed to improve the Harris corner detector.The detector's response function is extended from a first-order term to a second-order term to improve its robustness to SAR image noise.At the same time,a weight function combining pixel space and gray information is constructed to improve the accuracy of corner detection.Experimental results show that compared with conventional Harris corner detector,the improved detector can effectively reduce the influence of SAR image noise and has higher registration accuracy.

Key words: registration, Harris corner detector, Synthetic Apecture Radar(SAR) image, optical image, structural feature

中图分类号: