Multi-Scale PIIFD for Registration of Multi-Source Remote Sensing Images

• 作者: Chenzhong Gao Wei Li
• 来源期刊: 北京理工大学学报（英文版）
• 年，卷（期）: 2021,（2）
• 页码范围: 113-124
• 页数: 12页
• 语种: 英文
• DOI: 10.15918/j.jbit1004-0579.2021.016

摘要

This paper aims at providing multi-source remote sensing images registered in geometric space for image fusion. Focusing on the characteristics and differences of multi-source remote sens-ing images, a feature-based registration algorithm is implemented. The key technologies include im-age scale-space for implementing multi-scale properties, Harris corner detection for keypoints ex-traction, and partial intensity invariant feature descriptor (PIIFD) for keypoints description. Even-tually, a multi-scale Harris-PIIFD image registration algorithm framework is proposed. The experi-mental results of fifteen sets of representative real data show that the algorithm has excellent, stable performance in multi-source remote sensing image registration, and can achieve accurate spa-tial alignment, which has strong practical application value and certain generalization ability.