A Novel Harris Feature Detection-Based Registration for Remote Sensing Image
- PDF / 925,327 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 64 Downloads / 169 Views
RESEARCH ARTICLE
A Novel Harris Feature Detection-Based Registration for Remote Sensing Image Yali Wang1 • Huicheng Lai1,2 • Hongbing Ma3 • Zhenhong Jia1 • Liejun Wang1 Received: 15 August 2019 / Accepted: 18 August 2020 Ó Indian Society of Remote Sensing 2020
Abstract In view of the significant intensity difference between remote sensing image pairs, weak robustness, and insufficient key point correspondence, the novel remote sensing image registration method is proposed. Firstly, a nonlinear scale space is established by means of the anisotropic diffusion equation and fast explicit diffusion. Then, an improved gradient calculation method is used to calculate the gradient amplitude of the nonlinear scale-space image to establish the gradient amplitude space of the nonlinear scale space, and the multiscale Harris method is used to detect the feature points in the gradient amplitude space. The experimental results show that this feature extraction method can consider the boundaries and smoothness of objects and reduce the problem of gray-level difference to increase the number of feature points with potential of being correctly matched, and the distribution of feature points is relatively uniform. In addition, the improved gradient calculation method can effectively reduce the impact of nonlinear intensity differences on image registration. Overall, the algorithm can effectively solve the problem of registration difficulties caused by the significant grayscale difference between multisource remote sensing images and enhance the robustness. Compared with other advanced algorithms, this one has higher accuracy and more correct correspondence relations, and the registration performance has been significantly improved. Keywords Remote sensing Image registration Anisotropic diffusion Fast explicit diffusion (FED) Harris
Introduction Image registration is a matching (Ma and Lai 2019) process of two or more images taken at different times or different angles with a common scene (Guo et al. 2018). It plays an indispensable role in many fields, such as change detection (Cai et al. 2018), image fusion (Zhu and Bao 2019), and environmental monitoring. Therefore, researches on registration methods based on remote sensing images have been paid extensive attention.
& Huicheng Lai [email protected] 1
College of Information Science and Engineering, Xinjiang ¨ ru¨mqi 830046, China University, Tianshan District, U
2
Autonomous Region Key Laboratory of Signal Detection and ¨ ru¨mqi, China Processing, U
3
College of Electronic Engineering, Tsinghua University, Haidian District, Beijing 100084, China
The researches on registration algorithms can be roughly divided into two categories: One is the intensity-based method, and the other is the feature-based method (Ye et al. 2018). The intensity-based method (Chen et al. 2018) is to achieve image registration through optimizing the similarity measure between image pairs utilizing the crosscorrelation and mutual information of images. Such methods generally do not require comp
Data Loading...
