Non-Rigid Image Registration With Dynamic Gaussian Component Density and Space Curvature Preservation

Zhuoqian Yang, Yang Yang, Kun Yang, Ziquan Wei

Abstract: Image registration plays an important role in military and civilian applications, such as natural disaster damage assessment, environmental monitoring, ground change detection, and military damage assessment. This paper presents a new feature-based non-rigid image registration method. The main contributions of this paper are: 1) a dynamic Gaussian component density is designed to better exploit available potential image information and provide sufficient inlier pairs for image transformation and 2) a spatial structure preservation, which consists of an image transformation space curvature preservation and a local spatial structure constrain, is proposed to constrain the image transforming cost as well as the local structure of feature points during feature point set registration. The performances of the proposed method in multi-spectral natural images, low-altitude aerial images, and medical images against four types of nine state-of-the-art methods are tested where our method shows the best performances in most scenarios.