Robust Registration of Multimodal Remote Sensing Images Based on Structural Similarity

TL;DR

This paper introduces a novel structural similarity-based descriptor and metric, HOPC and HOPCncc, for robust multimodal remote sensing image registration, outperforming existing methods in handling complex radiometric differences.

Contribution

The paper proposes the HOPC descriptor and HOPCncc metric, enhancing robustness and accuracy in multimodal image registration compared to prior techniques.

Findings

HOPCncc outperforms NCC and mutual information in matching accuracy.

The proposed registration method is effective across various multimodal datasets.

Experimental results confirm robustness against non-linear radiometric differences.

Abstract

Automatic registration of multimodal remote sensing data (e.g., optical, LiDAR, SAR) is a challenging task due to the significant non-linear radiometric differences between these data. To address this problem, this paper proposes a novel feature descriptor named the Histogram of Orientated Phase Congruency (HOPC), which is based on the structural properties of images. Furthermore, a similarity metric named HOPCncc is defined, which uses the normalized correlation coefficient (NCC) of the HOPC descriptors for multimodal registration. In the definition of the proposed similarity metric, we first extend the phase congruency model to generate its orientation representation, and use the extended model to build HOPCncc. Then a fast template matching scheme for this metric is designed to detect the control points between images. The proposed HOPCncc aims to capture the structural similarity between images, and has been tested with a variety of optical, LiDAR, SAR and map data. The results show that HOPCncc is robust against complex non-linear radiometric differences and outperforms the state-of-the-art similarities metrics (i.e., NCC and mutual information) in matching performance. Moreover, a robust registration method is also proposed in this paper based on HOPCncc, which is evaluated using six pairs of multimodal remote sensing images. The experimental results demonstrate the effectiveness of the proposed method for multimodal image registration.