Abstract
Automatic image registration of multimodal urban remote sensing images remains a critical challenging task in remote sensing image analysis due to significant nonlinear radiation distortions between multimodal image pairs; most of the traditional methods focus on the feature point detection and its local description and ignore the robust road information in multimodal urban remote sensing images. Motivated by this, we propose a fast and robust registration method for multimodal urban remote sensing images via road intersection triangular features. The proposed method obtains three main stages: Road lines extraction from images, intersection triangular feature construction, and triangular feature matching. The qualitative and quantitative experimental results show that the proposed method significantly outperforms other state-of-the-art methods, even when others completely fail to achieve the registration task of cross-modal images, our method still maintains good robustness and matching efficiency.
Highlights
I MAGE registration is a fundamental and challenging problem in multimodal urban remote sensing images, the primary goal of which is to align the reference image and sensed image, which are about the same target scene captured by different sensors, at different times or even from different viewpoints
Multimodal urban remote sensing image registration is a critical prerequisite in a wide range of applications, such as image mosaic, image fusion [1], [2], environmental monitoring, change detection, autonomous positioning of unmanned aerial vehicle (UAV) [3]
Test image pairs: The experiment test image pairs include three kinds of multimodal urban remote sensing images as shown in Fig. 8. optical − N IR image pair is from the Potsdam dataset [35] which contains 38 the same size patches, each patch consisting of a true orthophoto extracted from a larger mosaic
Summary
I MAGE registration is a fundamental and challenging problem in multimodal urban remote sensing images, the primary goal of which is to align the reference image and sensed image, which are about the same target scene captured by different sensors, at different times or even from different viewpoints. Multimodal urban remote sensing image registration is a critical prerequisite in a wide range of applications, such as image mosaic, image fusion [1], [2], environmental monitoring, change detection, autonomous positioning of unmanned aerial vehicle (UAV) [3]. The registration problem of urban remote sensing image is typically addressed by two types of methods: Area-based methods [4] and feature-based methods [5]–[9]. Manuscript received January 8, 2021; revised February 22, 2021; accepted April 9, 2021.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
