Image registration is a prerequisite for image fusion from multiple modalities, such as infrared (IR) and visible (VIS) images. Although there have been many various methods of image registration, non-rigid registration for IR and VIS images is still challenging due to large differences between IR and VIS images. In this work, a point feature-based method is proposed to improve the performance on nonrigid IR and VIS image registration. Firstly, a feature descriptor - Gaussian weighted shape context (GWSC) - is improved from shape context (SC) to fast extract matching point pairs from edge maps in IR and VIS images. With the set of matching point pairs, a Gaussian-field-based objective function is established to measure the distance between IR and VIS images. Then, the enhanced affine transformation (EAT) model is proposed to generalize affine model from linear to non-linear case and describe the regularity of global deformation between IR and VIS images. At last, the derivative of the distance measure is expressed with respect to the EAT model and thus, the optimal parameters are estimated by using the quasi-Newton method. The qualitative and quantitative comparisons demonstrate that the proposed method (GWSC-EAT) can be successfully applied to non-rigid registration of IR and VIS images and moreover, it is superior to the state-of-the-art methods on the accuracy and speed of non-rigid registration.
Non‐rigid registration, performing well in all‐weather and all‐day/night conditions, directly determine the reliability of visible (VIS) and infrared (IR) image fusion. On account of non‐planar scenes and differences between IR and VIS cameras, non‐linear transformation models are more helpful to non‐rigid image registration than the affine model. However, most of non‐linear models usually used on non‐rigid registration are constructed by control points at present. Aiming at the issue that the adaptiveness and generalization of the control‐point‐based models are limited, adaptive enhanced affine transformation (AEAT) is proposed for image registration, generalizing the affine model from linear to non‐linear case. Firstly, Gaussian weighted shape context, measuring the structural similarity between multimodal images, is designed to extract putative matches from edge maps of IR and VIS images. Secondly, to implement global image registration, the optimal parameters of the AEAT modal are estimated from putative matches by a strategy of subsection optimization. Experiment results show that this approach is robust in different registration tasks and outperforms several competitive methods on registration precision and speed.
In this paper, we propose a simple but effective approximation—dark region approximation (DRA) to extract details from gray-scale images. The DRA is based on an assumption: there is little illumination in the dark regions of visible images. The Retinex model using the DRA is developed to improve the performance of preserving details from the dark regions in gray-scale images during reflectance estimation. Then, Gaussian field criterion is introduced to construct the objective function which could be solved by quasi-Newton method, in order to estimate the reflectance via the DRA-based Retinex model. The reflectance is considered as the final result of image detail extraction. Experiments on a variety of gray-scale images demonstrate the power of the DRA and the superiority of our method.