DCE and LSS-based infrared image and visible image registration method

Abstract

The present invention discloses a DCE and LSS-based infrared image and visible image registration method. The method comprises the steps of S1, through the DCE, respectively describing the target contour of a to-be-registered infrared image and the target contour of a visible image, extracting each DCE feature point in the vertex of a corresponding target contour, and obtaining DCE feature point sets respectively corresponding to the to-be-registered infrared image and the visible image; S2, based on the LSS method, respectively describing each DCE feature point in each DCE feature point set; S3, according to the description result of step S2, calculating the matching degree among each DCE feature point in the to-be-registered infrared image and the visible image so as to obtain the corresponding relationship between each DCE feature point; S4, according to the corresponding relationship obtained in the step S3, conducting the image transform to obtain a registered image and outputting the registered image. According to the technical scheme of the invention, the advantages of low registration implementation complexity, good registration accuracy, high efficiency and the like are realized.

Description

technical field [0001] The present invention relates to the technical field of digital image processing, in particular to a registration method for infrared images and visible light images based on DCE (discrete curveevolution, discrete curve evolution) and LSS (Local self-similarity, local self-similarity). Background technique [0002] Image registration is to determine the transformation parameters between images based on some similarity measures, so that two or more images of the same scene acquired from different sensors, different perspectives, and different times are transformed into the same coordinate system, and obtained at the pixel level. best match process. The image registration of single modality (imaged by the same device) has been well solved. Multimodal images can provide richer and more comprehensive information than single modality images. However, since multimodal images come from different Different imaging devices have different imaging principles, an...

AI Technical Summary

Problems solved by technology

However, due to the high complexity of corner detection, the amount of calculation is huge, the registration accuracy is low, and the configuration effect cannot be achieved. When used for infrared image and visible light image registration, the calculation time is long and the robustness to noise Not strong

[0009] When registering infrared images and visible light images, if the registration is based only on the contour, there are problems such as blurred boundaries of the target in the infrared image, and it is not easy to accurately segment; Different principles will lead to uneven distribution of feature points, and different feature points may exist for the same target in different images, resulting in higher registration error

Images