Image registration device and operation method of the same

摘要

Provided is an image registration device including a first feature vector magnitude calculating unit calculating magnitudes of feature vectors corresponding to any one first feature point among feature points of a reference image to create a first magnitude value, a second feature vector magnitude calculating unit calculating magnitudes of feature vectors corresponding to any one second feature point among feature points of a target image to create a second magnitude value, a magnitude difference calculating unit receiving the first and second magnitude values and calculating a difference between the received first and second magnitude values to create a third magnitude value, a first threshold value creating unit creating a first threshold value on the basis of the first magnitude value and a magnitude ratio, and a magnitude difference determining unit receiving the third magnitude value and the first threshold value, and determining a magnitude difference.

主权项

1. An image registration method for registering at least two images captured by a plurality of cameras, the method comprising:
receiving a target image and a reference image from the plurality of cameras; calculating, by a processor, a magnitude of a first feature vector according to a first feature point among a plurality of feature points extracted from a reference image; calculating, by the processor, a magnitude of a second feature vector according to a second feature point among a plurality of feature points extracted from a target image; calculating, by the processor, a difference between magnitude values of the first and second feature vectors; creating, by the processor, a first threshold value on the basis of the magnitude value of the first feature vector and a magnitude ratio; comparing, by the processor, a magnitude difference between the first and second feature vectors and a magnitude of the first threshold value; and constructing, by the processor, a single combined digital image from the target image and the reference image, wherein, when the magnitude difference between the first and second feature vectors is not determined to be greater than the first threshold value, similarity calculation is performed on the first and second feature points, and, when the magnitude difference between the first and second feature vectors is determined to be greater than the first threshold value, a magnitude of another feature point of the target image is compared with the magnitude of the first threshold value.