Depth image matching method based on ASIFT (Affine Scale-invariant Feature Transform)

Abstract

The invention discloses a depth image matching method based on ASIFT (Affine Scale-invariant Feature Transform). The method comprises the following steps: acquiring depth images and grayscale images of an object to be detected in two view fields, and respectively obtaining the corresponding relationship between the depth image and the grayscale image inside each of the two view fields; extracting the feature point pair sets of grayscale images inside the two view fields by adopting the ASIFT algorithm; acquiring depth image point pair sets corresponding to the feature point pair sets of grayscale images according to the corresponding relationships between the depth images and the grayscale images inside the two view fields, and then screening the depth image point pair sets according to the principle that the spatial features in rigid transformation are invariable, so as to obtain effective depth image point pair sets; computing an initial value rotation matrix and a translation matrix by adopting the least square method according to the effective depth image point pair sets; performing iteration by adopting the initial value rotation matrix and the translation matrix as iteration initial value of the ICP algorithm, so as to realize the precise matching of the depth images inside the two view fields. The depth image matching method is wide in adaptability and high in matching precision, and can be widely applied to the fields of three-dimensional digital imaging and optical three-dimensional reconstruction.

Description

technical field [0001] The invention relates to the fields of three-dimensional digital imaging and optical three-dimensional reconstruction, in particular to an ASIFT-based depth image matching method. Background technique [0002] 3D Digital Imaging and Modeling (3DIM, 3D Digital Imaging and Modeling) is an emerging interdisciplinary field that has been actively researched internationally in recent years. It is widely used in many aspects such as reverse engineering, cultural relics protection, medical diagnosis, industrial detection and virtual reality. The spatial matching of depth images is a very critical link in 3DIM technology. Due to the limitation of the field of view of the scanning device and the occlusion of the object itself, it is impossible to obtain all the information describing the shape of the object in one scan. Therefore, in order to obtain a complete data model of the measured object, it is necessary to scan the object repeatedly from multiple perspe...

AI Technical Summary

Problems solved by technology

However, the rough matching method based on geometric features is difficult to recognize the features of regular or symmetrical objects, and its adaptability is narrow.

The matching methods based on texture features, such as the feature extraction method based on Harris corner points and the point feature extraction method based on Scale Invariant Feature Transform (SIFT, Scale Invariant Feature Transform), are not completely affine invariant feature extraction methods. When there is a sufficiently large affine transformation in the two images, the matching method based on texture features cannot detect enough common features in the two images, resulting in poor matching accuracy in the case of large changes in the field of view. to a satisfactory result

Images