Efficient image matching method based on improved scale invariant feature transform (SIFT) algorithm

Abstract

The invention discloses an efficient image matching method based on an improved scale invariant feature transform (SIFT) algorithm. The method comprises the following steps of: (1) extracting feature points of an input reference image and an image to be matched by using an SIFT operator; (2) by using a Harris operator, optimizing the feature points which are extracted by the SIFT operator, and screening representative angular points as final feature points; (3) performing dimensionality reduction on an SIFT feature descriptor, and acquiring 64-dimension feature vector descriptors of the reference image and the image to be matched; and (4) initially matching the reference image and the image to be matched by using a nearest neighbor / second choice neighbor (NN / SCN) algorithm, and eliminating error matching by using a random sample consensus (RANSAC) algorithm, so the images can be accurately matched. The method has the advantages that by selecting points which can well represent or reflect image characteristics for image matching, matching accuracy is ensured, and the real-time performance of SIFT matching is improved.

Description

technical field [0001] The invention relates to an image matching method, which belongs to the technical field of image processing. Background technique [0002] Image matching refers to the corresponding relationship between images of the same scene at two different time points. It is a basic problem in the field of computer vision research, and it is also a computer vision application, such as depth restoration, camera calibration, motion analysis, and 3D reconstruction. The starting point or basis for research on a problem. [0003] Among the feature matching methods, point features are most widely used today. Now common feature point extraction algorithms include: Harris operator, ForIstner operator, SIFT algorithm and edge point extraction method based on wavelet transform. Among them, the SIFT algorithm has become the most stable algorithm due to its unique advantages. The SIFT (Scale Invariant Feature Transform) algorithm is a scale-invariant feature transformation...

AI Technical Summary

Problems solved by technology

[0013] Although the feature points extracted by SIFT are stable, the SIFT algorithm has many disadvantages, such as: high algorithm complexity, large amount of calculation data, and long time-consuming

Researchers have taken many improvements to address the above shortcomings, and Yanke et al. proposed the PCA-SIFT method [1] , the purpose is to reduce the data dimension of the feature description, although the matching speed is accelerated, but because there is no prior knowledge as the basis, this method increases the amount of calculation; Grabner et al. use the integral image method [2] , which increases the calculation speed of SIFT, but reduces the superiority of the SIFT method

Images