Contour vector feature-based embedded real-time image matching method

Abstract

The invention provides a contour vector feature-based embedded real-time image matching method. The method uses the linear feature based on X and Y direction vectors, and has strong capability of resisting image distortion, noise, shading, illumination changes, polarity inversion and so on. An image pyramid search strategy is used, templates are quickly matched in a high-layer low-resolution image to be tested, and then, a target position is found out accurately by stepwise downward search, so that matching time is reduced greatly. According to the template image specific information, the best pyramid hierarchy number and the best rotation angle step size for the pyramid template matching of each layer are calculated automatically. An image pyramid highest-layer three-level screening matching strategy is provided, treatment is carried out according to the specific content of the image to be tested, and the first level of screening and the second level of screening are carried out; the non-target position is eliminated just by the addition and subtraction and the conditional statements, which is more efficient in the embedded system than using the multiplication and division; and the third level only processes fewer positions meeting the requirements of the above two levels, so that the matching speed is improved greatly. The overall method can realize the work of matching and locating the target at any angle and any coordinate.

Description

technical field [0001] The invention relates to an image matching method, in particular to an embedded real-time image matching method based on contour vector features. Background technique [0002] Image matching refers to the establishment of an index based on information such as color, texture, shape, or their combination features contained in a given target image, and through the similarity measurement between image feature vectors, in one (or a batch) of images to find The process of image regions (subimages) that are the same or similar to a given object. The given target image is usually called a template image, and the subsequent sequence images to be searched are called images to be tested. [0003] Image matching technology has a wide range of applications in many fields, including the following aspects. Fusion of CT, MRI, PET, SPECT image structure information in medical image processing. Information fusion of multi-electromagnetic band images (such as microwav...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to solve the shortcomings of previous image matching methods, such as large amount of calculation, serious time-consuming, resistance to image distortion, noise, occlusion and illumination changes, etc., which have little influence on the external environment, and difficult to match when the polarity of the template is reversed. An embedded system that uses the contour point direction vector as a feature, considers the translation and rotation of the target, and realizes fast and accurate matching and positioning of the image target according to the specific image content of the image to be tested

Images