Image mosaic method

Abstract

The invention provides an image mosaic method, in particular a two-dimensional wide-scene ultrasonic image mosaic method, which is applied to a real-time acquired or stored ultrasonic video image sequence. The method comprises the following steps of: detecting key characteristic points in movable images by using a height relevance of two adjacent frames of images, namely a registration graph and a movable graph, and estimating a motion vector between the movable graph and the registration graph to finish motion matching and overall motion parameter estimation among the characteristic points of the adjacent images so as to obtain a rotating angle and a displacement and further finish a registration process of two images; mapping the current image to a coordinate system of the registration graph or the wide-scene image according to the obtained motion parameters so as to realize fusion between the current wide-scene image and the registered image; and if the wide-scene image exceeds the size of a current display equipment window, integrally moving the image backward with a plurality of pixel points till a new mosaic part of the wide-scene image is totally displayed; otherwise, processing the next image.

Description

technical field [0001] The invention provides an image splicing method, in particular to a A method for registering, merging, splicing and generating panoramic images of multiple two-dimensional images in time sequence. Background technique [0002] Image mosaic is a popular research field in computer vision, and has become a hot issue in the fields of multimedia, medical image processing and computer graphics. The image mosaic problem can be defined as a process of feature extraction, motion parameter estimation, image fusion and enhancement for a series of spatially overlapping images, and finally a seamless, high-resolution wide-view image is generated. [0003] Image stitching technology is mainly divided into three main steps: image preprocessing, image registration, image fusion and boundary smoothing, image preprocessing mainly refers to the image before registration, Image noise suppression, texture and contrast enhancement and Preprocessing such as normalizati...

AI Technical Summary

Problems solved by technology

[0009] Existing image mosaic techniques search for feature points and sub-regions that match the activity map in a larger image field corresponding to the corresponding feature points or sub-regions of the registration map to realize the feature point matching algorithm. The disadvantage is that the search process is very time-consuming, and the application of heuristic search can only find a local optimal solution, such as CN101455576A application of hill climbing method to solve the time-consuming problem of feature point matching algorithm

CN1839760A pointed out that due to factors such as noise and tissue movement, the error of the movement offset of the feature point will be caused, but it does not provide an effective solution

[0010] In summary, the existing image stitching technology cannot solve the problem of poor matching accuracy of feature points or sub-regions, nor can it effectively deal with the impact of moving objects on the estimation of rigid registration parameters, and the cost of matching search algorithms for feature points and sub-regions. time issue

Images