Infrared multi-target segmentation method based on minimum tree clustering

Abstract

The invention relates to an infrared multi-target segmentation method based on minimum tree clustering. The method is characterized in that an image is preprocessed by the adoption of a background differencing method and morphological operation, and a binary image with a target area and a background area separated is obtained; uniform sampling and nearest neighbor classification are carried out on all pixel points in the target area in the binary image so as to initially classify the pixels of the target area into subclasses; the minimum tree is constructed with the subclasses as top points and with the space, obtained by calculation through an L1 norm and a Gaussian kernel function, between the subclasses as the side length; the obtained side length threshold is calculated, the long side of the minimum tree is cut, a final clustering result is obtained, isolated points and noise points are removed, and each residue class serves as a target; all target centroids are marked through crosses in an original infrared image, and all target special ranges are marked through rectangular boxes.

Description

technical field [0001] The invention belongs to the field of image processing and machine vision, and relates to an infrared multi-target segmentation method based on minimum tree clustering. Background technique [0002] Target segmentation in infrared images includes two meanings, one is to separate the pixels of the target from the background pixels, and the other is to separate the pixels belonging to different targets. The target pixel is separated from the background pixel using a relatively mature background difference method, and the area with a large difference between the image to be detected and the background is considered as the target area. [0003] The present invention uses a clustering method to separate pixels belonging to different objects. Clustering is the process of dividing a data set without category labeling into several subsets according to the attribute characteristics of each object, so that the similarity between objects in the same subset is re...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose an improved minimum tree clustering method based on the L1 norm and Gaussian kernel function according to the distribution characteristics of the target pixels in the infrared image, aiming at the defects of some existing clustering methods, so as to complete the classification of multiple pixels in the infrared image. Target segmentation, solve the problems of initial value selection, non-spherical cluster recognition, noise point interference and low efficiency in processing large data sets in some existing clustering methods when segmenting multiple infrared targets

Images