Multi-feature image segmenting and positioning method suitable for spatial non-cooperative targets

Abstract

The invention discloses a multi-feature image segmenting and positioning technique suitable for spatial non-cooperative targets, which compensates the shortcomings of the existing algorithms in terms of operation efficiency, adaptation range and robustness. The technique comprises: at first, using an SLIC algorithm to segmenting an image to obtain super-pixels with similar sizes, then respectively calculating primary and secondary direction ratio features, variance features and area perimeter features of different super-pixels, cascading different feature weights to form final evaluation of the super-pixels, and using the super-pixels with evaluation values higher than a threshold as target positioning candidate areas; and finally, repeatedly executing the steps on a filtered fuzzy image to obtain another group of candidate areas, and using an overlapped part of the two groups of candidate areas as a target prediction area, so as to quickly detect and position an unknown target.

Description

【Technical field】 [0001] The invention belongs to the field of image processing and computer vision, and in particular relates to a multi-feature image segmentation and positioning method suitable for space non-cooperative targets. 【Background technique】 [0002] Vision is an important way for human beings to obtain external information. Studies have shown that in daily life, more than 70% of human information is obtained in the form of vision through eyes, and images are an important carrier of information. With the development of image processing technology, the size and resolution of images are gradually increasing, and the information contained in them is also constantly enriched, which brings great pressure to the operation of image processing algorithms and equipment. But for most applications, such as pedestrian monitoring, face recognition, etc., we generally only care about the area containing certain characteristic objects in the image, and are not interested in ot...

AI Technical Summary

Problems solved by technology

However, traditional image segmentation algorithms mainly face two problems in practical applications: 1. A general segmentation algorithm that can accurately process images has not yet appeared, and the algorithm needs to adjust parameter settings according to specific applications; 2. The time complexity of the algorithm is often high. Difficult to meet real-time requirements

For example, the GS (Graph-basedSegmentation) algorithm, although its running time is fast, but the algorithm cannot adjust the parameters such as the size of superpixels; the segmentation algorithm based on NC (NormalizedCuts) can easily adjust the number of superpixels, but its time overhead Too large, and the segmentation effect is not ideal

Images