Infrared image target recognition method

Abstract

The invention discloses an infrared image target recognition method. The method solves the technical problem of two-dimensional infrared image segmentation by using the concept of one-dimensional image processing, i.e. each row of image pixels for cyclic segmentation processing is synthesized into two-dimensional binary images; and the concrete steps of the method are as follows: firstly, the infrared image enhancement is performed by a multiscale wavelet transformation method; secondly, the stable segmentation of the infrared targets under various imaging conditions is realized by using the extraction to the convex area in the infrared image, and after each row of the pixels is processed, the processing results are synthesized into two-dimensional binary images with sizes consistent withthat of the original images; thirdly, the binary image connected component labeling is performed to the segmented images, meanwhile, the basic characteristics are extracted, then the characteristics to be extracted are defined on the basis, and the characteristic extraction is calculated by using the basic characteristics; fourthly, a candidate target area is determined by a voting method, the accurate recognition is performed by ultimately combining the prior knowledge of the target to be recognized, and the final target is determined from the candidate targets. The invention has the advantages of accuracy, real-time and robustness.

Description

technical field [0001] The invention relates to image processing, pattern recognition and automatic target recognition (ATR) technology, in particular to a segmentation and recognition method of an infrared image target to be recognized (especially an infrared airport runway). Background technique [0002] At present, infrared image segmentation and automatic target detection (Automatic Target Detection, ATD), automatic target recognition (Automatic Target Recognition, ATR) technology is being widely used in automatic target recognition, aircraft route terrain matching and landmark verification, target search and rescue wait. The advantages of this kind of technology are becoming more and more prominent, and the application is becoming more and more extensive. Therefore, it has attracted great attention from domestic and foreign scientific research institutions, and has always been a research hotspot at home and abroad. Among them, the long-distance forward-looking infrared...

AI Technical Summary

Problems solved by technology

[0014] The present invention utilizes the idea of ​​one-dimensional (1D) image processing to solve the technical problem of two-dimensional (2D) infrared image segmentation, that is; each line of image pixels processed by the loop segmentation process is synthesized into a two-dimensional binary image, specifically; 1) through multi-scale The wavelet transform method enhances the target to be recognized in the infrared image; 2) realizes the stable segmentation of the infrared target under various imaging conditions by extracting the convexity area of ​​the infrared image, processes one row of pixels each time, and synthesizes the processing result with the original image A two-dimensional binary image with the same size; 3) Then perform binary image connectivity marking on the segmented image and extract basic features at the same time, then define the features to be extracted on this basis, and use the basic features to calculate feature extraction; 4) Use voting The method to determine the suspected candidate target area, and finally combine the prior knowledge of the target to be identified for accurate identification, and determine the final target from the candidate targets

Images