A method and system for point target detection based on machine learning

Abstract

The invention discloses a point target detection method and system based on machine learning, comprising: determining an image to be detected, and dividing it into a plurality of sub-images with preset sizes; using MMF to filter each sub-image to obtain the filtered sub-image Output, if the filter output is less than or equal to the preset threshold, then it is judged that the sub-image is the background, otherwise the sub-image is marked as a candidate sub-image, and the filter scores of each candidate sub-image are determined; through the pre-trained BP neural network The classifier obtains the confidence score of each candidate sub-image containing the target; the filter score of each candidate sub-image and its confidence score of containing the target are input into the pre-trained Logistic regression classifier, and the output value of the Logistic regression classifier is combined Determine whether each candidate sub-image contains an object. The invention uses the Logistic regression algorithm to fuse the results of the MMF algorithm and the BP algorithm to make the classification result more accurate.

Description

technical field [0001] The present invention relates to the field of image processing and pattern recognition, and more specifically, to a machine learning-based point target detection method and system. Background technique [0002] Point object detection is a key technology in modern surveillance systems. Traditional detection methods are mainly filter-based. Filter-based algorithms regard point targets as high-frequency signals and construct specific filters to eliminate or highlight them. However, filter-based algorithms have poor anti-jamming ability, because the edges of noise and background are also high-frequency signals, and they are always misdetected as targets. Furthermore, most filter-based algorithms require prior information about the target, and they are sensitive to parameters. [0003] With the development of machine learning technology, some new point target detection algorithms have emerged. Y.Bi et al. (Y.Bi, X.Bai, Multiple feature analysis for infra...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the defects of the prior art, the purpose of the present invention is to solve the problem that the existing point target detection method has poor anti-interference ability and is sensitive to parameters when it is based on a filter; when using SVM classification, the detection result is greatly affected by the threshold; the infrared small target image is regarded as sparse Complicated technical issues in the calculation process when the low-rank background matrix is ​​destroyed by the target and noise matrices

Images