Infrared human body target image recognition method based on multi-feature fusion and multi-core transfer learning

Abstract

The invention discloses an infrared human body target recognition method based on multi-feature fusion and multi-core transfer learning. Firstly, based on the special imaging mechanism of infrared image, an improved CLBP feature is extracted from the target in the infrared scene, MSF-CLBP is used to express the texture information, and an improved local HOG feature-HOG-FV is used to express the shape information. In order to explore the effective features in the target; secondly, for the two heterogeneous features extracted above, the method of tandem fusion is used for feature fusion, so thatthe description of the target feature information is more objective and comprehensive. Finally, a classifier combining multi-core classification and TrAdaBoost migration learning framework is designed, which effectively solves the problem of insufficient image of labeled infrared samples, and enhances the distinguishability of the data to be classified to obtain better recognition results. The method starts from the improvement of feature extraction and the design of classifier, improves the expression of feature information, and improves the performance of infrared target recognition in complex background.

Description

technical field [0001] The invention belongs to the technical field of infrared image processing and pattern recognition, and in particular relates to an infrared human target image recognition method based on multi-feature fusion and multi-core transfer learning. Background technique [0002] Human target recognition in infrared scenes is an important research branch in the field of infrared image processing and pattern recognition, and it has been widely used in practical applications such as video surveillance, target tracking and automotive assisted driving systems. In order to realize the effective recognition of human targets in infrared images, the key lies in the accurate and comprehensive feature extraction of human targets and the design of a reasonable classifier for classification and recognition. [0003] First of all, in terms of infrared image target feature extraction, many scholars have proposed and improved many excellent feature extraction algorithms, such...

AI Technical Summary

Problems solved by technology

[0009] (1) In terms of feature extraction, although the extraction of a single feature of an image target can better mine the characteristics of a certain aspect of the target, the incomplete feature information actually reduces the accuracy of image feature extraction

In addition, many multi-feature extraction and fusion methods seem to enhance the completeness of feature description, but in fact they are repeated descriptions of the same type of information. The target feature extraction and fusion are still not very well realized, so the subsequent recognition performance can be further improved

[0010] (2) In terms of classifier design, although classifiers based on traditional machine learning algorithms have achieved a lot of results in the application of target classification and recognition, their strict use conditions hinder their practical application in infrared human target images

Images