Infrared human body object recognition method based on HOG-PCA and transfer learning

Abstract

The invention discloses an infrared human body object recognition method based on HOG-PCA and transfer learning. The method comprises the steps: firstly constructing an infrared and visual light human body or non-human object training sample library; secondly extracting the HOG features of each sample, carrying out the dimension reduction of the features through employing PCA, and obtaining an HOG-PCA target feature set after dimension reduction; thirdly carrying out the training based on the feature set through the transfer learning theory, and obtaining an infrared human body object recognition classifier; and finally completing the recognition of a to-be-detected infrared image. Compared with a conventional human body object recognition algorithm, the method provided by the invention achieves the transferring from a visible light image region to an infrared image field, effectively irons out the defect that a conventional object recognition classifier cannot achieve the training of an effective classifier because of the extremely small number of training samples in the infrared image field, and improves the object recognition rate.

Description

technical field [0001] The invention relates to a human body target recognition technology in an infrared image, which effectively recognizes a human body target in an infrared image, and belongs to the technical field of image processing and pattern recognition. Background technique [0002] Human object recognition is a hot issue in the field of computer vision, which combines the knowledge of many disciplines such as machine learning, digital image processing, and pattern recognition. At present, human target recognition technology for visible light images is relatively mature, but for infrared images, due to the generally small number of labeled training samples, it is difficult to obtain a classification model with excellent performance for human target recognition through training. In addition, in the actual infrared image application field, the imaging distance of the human target is generally far away, and the target only occupies a small pixel size in the image, res...

AI Technical Summary

Problems solved by technology

[0012] Purpose of the invention: Aiming at the problems existing in the prior art, the present invention provides an infrared human target recognition method based on HOG-PCA and transfer learning, which improves the traditional machine learning method due to the lack of sufficient training samples in the field of infrared images. The disadvantage of being unable to train an efficient classifier improves the accuracy of human target recognition in infrared scenes and improves the efficiency of recognition

Images