Artificial neural network-based multi-source gait feature extraction and identification method

Abstract

The invention relates to identification, image processing and the like, in particular to an artificial neural network-based multi-source gait feature extraction and identification method, which aims to reduce inferences with external factors such as complex background and shelters so as to more accurately extract the effective information reflecting the walking characteristics of the moving people and improve the gait identification accuracy. The technical scheme of the invention comprises the following steps: separately acquiring the gait data by using a camera and a pyroelectric infrared sensor; extracting the skeleton feature parameter and Radon change peak characteristic parameter from the image source information acquired by the camera, and for the pyroelectric infrared source information, converting an acquired voltage signal into frequency domain characteristic parameter; merging the skeleton feature parameter, the Radon change peak feature parameter and the frequency domain characteristic parameter which are subjected to dimension reduction and corresponding signal process; and finally, realizing classified identification of the merged characteristics by using a BP neutralnetwork as the classifier and evaluating the identification effect. The method is mainly applied to identification.

Description

technical field [0001] The invention relates to video processing, infrared pyroelectric signal analysis, image processing, feature extraction, pattern recognition and the like. Specifically, it involves a multi-source gait feature extraction and identification method based on artificial neural network. technical background [0002] Biometric identification is the identification of personal identity through various high-tech information detection methods and the use of the inherent physiological or behavioral characteristics of the human body. Biological characteristics mainly include physiological characteristics and behavioral characteristics: physiological characteristics refer to innate and congenital physical characteristics of the human body, such as fingerprints, irises, faces, etc.; behavioral characteristics refer to the characteristics extracted from the movements performed by people The characteristics that come out are mostly acquired, such as gait, handwriting a...

AI Technical Summary

Problems solved by technology

[0007] Most of the current gait recognition algorithms are based on shape information. The defect is that when the outline of the human body changes (such as backpacks, occlusion between objects and the environment, or between objects and objects), single shape feature recognition cannot achieve satisfactory results.

Images