Pedestrian identity recognition method based on mobile phone inertial sensor

Abstract

The invention provides a pedestrian identity recognition method based on a mobile phone inertial sensor. The core of the method is a deep neural network model. The model is composed of three convolution layers, two LSTM units, an attention mechanism module and a full connection layer, and after learning and training, the model can mine hidden biological characteristic information in inertial sensor data contained in the smart phone to realize identity verification of a mobile phone carrier. The method disclosed by the invention has the advantages of small data volume and high calculation speed, and the required cost is relatively low due to rapid development of electronic components such as sensors and the like in recent years.

Description

technical field [0001] The invention describes a deep neural network method for pedestrian identity verification based on mobile phone inertial sensors, and belongs to the technical field of biological feature recognition. Background technique [0002] Biometric identification technology refers to the use of the inherent physiological and behavioral characteristics of the human body to verify personal identity. This technology is not easy to forge or be stolen, and is safe and convenient. At present, most biometric identification technologies are to identify people's irises, fingerprints or faces. Most of these existing technologies are based on images, and the calculation speed is slow. Due to the low cost of sensors, small amount of data and easy calculation, biometric identification methods based on inertial sensors have more potential for development. However, most of the existing identification technologies based on inertial sensors use traditional machine learning met...

AI Technical Summary

Problems solved by technology

However, most of the existing identification technologies based on inertial sensors use traditional machine learning methods. Due to the limitations of the size and power consumption of wearable sensors, the collected data will have large data noise, which makes traditional methods unable to To effectively carry out data mining, it is necessary to manually extract the features in the sensor data sequence, and the information that these features can express is limited, and the final recognition effect is very low, and prior experience is often added to assist judgment

Images