People counting method and device based on Bi-LSTM network model, and readable storage medium

Abstract

The invention relates to the technical field of communication, and discloses a people counting method and device based on a Bi-LSTM network model, and a readable storage medium. The method comprises the following steps: collecting training wireless data of different people based on a wireless receiver; constructing and training a Bi-LSTM network model by utilizing the training wireless data; and acquiring current wireless data, inputting the current wireless data into the Bi-LSTM network model, and calculating to obtain a current people counting result. Accurate people counting can be realized, the influence of environment and building structures on people counting is reduced, the influence of illumination intensity on people counting is reduced, and the function of counting people by avoiding buildings is realized.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a method, device and readable storage medium for people counting based on a Bi-LSTM network model. Background technique [0002] At present, with the development of science and technology, people counting is playing an important role in military operations, emergency search and rescue, and public safety. However, the wearable people counting system needs to be worn all the time, so the application scenarios are very limited, and people counting cannot be achieved through occlusions; the people counting system of visible light machine vision is greatly affected by problems such as occlusion, changes in light intensity, and privacy protection. , cannot achieve accurate population statistics. Contents of the invention [0003] The main purpose of the present invention is to propose a people counting method, device and readable storage medium based on the Bi-LSTM network mo...

AI Technical Summary

Problems solved by technology

However, the wearable people counting system needs to be worn all the time, so the application scenarios are very limited, and people counting cannot be achieved through occlusions; the people counting system of visible light machine vision is greatly affected by problems such as occlusion, changes in light intensity, and privacy protection. , cannot achieve accurate population statistics

Images