Font Size: a A A

Design Of Sitting Position And Fall Detection System Based On Inertial Sensor

Posted on:2021-04-01Degree:MasterType:Thesis
Country:ChinaCandidate:X JiFull Text:PDF
GTID:2428330623467370Subject:Control engineering
Abstract/Summary:PDF Full Text Request
With the improvement of people's living standards,the issues of children's healthy growth and safety of the elderly have received more and more attention.Based on the analysis of existing domestic and foreign back posture controllers and elderly fall recognition research,this thesis designs a smart posture detection system that combines the detection of children's back posture and elderly recognition fall Most of the attitude correction devices based on inertial sensors are detection devices with a single sensor,with a single detection site and a single function.This article also focuses on the research of sitting and falling detection,which improves the cost performance and measurement accuracy of the product,and has certain market competitiveness.Based on the research of inertial sensor-based attitude detection systems at home and abroad,this thesis designs and develops a sitting and fall detection system based on inertial sensors.The main research work and results are as follows:(1)Based on the analysis of the research status at home and abroad,the needs for system design are determined.The system frame design and system software architecture design are carried out according to the design requirements of the system.(2)Designed the STM32F072CBU6 microprocessor sitting and fall detection system hardware architecture,using modular circuits,the module circuits mainly include the minimum system module,sensor acquisition module,switch module,voice module,charging circuit module,ADC power acquisition module,Bluetooth module,motor drive module and GPRS wireless communication module,expounded the working principle of each module,completed the production and debugging of the circuit.(3)Human fall experiments and other behavior experiments were performed.The SVM algorithm was used to classify the experimental data and determine the threshold.A method for identifying human fall behavior based on threshold analysis was proposed,which improved the performance of the fall detection system Recognition rate.(4)According to the requirements of the control system,the software of the sitting and falling system was developed,and the main program design,communication with the APP and the server,key scanning,sitting posture correction,fall recognition,low power consumption processing and remote Implementation of the upgrade procedure.Finally,the thesis summarizes the full text,analyzes the shortcomings of the system and future research directions.
Keywords/Search Tags:back posture, inertial sensor, modular, SVM
PDF Full Text Request
Related items