Tumble detecting and positioning system and method

Abstract

The invention discloses a tumble detecting and positioning system and method. The tumble detecting and positioning system comprises a tumble detecting and positioning device, which comprises an inertia navigation module, a GPS (Global Position System) module, a main controller and an Sim (Subscriber Identity Module)-300 module, wherein the inertia navigation module consists of a triaxial gyroscope, a triaxial magnetometer and a triaxial accelerometer; the GPS module and the inertia navigation module are respectively connected with the main controller; the main controller is connected with the Sim-300 module; and the tumble detecting and positioning device is connected with a kin mobile phone and a ward station, which are bound with tested personnel, through GSM (Global System for Mobile Communications) / GPRS (General Packet Radio Service). A tumble detection algorithm based on a nerve network and machine learning is further designed to accurately detect the tumble status and position information of human bodies, the information is transmitted to the ward station through the GSM / GPRS, and the status and the positions of tested personnel are real-timely displayed on a monitoring picture. The tumble detecting and positioning system can accurately detect the tumble status of the tested personnel and track and position the tested personnel in real time, is convenient and practical, and has high accuracy and strong stability.

Description

technical field [0001] The invention relates to a behavior analysis and identification method, a state monitoring and alarm, detection and positioning system, in particular to a fall detection and positioning system and method. Background technique [0002] The 21st century is an era of population aging. At present, all developed countries in the world have entered the aging society, and many developing countries are entering or will soon enter the aging society. China is the country with the largest elderly population in the world. According to statistics, by the end of 2004, China's elderly population aged 60 and above was 143 million, and it will reach 200 million in 2014 and 300 million in 2026. Accidental falls are the most common cause of people over 65 years old. The main health threats and causes of death, among the people who need medical care due to falls, people aged 65 and over account for more than 30%, and among the people who die due to falls, 40% are people o...

AI Technical Summary

Problems solved by technology

[0003] At present, human fall detection is generally divided into two types based on vision and wearable sensors in terms of hardware. Among them, the use of vision for human fall detection will be seriously affected by the external environment, such as lighting conditions, background, occlusion size and camera. Quality, etc. In addition, due to the limited monitoring area of ​​the camera, the range of activities of the monitored elderly or patients will be limited. In the research of using wearable sensors to detect human falls, one is to use accelerometers to detect the acceleration of human activities. By setting the threshold to judge whether to fall, it is difficult to distinguish falls from people's daily strenuous activities, such as jumping, going up and down stairs, etc.

Patents 200720125141.1 and 200910145045.7 both use a three-axis accelerometer to measure the acceleration of the human body, and at the same time calculate the tilt angle. The former judges whether a fall occurs by setting the acceleration and angle thresholds, and it is difficult to distinguish between fast walking and violent actions such as going up and down stairs. The latter is to judge the angle relationship before and after a period of time when a person is impacted during the fall process to determine whether a fall has occurred. This method requires that the human body has an obvious impact during the fall process, and it is difficult to identify the elderly who suddenly fainted or fell slightly. Moreover, other The angle is calculated by acceleration. Obviously, when the human body is violently moved or disturbed by vibration, the calculated tilt angle will be seriously deviated, and the recognition rate will be seriously reduced; the other is to detect the angle of the human body through the wearable angle sensor and set the angle threshold. and time threshold to judge whether to fall, this method is difficult to distinguish normal behaviors such as bending over and lying flat

For example, patents 200620075599.6 and 200620003000.8 judge whether a fall has occurred by detecting the inclination of the human body through sensors. The method has a high misjudgment rate and is very unstable

Images