Fall detection method and system based on multiple sensors

• Main Authors: ZENG QINGHUI, TANG YANPING, ZHANG YUWEI, GUO DEPING, HU YUNCAO, LI YUYOU, LUO WEI, LIU QI, GENG BINJIE, LIU YU, PAN XIAOYU
• Format: Patent
• Language: Chinese; English
• Published: 14.05.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DIAGNOSIS; ELECTRIC DIGITAL DATA PROCESSING; HUMAN NECESSITIES; HYGIENE; IDENTIFICATION; MEDICAL OR VETERINARY SCIENCE; PHYSICS; SURGERY

The invention relates to the field of tumble detection, in particular to a tumble detection method and system based on multiple sensors. A tumble detection method based on multiple sensors comprises a monitoring data acquisition module, a tumble preliminary judgment module, a tumble sampling strategy execution module and a tumble detection module. According to the invention, the current pose state of a person is monitored through a plurality of sensors, and whether the person is in a tumble state is preliminarily judged based on the obtained monitoring data and the set vertical acceleration threshold value, so that the situation that the execution of subsequent tumble judgment is influenced due to relatively low sampling frequency at the moment is avoided; according to the method, a tumble sampling strategy with a larger sampling frequency is executed, richer monitoring data can be obtained, a tumble detection time sequence data set is detected through a tumble detection model, and due to the fact that the ti