Human body tumble detection method based on multi-source heterogeneous data fusion

Abstract

The invention belongs to the field of human body tumble detection, and provides a human body tumble detection method based on multi-source heterogeneous data fusion. The method comprises the followingsteps: acquiring a behavior depth image and skeleton information of a human body through Kinect, and getting rid of constraints of a wearable sensor on selection of the sensor; secondly, solving theproblem that wearable sensors cannot be used in specific scenes such as bathrooms and toilets, and meanwhile, avoiding the problem that human privacy is invaded due to the fact that a common camera isused for monitoring; meanwhile, extracting features from multi-source heterogeneous data through a deep learning model, introducing keyless attention fusion into a data fusion mode, and avoiding dataredundancy and calculation complexity generated by data-level fusion. Compared with the prior art, the accuracy of tumble detection is remarkably improved.

Description

technical field [0001] The invention belongs to the field of human body fall detection, in particular to a human body fall detection method based on multi-source heterogeneous data fusion. Background technique [0002] With the development of aging society, falls have become a common health problem among the elderly, and fall detection has become an important research direction. Fall is usually defined as "unconsciously moving to the ground or lower." Fall detection is mainly through various types of sensors to monitor human body signals for collection, processing and judgment. Sensors are roughly divided into wearable sensors and environmental perception sensors; among them, in wearable sensor systems, accelerometers are usually used to sense the tester's orientation changes, gyroscopes are used to detect angular momentum, or other types of sensors such as barometers and magnetometers etc. These wearable sensors are generally placed on the wearer's chest, waist, wrist, thi...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a human body fall detection method based on multi-source heterogeneous data fusion in order to solve the problems of unstable signals, possible data loss, and inability to achieve real-time monitoring when using wearable sensors in current fall detection.

The present invention utilizes the Microsoft Kinect device to obtain depth images and bone data for fall detection. Firstly, the choice of sensors gets rid of the constraints of wearable sensors; At the same time, it can also avoid the use of ordinary cameras for monitoring and violation of human privacy; finally, the algorithm is improved in the fusion method of multi-source heterogeneous data, which improves the accuracy of fall detection

Images