Multi-sensor fused wristed falling detection method and device

Abstract

The invention discloses a multi-sensor fused wristed falling detection method and device. According to the invention, the human body moving attitude data can be acquired in real time, the characteristic vector is extracted after the acquired data is analyzed and fused, and whether the falling behavior occurs is determined through a secondary determination algorithm based on threshold positioning and a support vector machine, so that the limitation of the video detection test area is overcome, the anytime and anywhere detection can be realized, high falling detection accuracy is guaranteed, the use is convenient, better user experience effect is guaranteed, the design is reasonable and effective, and the cost is saved.

Description

technical field [0001] The invention relates to the field of fall detection, in particular to a multi-sensor fusion wrist-type fall detection method and device. Background technique [0002] Fall detection system based on video image: This system installs one or several video acquisition cameras fixedly in the room to capture images of human activities. The captured images are analyzed and processed by related algorithms, and then the features of the falling images are extracted to determine the occurrence of falling behavior. [0003] Fall detection systems based on wearable devices: Most of these systems are worn on fixed parts of the human body, usually on the chest, waist, legs, and wrists. By adding relevant posture sensors to the device, a wearable detection device is formed, and the data output by the sensor during the movement of the subject is collected to analyze and detect the fall behavior. [0004] The fall detection system based on video images is limited by ...

AI Technical Summary

Problems solved by technology

[0004] The fall detection system based on video images is limited by the space area. The system can only be installed in a fixed position indoors. When the detected person leaves the detectable range of the video camera, the system cannot realize the fall detection, thus limiting the detected person. Secondly, the video image has a delay, which may affect the real-time detection of activity behavior, and the image quality will also be affected by the environmental factors of the system; finally, the video image acquisition involves the personal privacy of the detected person. Obtained by others, the personal privacy of the detected person will not be guaranteed

[0005] The fall detection system based on waist and leg wearable devices is inconvenient to wear, the design of the fall detection system is relatively simple, and the appearance and use cannot achieve the desired effect

Images