Automatic detection method of human fall based on kinect depth image

Abstract

The invention provides an automatic human body fall-down detection method based on a Kinect depth image. The detection method comprises the following steps: using Kinect to obtain a depth image of a detection environment, performing segmentation and extraction on a human body foreground image, establishing a three-dimensional bounding box of the foreground image of a human body depth image, acquiring length, width and height values of the three-dimensional bounding box and the rate of change within a unit frame, and judging whether a fall-down event occurs according to judgment conditions and a critical value; if the human body is occluded by an obstacle, starting a occlusion fusion algorithm, fusing the human body depth image with an obstacle depth image to create a new three-dimensional bounding box, and judging whether the fall-down event occurs according to the judgment conditions and the critical value; once the fall-down event occurs, alarming through short message service. The automatic human body fall-down detection method utilizes the human body depth image, effectively reduces the misjudgment ratio, utilizes the occlusion fusion algorithm to solve the fall-down event judgment problem when the human body is occluded, reduces the missing report rate, and can perform 24-hour continuous real-time detection on the human body.

Description

[0001] Technical field: [0002] The invention relates to an automatic detection method of a human body fall based on a Kinect depth image. [0003] Background technique: [0004] The automatic detection method of human body fall refers to the technology of using external equipment to automatically monitor and detect the daily activities of the human body in the home environment to detect accidental human body fall events. At present, according to the technical principle of detecting fall events, the automatic human fall detection technology is mainly divided into three types: ① Based on wearable sensors: using three-axis accelerometers and three-axis gyroscopes to collect the acceleration values ​​of the trunk in various states and Angular velocity values, using the threshold method to detect fall events. However, the fall detection equipment based on wearable sensors is not comfortable to wear, hinders the normal movement of the human body, and has a high rate of false alarm...

AI Technical Summary

Problems solved by technology

However, it takes a lot of time to install and calibrate the camera lens; ordinary CCD cameras cannot work at night and under low light conditions, and cannot perform real-time detection; it is easier to leak user privacy; ③based on audio signal technology: by detecting the sound of the human body falling The size and frequency are used to detect the occurrence of human fall events. This type of system has high requirements on the acoustic background of the use environment, complicated installation, large capital investment, and low accuracy.

In the existing literature, there have been automatic human fall detection systems based on the above technologies, but their applicability and detection success rate in real life are not high

Images