Localization method of mobile device on human body based on sensor fusion
A mobile device and positioning method technology, applied in the direction of user/computer interaction input/output, mechanical mode conversion, computer components, etc., can solve the problem of unknown location of mobile/wearable devices
Active Publication Date: 2022-04-22
XUZHOU UNIV OF TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This patent proposes a positioning method for mobile / wearable devices on the human body based on RGB-D and inertial sensor fusion. Using the selected key joint point data, the position of the mobile / wearable device on the body can be accurately calculated. , to solve the problem of unknown location of mobile / wearable devices in human behavior recognition
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0054] The method of the present invention will be described in further detail below in conjunction with specific embodiments and accompanying drawings.
[0055] The mobile device is set as a smart bracelet with built-in inertial sensors, which is worn on the right wrist of the experimenter. The RGB-D somatosensory sensor is placed in a fixed position in the laboratory, and the experimenter moves within the observation range of the somatosensory sensor. Follow the attached figure 1 The steps describe the experimental procedure.
[0056] First, M frames of human body depth images are obtained through RGB-D somatosensory sensors, and the sampling rate of somatosensory sensors is set to 30Hz; at the same time, data from inertial sensors embedded in mobile devices are obtained within the same time period, and the sampling rate of inertial sensors is set to 90Hz;
[0057] Secondly, extract the coordinates of human skeleton points and obtain the positions of human joint points, and...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a positioning method of a movable device on a human body based on sensor fusion, by fusing the position data of different human body joint points collected by RGB‑D somatosensory sensors and the movable joint point data obtained by the fusion calculation of the built-in inertial sensor of the movable device. Device acceleration, determine the logarithmic likelihood value of the joint data, compare the matching degree between the position data and the acceleration data, and determine the position with the highest matching degree with the acceleration of the mobile device. This positioning information can be the position of the mobile device on the person. The method of the present invention is different from the traditional method of classifying the position of the mobile device, and also different from the method based on image processing, relying on the RGB-D somatosensory sensor placed in the environment and the built-in inertial sensor of the mobile device. The mobile device is automatically positioned when the personnel of the mobile device is active, which is suitable for various environmental conditions and has strong practicability.
Description
technical field [0001] The invention relates to a method for locating a movable device on a human body, in particular to a method for locating a mobile device on a human body based on sensor fusion. The present invention is not only applicable to wearable devices, but also to movable devices such as mobile phones. When the movable device is on the human body, the positioning method locates the movable device at the joint points of the human body. Background technique [0002] A basic challenge in human behavior recognition based on mobile devices is caused by the unknown location of mobile devices. Users can put mobile devices, such as mobile phones, on their waists, hands, etc., which brings great challenges to human behavior recognition. difficulty. Scholars at home and abroad have done a lot of research on human action recognition based on wearable / mobile devices. Assuming a known and definite wearable sensor location, research on human action recognition independent of ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F3/01
CPCG01C21/16
Inventor 冯仕民赵小虎丁恩杰
Owner XUZHOU UNIV OF TECH