Unlock instant, AI-driven research and patent intelligence for your innovation.

Suicide risk assessment method based on body language

A risk assessment and limb technology, applied in the field of emotion recognition, can solve the problems of being easily affected by noise, low computational complexity, low recognition accuracy, etc., to achieve the effect of improving accuracy

Active Publication Date: 2020-12-18
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Technically, audio data is readily available but susceptible to noise
In terms of computational complexity, the computational complexity of single detection of static posture or single detection of dynamic action to recognize emotion is lower, but it also leads to lower recognition accuracy

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Suicide risk assessment method based on body language
  • Suicide risk assessment method based on body language
  • Suicide risk assessment method based on body language

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0054] A body language-based approach to suicide risk assessment, such as figure 1 shown, including the following steps:

[0055] S1, in this embodiment, use a kinect placed within the range of 5 meters to capture video and collect the body behavior data of the personnel staying in the room as input data;

[0056] S2, such as figure 2 As shown, the input data is divided into static poses and dynamic actions, and the convolutional neural network is used to extract the features of static poses and the two-way long-term short-term memory neural network is used to extract the features of dynamic actions;

[0057] Static gesture recognition is as follows:

[0058] Input the frames in the video into the convolutional neural network (CNN) for training and testing. The input is the video frame, and the output is the static posture category corresponding to the person in the video frame, including right arm raised, right shoulder raised, head right Tilt, body leaning right, left ar...

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

No PUM Login to View More

Abstract

The invention discloses a suicide risk assessment method based on a body language. The method comprises the following steps: capturing limb behavior data of a video acquisition person by using kinectto serve as input data; dividing the input data into static postures and dynamic actions, and extracting the characteristics of the static postures by using a convolutional neural network and extracting the characteristics of the dynamic actions by using a bidirectional long-term and short-term memory neural network respectively; using a long-term and short-term memory neural network for effectively fusing features of static postures and features of dynamic actions and unifying the features to the same feature space; and outputting whether the person has the suicide tendency or not through thesoftmax layer. According to the invention, the static posture features and the dynamic action features of people are used at the same time, and emotion recognition accuracy can be effectively improved. According to the invention, dynamic and static characteristics of people are embedded into a unified characteristic space, so that the characteristics can be used more effectively and harmoniously.

Description

technical field [0001] The invention belongs to the field of emotion recognition, in particular to a body language-based suicide risk assessment method. Background technique [0002] Due to their poor social adaptability and unstable mental state, inmates are very easy to cause harm to themselves or others. To prevent inmates from self-harm or committing crimes, it is necessary to detect their emotional tendencies. Human emotional tendencies can be predicted in many ways, such as electrocardiogram, electroencephalogram (Journal of South China Normal University (Natural Science Edition), 2019(5)), speech (Computer Science, 2015(09):24-28), Facial expressions (Journal of Xi'an Technological University, 2015, 35(009):705-709), etc. Among various emotional signals, physiological signals are widely used for emotion recognition. Recently, body movements have also become a new feature. [0003] So far, many models for emotional tendency prediction have been proposed, but there ...

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
no application Login to View More
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/049G06N3/08G06V40/20G06V20/46G06N3/045G06N3/044G06F18/253Y02A90/10
Inventor 杜广龙
Owner SOUTH CHINA UNIV OF TECH