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

Human body abnormal behavior recognition method and device, equipment and storage medium

A recognition method and abnormal technology, applied in the direction of character and pattern recognition, instruments, computer parts, etc., can solve the problems of public property loss, life-threatening, unable to meet safety prevention and control, etc., to reduce the possibility of prediction errors, The effect of improving the recognition rate

Inactive Publication Date: 2022-02-15
NANJING COLLEGE OF INFORMATION TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] In recent years, with the continuous increase of urban population density, the personnel structure has become more and more complex, making urban management more and more difficult, and security problems caused by various abnormal behaviors (such as fighting, robbery, etc.) are constantly emerging; although the monitoring system has been Widely exist in many public places such as shopping malls, banks, traffic intersections and stations, but the actual monitoring tasks still require more people to complete, and the existing video monitoring systems generally only record video images, so provide us with The information is unexplained video images, which can only be used for evidence collection after the event, and cannot give full play to the initiative and real-time monitoring, resulting in the loss of property of the people and even endangering their lives, and cannot meet the requirements of security prevention and control.

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
  • Human body abnormal behavior recognition method and device, equipment and storage medium
  • Human body abnormal behavior recognition method and device, equipment and storage medium
  • Human body abnormal behavior recognition method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] This embodiment provides a method for identifying abnormal human behavior, including the following steps:

[0038] Based on the historical video data set, the first abnormal behavior recognition model, the second abnormal behavior recognition model and the third abnormal behavior recognition model are established through the 3D convolutional neural network.

[0039] Obtain the RGB video data to be recognized, obtain the coordinates of each joint of the human skeleton of each frame of the RGB video through the OpenPose software, take the coordinates of each joint of the human skeleton as the center, select a part of a certain size on the left and right, copy and paste it to a blank image of the same size. At the coordinates, other pixel values ​​are set to 0 to obtain an image with only the human body left, convert the image into a video, and obtain the video data of the human body area of ​​interest; obtain the human skeleton hand joint coordinates of each frame of the R...

Embodiment 2

[0048] In this embodiment, a device for identifying abnormal human behavior is provided, and the device includes:

[0049] An acquisition module, configured to acquire video data to be identified, and preprocess the video data to be identified, to obtain human body ROI video data and hand ROI video data;

[0050] The first recognition module is configured to input the acquired video data of the region of interest of the human body into the pre-trained first abnormal behavior recognition model to obtain the first abnormal behavior probability set;

[0051] The second identification module is used to input the obtained hand region-of-interest video data into the pre-trained second abnormal behavior identification model to obtain the second abnormal behavior probability set;

[0052] The third identification module is used to input the obtained video data to be identified into the pre-trained third abnormal behavior identification model to obtain the third abnormal behavior proba...

Embodiment 3

[0056] In this implementation, a device is provided, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the method described in Embodiment 1 is implemented. Describe the method of human abnormal behavior recognition.

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 human body abnormal behavior recognition method and device, equipment and a storage medium. The method comprises the following steps: obtaining to-be-recognized video data; preprocessing the to-be-identified video data to obtain human body region-of-interest video data and hand region-of-interest video data; inputting the human body region-of-interest video data into a first abnormal behavior recognition model to obtain a first abnormal behavior probability set; inputting the hand region-of-interest video data into a second abnormal behavior recognition model to obtain a second abnormal behavior probability set; inputting the to-be-recognized video data into a third abnormal behavior recognition model to obtain a third abnormal behavior probability set; and performing fusion processing on the first abnormal behavior probability set, the second abnormal behavior probability set and the third abnormal behavior probability set to obtain a final abnormal behavior probability set so as to determine an abnormal behavior identification result. Multiple models are combined, the possibility of prediction errors caused by model judgment errors is reduced, and the recognition rate is increased.

Description

technical field [0001] The invention relates to a human body abnormal behavior recognition method, device, equipment and storage medium, belonging to the field of image feature and pattern recognition. Background technique [0002] In recent years, with the continuous increase of urban population density, the personnel structure has become more and more complex, making urban management more and more difficult, and security problems caused by various abnormal behaviors (such as fighting, robbery, etc.) are constantly emerging; although the monitoring system has been Widely exist in many public places such as shopping malls, banks, traffic intersections and stations, but the actual monitoring tasks still require more people to complete, and the existing video monitoring systems generally only record video images, so provide us with The information is unexplained video images, which can only be used for evidence collection after the event, and cannot give full play to the initi...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06V40/20G06V20/40G06V10/25G06K9/62G06V10/774
CPCG06F18/214
Inventor 陈婷婷杜鹏飞高思佟刘佳豪胡续辉
Owner NANJING COLLEGE OF INFORMATION TECH