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

A method for detecting abnormal behavior of personnel based on target distribution

A technology of distribution law and detection method, applied in instrument, calculation, character and pattern recognition, etc., can solve the problems of large dependence between features, easy to be affected by occlusion, and high false positive rate.

Active Publication Date: 2020-10-20
SHANDONG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the current level of social development, the level of medical resources and the number of guardians are limited, it is difficult to provide a full range of personalized guardianship services for each need. treatment, which may lead to serious consequences
[0003] Most of the existing monitoring systems for the elderly and patients who need to be cared for use contact sensors to collect physiological parameters such as the heart rate, pulse, and exercise of the elderly, and pressure sensors to collect postures such as lying and sitting. There are many types of sensors and complex system deployment. Wearable style leads to poor user experience
[0004] In the existing technology, the position acquisition mostly uses active infrared and passive infrared sensors, which are easily affected by occlusion, are not accurate enough and require a large number of layouts; in the prior art, some abnormal feedbacks are used in the time series of sensor feedback in big data The position of the person trains a Bayesian network. The Bayesian network model only relies on location variables, time variables and abnormal probability variables to model. The model features are too few and the dependencies between features are too large. The performance of the established Bayesian network model is very poor. Poor, leading to overfitting of the model, lack of generalization ability and individual uniqueness, and judging whether the ward has abnormalities is a complex multi-dimensional problem. Only relying on location and time to speculate whether there are abnormalities has a high rate of misjudgment

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
  • A method for detecting abnormal behavior of personnel based on target distribution
  • A method for detecting abnormal behavior of personnel based on target distribution
  • A method for detecting abnormal behavior of personnel based on target distribution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] A method of target detection using deep learning to realize personnel anomaly detection based on distribution rules, such as figure 1 shown, including the following steps:

[0053] (1) Target detection: use the deep learning target detection network model pre-trained in the public data set, fine-tune the training according to the deployment scenario, and obtain the deployed target detection network for real-time personnel and various object detection, and detect the detected personnel and various objects Form a bounding box, that is, Boundingbox, and return the position information of the detected person and each object. The position information includes the coordinate information of the four vertices of the bounding box; for example, Faster-rcnn, Mask-rcnn, YOLO and other target detection network models in Imagenet data The model parameters are pre-trained on the set. After the initial pre-training, the detection of daily objects and people can be realized. Then, accor...

Embodiment 2

[0075] According to a method of using deep learning to detect objects based on distribution rules to realize abnormal detection of personnel according to Embodiment 1, the difference is that:

[0076] The abnormality detection of described step (6) is realized by abnormality detection system, and abnormality detection system comprises picture acquisition module, operation module and warning reminder module;

[0077] The image acquisition module includes four sets of Hikvision high-definition cameras, which are used to collect video and transmit it to the computing module for real-time video processing; the camera collects images, performs simple frame difference and background difference detection, and transmits images to Computing module, this design can reduce the pressure on the computing module;

[0078] The computing module is NVIDIA TX2, which is used to process the transmitted data in real time for target recognition and anomaly detection; NVIDIA TX2 is only the size of...

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 relates to a method for detecting abnormal behavior of personnel based on target distribution rules. It adopts a pre-trained deep learning network, learns and trains fine-tuning parameters according to the deployment scene target, performs target detection, detects the status of personnel and objects in the scene, and performs target detection according to the set status. Abnormal alarm point, if triggered, an abnormal alarm will be issued, and the real-time position of people and objects in the area will be obtained at the same time, the location information will be returned, the target point in the area will be set, the distance between the position of the person and the target point will be calculated, the distance between the position of the object and the target point will be calculated, and the human population will be calculated. The distance between various objects, calculation results, form a curve, respectively form the distribution activity curve of the item, the personnel status activity curve and the distance curve from the person to the preset mark item, and obtain the long-term iterative regression curve. When the curve fluctuation exceeds the preset If the deviation range does not meet the long-term regularity and the special date regularity curve, an abnormality will be triggered and an alarm will be issued.

Description

technical field [0001] The invention relates to a method for detecting abnormal behavior of personnel based on target distribution rules, and belongs to the technical field of health protection. Background technique [0002] With the increasingly serious problem of population aging, the demand for private guardians is increasing year by year. With the current level of social development, the level of medical resources and the number of guardians are limited, it is difficult to provide a full range of personalized guardianship services for each need. handling may lead to serious consequences. [0003] Most of the existing monitoring systems for the elderly and patients who need to be cared for use contact sensors to collect physiological parameters such as the heart rate, pulse, and exercise of the elderly, and pressure sensors to collect postures such as lying and sitting. There are many types of sensors and complex system deployment. The wearable mode leads to poor user e...

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 Patents(China)
IPC IPC(8): G08B21/04G06K9/00
CPCG08B21/0423G08B21/043G06V40/20G06V2201/07
Inventor 杨阳陈正晓刘云霞
Owner SHANDONG UNIV