Abnormal behavior detection method and system for smart community

A detection method and abnormal technology, which are applied in the field of abnormal behavior detection methods and systems, can solve the problems of inability to adapt to complex community scenarios and fixed areas where abnormal behavior occurs, so as to improve community management and safety quality, and reduce the probability of misidentification. Effect

Pending Publication Date: 2019-12-31
QINGDAO WINDAKA TECH
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method cannot adapt to the complex scene of the community, where the occurrence of abnormal behavior is very limited, and the areas where abnormal behavior may occur are relatively fixed

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
  • Abnormal behavior detection method and system for smart community
  • Abnormal behavior detection method and system for smart community

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] see figure 1 , in an embodiment of the present invention, a method for detecting abnormal behaviors oriented to a smart community, comprising the following steps:

[0042] S10, acquiring images in the video recorded by the surveillance camera frame by frame.

[0043] In the specific implementation process, the real-time video frame of the surveillance camera is pulled through RTSP, so as to obtain the corresponding image.

[0044] S20. Input the image into a human body detection model for analysis to determine whether there is a human body in the image.

[0045] Specifically, the human body detection model is trained using a convolutional neural network; the images of pedestrians obtained from surveillance cameras and human body images on the network are used as data sets, and SSDs are used for training. At first, default parameters are used for training. As a result, the initial weights, training speed and number of iterations are adjusted until the network converges...

Embodiment 2

[0065] see figure 2 , in an embodiment of the present invention, a smart community-oriented abnormal behavior detection system, the system is designed based on the method described in Embodiment 1, including:

[0066] The obtaining module is used to obtain images in the video recorded by the surveillance camera frame by frame;

[0067] A human body detection module, configured to input the image into a human body detection model for analysis to determine whether there is a human body in the image;

[0068] The abnormal behavior detection module is used to input the abnormal behavior detection model into the abnormal behavior detection model when there is a human body in the image and obtain the result.

[0069] Further: the abnormal behavior detection model includes:

[0070] The fall detection model is used to detect whether pedestrians have fallen in the surveillance video frame;

[0071] The fight detection model is used to detect whether pedestrians in the surveillance...

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 an abnormal behavior detection method and system for a smart community, and relates to the field of community safety monitoring. The method comprises the following steps: acquiring images in a video shot by a monitoring camera frame by frame; inputting the image into a human body detection model for analysis to judge whether a human body exists in the image or not; when thehuman body exists in the image, inputting the human body into an abnormal behavior detection model for abnormal behavior detection and obtaining a result. The system is designed based on the method,human body detection is carried out by using deep learning, and then three abnormal behaviors possibly existing in a community are judged by using the trained fall detection model, fighting model andcrowd judgment model, wherein a Mahalanobis distance, an Euclidean distance and an IOU are used in the algorithm. The method can adapt to complex scenes of a community environment, the probability oferror identification is greatly reduced, and the method has important significance for improving community management and safety quality.

Description

technical field [0001] The invention relates to the field of community safety monitoring, in particular to a smart community-oriented abnormal behavior detection method and system. Background technique [0002] With the improvement of the level of science and technology, the smart community came into being, which refers to a new concept of community management and a new model of social management innovation under the new situation. Make full use of the Internet and the Internet of Things, involving many fields such as smart buildings, smart homes, road network monitoring, personal health and digital life, and give full play to the advantages of developed information and communication (ICT) industry, telecommunication services and excellent information infrastructure. Abnormal behavior detection in smart communities, as part of community security automation operation and maintenance, is of great significance in ensuring community security. [0003] Currently, abnormal behavi...

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): G06K9/00G06K9/62G06N3/08G06T7/00
CPCG06T7/0002G06N3/08G06T2207/20081G06T2207/20084G06T2207/30232G06V20/10G06V20/46G06V20/52G06F18/214
Inventor 管洪清管延成肖常升王伟张元杰
Owner QINGDAO WINDAKA TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap