Movement human abnormal behavior identification method based on template matching

A technology of template matching and recognition methods, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of no abnormal behavior recognition method, no reports or literature found, no intelligent monitoring, etc., to improve the recognition effect. , the effect of reducing the amount of calculation and improving the efficiency

Inactive Publication Date: 2010-06-02
XIDIAN UNIV
View PDF0 Cites 115 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, there are still some problems in these researches and applications: the current research part of the visual understanding method adopts the mechanical human body model method, and restores the state of human joint motion by matching video images, and then understands the behavior of the human body. This process increases the intermediate link , making the model more complex and difficult to achieve accurately
[0007] Surveillance systems that are widely used today are mainly based on camera and recorded images. They are either manual monitoring or post-event playback and analysis. There is basically no intelligent monitoring. Even if some monitoring of the environment and still life has an alarm system, Only moving and not moving can be used as the criterion to distinguish whether it is normal or not. For the normal and abnormal judgment of dynamic or moving objects, most of them are in the stage of theoretical research and discussion, and no practical abnormal behavior identification method has been applied.
[0008] The project team of this invention has searched domestic and foreign patent documents and published journal papers, and has not found any reports or documents closely related to the present invention.

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
  • Movement human abnormal behavior identification method based on template matching
  • Movement human abnormal behavior identification method based on template matching
  • Movement human abnormal behavior identification method based on template matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] see figure 1 , the present invention is a method for identifying abnormal behaviors of moving human bodies based on template matching, which is mostly used in banks, museums and other places involving public safety issues that require real-time monitoring. Using computer vision technology to analyze and understand human motion, and to collect, record, identify abnormal behaviors and alarm in real time, see figure 1 . The required hardware minimum configuration of the inventive method is: P4 3.0G CPU, the computer of 512M internal memory; Minimum resolution is the health camera of 320 * 240 or DV video camera; The frame rate is 25 frames per second video acquisition card and MD decoding card . figure 1 It is a schematic diagram of the operation flow of the present invention, according to figure 1 Flow process, detection method of the present invention comprises the following steps: 1. sample video data collection: collect the normal behavior video sequence in the pred...

Embodiment 2

[0089] The abnormal behavior recognition method of moving human body based on template matching is the same as embodiment 1, see figure 2 , the image analysis and behavior feature extraction in step 2 in the present invention comprise the following steps:

[0090] Step S1: The Gaussian filtering method combined with the neighborhood denoising method is used to remove noise.

[0091] Step S2: performing background modeling on the denoised image sequence using a Gaussian mixture model;

[0092] Step S3: Extract the changing area from the background model to obtain the moving target;

[0093] Step S4: Use the HSV model to distinguish the moving object from the moving shadow, and use the Gaussian mixture model to remove the shadow.

[0094] The purpose of moving target detection is to segment and extract the changing area from the background image in the sequence image. Since the post-processing of the image, such as target classification, tracking and behavior understanding, o...

Embodiment 3

[0098] The abnormal behavior recognition method of moving human body based on template matching is the same as that of Embodiment 1-2, and the background modeling in step 2 of the present invention includes the following steps:

[0099] Step S21: Divide the video sequence image into W×W small partitions:

[0100] Step S22: modeling each small subregion according to the mixed Gaussian model.

[0101] Divide the video sequence image into 3×3 small partitions. In the next update, only those areas with significant changes can be updated, and the areas with insignificant changes do not need to be updated. The invention partitions the image, reduces the calculation amount of the mixed Gaussian model, and improves the efficiency.

[0102] The invention proposes and adopts an improved mixed Gaussian method to detect moving targets, and adopts a mixed Gaussian method to model each small subregion. The basic idea of ​​the mixed Gaussian model is: for each pixel, K states are defined, ...

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 movement human abnormal behavior identification method based on template matching, which mainly comprises the steps of: video image acquisition and behavior characteristic extraction. The movement human abnormal behavior identification method is a mode identification technology based on statistical learning of samples. The movement of a human is analyzed and comprehended by using a computer vision technology, the behavior identification is directly carried out based on geometric calculation of a movement region and recording and alarming are carried out; the Gaussian filtering denoising and the neighborhood denoising are combined for realizing the denoising, thereby improving the independent analysis property and the intelligent monitoring capacity of an intelligent monitoring system, achieving higher identification accuracy for abnormal behaviors, effectively removing the complex background and the noise of a vision acquired image, and improving the efficiency and the robustness of the detection algorithm. The invention has simple modeling, simple algorithm and accurate detection, can be widely applied to occasions of banks, museums and the like, and is also helpful to improve the safety monitoring level of public occasions.

Description

technical field [0001] The invention belongs to the fields of computer vision and intelligent information processing. It involves computer monitoring technology based on moving images and pattern recognition technology based on statistical learning. The invention mainly relates to an intelligent analysis method of video monitoring content, in particular to a template matching-based abnormal behavior recognition method of a moving human body. Background technique [0002] As society pays more attention to public safety issues, real-time monitoring has been more and more widely used. The main problem of the existing monitoring system is that it is difficult to process a large amount of monitoring information in a timely and effective manner. The recognition of human behavior and events through computer assistance has become a hot issue in the field of computer vision. [0003] The intelligent analysis technology of visual surveillance is a hot and difficult issue in the fiel...

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): G06K9/00
Inventor 刘志镜赵海勇张军王韦桦张浩侯晓慧鱼滨
Owner XIDIAN UNIV
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