A method and a system for analyzing human behavior of an educational examination monitoring video

A monitoring video and behavior analysis technology, which is applied in the field of video recognition, can solve the problems of complex education and examination monitoring video scenarios and simple trial scenarios, and achieve the effects of improving detection results, efficiency, and accuracy

Inactive Publication Date: 2019-01-25
WUHAN UNIV
View PDF5 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The reason is that the scenarios of surveillance video for education and examinations are too complex, and the current behavioral video intelligent analysis technology that can cope with dynamic scene analysis has many defects such as simple trial scenarios.

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 and a system for analyzing human behavior of an educational examination monitoring video
  • A method and a system for analyzing human behavior of an educational examination monitoring video
  • A method and a system for analyzing human behavior of an educational examination monitoring video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] This embodiment provides a human behavior analysis method for educational examination monitoring video, please refer to figure 1 , the method includes:

[0048] First, step S1 is performed: detecting the preset educational examination monitoring video frame by frame, and detecting all target objects in the examination room, wherein the target objects include candidates and invigilators.

[0049] Specifically, the preset educational examination monitoring video can be selected from the saved monitoring videos, and then the educational examination monitoring video is divided into several video frames according to preset rules, and each video frame is detected respectively.

[0050] In the specific implementation process, the target object can be detected in the following ways:

[0051] The first is to pre-save the features that can distinguish the target object, and then detect the target object through feature recognition. For example, if the feature is a face feature, ...

Embodiment 2

[0090] This embodiment provides a human behavior analysis system for educational examination monitoring video, please refer to figure 2 , the system consists of:

[0091] The target detector 201 is used to detect the preset educational examination monitoring video frame by frame, and detect all target objects in the examination room, wherein the target objects include candidates and invigilators;

[0092] A classifier 202, configured to obtain a feature representation of the target object, and classify the target object according to the feature representation;

[0093] Anomaly detector 203 is used to use the convolutional layer of the pre-trained VGG network as a feature extractor to extract the classification result as the convolution feature of the examinee, and judge whether the current action of the examinee is abnormal according to the convolution feature, if it is , then add the candidate’s relevant information to the preset sequence;

[0094] The integrator 204 is us...

Embodiment 3

[0109] Based on the same inventive concept, the present application also provides a computer-readable storage medium 700, please refer to Figure 7 , on which a computer program 711 is stored, and the method in Embodiment 1 is implemented when the program is executed.

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 provides a method and a system for analyzing human behavior of an educational examination monitoring video, wherein the method comprises: obtaining a current preset video frame and sending the preset video frame to an object detector, obtaining all object objects in the examination room, then sending the feature representation of the object objects to a classifier, and executing classification of the examinee and the invigilating teacher. If you are an examinee, the step of anomaly detection is further performed, the characteristic representation of the examinee is sent into theabnormality detector, the action analysis is performed, and whether the abnormality exists is judged. If it is judged that the abnormality occurs, the relevant information of the examinee is added into the preset sequence, and when the stack of the violation sequence is full, the integrator is called to perform the integration operation, so as to obtain the analysis result. The invention solves the technical problem that the current video analysis technology has poor detection effect when dealing with complex dynamic environment, and limits the application range of video analysis technology.

Description

technical field [0001] The invention relates to the technical field of video recognition, in particular to a human behavior analysis method and system for educational examination monitoring video. Background technique [0002] Intelligent video analysis technology is an application field of computer vision technology. It can establish a mapping relationship between images or image sequences and event descriptions, so that the computer can distinguish and identify the behavior of key targets from numerous video images, and filter information that users do not care about. Its essence is to automatically analyze, extract, and identify Key information in the video source. [0003] At present, intelligent video analysis technologies are distinguished according to the way of implementation, which can be summarized as the following types of intelligent analysis: [0004] (1) Intelligent analysis of diagnostic video. Diagnostic video intelligent analysis is mainly aimed at accura...

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
CPCG06V20/42G06V20/41
Inventor 涂志刚张德军张钊
Owner WUHAN 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