A smart campus monitoring system and method for predicting campus bullying

Abstract

The present invention relates to the field of smart campus technology, and provides a smart campus monitoring system and method for predicting campus bullying. The smart campus monitoring method comprises the following steps: obtaining student image information in a region and preprocessing the student image information; performing scenario analysis on the preprocessed student image information to identify the current scenario state and scenario development trend; identifying student behavior according to the current scenario state and scenario development trend, and calculating the campus bullying occurrence index; when the campus bullying occurrence index is greater than a preset threshold, sounding an alarm. The present invention can timely detect and stop campus bullying before campus bullying occurs, and it does not require monitoring personnel to monitor and identify real-time portraits of various campus areas, and has a high degree of automation and intelligence.

Description

Technical Field

[0001] The present invention relates to the technical field of smart campuses, and in particular to a smart campus monitoring system and method for predicting campus bullying. Background Art

[0002] School bullying is a common social phenomenon that mostly occurs among young people. School bullying is considered an important factor leading to depression, school dropouts and even suicide among young people. School bullying takes the form of physical violence, verbal bullying, and destruction of personal finances. Physical violence is the most serious harm to young people, damaging their physical and mental health. When students are bullied by other classmates on campus, it is generally difficult for them to escape and report to security personnel or teachers, and bystanders dare not take the initiative to persuade or inform teachers, so that the bullied students allow other classmates to bully them for a long time, which may cause physical injuries at the least and life threats at the worst.

[0003] In the current campus management, cameras are usually used to monitor various areas of the school. The real-time images of the campus are collected by cameras and sent to the monitoring room, where the monitoring personnel monitor the images. In this way, the monitoring personnel need to monitor the images in real time and need to monitor the images of multiple cameras. They often cannot detect bullying behaviors in time and rush to the scene to stop them in time, and the monitoring efficiency is low. Summary of the invention

[0004] Based on this, in order to solve the problem that the existing campus management requires monitoring personnel to monitor the screen in real time, and needs to monitor the screens of multiple cameras, often cannot detect bullying behavior in time and rush to the scene to stop it in time, and the monitoring efficiency is low, the present invention provides a smart campus monitoring system and method for predicting campus bullying, and its specific technical solution is as follows:

[0005] A smart campus monitoring system for predicting campus bullying includes an image acquisition module, a scenario analysis module, a behavior prediction module and an alarm module.

[0006] The image acquisition module is used to acquire the image information of students in the area and pre-process the image information of students.

[0007] The scenario analysis module is used to perform scenario analysis on the preprocessed student image information and identify the current scenario status and scenario development trend.

[0008] The behavior prediction module is used to identify student behavior based on the current situation status and situation development trend, and calculate the campus bullying occurrence index.

[0009] The alarm module is used to issue an alarm when the campus bullying index exceeds the preset threshold.

[0010] The smart campus monitoring system for predicting campus bullying obtains student images and identifies the current situation status and situation development trend, identifies student behavior based on the current situation status and situation development trend, and calculates the campus bullying occurrence index. It can timely discover and stop campus bullying before it occurs. It does not require monitoring personnel to monitor and identify real-time portraits of various areas of the campus. It has a high degree of automation and intelligence, improves the monitoring efficiency of campus bullying behavior, and solves the problem that existing campus management requires monitoring personnel to monitor the pictures in real time, and needs to monitor the pictures of multiple cameras, often fails to discover bullying behavior in time and arrive at the scene in time to stop it, and has low monitoring efficiency.

[0011] Furthermore, the smart campus monitoring system also includes:

[0012] A voice acquisition module, used to acquire voice information in the area;

[0013] A text extraction module is used to convert voice information into text and extract keywords from the text;

[0014] Frequency calculation module, used to calculate the frequency of keyword occurrence;

[0015] Among them, the behavior prediction module is used to identify student behavior according to the current situation status, situation development trend and keyword occurrence frequency, and calculate the campus bullying occurrence index.

[0016] Furthermore, the scenario analysis module includes:

[0017] A feature extraction unit, used to extract posture features and limb key points of the preprocessed student image;

[0018] The scenario analysis unit is used to identify the current scenario status and scenario development trend based on posture features and limb key points.

[0019] Furthermore, the smart campus monitoring system also includes a keyword storage module, which is used to store preset campus bullying keyword texts.

[0020] A smart campus monitoring method for predicting campus bullying comprises the following steps:

[0021] Acquire the student image information in the area and pre-process the student image information;

[0022] Conduct situational analysis on the pre-processed student image information to identify the current situational status and situational development trend;

[0023] Identify student behaviors based on the current situation status and situation development trends, and calculate the campus bullying index;

[0024] When the campus bullying index exceeds the preset threshold, an alarm is issued.

[0025] Furthermore, the smart campus monitoring method further comprises the following steps:

[0026] Get voice information in the area;

[0027] Convert voice information into text and extract key words from the text;

[0028] Calculate the frequency of keyword occurrence;

[0029] Student behaviors are identified based on the current situation status, situation development trends, and keyword occurrence frequency, and the campus bullying index is calculated.

[0030] Furthermore, the specific method of performing situation analysis on the preprocessed student image information and identifying the current situation state and situation development trend includes the following steps:

[0031] Extract posture features and limb key points of the preprocessed student images;

[0032] Identify the current situation status and situation development trend based on posture features and body key points.

[0033] A computer-readable storage medium stores a computer program, which implements the smart campus monitoring method when the computer program is executed.

[0034] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the smart campus monitoring method is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0036] Figure 1 It is a schematic diagram of the overall process of a smart campus monitoring method for predicting campus bullying in one embodiment of the present invention;

[0037] Figure 2 It is a flow chart of a smart campus monitoring method for predicting campus bullying in another embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with its embodiments. It should be understood that the specific implementation methods described herein are only used to explain the present invention and do not limit the protection scope of the present invention.

[0039] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only and do not represent the only implementation method.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0041] The “first” and “second” mentioned in the present invention do not represent specific quantities and orders, but are merely used to distinguish names.

[0042] Embodiment 1:

[0043] A smart campus monitoring system for predicting campus bullying includes an image acquisition module, a scenario analysis module, a behavior prediction module and an alarm module.

[0044] The image acquisition module is used to acquire the image information of students in the area and pre-process the image information of students.

[0045] The image acquisition module includes but is not limited to cameras installed in different areas of the campus and an image preprocessing unit. In each campus area, at least one camera is installed to better obtain student image information in the area, so that the scenario analysis module can perform scenario analysis on the preprocessed student image information. That is to say, through the image acquisition unit, multiple student image information in a certain area of ​​the campus can be obtained, and the multiple student image information has different visual effects, such as front image vision and side image vision.

[0046] The scenario analysis module is used to perform scenario analysis on the preprocessed student image information and identify the current scenario status and scenario development trend.

[0047] Specifically, the scenario analysis module includes a feature extraction unit and a scenario analysis unit.

[0048] The feature extraction unit is used to extract the posture features and limb key points of the preprocessed student image.

[0049] The scenario analysis unit is used to identify the current scenario status and scenario development trend based on posture features and limb key points.

[0050] The key points of the body parts include the head, body, hands and feet. The situation states include but are not limited to the normal state, the intimate state, the quarrel state, the dispute state, the push and pull state and the fight state.

[0051] The scenario analysis unit identifies the scenario state according to the distance between the key points of different students' limbs in the student image and the time the distance is maintained. At the same time, the scenario analysis unit identifies the scenario development trend according to the trend of increase and decrease of the distance between the key points of different students' limbs in the student image.

[0052] The behavior prediction module is used to identify student behavior based on the current situation status and situation development trend, and calculate the campus bullying occurrence index.

[0053] Specifically, in the smart campus monitoring system, different situation state coefficients and situation development trend values ​​are preset. For example, the normal state, intimate state, quarrel state, dispute state, push-pull and fight state can be set to different and gradually increasing or decreasing coefficients. More specifically, one of the schemes is that the coefficients of the normal state, intimate state, quarrel state, dispute state, push-pull and fight state are set to 0.1, 0.3, 0.5, 0.7, 0.9, 1.1 respectively.

[0054] The scenario development trend value is calculated based on the trend of the increase or decrease of the distance between the key points of the student's body. For example, the scenario development trend value can be the change in the distance between the key points of the student's body within a preset time period.

[0055] The campus bullying occurrence index is the product of the situation state coefficient and the situation development trend value.

[0056] The alarm module is used to issue an alarm when the campus bullying index exceeds the preset threshold.

[0057] The smart campus monitoring system for predicting campus bullying obtains student images and identifies the current situation status and situation development trend, identifies student behavior based on the current situation status and situation development trend, and calculates the campus bullying occurrence index. It can timely discover and stop campus bullying before it occurs. It does not require monitoring personnel to monitor and identify real-time portraits of various areas of the campus. It has a high degree of automation and intelligence, improves the monitoring efficiency of campus bullying behavior, and solves the problem that existing campus management requires monitoring personnel to monitor the pictures in real time, and needs to monitor the pictures of multiple cameras, often fails to discover bullying behavior in time and arrive at the scene in time to stop it, and has low monitoring efficiency.

[0058] Embodiment 2:

[0059] A smart campus monitoring system for predicting campus bullying includes an image acquisition module, a scenario analysis module, a behavior prediction module and an alarm module.

[0060] The image acquisition module is used to acquire the image information of students in the area and pre-process the image information of students.

[0061] The image acquisition module includes but is not limited to cameras installed in different areas of the campus and an image preprocessing unit. In each campus area, at least one camera is installed to better obtain student image information in the area, so that the scenario analysis module can perform scenario analysis on the preprocessed student image information. That is to say, through the image acquisition unit, multiple student image information in a certain area of ​​the campus can be obtained, and the multiple student image information has different visual effects, such as front image vision and side image vision.

[0062] The scenario analysis module is used to perform scenario analysis on the preprocessed student image information and identify the current scenario status and scenario development trend.

[0063] Specifically, the scenario analysis module includes a feature extraction unit and a scenario analysis unit.

[0064] The feature extraction unit is used to extract the posture features and limb key points of the preprocessed student image.

[0065] The scenario analysis unit is used to identify the current scenario status and scenario development trend based on posture features and limb key points.

[0066] The key points of the body parts include the head, body, hands and feet. The situation states include but are not limited to the normal state, the intimate state, the quarrel state, the dispute state, the push and pull state and the fight state.

[0067] The scenario analysis unit identifies the scenario state according to the distance between the key points of different students' limbs in the student image and the time the distance is maintained. At the same time, the scenario analysis unit identifies the scenario development trend according to the trend of increase and decrease of the distance between the key points of different students' limbs in the student image.

[0068] The behavior prediction module is used to identify student behavior based on the current situation status and situation development trend, and calculate the campus bullying occurrence index.

[0069] Specifically, in the smart campus monitoring system, different situation state coefficients and situation development trend values ​​are preset. For example, the normal state, intimate state, quarrel state, dispute state, push-pull and fight state can be set to different and gradually increasing or decreasing coefficients. More specifically, one of the schemes is that the coefficients of the normal state, intimate state, quarrel state, dispute state, push-pull and fight state are set to 0.1, 0.3, 0.5, 0.7, 0.9, 1.1 respectively.

[0070] The scenario development trend value is calculated based on the trend of the increase or decrease of the distance between the key points of the student's body. For example, the scenario development trend value can be the change in the distance between the key points of the student's body within a preset time period.

[0071] The campus bullying occurrence index is the product of the situation state coefficient and the situation development trend value.

[0072] The alarm module is used to issue an alarm when the campus bullying index exceeds the preset threshold.

[0073] The smart campus monitoring system for predicting campus bullying obtains student images and identifies the current situation status and situation development trend, identifies student behavior based on the current situation status and situation development trend, and calculates the campus bullying occurrence index. It can timely discover and stop campus bullying before it occurs. It does not require monitoring personnel to monitor and identify real-time portraits of various areas of the campus. It has a high degree of automation and intelligence, improves the monitoring efficiency of campus bullying behavior, and solves the problem that existing campus management requires monitoring personnel to monitor the pictures in real time, and needs to monitor the pictures of multiple cameras, often fails to discover bullying behavior in time and arrive at the scene in time to stop it, and has low monitoring efficiency.

[0074] In this embodiment, the smart campus monitoring system also includes a voice acquisition module, a text extraction module, a frequency calculation module and a keyword storage module.

[0075] The voice acquisition module is used to acquire voice information in the area, the text extraction module is used to convert the voice information into text and extract keywords in the text, and the frequency calculation module is used to calculate the frequency of keyword occurrence. The keyword storage module is used to store preset campus bullying keyword texts. The behavior prediction module is used to identify student behavior based on the current situation status, situation development trend and keyword occurrence frequency, and calculate the campus bullying occurrence index.

[0076] Here, the keywords refer to words related to school bullying. Generally speaking, keywords related to school bullying can be stored in the keyword storage module by means of preset and screening.

[0077] Specifically, the campus bullying occurrence index is the product of the situation state coefficient, the situation development trend and the keyword occurrence frequency value.

[0078] By setting up a voice acquisition module, a text extraction module, a frequency calculation module and a keyword storage module, the campus bullying occurrence index can be calculated more accurately, so as to more accurately monitor and predict campus bullying.

[0079] Embodiment three:

[0080] like Figure 1 As shown, the present invention provides a smart campus monitoring method for predicting campus bullying, which includes the following steps:

[0081] S1, obtaining the student image information in the area and preprocessing the student image information.

[0082] S2, conducts situation analysis on the pre-processed student image information to identify the current situation status and situation development trend.

[0083] S3, identifies student behaviors based on the current situation status and situation development trends, and calculates the campus bullying occurrence index.

[0084] S4, when the campus bullying index is greater than the preset threshold, an alarm is issued.

[0085] Specifically, the situation state includes but is not limited to a normal state, an intimate state, a quarrel state, a dispute state, a push-pull state, and a fight state. The method for acquiring the situation state includes: acquiring the distance between the key points of the students' limbs and the time the distance is maintained, and judging and identifying different situation states according to the distance between the key points of the students' limbs and the time the distance is maintained. More specifically, the method for acquiring the situation state also includes: acquiring the position coordinates of each student in the student image information and the amount of position change within a preset time period; judging and identifying different situation states according to the distance between the key points of the students' limbs, the time the distance is maintained, the position coordinates of each student and the amount of position change within a preset time period.

[0086] Due to different situational states, the distance between key points of students' limbs, the time the distance is maintained, the position coordinates of each student, and the position change within a preset time period are all different. By obtaining the distance between key points of students' limbs, the time the distance is maintained, the position coordinates of each student, and the position change within a preset time period, different situational states can be better judged and identified.

[0087] In actual application, corresponding to different situation states, the distance between key points of students' limbs, the time the distance is maintained, the position coordinates of each student, and the position change amount within a preset time period all correspond to different preset range values. The method determines and identifies different situation states based on the relationship between the distance between key points of students' limbs, the time the distance is maintained, the position coordinates of each student, and the position change amount within a preset time period and the corresponding preset range values.

[0088] The smart campus monitoring method obtains student images and identifies the current situation status and situation development trend, identifies student behavior according to the current situation status and situation development trend, and calculates the campus bullying occurrence index. It can timely discover and stop campus bullying before it occurs. It does not require monitoring personnel to monitor and identify real-time portraits of various areas of the campus. It has a high degree of automation and intelligence, improves the monitoring efficiency of campus bullying behavior, and solves the problem that the existing campus management needs monitoring personnel to monitor the pictures in real time, and needs to monitor the pictures of multiple cameras, often fails to discover bullying behavior in time and arrive at the scene in time to stop it, and has low monitoring efficiency.

[0089] Embodiment 4:

[0090] It should be understood that this embodiment at least includes all the technical solutions of the above embodiments, and is further described in detail on the basis of the above embodiments.

[0091] In this embodiment, the smart campus monitoring method further includes the following steps:

[0092] S5, obtaining voice information in the area.

[0093] S6, converting the voice information into text and extracting keywords from the text.

[0094] S7, calculate the frequency of keyword occurrence.

[0095] Student behaviors are identified based on the current situation status, situation development trends, and keyword occurrence frequency, and the campus bullying index is calculated.

[0096] Among them, in step S2, if Figure 2 As shown, the specific method of performing situation analysis on the preprocessed student image information and identifying the current situation state and situation development trend includes the following steps:

[0097] S20, extracting posture features and limb key points of the preprocessed student image.

[0098] S21, identifying the current situation status and situation development trend according to posture features and body key points.

[0099] Specifically, the campus bullying occurrence index is the product of the situation state coefficient, the situation development trend and the keyword occurrence frequency value.

[0100] By setting up a voice acquisition module, a text extraction module, a frequency calculation module and a keyword storage module, the campus bullying occurrence index can be calculated more accurately, so as to more accurately monitor and predict campus bullying.

[0101] As a preferred technical solution, in this embodiment, the smart campus monitoring method further includes the following steps:

[0102] identifying each student's body contour line in the preprocessed student image information;

[0103] Based on the students' body contours, identify whether there are students in a curled-up defensive state or an attacking state;

[0104] If a student is in a curled-up defensive state or an attacking state, it is judged that school bullying has occurred. The alarm module sounds an alarm and sends the alarm information to the campus management platform or the smart terminal bound to different school administrators.

[0105] Specifically, the method for judging and identifying the curled-up defensive state is: judging whether the student's hands and feet are in a contracted state based on the student's body contour line analysis; if so, judging whether there is a contact area between the student's hands and feet; if there is a contact area, judging and identifying that the student is in a curled-up defensive state.

[0106] The method for judging and identifying the attacking state is as follows: if at least one of the students is judged to be in a curled-up defensive state, the body contours of the remaining students are analyzed and judged; if the student's hands and / or feet are in an over-extended state within a preset time period and the extension and retraction frequency is greater than a preset value, the student is judged to be in an attacking state.

[0107] Through the above methods, it is possible to identify whether school bullying has occurred and prevent further development of school bullying in time.

[0108] This embodiment provides a computer-readable storage medium and an electronic device, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed, the smart campus monitoring method is implemented. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the smart campus monitoring method is implemented.

[0109] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A smart campus monitoring system for predicting campus bullying, characterized in that: The smart campus monitoring system includes: An image acquisition module is used to acquire image information of students in the area and pre-process the image information of students; The scenario analysis module is used to perform scenario analysis on the pre-processed student image information and identify the current scenario status and scenario development trend; Behavior prediction module, used to identify student behavior based on the current situation status and situation development trend, and calculate the campus bullying index; An alarm module is used to issue an alarm when the campus bullying index exceeds a preset threshold; Before the alarm is issued, the scenario analysis module further includes: If there are students in a curled-up defensive state or an attacking state, it is judged that school bullying has occurred; The method for judging and identifying the curled-up defensive state is as follows: judging whether the student's hands and feet are in a contracted state based on the student's body contour line analysis; if so, judging whether there is a contact area between the student's hands and feet; if there is a contact area, judging and identifying that the student is in a curled-up defensive state; The method for judging and identifying the attacking state is as follows: if at least one of the students is judged to be in a curled-up defensive state, the body contours of the remaining students are analyzed and judged; if the student's hands and / or feet are in an over-extended state within a preset time period and the extension and retraction frequency is greater than a preset value, the student is judged to be in an attacking state.

2. A smart campus monitoring system for predicting campus bullying as claimed in claim 1, characterized in that: The smart campus monitoring system also includes: A voice acquisition module, used to acquire voice information in the area; A text extraction module is used to convert voice information into text and extract keywords from the text; Frequency calculation module, used to calculate the frequency of keyword occurrence; Among them, the behavior prediction module is used to identify student behavior according to the current situation status, situation development trend and keyword occurrence frequency, and calculate the campus bullying occurrence index.

3. A smart campus monitoring system for predicting campus bullying as claimed in claim 2, characterized in that: The scenario analysis module includes: A feature extraction unit, used to extract posture features and limb key points of the preprocessed student image; The scenario analysis unit is used to identify the current scenario status and scenario development trend based on posture features and limb key points.

4. A smart campus monitoring system for predicting campus bullying as claimed in claim 3, characterized in that: The smart campus monitoring system also includes a keyword storage module, which is used to store preset campus bullying keyword texts.

5. A smart campus monitoring method for predicting campus bullying, characterized in that: The smart campus monitoring method comprises the following steps: Acquire the student image information in the area and pre-process the student image information; Conduct situational analysis on the pre-processed student image information to identify the current situational status and situational development trend; Identify student behaviors based on the current situation status and situation development trends, and calculate the campus bullying index; When the campus bullying index exceeds the preset threshold, an alarm is issued; Before issuing the alarm, it also includes: If there are students in a curled-up defensive state or an attacking state, it is judged that school bullying has occurred; The method for judging and identifying the curled-up defensive state is as follows: judging whether the student's hands and feet are in a contracted state based on the student's body contour line analysis; if so, judging whether there is a contact area between the student's hands and feet; if there is a contact area, judging and identifying that the student is in a curled-up defensive state; The method for judging and identifying the attacking state is as follows: if at least one of the students is judged to be in a curled-up defensive state, the body contours of the remaining students are analyzed and judged; if the student's hands and / or feet are in an over-extended state within a preset time period and the extension and retraction frequency is greater than a preset value, the student is judged to be in an attacking state.

6. A smart campus monitoring method for predicting campus bullying as claimed in claim 5, characterized in that: The smart campus monitoring method also includes the following steps: Get voice information in the area; Convert voice information into text and extract key words from the text; Calculate the frequency of keyword occurrence; Student behaviors are identified based on the current situation status, situation development trends, and keyword occurrence frequency, and the campus bullying index is calculated.

7. A smart campus monitoring method for predicting campus bullying as claimed in claim 5, characterized in that: The specific method of performing situation analysis on the preprocessed student image information and identifying the current situation status and situation development trend includes the following steps: Extract posture features and limb key points of the preprocessed student images; Identify the current situation status and situation development trend based on posture features and body key points.

8. A computer-readable storage fluid medium, characterized in that: The computer-readable storage fluid medium stores a computer program, and when the computer program is executed, the smart campus monitoring method as described in any one of claims 5 to 7 is implemented.

9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the smart campus monitoring method as described in any one of claims 5 to 7 is implemented.

Images