Smart campus system based on Internet of Things

Abstract

The invention relates to the field of smart campus, and discloses a smart campus system based on the Internet of Things, and the system comprises a multi-mode sensing equipment network which is used for deploying a plurality of sensors in key areas such as campus boundaries, building entrances and exits, and the like, so as to collect the temperature, vibration and radar parameters of a target object; the data transmission module transmits the temperature, vibration and radar parameters of the target object to the data processing center through the Internet of Things; the data processing module obtains a temperature index, a vibration index and an abnormal movement index through each parameter, and then calculates a weight coefficient of each sensor by adopting an entropy method; the intrusion behavior analysis and judgment module is used for inputting the temperature index, the vibration index, the abnormal movement index and the weight coefficient into an intrusion analysis model to obtain a behavior abnormal index, and comparing the behavior abnormal index with a preset threshold to judge whether the behavior is an intrusion behavior; if invasion is determined, the invasion behavior early warning module immediately sends out an early warning signal so as to guarantee campus safety.

Description

Technical Field

[0001] The present invention relates to the field of smart campuses, and in particular to a smart campus system based on the Internet of Things. Background Art

[0002] The smart campus system mainly includes three modules: education management, campus life services and campus safety management. Campus safety management includes security management, fire management and emergency intelligence. Among them, security management is an important guarantee for the development of campus safety. With the expansion of campus scale and the increase in personnel flow, intrusion threats have become one of the severe challenges facing campus security; traditional campus intrusion detection methods have many limitations and are difficult to meet the needs of modern campus safety management.

[0003] Early campus intrusion detection mainly relied on manual patrols, which not only consumed a lot of manpower and time, but also had problems such as patrol blind spots and untimely responses. Manual patrols could not achieve real-time monitoring, and intrusions might occur between patrols. Moreover, when intrusions were discovered, the best time to deal with them had often been missed.

[0004] The intrusion detection method based on a simple access control system that was developed later can exercise certain control over the entry and exit of personnel at normal entrances and exits, but its ability to monitor intrusion behaviors at informal entrances and exits, such as climbing over walls and breaking into windows, is limited. The access control system can only identify the identity information of people passing through the access control device and cannot effectively monitor the campus perimeter and other potential intrusion routes.

[0005] Some existing intrusion detection technologies based on a single sensor, such as simple infrared sensors or vibration sensors, also have obvious defects. Among them, infrared sensors are easily affected by factors such as ambient temperature changes and obstruction by target objects, resulting in a high false alarm rate. Vibration sensors may make misjudgments due to vibrations caused by wind, small animal activities, etc. Moreover, the information that a single sensor can obtain is limited, making it difficult to comprehensively and accurately judge intrusion behavior. Summary of the invention

[0006] The purpose of the present invention is to provide a smart campus system based on the Internet of Things to solve the technical problem that the monitoring capability of irregular intrusion behavior is limited and the information that can be obtained by a single sensor is limited, making it difficult to comprehensively and accurately judge the intrusion behavior.

[0007] The purpose of the present invention can be achieved through the following technical solutions: A smart campus system based on the Internet of Things, comprising: A multi-modal sensing device network, including multiple sensors deployed at campus boundaries, building entrances and exits, and important areas, to collect temperature parameters, vibration parameters, and radar parameters of target objects; The data transmission module transmits the collected temperature parameters, vibration parameters and radar parameters of the target object to the data processing center through the Internet of Things; The data processing module processes the target object temperature parameters, vibration parameters and radar parameters to obtain the temperature index. , vibration index , Abnormal Movement Index ; Then, a multi-source data fusion algorithm based on entropy method is used to analyze and obtain the weight coefficient of each sensor ; The intrusion behavior analysis module converts the temperature index , vibration index , Abnormal Movement Index And the weight coefficient of each sensor Input into the intrusion analysis model to obtain abnormal behavior indicators ; Behavioral abnormality indicators The pre-set abnormal behavior threshold For comparison, when When When the The intrusion behavior warning module immediately issues a warning signal if the intrusion behavior analysis and judgment module determines that there is an intrusion behavior.

[0008] In a further solution, the system further includes a linkage response module; The linkage response module is used to immediately activate the sound and light alarm device in the campus after the intrusion behavior warning module sends a warning signal, and send alarm information containing the intrusion location, time and various sensor data to the mobile terminal of the campus security personnel.

[0009] A further solution is to send an alarm message to the mobile terminal of the campus security personnel as follows: Obtain the location information of each campus security personnel in real time based on GPS positioning; Get the distance between the current intrusion location and each campus security officer , the allocation can be done in the shortest time campus security personnel who arrived at the site of the intrusion within 24 hours; Among them, the shortest time satisfy The condition of; In the formula, represents the moving speed of each campus security personnel, Indicates the number of campus security personnel.

[0010] A further solution is to analyze and obtain the weight coefficients of the temperature index, vibration index and abnormal movement index as follows: For data from various sensors ,in , indicating the type of sensor, , represents the data points collected by any sensor at different times; By formula Calculate the first Information entropy of sensor data ; in, , ; Then through the formula: Calculate the weight coefficient of each sensor .

[0011] In a further solution, the intrusion analysis model is expressed as: ; , , Respectively represent the curves of temperature index, vibration index and abnormal movement index changing with time, , , Respectively represent the weight coefficients of temperature index, vibration index and abnormal movement index; In the formula represents the time weight function, and the expression is: ,in Indicates time, Represents the attenuation coefficient; initially, the default ; represents the influence coefficient, , Respectively represent the starting point and end point of the detection period.

[0012] In a further embodiment, the influence coefficient The expression is: ; In the formula, , , Weight adjustment factor, , , They represent the fluctuation coefficients of temperature index, vibration index and abnormal movement index respectively, and the expressions are as follows: ; in, Indicates the calibration period The number of internal samplings, Indicates Subsampling, , , Respectively represent The corresponding observation value at sampling time is , , They represent the mean values ​​of temperature index, vibration index and abnormal movement index respectively.

[0013] In a further embodiment, the temperature index The acquisition process is: Based on infrared thermal imaging sensor to collect location Temperature measurement at , Ambient temperature , substitute into the formula The temperature index is calculated ; In the formula, Indicates the number of pixels in the measurement area. , They respectively represent the upper limit and lower limit of the temperature detected by the infrared thermal imaging sensor.

[0014] In a further embodiment, the vibration index The acquisition process is: Vibration amplitude is collected based on vibration sensor and vibration frequency The curve of change over time, substitute into the formula: The vibration index is calculated ; In the formula, , represents the preset weight factor, , Respectively represent the starting point and end point of the monitoring period; In a further embodiment, the abnormal movement index The acquisition process is: The speed of the target object is collected based on the microwave radar sensor , the distance to the microwave radar sensor and angle Data, substitute into the formula: The abnormal movement index is calculated ; In the formula, Represents the curve of the target object's velocity changing with time. represents the reference distance, represents the reference angle, , , is the preset scale factor.

[0015] Beneficial effects of the present invention: (1) Through a multimodal sensing device network, multiple sensors are deployed at campus boundaries, building entrances and exits, and important areas to collect temperature, vibration, and radar parameters of target objects in real time, making up for the defect that early manual patrols could not monitor in real time. Regardless of day or night, and during patrol breaks, the campus can be continuously monitored, greatly reducing patrol blind spots and ensuring all-round, uninterrupted monitoring of campus safety. (2) The processing of the data processing module integrates information from multiple sensors. Compared with the traditional single sensor detection technology, it can effectively avoid false alarms and misjudgments caused by environmental factors, such as infrared sensors being affected by ambient temperature changes, target objects being blocked or other interference, and vibration sensors being affected by wind and small animals. Through multi-dimensional information fusion, it can comprehensively and accurately judge intrusion behavior, thereby improving the accuracy of detection; (3) The campus sound and light alarm devices are immediately activated through the linkage response module. At the same time, the location of security personnel is obtained in real time based on GPS positioning, and security personnel are assigned to reach the intrusion site in the shortest time. This can shorten the response time and change the situation where manual patrols fail to respond in time and miss the best time to deal with the situation. It also overcomes the problem of the limited monitoring ability of simple access control systems for intrusion behaviors at informal entrances and exits, and comprehensively improves the emergency response efficiency of campus security management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings.

[0017] Figure 1 It is a schematic diagram of the system logic structure of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] See also Figure 1 As shown, the present invention is a smart campus system based on the Internet of Things, comprising: The multimodal sensing device network includes a variety of sensors deployed at the campus boundaries, building entrances and exits, and important areas to collect temperature parameters, vibration parameters, and radar parameters of target objects; the sensors include infrared thermal imaging sensors, vibration sensors, and microwave radar sensors. The installation method is determined according to the actual situation on site and will not be elaborated here; The data transmission module transmits the collected temperature parameters, vibration parameters and radar parameters of the target object to the data processing center through the Internet of Things; The data processing module processes the target object temperature parameters, vibration parameters and radar parameters to obtain the temperature index. , vibration index , Abnormal Movement Index ; Then, a multi-source data fusion algorithm based on entropy method is used to analyze and obtain the weight coefficient of each sensor ; The intrusion behavior analysis module uses the temperature index , vibration index , Abnormal Movement Index And the weight coefficient of each sensor Input into the intrusion analysis model to obtain abnormal behavior indicators ; Behavioral abnormality indicators The pre-set abnormal behavior threshold For comparison, when When When the The intrusion behavior warning module immediately issues a warning signal if the intrusion behavior analysis and judgment module determines that there is an intrusion behavior.

[0020] The system also includes a linkage response module; The linkage response module is used to immediately activate the sound and light alarm device in the campus after the intrusion behavior warning module sends a warning signal, and send alarm information containing the intrusion location, time and various sensor data to the mobile terminal of the campus security personnel.

[0021] The process of sending an alarm message to the mobile terminal of campus security personnel is as follows: Obtain the location information of each campus security personnel in real time based on GPS positioning; Get the distance between the current intrusion location and each campus security officer , the allocation can be done in the shortest time campus security personnel who arrived at the site of the intrusion within 10 days; Among them, the shortest time satisfy The condition of; In the formula, represents the moving speed of each campus security personnel, Indicates the number of campus security personnel.

[0022] This smart campus system uses a multi-modal sensing device network to deploy multiple sensors at campus boundaries, building entrances and exits, and important areas. It can collect temperature, vibration, and radar parameters of target objects in real time, making up for the defect that early manual patrols could not monitor in real time. Regardless of day or night, and during patrol breaks, it can continuously monitor the campus, greatly reducing patrol blind spots and ensuring all-round and uninterrupted monitoring of campus safety. Subsequently, the temperature index, vibration index, and abnormal movement index are obtained by processing various parameters separately, and the entropy method is used to fuse multi-source data to obtain the sensor weight coefficient, which is then input into the intrusion analysis model through the intrusion behavior analysis and judgment module to obtain the behavior abnormality index; the above process integrates information from multiple sensors. Compared with the traditional single sensor detection technology, it can effectively avoid false alarms and misjudgments caused by environmental factors, such as infrared sensors affected by ambient temperature changes, target object occlusion or other interference, such as vibration sensors affected by wind and small animal activities; through multi-dimensional information fusion, intrusion behavior can be comprehensively and accurately judged, thereby improving the accuracy of detection; At the same time, when the intrusion behavior warning module sends out a warning signal, the linkage response module immediately activates the sound and light alarm device in the campus, and sends alarm information containing the intrusion location, time and sensor data to the mobile terminal of the campus security personnel. At the same time, based on GPS positioning, the security personnel's location is obtained in real time, and security personnel who can reach the intrusion location in the shortest time are assigned. This can shorten the response time, change the situation where manual patrols respond untimely and miss the best time to deal with the situation, and overcome the problem of limited monitoring ability of simple access control systems for intrusion behaviors at informal entrances and exits, and comprehensively improve the emergency response efficiency of campus security management.

[0023] The process of analyzing and obtaining the weight coefficients of the temperature index, vibration index and abnormal movement index is as follows: For data from various sensors ,in , indicating the type of sensor, , represents the data points collected by any sensor at different times; By formula Calculate the first Information entropy of sensor data ; in, , ; Indicates The sensor is Data points collected at all times The normalized value of Then through the formula: Calculate the weight coefficient of each sensor .

[0024] In the present invention, a method for obtaining the weight of each sensor is provided. Specifically, , and Calculate the information entropy. It can be seen from the above formula that the data of infrared thermal imaging sensors, vibration sensors and microwave radar sensors are First, each data point Divide by the sum of the data collected by the sensor at different times to get , and then calculate the information entropy of the sensor data according to the above formula , information entropy The larger the value, the greater the uncertainty of the sensor data, that is, the more dispersed the data distribution is, which means that the information provided by the sensor is more confusing or difficult to distinguish different situations, the lower the data validity is, and therefore the lower the weight is; Substitute again The weight coefficient is calculated in the formula. It can be seen from the formula that the information entropy of the sensor data The larger the weight, The smaller it is, the more uncertain the data with large information entropy are, and the less their contribution to the final decision is. Through the above technical scheme, the importance of different sensor data can be allocated according to the uncertainty of the data, rather than simply treating them equally. When fusing multi-source data, the advantages of various sensors can be fully utilized to avoid wrong judgments caused by blindly using certain sensor data with uncertain information. At the same time, the performance of different sensors will change under different environmental conditions. For example, in bad weather or complex environments, the data quality of some sensors will decline. For example, infrared thermal imaging sensors are affected by bad weather, resulting in increased data information entropy. At this time, the weight coefficient is automatically adjusted through the entropy method. The system can dynamically adjust the degree of dependence on the data of each sensor, improve adaptability to environmental changes, make the system more robust, and avoid failure of the entire system due to performance degradation of a single sensor. Finally, the information quality of each sensor under different conditions is comprehensively considered, which can more comprehensively and accurately reflect the actual situation of the campus and reduce misjudgments and missed judgments caused by environmental factors or limitations of the sensor itself.

[0025] The expression of the intrusion analysis model is: ; , , Respectively represent the curves of temperature index, vibration index and abnormal movement index changing with time, , , Respectively represent the weight coefficients of temperature index, vibration index and abnormal movement index; In the formula represents the time weight function, and the expression is: ,in Indicates time, Represents the attenuation coefficient; initially, the default ; represents the influence coefficient, , Respectively represent the starting point and end point of the detection period.

[0026] In the present invention, by formula The weighted indicators over a period of time are integrated, taking into account the changes in different sensor indicators over time, and the data at different times are weighted and integrated according to the time weight function, so as to comprehensively consider the information at different times and avoid relying only on the current moment data, making the system more robust; for example, if the recent indicators are more important, Can take a larger value, so More weight is given to recent data.

[0027] The influence coefficient The expression is: ; In the formula, , , Weight adjustment factor, , , They represent the fluctuation coefficients of temperature index, vibration index and abnormal movement index respectively, and the expressions are as follows: ; in, Indicates the calibration period The number of internal samplings, Indicates Subsampling, , , Respectively represent The corresponding observation value at sampling time is , , They represent the mean values ​​of temperature index, vibration index and abnormal movement index respectively.

[0028] In the present invention, by formula The discreteness of each sensor data is considered, that is, the fluctuation of the data. The higher the discreteness, the higher the abnormality of the data. Therefore, adding the discreteness can improve the detection ability of abnormal behavior; for example, if If the temperature of the target object fluctuates greatly, it may indicate an abnormal situation. Adjustments can determine the extent to which this fluctuation affects the abnormal behavior indicators.

[0029] The temperature index The acquisition process is: Based on infrared thermal imaging sensor to collect location Temperature measurement at , Ambient temperature , substitute into the formula The temperature index is calculated ; In the formula, Indicates the number of pixels in the measurement area. , They respectively represent the upper limit and lower limit of the temperature detected by the infrared thermal imaging sensor.

[0030] In the present invention, The difference reflects the degree of deviation of the temperature of the object represented by the pixel relative to the ambient temperature. If an object is much hotter than the ambient temperature, for example, a human body in a normal temperature environment, the difference will be larger; if the object temperature is close to the ambient temperature, the difference will be smaller; and then through the formula The normalized results of all pixels are added together and divided by the total number of pixels (depending on the spatial resolution of the sensor) to obtain the temperature index of the entire area, which reflects the overall level of the temperature of objects in the area relative to the detectable range of the sensor. It can be used to determine whether there are abnormal high-temperature objects. For example, in intrusion detection applications, it is used to detect whether there are human bodies with body temperatures higher than the ambient temperature, i.e. potential intruders, within the monitoring area of ​​the infrared thermal imaging sensor. The calculation method based on spatial position allows the infrared thermal imaging sensor to comprehensively monitor an area instead of focusing on only one point, thus improving the ability to detect abnormal situations. It is especially suitable for monitoring large areas, such as the boundaries of campuses, around large buildings, and other areas.

[0031] The vibration index The acquisition process is: Vibration amplitude is collected based on vibration sensor and vibration frequency The curve of change over time, substitute into the formula: The vibration index is calculated ; In the formula, , represents the preset weight factor, , Respectively represent the starting point and end point of the monitoring period; In the present invention, in vibration monitoring, the vibration information within a period of time is comprehensively considered, rather than the vibration situation at a certain moment, because the instantaneous vibration may not be representative. The overall vibration characteristics within the monitoring period can be comprehensively considered through integration. It means that the vibration amplitude and vibration frequency are taken into consideration. reflects the intensity of the vibration, while the vibration frequency Reflects the periodicity or frequency characteristics of vibration; This weight coefficient can be used to adjust the weight of the frequency on the vibration index as needed; for example, for some periodic vibration sources, frequency may be a more important feature, while for some sudden vibration events, amplitude may be more important. Multiply by This is to further adjust the size of the entire integral result so that it is within an appropriate numerical range, which is convenient for comparison with other indicators and subsequent decision-making. When it is larger, the entire vibration index will be more dependent on the combined effect of vibration amplitude and frequency; When the value is smaller, the vibration index will be relatively small, which may be suitable for scenes that need to be more sensitive or insensitive to vibration.

[0032] The abnormal movement index The acquisition process is: The speed of the target object is collected based on the microwave radar sensor , the distance to the microwave radar sensor and angle Data, substitute into the formula: The abnormal movement index is calculated ; In the formula, Represents the curve of the target object's velocity changing with time. represents the reference distance, represents the reference angle, , , is the preset scale factor.

[0033] In the present invention, by formula The deviation of the target object's speed, distance and angle relative to the reference value is comprehensively considered, and the comprehensive index of abnormal movement is obtained through integration and weighted calculation. The greater the deviation, the higher the abnormal movement index.

[0034] It should be noted that the calculation formulas and various parameters involved in the calculation in the present invention have been dimensionally processed in advance, and the process of dimensionless processing is well known in the industry and will not be described here.

[0035] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A smart campus system based on the Internet of Things, characterized in that: include: A multi-modal sensing device network, including multiple sensors deployed at campus boundaries, building entrances and exits, and important areas, to collect temperature parameters, vibration parameters, and radar parameters of target objects; The data transmission module transmits the collected temperature parameters, vibration parameters and radar parameters of the target object to the data processing center through the Internet of Things; The data processing module processes the target object temperature parameters, vibration parameters and radar parameters to obtain the temperature index. , vibration index , Abnormal Movement Index ; Then, a multi-source data fusion algorithm based on entropy method is used to analyze and obtain the weight coefficient of each sensor ; The intrusion behavior analysis module uses the temperature index , vibration index , Abnormal Movement Index And the weight coefficient of each sensor Input into the intrusion analysis model to obtain abnormal behavior indicators ; Behavioral abnormality indicators The pre-set abnormal behavior threshold For comparison, when When When the The intrusion behavior warning module immediately issues a warning signal if the intrusion behavior analysis and judgment module determines that there is an intrusion behavior.

2. The smart campus system based on the Internet of Things according to claim 1 is characterized in that: The system also includes a linkage response module; The linkage response module is used to immediately activate the sound and light alarm device in the campus after the intrusion behavior warning module sends a warning signal, and send alarm information containing the intrusion location, time and various sensor data to the mobile terminal of the campus security personnel.

3. The smart campus system based on the Internet of Things according to claim 2 is characterized in that: The process of sending an alarm message to the mobile terminal of campus security personnel is as follows: Obtain the location information of each campus security personnel in real time based on GPS positioning; Get the distance between the current intrusion location and each campus security officer , the allocation can be done in the shortest time campus security personnel who arrived at the site of the intrusion within 10 days; Among them, the shortest time satisfy The condition of; In the formula, represents the moving speed of each campus security personnel, Indicates the number of campus security personnel.

4. The smart campus system based on the Internet of Things according to claim 1 or 3, characterized in that: The process of analyzing and obtaining the weight coefficients of the temperature index, vibration index and abnormal movement index is as follows: For data from various sensors ,in , indicating the type of sensor, , represents the data points collected by any sensor at different times; By formula Calculate the first Information entropy of sensor data ; in, , ; Then through the formula: Calculate the weight coefficient of each sensor .

5. The smart campus system based on the Internet of Things according to claim 4 is characterized in that: The expression of the intrusion analysis model is: ; , , Respectively represent the curves of temperature index, vibration index and abnormal movement index changing with time, , , Respectively represent the weight coefficients of temperature index, vibration index and abnormal movement index; In the formula represents the time weight function, and the expression is: ,in Indicates time, represents the attenuation coefficient; represents the influence coefficient, , Respectively represent the starting point and end point of the detection period.

6. The smart campus system based on the Internet of Things according to claim 5 is characterized in that: The influence coefficient The expression is: ; In the formula, , , Weight adjustment factor, , , They represent the fluctuation coefficients of temperature index, vibration index and abnormal movement index respectively, and the expressions are as follows: ； in, Indicates the calibration period The number of internal samplings, Indicates Subsampling, , , Respectively represent The corresponding observation value at sampling time is , , They represent the mean values ​​of temperature index, vibration index and abnormal movement index respectively.

7. The smart campus system based on the Internet of Things according to claim 1 is characterized in that: The temperature index The acquisition process is: Based on infrared thermal imaging sensor to collect location Temperature measurement at , Ambient temperature , substitute into the formula The temperature index is calculated ; In the formula, Indicates the number of pixels in the measurement area. , They respectively represent the upper limit and lower limit of the temperature detected by the infrared thermal imaging sensor.

8. The smart campus system based on the Internet of Things according to claim 1 is characterized in that: The vibration index The acquisition process is: Vibration amplitude is collected based on vibration sensor and vibration frequency The curve of change over time, substitute into the formula: The vibration index is calculated ; In the formula, , represents the preset weight factor, , They represent the starting point and end point of the monitoring period respectively.

9. The smart campus system based on the Internet of Things according to claim 1 is characterized in that: The abnormal movement index The acquisition process is: The speed of the target object is collected based on the microwave radar sensor , the distance to the microwave radar sensor and angle Data, substitute into the formula: The abnormal movement index is calculated ; In the formula, Represents the curve of the target object's velocity changing with time. represents the reference distance, represents the reference angle, , , is the preset scale factor.

Images