Campus safety management method and system

Abstract

The invention discloses a campus security management method and system. The method comprises the following steps: acquiring a point cloud picture of a target campus and point cloud pictures of other campuses in a global jurisdiction in which the target campus is located; determining a plurality of augmented patrol areas according to the conditions of the historical security events of the other campuses; calculating a group of point cloud picture feature descriptors of the target campus and a group of point cloud picture feature descriptors of the other campuses, and determining a transformation matrix of the two groups of point cloud picture feature descriptors; according to the plurality of augmented patrol areas and the transformation matrix, performing alignment to obtain a plurality of similar areas in the target campus; and according to the frequency of the historical security events occurring in the plurality of similar areas corresponding to the plurality of augmented patrol areas, allocating security personnel in a corresponding proportion. Through data-driven prediction, accurate resource allocation, real-time behavior identification and a flexible dynamic adjustment mechanism, more efficient and more intelligent campus security management is realized.

Description

Technical Field

[0001] The present invention relates to the field of campus monitoring, and in particular to a campus safety management method and system. Background Art

[0002] In traditional campus safety management, identifying and predicting potential safety hazard areas usually relies on historical data, human judgment or simple statistical analysis. This approach has the following problems:

[0003] First, methods based on human judgment are easily affected by personal experience and bias, resulting in less than objective prediction results. Second, traditional methods often fail to accurately locate high-risk areas, resulting in irrational resource allocation, where some areas may be overprotected while others are underprotected. Moreover, the allocation of security personnel is usually fixed and cannot be adjusted dynamically according to real-time conditions. This may result in insufficient security forces in some areas during specific time periods, while resources are wasted in other time periods. The existing allocation mechanism is difficult to flexibly respond to emergencies or temporary increased security needs. Summary of the invention

[0004] The embodiment of the present invention provides a campus security management method and system, which automatically identifies high-risk areas based on historical security incident data of other campuses, continuously obtains location information of security personnel, and combines behavior recognition models to monitor and adjust security forces in real time.

[0005] To achieve the above objectives, a first aspect of an embodiment of the present application provides a campus safety management method, comprising:

[0006] Obtaining a point cloud map of a target campus and point cloud maps of other campuses in the global jurisdiction where the target campus is located;

[0007] Determine multiple additional patrol areas based on historical security incidents that occurred on other campuses;

[0008] Calculating a set of point cloud feature descriptors of the target campus and a set of point cloud feature descriptors of the other campuses, and determining transformation matrices of the two sets of point cloud feature descriptors;

[0009] Aligning multiple similar areas in the target campus according to the multiple patrol-added areas and the transformation matrix;

[0010] According to the frequency of historical security incidents occurring in the multiple similar areas corresponding to the multiple additional patrol areas, security personnel in corresponding proportions are allocated; each security personnel is responsible for one similar area;

[0011] Continuously obtain the position vector corresponding to the location of the security personnel in the point cloud map of the target campus; when the preset recognition model identifies the person to be managed, calculate the distance between the position vector and the position vector corresponding to the position of the person to be managed in the point cloud map of the target campus; and according to the distance and the safety level of the person to be managed, assign a preset number of the security personnel to the location of the person to be managed.

[0012] In a possible implementation manner of the first aspect, obtaining a point cloud map of a target campus and point cloud maps of other campuses in the global jurisdiction where the target campus is located specifically includes:

[0013] For the target campus and other campuses in the overall jurisdiction where the target campus is located, multiple scanning stations are set according to a preset overlap range percentage; the preset overlap range percentage is equal to the overlap percentage of the patrol ranges of two adjacent security personnel, the preset overlap range percentage is the ratio of the overlapping scanning area of ​​adjacent scanning stations to the scanning area of ​​each of the scanning stations, and the patrol range overlap percentage is the ratio of the overlapping patrol area of ​​two adjacent security personnel to the scanning area of ​​each of the security personnel.

[0014] In a possible implementation of the first aspect, determining a plurality of additional patrol areas according to historical security incidents occurring in other campuses specifically includes:

[0015] Performing K-means clustering on the historical security events that occurred in the other campuses, and taking multiple locations corresponding to the most recent historical security events of multiple clusters as the centers of multiple additional patrol areas;

[0016] A plurality of additional patrol areas are determined according to a preset patrol range and the centers of the plurality of additional patrol areas.

[0017] In a possible implementation manner of the first aspect, calculating a set of point cloud feature descriptors of the target campus and a set of point cloud feature descriptors of the other campuses, and determining a transformation matrix of the two sets of point cloud feature descriptors specifically includes:

[0018] Calculate the FPFH and SHOT of the target campus point cloud image as a set of point cloud image feature descriptors, and calculate the FPFH and SHOT of the other campus point cloud images as another set of point cloud image feature descriptors;

[0019] According to the two sets of point cloud feature descriptors, all valid nearest neighbor point pairs between the point cloud of the target campus and the point cloud of other campuses are found through the nearest neighbor algorithm;

[0020] According to all the valid nearest neighbor point pairs, the transformation matrices of two groups of point cloud feature descriptors are calculated.

[0021] In a possible implementation of the first aspect, finding all valid nearest neighbor point pairs between the point cloud image of the target campus and the point cloud images of other campuses by using a nearest neighbor algorithm based on the two sets of point cloud image feature descriptors specifically includes:

[0022] Calculate the mean projection distance of the FPFH feature descriptor of each point in the other campus point cloud map on the fitness vector of the corresponding point as the FPFH distance;

[0023] Calculate the SHOT feature descriptor of each point in the other campus point cloud map and the average of the projection distances of the corresponding point fitness vectors as the SHOT distance;

[0024] Using the difference between the FPFH distance and the SHOT distance as a distance threshold;

[0025] Use the nearest neighbor algorithm to find all valid nearest neighbor point pairs between the point cloud of the target campus and the point cloud of other campuses;

[0026] The nearest neighbor point pairs whose distance is less than or equal to the distance threshold are regarded as valid nearest neighbor point pairs.

[0027] In a possible implementation of the first aspect, before finding all valid nearest neighbor point pairs between the point cloud image of the target campus and the point cloud images of other campuses using a nearest neighbor algorithm based on the two sets of point cloud image feature descriptors, the method further includes:

[0028] A KD tree index structure is established based on two sets of point cloud feature descriptors.

[0029] In a possible implementation manner of the first aspect, the method for aligning a plurality of similar areas in the target campus according to the plurality of patrol-added areas and the transformation matrix specifically includes:

[0030] According to the transformation matrix, coordinate transformation is performed on each point of the plurality of patrol-added areas to obtain a plurality of similar areas.

[0031] In a possible implementation of the first aspect, allocating security personnel in corresponding proportions according to the frequencies of historical security incidents occurring in the multiple similar areas corresponding to the multiple additional patrol areas specifically includes:

[0032] According to a first ratio of the frequency of historical security incidents occurring in each similar area corresponding to the additional patrol area to the frequency of historical security incidents occurring in all similar areas, security personnel in the same ratio as the first ratio are allocated to the corresponding similar areas.

[0033] In a possible implementation of the first aspect, when a preset recognition model identifies a person to be managed, calculating a distance between a position vector and a position vector corresponding to the person to be managed in a point cloud map of the target campus, and assigning, according to the distance and a security level of the person to be managed, a number of security personnel matching the security level to go to the location of the person to be managed, specifically includes:

[0034] Obtaining a database of registered personnel of the target campus;

[0035] In the preset C3D model, the weight of each camera is evaluated according to the Taylor expansion method for structured pruning;

[0036] The C3D model is called to perform behavior recognition on the personnel in the registered personnel database. If the personnel is recognized to perform the target action, the personnel is regarded as the first person to be managed, and the first distance between the position vector and the position vector corresponding to the first person to be managed in the point cloud map of the target campus is calculated. According to the ascending order of the first distance and the security level corresponding to the target action, a number of security personnel matching the security level are assigned to the location of the person to be managed;

[0037] Add context variables including regional road direction information and regional location information to the preset VAEs model;

[0038] The VAEs model is called to perform behavior recognition on personnel in the non-registered personnel database. If a person is recognized to perform a target action, the person is regarded as a second person to be managed, and a second distance between a position vector and a position vector corresponding to the second person to be managed in the point cloud map of the target campus is calculated. According to the ascending order of the second distances and the security level corresponding to the target action, security personnel with a number matching the security level are assigned to the location of the person to be managed.

[0039] A second aspect of an embodiment of the present application provides a campus safety management system, including:

[0040] A point cloud acquisition module, used to acquire a point cloud map of a target campus and point cloud maps of other campuses in the global jurisdiction where the target campus is located;

[0041] An area determination module, used to determine a plurality of additional patrol areas according to historical security incidents that occurred in other campuses;

[0042] A matrix determination module, used to calculate a set of point cloud feature descriptors of the target campus and a set of point cloud feature descriptors of the other campuses, and determine the transformation matrix of the two sets of point cloud feature descriptors;

[0043] A region alignment module, used for aligning a plurality of similar regions in the target campus according to the plurality of patrol-added regions and the transformation matrix;

[0044] A personnel allocation module is used to allocate security personnel in a corresponding proportion according to the frequency of historical security incidents occurring in the multiple similar areas corresponding to the multiple additional patrol areas; each security personnel is responsible for one similar area;

[0045] The real-time allocation module is used to continuously obtain the position vector corresponding to the location of the security personnel in the point cloud map of the target campus. When the preset recognition model identifies the person to be managed, the distance between the position vector and the position vector corresponding to the person to be managed in the point cloud map of the target campus is calculated. According to the distance and the safety level of the person to be managed, a preset number of the security personnel are allocated to the location of the person to be managed.

[0046] Compared with the prior art, the present invention ensures the comprehensiveness and accuracy of the data by obtaining the point cloud map of the target campus and other campuses in its global jurisdiction. Then the high-risk area is automatically identified and used as the center of the patrol area, avoiding the subjectivity and deviation of human judgment, making the prediction more scientific and objective. By calculating the feature descriptor, the feature information of the point cloud map is accurately extracted, and then the corresponding point pairs are found using the nearest neighbor algorithm, and the transformation matrix between the two sets of point cloud maps is calculated based on these point pairs. This process realizes the precise registration of point cloud maps between different campuses, providing a reliable basis for subsequent security management. Then, according to the transformation matrix, the patrol areas in other campuses are mapped to the target campus to form similar areas. In this way, the successful experience of other campuses can be directly applied to quickly locate the high-risk areas in the target campus. Finally, security personnel are allocated according to the ratio of the frequency of historical security events in the similar area corresponding to the patrol area, ensuring that each area obtains security forces that match its risks. This method avoids the problem of waste of resources or insufficient protection and improves the effectiveness of resource allocation.

[0047] In addition, the present invention continuously obtains the location information of security personnel, and combines the behavior recognition model to monitor and adjust the security force in real time. Once abnormal behavior is identified, the system can quickly calculate the location vector of the person to be managed, and assign the corresponding security personnel to handle it according to the distance and security level. This dynamic response mechanism enhances the flexibility and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flow chart of a campus safety management method provided by an embodiment of the present invention;

[0049] Figure 2 The present invention provides a schematic diagram of the structure of a campus safety management system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] 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.

[0051] To solve the above problems, see Figure 1 An embodiment of the present invention provides a campus safety management method, comprising:

[0052] S10. Obtain a point cloud map of the target campus and point cloud maps of other campuses in the global jurisdiction where the target campus is located.

[0053] S11. Determine multiple additional patrol areas based on historical security incidents that occurred in other campuses.

[0054] S12. Calculate a set of point cloud feature descriptors of the target campus and a set of point cloud feature descriptors of the other campuses, and determine transformation matrices of the two sets of point cloud feature descriptors.

[0055] S13. Aligning multiple similar areas in the target campus according to the multiple patrol-added areas and the transformation matrix.

[0056] S14. Allocate security personnel in corresponding proportions according to the frequency of historical security incidents occurring in the multiple similar areas corresponding to the multiple additional patrol areas; each security personnel is responsible for one similar area.

[0057] S15. Continuously obtain the position vector corresponding to the location of the security personnel in the point cloud map of the target campus. When the preset recognition model identifies the person to be managed, calculate the distance between the position vector and the position vector corresponding to the position of the person to be managed in the point cloud map of the target campus. According to the distance and the safety level of the person to be managed, assign a preset number of the security personnel to the location of the person to be managed.

[0058] S10 ensures the comprehensiveness and accuracy of the data by obtaining the point cloud map of the target campus and other campuses in its global jurisdiction. This not only covers all key areas within the campus, but also uses the data of other campuses for cross-campus analysis, improving the richness of the overall data. S11 can automatically identify high-risk areas by counting historical security events on other campuses and use them as the center of the additional patrol area. According to the actual patrol range and the center position of the additional patrol area, the additional patrol area can be flexibly adjusted to adapt to different campus layouts and security needs. S12 can accurately extract the feature information of the point cloud map by calculating feature descriptors. These feature descriptors not only contain spatial geometric information, but also consider local shape features to improve matching accuracy. Then the nearest neighbor algorithm is used to find corresponding point pairs, and the transformation matrix between the two sets of point cloud maps is calculated based on these point pairs. This process realizes the precise registration of point cloud maps between different campuses, providing a reliable foundation for subsequent security management. S13 maps the additional patrol areas in other campuses to the target campus according to the transformation matrix to form similar areas. In this way, the successful experience of other campuses can be directly applied to quickly locate high-risk areas in the target campus. S14 allocates security personnel based on the historical security incident frequency ratio of similar areas to the corresponding patrol areas, ensuring that each area receives security forces that match its risks. This method avoids the problem of resource waste or insufficient protection and improves the effectiveness of resource allocation. S15 continuously obtains the location information of security personnel, and combines the behavior recognition model to monitor and adjust the security force in real time. Once abnormal behavior is identified, the system can quickly calculate the location vector of the person to be managed, and assign the corresponding security personnel to handle it according to the distance and security level. This dynamic response mechanism enhances the flexibility and adaptability of security management.

[0059] In summary, the above method uses historical security event data and advanced point cloud processing technology to ensure the accuracy and scientificity of the prediction, avoiding the subjectivity and uncertainty in traditional methods; through precise point cloud map registration and similar area alignment, data sharing and application between different campuses are realized, improving the overall management efficiency; security personnel are allocated according to the frequency ratio of historical events, combined with real-time monitoring and dynamic adjustment mechanisms, ensuring the rational allocation and efficient use of resources. These advantages work together to make this method have a significant effect in improving the overall effectiveness of campus security management.

[0060] Exemplarily, the step of obtaining a point cloud map of a target campus and point cloud maps of other campuses in the global jurisdiction where the target campus is located specifically includes:

[0061] For the target campus and other campuses in the overall jurisdiction where the target campus is located, multiple scanning stations are set according to a preset overlap range percentage; the preset overlap range percentage is equal to the overlap percentage of the patrol ranges of two adjacent security personnel, the preset overlap range percentage is the ratio of the overlapping scanning area of ​​adjacent scanning stations to the scanning area of ​​each of the scanning stations, and the patrol range overlap percentage is the ratio of the overlapping patrol area of ​​two adjacent security personnel to the scanning area of ​​each of the security personnel.

[0062] In order to set up multiple scanning stations on the target campus and other campuses in its global jurisdiction to ensure full coverage and obtain high-quality point cloud data, it is necessary to determine the preset overlap range percentage, select compliant scanning equipment, and plan the scanning station locations.

[0063] Assume that after analysis and testing, it is decided to use 30% as the preset overlap range percentage. This means that the overlap area between two adjacent scanning stations should account for 30% of the total area of ​​each scanning station. This ratio is also applied to the overlap area when security personnel patrol to ensure that there are no blind spots in monitoring.

[0064] Then, according to the specific environment of the campus (such as building density, vegetation coverage, etc.), choose a suitable laser scanner or other 3D scanning equipment. Considering cost and efficiency, it may be necessary to use portable or vehicle-mounted scanning equipment.

[0065] Finally, use GIS software or professional scanning station planning tools to plan the best location for each scanning station based on the campus map and the preset overlap range percentage. This process needs to ensure that there is enough overlap between the scanning stations, but also avoid data redundancy caused by excessive overlap.

[0066] In this way, not only can high-quality point cloud data be obtained, but it also provides a solid foundation for campus safety management. The advantage of this method is that it combines scientific planning with advanced technical means to ensure the integrity and accuracy of the data, thereby supporting more accurate and effective safety management and decision-making.

[0067] Exemplarily, the determining of a plurality of additional patrol areas according to the historical security incidents occurring in the other campuses specifically includes:

[0068] Performing K-means clustering on the historical security events that occurred in the other campuses, and taking multiple locations corresponding to the most recent historical security events of multiple clusters as the centers of multiple additional patrol areas;

[0069] A plurality of additional patrol areas are determined according to a preset patrol range and the centers of the plurality of additional patrol areas.

[0070] The K-means clustering algorithm is used to perform cluster analysis on the location coordinates of all historical security events. Each cluster represents a group of security events with similar geographical locations.

[0071] The centroid (i.e., geometric center) of each cluster can be regarded as the center of a potential high-risk area. For each cluster, find one or more historical security incident locations closest to the centroid and use them as the center of the additional patrol area corresponding to the cluster. These center points will become reference points for determining the additional patrol area in the future.

[0072] Then, according to the actual patrol capabilities of security personnel and the layout of the campus, set a reasonable patrol range radius (for example, 100 meters). This range should ensure coverage of high-risk areas and their surrounding areas. Circular areas can be drawn with the center of each additional patrol area as the center of the circle, using the preset patrol range radius. These circular areas are the additional patrol areas. If there is overlap between certain areas, the boundaries can be adjusted according to actual conditions to avoid repeated patrols or missing key areas. All additional patrol areas can be reviewed to ensure that they cover all high-risk points and there are no obvious blank areas. If necessary, the regional division can be further optimized in combination with geographic information system (GIS) tools, taking into account factors such as terrain and building distribution.

[0073] The above method can not only scientifically and reasonably determine the additional patrol areas on campus, but also provide a solid foundation for the subsequent allocation of security resources. The advantage of this method is that it is based on actual historical data for analysis, reducing the subjectivity and bias caused by human judgment, and improving the accuracy of predictions and the scientific nature of management decisions.

[0074] Exemplarily, the calculating a set of point cloud feature descriptors of the target campus and a set of point cloud feature descriptors of the other campuses, and determining the transformation matrix of the two sets of point cloud feature descriptors specifically includes:

[0075] Calculate the FPFH and SHOT of the target campus point cloud image as a set of point cloud image feature descriptors, and calculate the FPFH and SHOT of the other campus point cloud images as another set of point cloud image feature descriptors;

[0076] According to the two sets of point cloud feature descriptors, all valid nearest neighbor point pairs between the point cloud of the target campus and the point cloud of other campuses are found through the nearest neighbor algorithm;

[0077] According to all the valid nearest neighbor point pairs, the transformation matrices of two groups of point cloud feature descriptors are calculated.

[0078] First, for the point cloud data of each other reference campus, the FPFH algorithm is used to calculate the local geometric features of each point. FPFH considers the distance and angle relationship between a point and its neighborhood, and can effectively capture the local structural information in the point cloud. Similarly, for the point cloud data of each other reference campus, the SHOT algorithm is used to calculate the feature descriptor of each point. SHOT not only considers the geometric information, but also contains the information of the surface normal direction, which is suitable for point cloud registration tasks.

[0079] Next, use the nearest neighbor search algorithm (such as the K-nearest neighbor algorithm KNN) to find the nearest neighbor points of each target campus point in the feature descriptor KD tree of the reference campus. This step will find one or more most similar reference campus points for each point of the target campus. According to a predefined distance threshold or other criteria, filter out valid nearest neighbor point pairs. For example, a distance threshold can be set, and only when the distance between the nearest neighbor points is less than or equal to the threshold, they are considered to be a pair of valid matching points.

[0080] The target campus point coordinates and the corresponding reference campus point coordinates of all valid nearest neighbor point pairs can be sorted into two matrices respectively. These two matrices represent the source point set (target campus point) and the target point set (reference campus point). Using algorithms such as SVD (singular value decomposition) or RANSAC (random sampling consensus), the optimal rigid body transformation matrix (including rotation and translation) is calculated based on the source point set and the target point set. This transformation matrix can align the target campus point cloud map with the reference campus point cloud map.

[0081] Through the above method, accurate registration of point cloud images between different campuses is achieved, and an important spatial analysis basis is provided for subsequent safety management strategies. The advantage of this method is that it combines point cloud processing technology and data analysis methods to ensure high accuracy and reliability of the registration results.

[0082] Exemplarily, the method of finding all valid nearest neighbor point pairs between the point cloud image of the target campus and the point cloud images of other campuses by using the nearest neighbor algorithm based on the two sets of point cloud image feature descriptors specifically includes:

[0083] Calculate the mean projection distance of the FPFH feature descriptor of each point in the other campus point cloud map on the fitness vector of the corresponding point as the FPFH distance;

[0084] Calculate the SHOT feature descriptor of each point in the other campus point cloud map and the average of the projection distances of the corresponding point fitness vectors as the SHOT distance;

[0085] Using the difference between the FPFH distance and the SHOT distance as a distance threshold;

[0086] Use the nearest neighbor algorithm to find all valid nearest neighbor point pairs between the point cloud of the target campus and the point cloud of other campuses;

[0087] The nearest neighbor point pairs whose distance is less than or equal to the distance threshold are regarded as valid nearest neighbor point pairs.

[0088] For each point in the cloud map, the difference between its FPFH distance and SHOT distance is calculated. This difference reflects the degree of difference between different feature descriptors. A global distance threshold can be determined by performing statistical analysis on the distance differences of all points (such as taking the average value or setting a fixed ratio). For example, the average value of the distance differences of all points can be selected as the threshold.

[0089] The K-nearest neighbor algorithm (KNN) can be used to find the nearest neighbor of each target campus point in the feature descriptor KD tree of the reference campus. The distance between each target campus point and its nearest neighbor is recorded. According to the pre-set distance threshold, the valid nearest neighbor point pairs that meet the conditions are screened out. Specifically, only when the distance between the nearest neighbor point pairs is less than or equal to the global distance threshold, they are considered to be a pair of valid matching points.

[0090] This method not only achieves accurate registration of point cloud images between different campuses, but also ensures the validity and accuracy of matching point pairs. The advantage of this method is that it combines advanced point cloud processing technology and scientific data analysis methods to ensure the high accuracy and reliability of the registration results, providing an important spatial analysis basis for subsequent safety management strategies.

[0091] Exemplarily, before finding all valid nearest neighbor point pairs between the point cloud image of the target campus and the point cloud images of other campuses using the nearest neighbor algorithm according to the two sets of point cloud image feature descriptors, the method further includes:

[0092] A KD tree index structure is established based on two sets of point cloud feature descriptors.

[0093] A KD tree index structure can be constructed for the point cloud feature descriptors of the target campus and the reference campus (other campuses) respectively to accelerate the nearest neighbor search process.

[0094] Exemplarily, the method for aligning a plurality of similar areas in the target campus according to the plurality of patrol-added areas and the transformation matrix specifically includes:

[0095] According to the transformation matrix, coordinate transformation is performed on each point of the plurality of patrol-added areas to obtain a plurality of similar areas.

[0096] For each point in each additional patrol area, the transformation matrix is ​​used to transform the coordinates. The transformed coordinate points are recombined into new areas, which are similar areas in the target campus. For example, after the transformation, the additional patrol area of ​​the old campus is transformed into a similar area in the new campus.

[0097] This method not only achieves accurate alignment of patrol areas between different campuses, but also provides a scientific basis for the security management of new campuses. The advantage of this method is that it combines advanced point cloud processing technology and spatial transformation methods to ensure high accuracy and reliability of similar areas, which helps to deploy security resources more accurately and improve the overall efficiency of campus security management.

[0098] Exemplarily, the allocating corresponding proportions of security personnel according to the frequencies of historical security incidents occurring in the plurality of similar areas corresponding to the plurality of additional patrol areas specifically includes:

[0099] According to a first ratio of the frequency of historical security incidents occurring in each similar area corresponding to the additional patrol area to the frequency of historical security incidents occurring in all similar areas, security personnel in the same ratio as the first ratio are allocated to the corresponding similar areas.

[0100] Assume that through the aforementioned method, three similar areas in the target campus have been identified: Area A, Area B, and Area C, which correspond to the additional patrol areas in other campuses: Area D, Area E, and Area F. Assume that the following number of security incidents occurred in the additional patrol areas of his campus:

[0101] There were 50 incidents in area D, 30 incidents in area E, and 20 incidents in area F. The incident frequencies of each additional patrol area (area D, area E, and area F) accounted for 0.5, 0.3, and 0.2 of the total incident numbers, respectively.

[0102] Assume that the target campus plans to deploy a total of 100 security personnel for security management. According to the first ratio of each similar area, the corresponding number of security personnel is allocated. The specific allocation is as follows: 50 security personnel are allocated to area A, 30 security personnel are allocated to area B, and 20 security personnel are allocated to area C.

[0103] This method not only achieves accurate alignment of patrol areas between different campuses and effective statistics of the frequency of security incidents, but also ensures the rational allocation of security resources. The advantage of this method is that it combines historical data analysis with a scientific resource allocation strategy to ensure that each similar area can get security forces that match its risks, thereby improving the efficiency and effectiveness of overall security management. If the actual demand exceeds the allocated number, the shortage can be compensated by dynamically adjusting the patrol frequency or introducing temporary security forces.

[0104] Exemplarily, when the preset recognition model recognizes the person to be managed, the distance between the position vector and the position vector corresponding to the person to be managed in the point cloud map of the target campus is calculated, and according to the distance and the security level of the person to be managed, the security personnel whose number matches the security level are assigned to the location of the person to be managed, specifically including:

[0105] Obtaining a database of registered personnel of the target campus;

[0106] In the preset C3D model, the weight of each camera is evaluated according to the Taylor expansion method for structured pruning;

[0107] The C3D model is called to perform behavior recognition on the personnel in the registered personnel database. If the personnel is recognized to perform the target action, the personnel is regarded as the first person to be managed, and the first distance between the position vector and the position vector corresponding to the first person to be managed in the point cloud map of the target campus is calculated. According to the ascending order of the first distance and the security level corresponding to the target action, a number of security personnel matching the security level are assigned to the location of the person to be managed;

[0108] Add context variables including regional road direction information and regional location information to the preset VAEs model;

[0109] The VAEs model is called to perform behavior recognition on personnel in the non-registered personnel database. If a person is recognized to perform a target action, the person is regarded as a second person to be managed, and a second distance between a position vector and a position vector corresponding to the second person to be managed in the point cloud map of the target campus is calculated. According to the ascending order of the second distances and the security level corresponding to the target action, security personnel with a number matching the security level are assigned to the location of the person to be managed.

[0110] The Taylor expansion method can be used to evaluate the weight of each camera and perform structured pruning accordingly. This step aims to reduce unnecessary computation and improve the efficiency of the model on edge devices. The optimized C3D model is then called to perform real-time behavior recognition on the personnel in the registered personnel database. If a person is detected to make a predefined target action (such as running, climbing, etc.), he or she is marked as the first person to be managed. Based on the location information of the surveillance camera, the corresponding position vector of the first person to be managed in the target campus point cloud map is calculated. Finally, the distance between the current location of the security personnel and the first person to be managed is calculated and sorted in ascending order according to the distance.

[0111] Combined with the safety level of the target action (for example, running may be marked as medium risk, while climbing is high risk), the corresponding number of security personnel are assigned to handle it. For example, for high-risk actions, more or higher-quality security personnel can be dispatched first.

[0112] When using the VAEs model, context variables including regional road direction information and regional location information can be added to the preset VAEs model. This additional information helps to improve the recognition accuracy of the model in complex environments. Then call the optimized VAEs model to identify the behavior of non-registered persons in real time. If a person is detected to make a predefined target action, he or she is marked as the second person to be managed. Similarly, based on the location information of the surveillance camera, the corresponding position vector of the second person to be managed in the target campus point cloud map is calculated. The distance between the current location of the security personnel and the second person to be managed is calculated, and sorted in ascending order according to the distance. Combined with the security level corresponding to the target action, the corresponding number of security personnel are assigned to handle it. Since non-registered persons may have higher uncertainty, the response level can be appropriately increased.

[0113] This method not only achieves efficient identification and rapid response to the behavior of people on campus, but also ensures the rational allocation of security resources. The advantage of this method is that it combines behavior recognition technology and resource scheduling strategy, which can significantly improve the overall effectiveness of campus security management.

[0114] Compared with the prior art, a campus safety management method provided by an embodiment of the present invention ensures the comprehensiveness and accuracy of data by obtaining the point cloud map of the target campus and other campuses in its global jurisdiction. Then the high-risk area is automatically identified and used as the center of the patrol area, avoiding the subjectivity and deviation of human judgment, making the prediction more scientific and objective. By calculating the feature descriptor, the feature information of the point cloud map is accurately extracted, and then the corresponding point pairs are found using the nearest neighbor algorithm, and the transformation matrix between the two sets of point cloud maps is calculated based on these point pairs. This process realizes the precise registration of point cloud maps between different campuses, providing a reliable basis for subsequent security management. Then, according to the transformation matrix, the patrol area in other campuses is mapped to the target campus to form a similar area. In this way, the successful experience of other campuses can be directly applied to quickly locate the high-risk area in the target campus. Finally, security personnel are allocated according to the historical security event frequency ratio of the similar area corresponding to the patrol area, ensuring that each area obtains security forces that match its risk. This method avoids the problem of waste of resources or insufficient protection and improves the effectiveness of resource allocation.

[0115] In addition, the present invention continuously obtains the location information of security personnel, and combines the behavior recognition model to monitor and adjust the security force in real time. Once abnormal behavior is identified, the system can quickly calculate the location vector of the person to be managed, and assign the corresponding security personnel to handle it according to the distance and security level. This dynamic response mechanism enhances the flexibility and adaptability of the system.

[0116] An embodiment of the present application provides a campus safety management system, including a point cloud acquisition module 20, an area determination module 21, a matrix determination module 22, an area alignment module 23, a personnel allocation module 24 and a real-time allocation module 25.

[0117] The point cloud acquisition module 20 is used to obtain a point cloud map of the target campus and point cloud maps of other campuses in the global jurisdiction where the target campus is located.

[0118] The area determination module 21 is used to determine a plurality of additional patrol areas according to the historical security incidents that occurred in the other campuses.

[0119] The matrix determination module 22 is used to calculate a set of point cloud feature descriptors of the target campus and a set of point cloud feature descriptors of the other campuses, and determine the transformation matrix of the two sets of point cloud feature descriptors.

[0120] The area alignment module 23 is used to align multiple similar areas in the target campus according to the multiple patrol-added areas and the transformation matrix.

[0121] The personnel allocation module 24 is used to allocate security personnel in a corresponding proportion according to the frequency of historical security incidents occurring in the multiple similar areas corresponding to the multiple additional patrol areas; each security personnel is responsible for one similar area.

[0122] The real-time allocation module 25 is used to continuously obtain the position vector corresponding to the location of the security personnel in the point cloud map of the target campus. When the preset recognition model identifies the person to be managed, the distance between the position vector and the position vector corresponding to the person to be managed in the point cloud map of the target campus is calculated. According to the distance and the safety level of the person to be managed, a preset number of the security personnel are allocated to the location of the person to be managed.

[0123] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the campus security management system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0124] Compared with the prior art, a campus security management system provided by an embodiment of the present invention ensures the comprehensiveness and accuracy of data by obtaining the point cloud map of the target campus and other campuses in its global jurisdiction. Then, the high-risk area is automatically identified and used as the center of the patrol area, avoiding the subjectivity and deviation of human judgment, making the prediction more scientific and objective. By calculating the feature descriptor, the feature information of the point cloud map is accurately extracted, and then the corresponding point pairs are found using the nearest neighbor algorithm, and the transformation matrix between the two sets of point cloud maps is calculated based on these point pairs. This process realizes the precise registration of point cloud maps between different campuses, providing a reliable basis for subsequent security management. Then, according to the transformation matrix, the patrol area in other campuses is mapped to the target campus to form a similar area. In this way, the successful experience of other campuses can be directly applied to quickly locate the high-risk area in the target campus. Finally, security personnel are allocated according to the ratio of the frequency of historical security events in the similar area corresponding to the patrol area, ensuring that each area obtains security forces that match its risk. This method avoids the problem of waste of resources or insufficient protection and improves the effectiveness of resource allocation.

[0125] In addition, the present invention continuously obtains the location information of security personnel, and combines the behavior recognition model to monitor and adjust the security force in real time. Once abnormal behavior is identified, the system can quickly calculate the location vector of the person to be managed, and assign the corresponding security personnel to handle it according to the distance and security level. This dynamic response mechanism enhances the flexibility and adaptability of the system.

[0126] An embodiment of the present application provides a computer-readable storage medium storing a computer program, which implements the campus safety management method as described above when the computer program is executed by a processor.

[0127] The computer device may be a computing device such as a smart phone, a tablet computer, a desktop computer, and a cloud server. The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the figure is merely an example of a computer device and does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or a combination of certain components, or different components, such as input and output devices, network access devices, etc.

[0128] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0129] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Further, the memory may also include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory may also be used to temporarily store data that has been output or is to be output.

[0130] An embodiment of the present application provides a computer program product. When the computer program product is run on a computer device, the computer device implements the steps in the above-mentioned method embodiments when executing the computer device.

[0131] In several embodiments provided in the present application, it is understood that each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved.

[0132] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0133] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A campus safety management method, characterized in that: include: Obtaining a point cloud map of a target campus and point cloud maps of other campuses in the global jurisdiction where the target campus is located; Determine multiple additional patrol areas based on historical security incidents that occurred on other campuses; Calculating a set of point cloud feature descriptors of the target campus and a set of point cloud feature descriptors of the other campuses, and determining transformation matrices of the two sets of point cloud feature descriptors; Aligning multiple similar areas in the target campus according to the multiple patrol-added areas and the transformation matrix; According to the frequency of historical security incidents occurring in the multiple similar areas corresponding to the multiple additional patrol areas, security personnel in corresponding proportions are allocated; each security personnel is responsible for one similar area; Continuously obtain the position vector corresponding to the location of the security personnel in the point cloud map of the target campus; when the preset recognition model identifies the person to be managed, calculate the distance between the position vector and the position vector corresponding to the position of the person to be managed in the point cloud map of the target campus; and according to the distance and the safety level of the person to be managed, assign a preset number of the security personnel to the location of the person to be managed.

2. A campus safety management method as claimed in claim 1, characterized in that: The step of obtaining a point cloud map of the target campus and point cloud maps of other campuses in the global jurisdiction where the target campus is located specifically includes: For the target campus and other campuses in the overall jurisdiction where the target campus is located, multiple scanning stations are set according to a preset overlap range percentage; the preset overlap range percentage is equal to the overlap percentage of the patrol ranges of two adjacent security personnel, the preset overlap range percentage is the ratio of the overlapping scanning area of ​​adjacent scanning stations to the scanning area of ​​each of the scanning stations, and the patrol range overlap percentage is the ratio of the overlapping patrol area of ​​two adjacent security personnel to the scanning area of ​​each of the security personnel.

3. A campus safety management method as claimed in claim 1, characterized in that: According to the historical security incidents that occurred on other campuses, multiple additional patrol areas are determined, including: Performing K-means clustering on the historical security events that occurred in the other campuses, and taking multiple locations corresponding to the most recent historical security events of multiple clusters as the centers of multiple additional patrol areas; A plurality of additional patrol areas are determined according to a preset patrol range and the centers of the plurality of additional patrol areas.

4. A campus safety management method as claimed in claim 1, characterized in that: The calculating a set of point cloud feature descriptors of the target campus and a set of point cloud feature descriptors of the other campuses, and determining the transformation matrix of the two sets of point cloud feature descriptors, specifically includes: Calculate the FPFH and SHOT of the target campus point cloud image as a set of point cloud image feature descriptors, and calculate the FPFH and SHOT of the other campus point cloud images as another set of point cloud image feature descriptors; According to the two sets of point cloud feature descriptors, all valid nearest neighbor point pairs between the point cloud of the target campus and the point cloud of other campuses are found through the nearest neighbor algorithm; According to all the valid nearest neighbor point pairs, the transformation matrices of two groups of point cloud feature descriptors are calculated.

5. A campus safety management method as claimed in claim 4, characterized in that: The method of finding all valid nearest neighbor point pairs between the point cloud image of the target campus and the point cloud images of other campuses through the nearest neighbor algorithm according to the two sets of point cloud image feature descriptors specifically includes: Calculate the mean projection distance of the FPFH feature descriptor of each point in the other campus point cloud map on the fitness vector of the corresponding point as the FPFH distance; Calculate the SHOT feature descriptor of each point in the other campus point cloud map and the average of the projection distances of the corresponding point fitness vectors as the SHOT distance; Using the difference between the FPFH distance and the SHOT distance as a distance threshold; Use the nearest neighbor algorithm to find all valid nearest neighbor point pairs between the point cloud of the target campus and the point cloud of other campuses; The nearest neighbor point pairs whose distance is less than or equal to the distance threshold are regarded as valid nearest neighbor point pairs.

6. A campus safety management method as claimed in claim 4, characterized in that: Before using the nearest neighbor algorithm to find all valid nearest neighbor point pairs between the point cloud image of the target campus and the point cloud images of other campuses based on the two sets of point cloud image feature descriptors, the method further includes: A KD tree index structure is established based on two sets of point cloud feature descriptors.

7. A campus safety management method as claimed in claim 1, characterized in that: The method for aligning a plurality of similar areas in the target campus according to the plurality of patrol-added areas and the transformation matrix specifically includes: According to the transformation matrix, coordinate transformation is performed on each point of the plurality of patrol-added areas to obtain a plurality of similar areas.

8. A campus safety management method as claimed in claim 1, characterized in that: The allocating of security personnel in corresponding proportions according to the frequency of historical security incidents occurring in the plurality of similar areas corresponding to the plurality of additional patrol areas specifically includes: According to a first ratio of the frequency of historical security incidents occurring in each similar area corresponding to the additional patrol area to the frequency of historical security incidents occurring in all similar areas, security personnel in the same ratio as the first ratio are allocated to the corresponding similar areas.

9. A campus safety management method as claimed in claim 1, characterized in that: When the preset recognition model recognizes the person to be managed, the distance between the position vector and the position vector corresponding to the person to be managed in the point cloud map of the target campus is calculated, and according to the distance and the security level of the person to be managed, the security personnel whose number matches the security level are assigned to the location of the person to be managed, specifically including: Obtaining a database of registered personnel of the target campus; In the preset C3D model, the weight of each camera is evaluated according to the Taylor expansion method for structured pruning; The C3D model is called to perform behavior recognition on the personnel in the registered personnel database. If the personnel is recognized to perform the target action, the personnel is regarded as the first person to be managed, and the first distance between the position vector and the position vector corresponding to the first person to be managed in the point cloud map of the target campus is calculated. According to the ascending order of the first distance and the security level corresponding to the target action, a number of security personnel matching the security level are assigned to the location of the person to be managed; Add context variables including regional road direction information and regional location information to the preset VAEs model; The VAEs model is called to perform behavior recognition on personnel in the non-registered personnel database. If a person is recognized to perform a target action, the person is regarded as a second person to be managed, and a second distance between a position vector and a position vector corresponding to the second person to be managed in the point cloud map of the target campus is calculated. According to the ascending order of the second distances and the security level corresponding to the target action, security personnel with a number matching the security level are assigned to the location of the person to be managed.

10. A campus safety management system, characterized in that: include: A point cloud acquisition module, used to acquire a point cloud map of a target campus and point cloud maps of other campuses in the global jurisdiction where the target campus is located; An area determination module, used to determine a plurality of additional patrol areas according to historical security incidents that occurred in other campuses; A matrix determination module, used to calculate a set of point cloud feature descriptors of the target campus and a set of point cloud feature descriptors of the other campuses, and determine the transformation matrix of the two sets of point cloud feature descriptors; A region alignment module, used for aligning a plurality of similar regions in the target campus according to the plurality of patrol-added regions and the transformation matrix; A personnel allocation module is used to allocate security personnel in a corresponding proportion according to the frequency of historical security incidents occurring in the multiple similar areas corresponding to the multiple additional patrol areas; each security personnel is responsible for one similar area; The real-time allocation module is used to continuously obtain the position vector corresponding to the location of the security personnel in the point cloud map of the target campus. When the preset recognition model identifies the person to be managed, the distance between the position vector and the position vector corresponding to the person to be managed in the point cloud map of the target campus is calculated. According to the distance and the safety level of the person to be managed, a preset number of the security personnel are allocated to the location of the person to be managed.

Images