Museum intelligent monitoring system based on multi-source electronic information fusion

Abstract

The invention relates to the technical field of museum safety management, and discloses a museum intelligent monitoring system based on multi-source electronic information fusion, and the system comprises a multi-source electronic information collection module which obtains video monitoring data, environment sensor data and passenger flow monitoring data distributed in a museum; the data fusion module is used for extracting dynamic behavior characteristics from the video monitoring data, extracting abnormal environment parameters from the environment sensor data, extracting density distribution characteristics from the passenger flow monitoring data, and generating a comprehensive risk map through multi-modal characteristic fusion; the intelligent early warning module is used for generating graded early warning signals based on risk types contained in the comprehensive risk map; and the linkage control module is used for triggering corresponding control operations in security and protection equipment starting, environment regulation equipment regulation or passenger flow dispersion terminal prompting in the corresponding areas according to the graded early warning signals. The safety supervision and management efficiency of the museum can be improved, and various risks in the museum can be comprehensively, accurately and timely managed, controlled and handled.

Description

Technical Field

[0001] The present invention relates to the technical field of museum security management, and in particular to a museum intelligent monitoring system integrating multi-source electronic information. Background Art

[0002] In today's digital age, museums face the dual challenges of security oversight and efficient management. Traditional surveillance systems are no longer able to meet the diverse needs of museums. For one thing, traditional surveillance systems, often based on a single video surveillance method, only provide limited on-site image information. They lack comprehensive awareness of complex and ever-changing museum environments, such as crowded areas and artifact display areas, and are unable to effectively identify potential risks. Furthermore, various electronic information sources within museums, such as temperature and humidity sensors and visitor flow monitors, are independent of each other, making information integration and sharing difficult. This leads to severe data silos and hinders the formation of effective collaborative management mechanisms.

[0003] Therefore, it is urgent to provide a technical solution to solve the above problems. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention provides a museum intelligent monitoring system that integrates multi-source electronic information.

[0005] In a first aspect, the present invention provides a museum intelligent monitoring system that integrates multi-source electronic information. The technical solution of the system is as follows:

[0006] Multi-source electronic information acquisition module, used to obtain real-time video surveillance data, environmental sensor data, and visitor flow monitoring data distributed throughout the museum;

[0007] a data fusion module, configured to extract dynamic behavior features from the video surveillance data, extract abnormal environmental parameters from the environmental sensor data, extract density distribution features from the passenger flow monitoring data, and generate a comprehensive risk map containing risk types through multimodal feature fusion;

[0008] An intelligent early warning module, configured to generate a graded early warning signal based on the risk types included in the comprehensive risk map;

[0009] The linkage control module is used to automatically trigger the corresponding control operations in the security equipment startup, environmental conditioning equipment regulation or passenger flow guidance terminal prompts in the corresponding area according to the graded warning signal.

[0010] The beneficial effects of the museum intelligent monitoring system with multi-source electronic information fusion of the present invention are as follows:

[0011] The system of the present invention can effectively solve the problems of limited perception ability and data silos existing in traditional monitoring systems in museum security management, improve the efficiency of museum security supervision and management, and can comprehensively, accurately and timely control and respond to various risks in the museum.

[0012] Based on the above solution, the museum intelligent monitoring system with multi-source electronic information fusion of the present invention can also be improved as follows.

[0013] In an optional manner, the multi-source electronic information collection module is specifically used to:

[0014] Using video surveillance equipment deployed in the cultural relics display area to obtain the video surveillance data in real time;

[0015] Collecting the environmental sensor data using environmental sensors distributed in the exhibition hall;

[0016] The passenger flow monitoring data is collected using an entrance gate and a thermal imager.

[0017] In an optional manner, the data fusion module is specifically configured to:

[0018] Performing moving target detection and behavior trajectory analysis on the video surveillance data to extract the dynamic behavior features;

[0019] Performing threshold comparison on the environmental sensor data to extract the abnormal environmental parameters that deviate from the preset cultural relic preservation threshold;

[0020] The passenger flow monitoring data is calculated through a spatial heat map to extract the density distribution characteristics.

[0021] In an optional manner, the data fusion module is specifically configured to:

[0022] Perform inter-frame difference calculation on the video surveillance data collected in real time to extract the moving target area, and the expression is:

[0023]

[0024] Where M t (x,y) represents the binary mask of the moving target area in the tth frame, F t (x, y) represents the pixel value of the video frame of the tth frame in the video surveillance data, F t-1 (x, y) represents the pixel value of the video frame of the t-1th frame in the video surveillance data, θ v represents the pixel threshold;

[0025] Performing connected domain analysis and target instantiation processing on the moving target area to obtain multiple connected domains, assigning a target ID to each connected domain, and generating a trajectory point set;

[0026] The velocity vector is calculated based on the trajectory point set, and the velocity vector is input into the behavior classification model to output the dynamic behavior feature, which is expressed as:

[0027] β=CNN-LSTM({v id})

[0028] Where, v id represents the velocity vector, (x i ,y i ) represents the coordinates of the i-th trajectory point in the trajectory point set, Δt represents the frame time interval, and β represents the dynamic behavior feature.

[0029] In an optional manner, the preset cultural relic preservation threshold includes: a temperature threshold, a humidity threshold, and a light intensity threshold; and the data fusion module is specifically configured to:

[0030] The deviation between the environmental sensor data and the preset cultural relic preservation threshold is calculated using the following expression:

[0031]

[0032] Where, τ temp represents the temperature threshold, τ humid represents the humidity threshold, τ light represents the light intensity threshold; δ temp Indicates the allowable temperature deviation, δ humid Indicates the humidity tolerance, δ light Indicates the allowable deviation of light intensity; temp t Indicates the temperature value at time t, humid t Indicates the humidity value at time t, light t Indicates the light intensity value at time t, Δe t represents the environmental deviation vector at time t;

[0033] When the continuous exceeding time exceeds the limit, the abnormal environment parameter deviating from the preset cultural relic preservation threshold is output, and its expression is:

[0034]

[0035] Where, α represents the abnormal environment parameter, T c Indicates the continuous monitoring time, T th Indicates the duration threshold for exceeding the limit.

[0036] In an optional manner, the passenger flow monitoring data includes: a set of personnel coordinates and the real-time number of people at the gate; the data fusion module is specifically used to:

[0037] Correcting the personnel coordinate set according to the real-time number of people at the gate to obtain a corrected personnel coordinate set;

[0038] The spatial heat map is calculated based on the corrected personnel coordinate set, and its expression is:

[0039]

[0040] In the formula, (x p ,y p ) represents the pth person in the corrected person coordinate set, N total represents the total number of people in the corrected personnel coordinate set, σ represents the Gaussian kernel bandwidth, and D(x,y) represents the spatial heat map;

[0041] According to the spatial heat map, the density distribution feature is extracted, and its expression is:

[0042]

[0043] Where, ρ j represents the density of the jth sub-area of ​​the museum, Ω j represents the jth sub-region, K calib represents the density calibration coefficient, γ=[ρ1,ρ2,...,ρ m ] T ; m represents the total number of sub-areas of the museum.

[0044] In an optional manner, the data fusion module is specifically configured to:

[0045] The dynamic behavior characteristics, the abnormal environmental parameters and the density distribution characteristics are mapped into time-space coordinates and multi-source weights are assigned to generate a comprehensive risk map containing risk types.

[0046] In an optional manner, the intelligent early warning module is specifically used to:

[0047] When the risk type is a threat to the safety of cultural relics, a first-level warning signal is generated;

[0048] When the risk type is environmental exceeding the standard, a secondary warning signal is generated;

[0049] When the risk type is passenger congestion, a third-level warning signal is generated.

[0050] In an optional manner, the linkage control module is specifically configured to:

[0051] In response to the first-level warning signal, the sound and light alarm and camera automatic tracking in the cultural relics display area are activated;

[0052] In response to the secondary warning signal, regulating the constant temperature equipment and constant humidity equipment in the corresponding area;

[0053] In response to the third-level warning signal, the electronic guide screen diversion prompt of the diversion area is activated.

[0054] In a second aspect, the present invention provides a museum intelligent monitoring method based on multi-source electronic information fusion, the technical solution of which is as follows:

[0055] Real-time acquisition of video surveillance data, environmental sensor data, and visitor flow monitoring data distributed throughout the museum;

[0056] Extracting dynamic behavior features from the video surveillance data, extracting abnormal environmental parameters from the environmental sensor data, extracting density distribution features from the passenger flow monitoring data, and generating a comprehensive risk map containing risk types through multimodal feature fusion;

[0057] Generating graded warning signals based on the risk types included in the comprehensive risk map;

[0058] According to the graded warning signal, the corresponding area's security equipment startup, environmental conditioning equipment regulation or passenger flow guidance terminal prompt corresponding control operations are automatically triggered.

[0059] The beneficial effects of the museum intelligent monitoring method of multi-source electronic information fusion of the present invention are as follows:

[0060] The method of the present invention can effectively solve the problems of limited perception ability and data silos existing in traditional monitoring systems in museum security management, improve the museum's security supervision and management efficiency, and can comprehensively, accurately and timely control and respond to various risks in the museum.

[0061] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0063] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the drawings. In the drawings:

[0064] Figure 1 A schematic structural diagram of an embodiment of a museum intelligent monitoring system for multi-source electronic information fusion according to the present invention;

[0065] Figure 2 This is a flow chart of an embodiment of the museum intelligent monitoring method based on multi-source electronic information fusion of the present invention. DETAILED DESCRIPTION

[0066] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0067] Figure 1 FIG1 shows a schematic diagram of the structure of an embodiment of a museum intelligent monitoring system for multi-source electronic information fusion provided by the present invention. Figure 1 As shown, the system includes:

[0068] The multi-source electronic information acquisition module 110 is used to obtain video surveillance data, environmental sensor data and visitor flow monitoring data distributed in the museum in real time.

[0069] Video surveillance data refers to video stream data collected in real time by video surveillance equipment deployed in the museum's cultural relic display area. It contains timestamps, spatial coordinates, and pixel information, and is used to detect human behavior and moving targets. Environmental sensor data refers to time series data collected by temperature, humidity, and light intensity sensors distributed throughout the museum's exhibition halls. It is used to monitor the environmental conditions for cultural relic preservation. The data units are ℃ (temperature), %RH (humidity), and Lux ​​(light intensity). Passenger flow monitoring data refers to data sets acquired synchronously by the entrance gate's counter and thermal imager. It includes the real-time cumulative number of people and a collection of their spatial coordinates, and is used to analyze passenger flow distribution.

[0070] The data fusion module 120 is used to extract dynamic behavior features from the video surveillance data, extract abnormal environmental parameters from the environmental sensor data, extract density distribution features from the passenger flow monitoring data, and generate a comprehensive risk map containing risk types through multimodal feature fusion.

[0071] Among them, dynamic behavior characteristics refer to the vectorized features generated after motion target detection, trajectory tracking and behavior classification of video surveillance data, which are used to characterize the probability of threatening behaviors such as climbing display cabinets and abnormal detention. Abnormal environmental parameters refer to the exceeded quantitative values ​​generated after comparing environmental sensor data with the preset cultural relics preservation threshold, including the continuous deviation of temperature, humidity and light (the unit is the same as the original data). Density distribution characteristics refer to the vector generated by passenger flow monitoring data after spatial heat map calculation and regional integration. The element value is the number of people per unit area of ​​each sub-area (people / m 2 ) is used to quantify the degree of passenger congestion. The comprehensive risk map refers to a data structure generated by integrating dynamic behavior characteristics, abnormal environmental parameters and density distribution characteristics through spatiotemporal coordinate mapping and multi-source weight allocation. represents the risk type label, and W represents the comprehensive feature vector. Risk type refers to the risk category label determined in the comprehensive risk map. When , the risk type is cultural relics security threat (triggered by behavioral characteristics); When , the risk type is environmental exceeding the standard (parameter continuously exceeds the threshold); When , the risk type is passenger congestion (density exceeds the safety upper limit).

[0072] The intelligent early warning module 130 is used to generate a graded early warning signal based on the risk types included in the comprehensive risk map.

[0073] Among them, the graded warning signal refers to the digital signal generated based on the risk type and is strictly bound to the risk type.

[0074] The linkage control module 140 is used to automatically trigger the corresponding control operations in the security equipment startup, environmental conditioning equipment regulation or passenger flow guidance terminal prompts in the corresponding area according to the graded warning signal.

[0075] Among them, security equipment activation refers to the equipment triggered in response to the first-level warning signal, environmental adjustment equipment refers to the constant temperature and humidity equipment adjusted in response to the second-level warning signal, and passenger flow guidance terminal refers to the electronic guide screen activated in response to the third-level warning signal.

[0076] The technical solution of this embodiment can effectively solve the problems of limited perception capabilities and data silos in traditional monitoring systems in museum security management, improve the museum's security supervision and management efficiency, and can comprehensively, accurately and timely control and respond to various risks in the museum.

[0077] In an optional manner, the multi-source electronic information collection module 110 is specifically configured to:

[0078] The video surveillance data is acquired in real time using video surveillance equipment deployed in the cultural relics display area, the environmental sensor data is collected using environmental sensors distributed in the exhibition hall, and the passenger flow monitoring data is collected using entrance gates and thermal imagers.

[0079] Among them, video surveillance equipment refers to network cameras fixed on the top of the cultural relics display area, with a resolution of ≥1080P, a frame rate of ≥25fps, and a coverage range that includes the 3-meter area around all display cabinets. Environmental sensors refer to multi-parameter sensors (temperature, humidity, and light intensity) deployed on the walls of the exhibition hall or inside the display cabinets. The entrance gate refers to a two-way counting gate installed at the main entrance of the museum, equipped with a facial recognition module, and a counting error rate of ≤0.1%. The thermal imager refers to an infrared array device mounted on the ceiling of the exhibition hall, with a spatial positioning accuracy of ±0.1 meter and a temperature measurement range of 20-50°C.

[0080] In the above optional technical solutions, the data sources and collection methods of the multi-source electronic information collection module are further clarified, and video surveillance equipment, environmental sensors, entrance gates and thermal imagers are used to collect video, environmental and passenger flow data respectively to ensure the pertinence and accuracy of data collection, provide a reliable foundation for subsequent fusion processing and risk control, and enhance the applicability and effectiveness of the system in museum security management.

[0081] In an optional manner, the data fusion module 120 is specifically configured to:

[0082] Perform moving target detection and behavior trajectory analysis on the video surveillance data to extract the dynamic behavior features, specifically:

[0083] Perform inter-frame difference calculation on the video surveillance data collected in real time to extract the moving target area, and the expression is:

[0084]

[0085] Where M t (x,y) represents the binary mask of the moving target area in the tth frame, F t (x, y) represents the pixel value of the video frame of the tth frame in the video surveillance data, F t-1 (x, y) represents the pixel value of the video frame of the t-1th frame in the video surveillance data, θ v represents the pixel threshold;

[0086] Performing connected domain analysis and target instantiation processing on the moving target area to obtain multiple connected domains, assigning a target ID to each connected domain, and generating a trajectory point set;

[0087] The velocity vector is calculated based on the trajectory point set, and the velocity vector is input into the behavior classification model to output the dynamic behavior feature, which is expressed as:

[0088] β=CNN-LSTM({v id})

[0089] Where, v id represents the velocity vector, (x i ,y i ) represents the coordinates of the i-th trajectory point in the trajectory point set, Δt represents the frame time interval, and β represents the dynamic behavior feature.

[0090] Perform threshold comparison on the environmental sensor data to extract the abnormal environmental parameters that deviate from the preset cultural relic preservation threshold. Specifically:

[0091] The preset cultural relic preservation thresholds include: temperature threshold, humidity threshold and light intensity threshold.

[0092] The deviation between the environmental sensor data and the preset cultural relic preservation threshold is calculated using the following expression:

[0093]

[0094] Where, τ temp represents the temperature threshold, τ humid represents the humidity threshold, τ light represents the light intensity threshold; δ temp Indicates the temperature tolerance, δ humid Indicates the humidity tolerance, δ light Indicates the allowable deviation of light intensity; temp t Indicates the temperature value at time t, humid t Indicates the humidity value at time t, light t Indicates the light intensity value at time t, Δe t represents the environmental deviation vector at time t;

[0095] When the continuous exceeding time exceeds the limit, the abnormal environment parameter deviating from the preset cultural relic preservation threshold is output, and its expression is:

[0096]

[0097] Where, α represents the abnormal environment parameter, T c Indicates the continuous monitoring time, T th Indicates the duration threshold for exceeding the limit.

[0098] The passenger flow monitoring data is calculated through a spatial heat map to extract the density distribution characteristics, specifically:

[0099] Passenger flow monitoring data includes: personnel coordinate sets and the real-time number of people at the gate.

[0100] Correcting the personnel coordinate set according to the real-time number of people at the gate to obtain a corrected personnel coordinate set;

[0101] The spatial heat map is calculated based on the corrected personnel coordinate set, and its expression is:

[0102]

[0103] In the formula, (x p ,y p ) represents the pth person in the corrected person coordinate set, N total represents the total number of people in the corrected personnel coordinate set, σ represents the Gaussian kernel bandwidth, and D(x,y) represents the spatial heat map;

[0104] According to the spatial heat map, the density distribution feature is extracted, and its expression is:

[0105]

[0106] Where, ρ j represents the density of the jth sub-area of ​​the museum, Ω j represents the jth sub-region, K calib represents the density calibration coefficient, γ=[ρ1,ρ2,...,ρ m ] T ; m represents the total number of sub-areas of the museum.

[0107] In the above optional technical solutions, motion target detection and trajectory analysis are further performed on video surveillance data to extract dynamic behavior characteristics, abnormal environmental parameters are extracted by threshold comparison of environmental sensor data, and density distribution characteristics are extracted by heat map calculation of passenger flow monitoring data. Accurate feature extraction of multi-type data is achieved, providing a key basis for generating a comprehensive risk map and improving the comprehensiveness and accuracy of risk identification.

[0108] In an optional manner, the data fusion module 120 is specifically configured to:

[0109] The dynamic behavior characteristics, the abnormal environmental parameters and the density distribution characteristics are mapped into time-space coordinates and multi-source weights are assigned to generate a comprehensive risk map containing risk types.

[0110] The process of spatiotemporal coordinate mapping is as follows: mapping the dynamic behavior feature β to the museum's global coordinate system through the video space transformation matrix to obtain the mapped behavior feature β'; mapping the abnormal environment parameter α to the museum's global coordinate system through the video space transformation matrix to obtain the mapped environment parameter α'; mapping the density distribution feature γ to the museum's global coordinate system through the video space transformation matrix to obtain the mapped density feature γ'. The process of multi-source weight allocation is as follows: assigning the cultural relic security weight ω to the mapped behavior feature β' v , assign environmental risk weight ω to the mapped environmental parameter α′ e , assign passenger flow risk weight ω to the mapped density feature γ′ c The process of weighted feature fusion is to combine the weighted features into a comprehensive feature vector The process of risk type determination is as follows: input the comprehensive feature vector W into the risk classifier and output the risk type Q k Represents the learnable weight vector of the risk classifier; the final output is the comprehensive risk map

[0111] In the above optional technical solutions, the data fusion module is further elaborated to generate a comprehensive risk map by mapping dynamic behavior characteristics, abnormal environmental parameters and density distribution characteristics through spatiotemporal coordinates and multi-source weight distribution, and to fuse multi-source data to realize risk type determination and comprehensive feature vector generation, providing a comprehensive and accurate basis for intelligent early warning, making the risk presentation more intuitive and clear, and enhancing the system's comprehensive management and response capabilities for multiple risks.

[0112] In an optional manner, the intelligent early warning module 130 is specifically configured to:

[0113] When the risk type is a threat to the safety of cultural relics, a first-level warning signal is generated; when the risk type is environmental exceeding the standard, a second-level warning signal is generated; when the risk type is passenger congestion, a third-level warning signal is generated.

[0114] Cultural relic safety threats refer to events where dynamic behavioral characteristics match pre-set threat patterns, such as individuals climbing display cases (trajectory inclination > 60°), abnormal lingering (duration > 300 seconds), and rapid collisions (speed > 3m / s). Environmental violations refer to events where environmental parameters consistently deviate from cultural relic preservation thresholds. Passenger congestion refers to events where density distribution characteristics exceed fire safety pressure standards.

[0115] In the above optional technical solutions, corresponding graded warning signals are further generated according to different risk types. Cultural relics safety threats, environmental violations, and passenger congestion correspond to level one, level two, and level three warnings respectively. The correspondence between risk levels and warning signals is clarified, and the precision and standardization of graded warnings are achieved, which facilitates the rapid determination of risk levels and the adoption of targeted measures to improve emergency response efficiency.

[0116] In an optional manner, the linkage control module 140 is specifically configured to:

[0117] In response to the first-level warning signal, the sound and light alarm and camera automatic tracking in the cultural relics display area are activated; in response to the second-level warning signal, the constant temperature equipment and constant humidity equipment in the corresponding area are adjusted; in response to the third-level warning signal, the electronic guide screen diversion prompt in the diversion area is activated.

[0118] In the above optional technical solutions, corresponding control operations are further automatically triggered based on the graded warning signals. The first-level warning activates the sound and light alarm and camera tracking, the second-level adjusts the constant temperature and humidity equipment, and the third-level activates the electronic guide screen diversion prompt, establishing a direct linkage mechanism between warning and control, achieving rapid, automatic and accurate response to different risks, and strengthening the museum's security, environment and passenger flow management capabilities.

[0119] Figure 2 The flow chart of an embodiment of the museum intelligent monitoring method based on multi-source electronic information fusion provided by the present invention is shown. Figure 2 As shown, the following steps are included:

[0120] S1. Real-time acquisition of video surveillance data, environmental sensor data, and visitor flow monitoring data distributed throughout the museum;

[0121] S2. Extracting dynamic behavior features from the video surveillance data, extracting abnormal environmental parameters from the environmental sensor data, and extracting density distribution features from the passenger flow monitoring data, and generating a comprehensive risk map containing risk types through multimodal feature fusion;

[0122] S3. Generate a graded warning signal based on the risk types included in the comprehensive risk map;

[0123] S4. According to the graded warning signal, automatically trigger the corresponding area's security equipment startup, environmental conditioning equipment regulation or passenger flow management terminal prompt corresponding control operations.

[0124] The technical solution of this embodiment can effectively solve the problems of limited perception capabilities and data silos in traditional monitoring systems in museum security management, improve the museum's security supervision and management efficiency, and can comprehensively, accurately and timely control and respond to various risks in the museum.

[0125] Furthermore, the above embodiments provide systems that implement their functions using only the division of the above functional modules as examples. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the system can be divided into different functional modules according to actual conditions to complete all or part of the functions described above. Furthermore, the systems and method embodiments provided in the above embodiments share the same concept. The specific implementation process is detailed in the method embodiments and will not be repeated here.

[0126] The above description is merely a preferred embodiment of the present invention and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present invention is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in the present invention.

[0127] It should be noted that the terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects and to define a specific order or precedence. Where appropriate, the order used for similar objects may be interchanged, such that the embodiments of the present application described herein can be implemented in an order other than the order shown or described.

[0128] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. The museum intelligent monitoring system integrating multi-source electronic information is characterized by: The system comprises: Multi-source electronic information acquisition module, used to obtain real-time video surveillance data, environmental sensor data, and visitor flow monitoring data distributed throughout the museum; a data fusion module, configured to extract dynamic behavior features from the video surveillance data, extract abnormal environmental parameters from the environmental sensor data, extract density distribution features from the passenger flow monitoring data, and generate a comprehensive risk map containing risk types through multimodal feature fusion; An intelligent early warning module, configured to generate a graded early warning signal based on the risk types included in the comprehensive risk map; The linkage control module is used to automatically trigger the corresponding control operations in the security equipment startup, environmental conditioning equipment regulation or passenger flow guidance terminal prompts in the corresponding area according to the graded warning signal.

2. The museum intelligent monitoring system based on multi-source electronic information fusion according to claim 1 is characterized in that: The multi-source electronic information acquisition module is specifically used for: Using video surveillance equipment deployed in the cultural relics display area to obtain the video surveillance data in real time; Collecting the environmental sensor data using environmental sensors distributed in the exhibition hall; The passenger flow monitoring data is collected using an entrance gate and a thermal imager.

3. The museum intelligent monitoring system based on multi-source electronic information fusion according to claim 1 is characterized in that: The data fusion module is specifically used for: Performing moving target detection and behavior trajectory analysis on the video surveillance data to extract the dynamic behavior features; Performing threshold comparison on the environmental sensor data to extract the abnormal environmental parameters that deviate from the preset cultural relic preservation threshold; The passenger flow monitoring data is calculated through a spatial heat map to extract the density distribution characteristics.

4. The museum intelligent monitoring system based on multi-source electronic information fusion according to claim 3 is characterized in that: The data fusion module is specifically used for: Perform inter-frame difference calculation on the video surveillance data collected in real time to extract the moving target area, and the expression is: Where M t (x,y) represents the binary mask of the moving target area in the tth frame, F t (x, y) represents the pixel value of the video frame of the tth frame in the video surveillance data, F t-1 (x, y) represents the pixel value of the video frame of the t-1th frame in the video surveillance data, θ v represents the pixel threshold; Performing connected domain analysis and target instantiation processing on the moving target area to obtain multiple connected domains, assigning a target ID to each connected domain, and generating a trajectory point set; The velocity vector is calculated based on the trajectory point set, and the velocity vector is input into the behavior classification model to output the dynamic behavior feature, which is expressed as: β=CNN-LSTM({v id }) Where, v id represents the velocity vector, (x i ,y i ) represents the coordinates of the i-th trajectory point in the trajectory point set, Δt represents the frame time interval, and β represents the dynamic behavior feature.

5. The museum intelligent monitoring system based on multi-source electronic information fusion according to claim 4 is characterized in that: The preset cultural relic preservation thresholds include: temperature threshold, humidity threshold and light intensity threshold; the data fusion module is specifically used to: The deviation between the environmental sensor data and the preset cultural relic preservation threshold is calculated using the following expression: Where, τ temp represents the temperature threshold, τ humid represents the humidity threshold, τ light represents the light intensity threshold; δ temp Indicates the allowable temperature deviation, δ humid Indicates the humidity tolerance, δ light Indicates the allowable deviation of light intensity; temp t Indicates the temperature value at time t, humid t Indicates the humidity value at time t, light t Indicates the light intensity value at time t, Δe t represents the environmental deviation vector at time t; When the continuous exceeding time exceeds the limit, the abnormal environment parameter deviating from the preset cultural relic preservation threshold is output, and its expression is: Where, α represents the abnormal environment parameter, T c Indicates the continuous monitoring time, T th Indicates the duration threshold for exceeding the limit.

6. The museum intelligent monitoring system based on multi-source electronic information fusion according to claim 5 is characterized in that: The passenger flow monitoring data includes: a set of personnel coordinates and the real-time number of people at the gate; the data fusion module is specifically used to: Correcting the personnel coordinate set according to the real-time number of people at the gate to obtain a corrected personnel coordinate set; The spatial heat map is calculated based on the corrected personnel coordinate set, and its expression is: In the formula, (x p ,y p ) represents the pth person in the corrected person coordinate set, N total represents the total number of people in the corrected personnel coordinate set, σ represents the Gaussian kernel bandwidth, and D(x,y) represents the spatial heat map; According to the spatial heat map, the density distribution feature is extracted, and its expression is: Where, ρ j represents the density of the jth sub-area of ​​the museum, Ω j represents the jth sub-region, K calib represents the density calibration coefficient, γ=[ρ1,ρ2,...,ρ m ] T ; m represents the total number of sub-areas of the museum.

7. The museum intelligent monitoring system based on multi-source electronic information fusion according to claim 6 is characterized in that: The data fusion module is specifically used for: The dynamic behavior characteristics, the abnormal environmental parameters and the density distribution characteristics are mapped into time-space coordinates and multi-source weights are assigned to generate a comprehensive risk map containing risk types.

8. The museum intelligent monitoring system based on multi-source electronic information fusion according to claim 7 is characterized in that: The intelligent early warning module is specifically used for: When the risk type is a threat to the safety of cultural relics, a first-level warning signal is generated; When the risk type is environmental exceeding the standard, a secondary warning signal is generated; When the risk type is passenger congestion, a third-level warning signal is generated.

9. The museum intelligent monitoring system based on multi-source electronic information fusion according to claim 8 is characterized in that: The linkage control module is specifically used for: In response to the first-level warning signal, the sound and light alarm and camera automatic tracking in the cultural relics display area are activated; In response to the secondary warning signal, regulating the constant temperature equipment and constant humidity equipment in the corresponding area; In response to the third-level warning signal, the electronic guide screen diversion prompt of the diversion area is activated.

10. A museum intelligent monitoring method based on multi-source electronic information fusion, characterized in that: The method comprises: Real-time acquisition of video surveillance data, environmental sensor data, and visitor flow monitoring data distributed throughout the museum; Extracting dynamic behavior features from the video surveillance data, extracting abnormal environmental parameters from the environmental sensor data, extracting density distribution features from the passenger flow monitoring data, and generating a comprehensive risk map containing risk types through multimodal feature fusion; Generating graded warning signals based on the risk types included in the comprehensive risk map; According to the graded warning signal, the corresponding area's security equipment startup, environmental conditioning equipment regulation or passenger flow guidance terminal prompt corresponding control operations are automatically triggered.

Images