Emergency field data sensing system based on cloud side end processing

Abstract

The invention discloses an emergency field data sensing system based on cloud side end processing, which relates to the technical field of emergency data sensing and comprises an identification model construction unit, a target frame detection unit, a global position analysis unit, an influence degree judgment unit, an evacuation path generation unit and an emergency processing unit. According to the invention, local position information contained in an image data frame corresponding to each sub-region is analyzed in an edge server through a global position analysis unit, and the local position information related to each sub-region is converted by using a coordinate optimization algorithm in a cloud server to obtain global position information in a specified scene. By means of the design, on one hand, the accurate position of the target can be obtained, on the other hand, the calculation speed of the system is greatly improved, the requirement for server performance is lowered, and the optimal evacuation path of each crowd in the emergency site is calculated through the influence degree judgment unit and the evacuation path generation unit; and the condition that the personnel are congested during evacuation is avoided.

Description

Technical Field

[0001] The present invention relates to the field of emergency data perception technology, and specifically to an emergency on-site data perception system based on cloud-edge processing. Background Art

[0002] The cloud-edge-end architecture refers to a distributed computing architecture, including three parts: cloud, edge and end. The emergency site data perception system organically combines functions such as information perception, command and dispatch, resource allocation, monitoring and early warning to improve the response speed and handling efficiency of emergency events and reduce the losses caused by the events. In the invention patent with application number 202310361774.6, an "emergency management method based on dynamic perception and fusion of disaster site information" is disclosed. Disaster site emergency management refers to the management activities of organizing and coordinating various emergency resources, implementing emergency rescue and post-disaster recovery work when natural disasters, accident disasters and other emergencies occur, which helps to improve the efficiency of disaster site rescue and recovery. rate, minimizing casualties and property losses caused by disasters. However, the current limited resources of disaster site information perception sensor technology and monitoring equipment, coupled with insufficient personnel at the disaster site, make the efficiency of disaster site information collection and processing low, and it is difficult to meet the needs of disaster emergency management. To this end, the present invention proposes an emergency management method based on dynamic perception and fusion of disaster site information, which integrates technologies such as the Internet of Things, big data, and artificial intelligence to perform real-time, dynamic, and interactive perception and fusion of data to generate a disaster site situation perception map, and performs data analysis and timely warning based on the disaster site situation perception map, which helps to achieve precise disaster disposal, intelligent rescue command, and efficient scheduling work."

[0003] The above-mentioned existing technology solves the problem that key information of the disaster area cannot be obtained in time. However, when the system is running, since no target recognition model is built, it is impossible to obtain the location information of the crowd, obstacles, dangerous objects and exit signs in the specified scene, so that the system cannot provide a passage plan for the people in the scene in a short time, resulting in congestion of a large number of people during the evacuation process, and it is impossible to determine the urgency of each dangerous object, so it takes a long time to dispatch professional personnel. Summary of the invention

[0004] The purpose of the present invention is to provide an emergency scene data perception system based on cloud-edge processing to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an emergency scene data perception system based on cloud-edge-end processing, comprising an evacuation path generation unit and an emergency processing unit;

[0006] A recognition model building unit, wherein the recognition model building unit obtains a sample data set of a crowd, an obstacle, a dangerous object, and an exit sign. Since each sample information in the data set contains multiple image data frames, a pixel point analysis algorithm is used to calculate the gradient amplitude and direction of each pixel point in the image data frame, and a gradient feature vector of the image data frame is determined based on these data. The color feature vector is fused with the gradient feature vector, and a target recognition model is constructed using a kernel correlation filter and a regression model. All fusion results contained in each sample information are input into the target recognition model for analysis to obtain a response map corresponding to each frame;

[0007] A target frame detection unit, wherein the target frame detection unit scans the image information contained in the frame according to the peak position of the response graph of each frame and the size of the target frame of the previous frame, outputs the target frame position and size corresponding to the current image data frame, determines the similarity between the target frame position and size of the image data frame contained in each sample information and the position and size of the identification frame, and if the similarity is lower than a preset value, recalculates the peak of the response graph corresponding to the image data frame and updates the detection parameters, otherwise calculates the similarity between the target frame position and size of the current frame and the previous frame;

[0008] A global position analysis unit, wherein the global position analysis unit divides a specified scene into multiple sub-areas, shoots the sub-areas with a camera, transmits the obtained video data to an edge server, sorts the data frames in each video data according to a time series, stores them in a sampling set, uses a target recognition model to analyze the local position information of the crowd, obstacles, dangerous objects and exits contained in the image data frame corresponding to each sub-area, and uses a coordinate optimization algorithm to convert the local position information involved in each sub-area to obtain the global position information of each crowd, obstacle, dangerous object and exit in the specified scene;

[0009] The impact degree judgment unit divides the sub-area to generate multiple grid units, determines the position coordinates of each obstacle and dangerous object in the sub-area, and then uses the impact value determination algorithm to calculate the total obstacle impact value of each grid unit, calculates the total exit impact value of each grid unit according to the exit impact coefficient and the Euclidean distance between the center point of the grid unit and the exit, and calculates the total crowd impact value of each grid unit using the crowd impact coefficient and the Euclidean distance between the center point of the grid unit and the crowd. After accumulating the three, the field value of each grid unit is obtained, and these data are used to determine the moving direction corresponding to any center point.

[0010] Preferably, the recognition model building unit includes a sample information acquisition module and a feature vector determination module. After the sample information acquisition module obtains the sample data sets of the crowd, obstacles, dangerous objects and exit signs, the corresponding identification frame is set for the sample information in each sample data set. Each sample information includes multiple image data frames. The pixel point analysis algorithm is used to calculate the amplitude and direction of the gradient of each pixel point in the image data frame. The gradient feature vector determination module divides the area involved in the image data frame to obtain multiple small units. According to the pixel point gradient amplitude and direction in each small unit, the corresponding nine-level gradient histogram is analyzed, and the histograms corresponding to the adjacent areas are counted. After the four-dimensional feature vector corresponding to each small unit is analyzed according to these data, the histograms of all small units are aggregated to obtain a nine-dimensional feature vector, and the corresponding eighteen-level gradient histogram is analyzed using the pixel point gradient amplitude and direction in each small unit, which is aggregated to obtain an eighteen-dimensional feature vector, and all feature vectors are associated to determine the final gradient feature vector of the image data frame. The pixel point analysis algorithm is specifically as follows:

[0011]

[0012] θ(x,y)=arctan(Gy(x,y) / Gx(x,y))

[0013] Among them, G(x,y) represents the gradient amplitude of the pixel at (x,y), θ(x,y) represents the gradient direction of the pixel at (x,y), and G x (x, y) represents the horizontal gradient of the pixel at (x, y), G y (x,y) represents the vertical gradient of the pixel at (x,y), and (x,y) represents the specific position corresponding to the pixel.

[0014] Preferably, the recognition model construction unit also includes a parameter updating module, which extracts the color feature vector of the image data frame and fuses it with the gradient feature vector, constructs a target recognition model using a kernel correlation filter and a regression model, inputs all fusion results contained in each sample information into the target recognition model for analysis, obtains a response graph corresponding to each frame, calculates the accuracy corresponding to the model result according to the difference between the peak value of the response graph of each frame and other points in the graph, and if the accuracy is lower than a threshold, determines that the tracking is invalid, otherwise determines that the tracking is valid, and optimizes the filter parameters and the target template using a parameter updating algorithm, wherein the kernel correlation filter is specifically a correlation filter based on a KCF algorithm, the regression model is specifically a ridge regression model, and the parameter updating algorithm is specifically:

[0015]

[0016] Among them, α represents the updated filter parameter, x represents the updated target template, and x t-1 represents the target template of the previous frame, x t represents the target template of the current frame, η represents the linear interpolation factor, α t Represents the filter parameters of the current frame, α t-1 Represents the filter parameters of the previous frame.

[0017] Preferably, the target frame detection unit includes a position analysis module, a similarity calculation module and a sample information deletion module. If the tracking is effective, the position analysis module uses the target recognition model to scan the image information contained in the frame according to the peak position of each frame response graph and the size of the target frame of the previous frame, and outputs the target frame position and size corresponding to the current image data frame. If the tracking is invalid, the image information contained in the frame is scanned one by one, and the target frame position and size corresponding to the current image data frame are output. The similarity calculation module determines the position and size of the target frame of the image data frame contained in each sample information and the identification The similarity between the position and size of the frame is calculated. If the similarity is lower than the preset value, the peak value of the response graph corresponding to the image data frame is recalculated, and the detection parameters are updated. Otherwise, the similarity between the position and size of the target frame of the current frame and the previous frame is calculated. If the similarity between the current image data frame and the previous frame is greater than the average value, the sample information deletion module deletes the current frame. If the value is less than or equal to the average value, the current frame is retained until the similarity of all image data frames in the sample information is determined. The number of image data frames contained in the current sample information is counted. If the number is lower than the threshold, the sample information is deleted, otherwise no operation is performed.

[0018] Preferably, the global position analysis unit includes a data frame sampling module, an exit position parsing module and a coordinate conversion module. The data frame sampling module divides the specified scene into multiple sub-areas, numbers each sub-area, shoots the sub-area with a camera, transmits the obtained video data to the edge server, sets a sampling interval, collects the image data frames contained in each video data according to the sampling interval, sorts the data frames in each video data according to the time series, and stores them in the sampling set. The exit position parsing module uses the target recognition model to scan the image data frames in the sampling set in sequence, and respectively obtains the local position information of the crowd, obstacles, dangerous objects and exit signs contained in the image data frames corresponding to each sub-area, and uses deep learning technology to analyze the exit local position information contained in the image data frame corresponding to each sub-area according to the content and local position information of the exit sign. The coordinate conversion module transmits the local position information involved in each sub-area to the cloud server, and uses the coordinate optimization algorithm to convert the local position information involved in each sub-area to obtain the global position information of each crowd, obstacle, dangerous object and exit in the specified scene.

[0019] Preferably, the impact degree judgment unit includes an obstacle impact value calculation module, an exit impact value calculation module, a crowd impact value calculation module and a field value calculation module. The obstacle impact value calculation module analyzes all the passage paths according to the local position information of all exits in the sub-area, divides the area involved in the passage path, generates multiple grid units, determines the position coordinates of each obstacle and dangerous object in the sub-area, and uses the impact value determination algorithm to count the degree of influence of each obstacle and dangerous object on each grid unit, and calculates the total obstacle impact value of each grid unit according to the weights corresponding to the dangerous objects and obstacles. After the exit impact value calculation module determines the local position coordinates of each exit in the sub-area, it calculates the total obstacle impact value of each grid unit according to the exit impact coefficient and the Euclidean distance between the center point of the grid unit and the exit. The distance is used to calculate the degree to which each grid unit is affected by each exit, and the maximum exit influence degree is taken as the total exit influence value of the corresponding grid unit. The crowd influence value calculation module obtains the local position coordinates of each crowd in the sub-area, and calculates the degree to which each grid unit is affected by the crowd at each location according to the crowd influence coefficient and the Euclidean distance between the center point of the grid unit and the crowd. The total crowd influence value of the corresponding grid unit is obtained by adding them up. The field value calculation module counts the total obstacle influence value, the total exit influence value and the total crowd influence value corresponding to each grid unit, and after adding the three, the field value of each grid unit is obtained. The path loss value from the center point of each grid unit to the exit position is calculated according to the field value, and these data are used to determine the moving direction corresponding to any center point.

[0020] Preferably, the evacuation path generation unit includes a moving direction optimization module, a speed analysis module and a moving path simulation module. The moving direction optimization module transmits the field value, the passage path loss value and the moving direction of the grid unit in each sub-area to the cloud server, calculates the global field value of each grid unit using the global coordinate information of the center point of the grid unit in each sub-area, and adjusts the moving direction of the center point, and returns these data to the edge server. The speed analysis module calculates the density value corresponding to each grid unit according to the local position information of the crowd in the sub-area, uses the density value to analyze the moving speed when passing through each center point, and transmits it to the cloud server. The moving path and speed of each crowd evacuation are analyzed by the aggregation analysis algorithm to obtain the global passage path, which is returned to the edge server. The moving path simulation module builds a real-time scene model according to all the global position information and the local position information of each sub-area in the specified scene through simulation software, receives the moving path and speed corresponding to each crowd evacuation, and simulates it, and outputs the obtained results through a visual interface. The aggregation analysis algorithm is specifically an aggregation optimization artificial bee colony algorithm.

[0021] Preferably, the emergency handling unit includes an emergency value determination module and a personnel scheduling module. The emergency value determination module transmits the local position information of the temperature and humidity sensors, gas sensors and smoke sensors in each sub-area and the collected data to the edge server, defines multiple abnormal ranges for each data, and sets emergency values ​​for it. The distance between each dangerous object and each sensor is calculated according to the local position information of the dangerous objects and sensors in each sub-area. After determining the weight of the emergency value corresponding to each sensor in different dangerous objects according to the distance, the actual emergency value of each dangerous object in the sub-area is calculated. After receiving the actual emergency value of the dangerous object in each sub-area, the personnel scheduling module transmits it to the cloud server, sorts the dangerous objects in the specified scene according to the actual emergency value, and the control center schedules and deploys personnel according to the global position information and arrangement order of the dangerous objects.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] 1. The present invention analyzes the image data frame in the sample data through the recognition model construction unit to obtain a multi-dimensional gradient feature vector corresponding to each data frame. This feature vector can more accurately extract the details in the image data frame and reduce the number of errors of the model in the recognition process. At the same time, each frame will generate a corresponding response graph, and the accuracy corresponding to the model result is calculated according to the difference between the peak value of the response graph and other points in the graph. If the accuracy is high, it means that the model can estimate the target range in the image data frame, and updating the corresponding parameters can further improve the performance of the filter. If the accuracy is low, it means that the model cannot estimate the target range. Avoiding updating parameters can reduce the number of calculations and optimize the running speed of the overall system. The target frame detection unit is used to scan the collected sample information, and the redundant sample information is deleted. Under the premise of not affecting the model training, the storage space size is increased;

[0024] 2. The present invention uses a global position analysis unit in the edge server to analyze the local position information of the crowd, obstacles, dangerous objects and exit signs contained in the image data frame corresponding to each sub-area, and uses a coordinate optimization algorithm in the cloud server to convert the local position information involved in each sub-area to obtain the global position information in the specified scene. On the one hand, this design can obtain the accurate position of the target, and on the other hand, it greatly improves the calculation speed of the system and reduces the requirements for server performance. The impact degree judgment unit and the evacuation path generation unit are used to calculate the optimal evacuation path for each crowd in the emergency site to avoid congestion when people evacuate. The emergency handling unit clarifies the urgency and location of the dangerous objects, which is convenient for scheduling and deploying professional personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 Provides a schematic diagram of the overall system flow for an embodiment of the present invention;

[0026] Figure 2 An internal module block diagram of a recognition model building unit provided in an embodiment of the present invention;

[0027] Figure 3 An internal module block diagram of a target frame detection unit provided by an embodiment of the present invention;

[0028] Figure 4 An internal module block diagram of a global position analysis unit provided in an embodiment of the present invention;

[0029] Figure 5 A block diagram of the internal modules of the impact degree determination unit provided by an embodiment of the present invention;

[0030] Figure 6 This is a block diagram of the internal modules of the evacuation path generation unit provided in an embodiment of the present invention.

[0031] In the figure: 1. Recognition model building unit; 101. Sample information acquisition module; 102. Feature vector determination module; 103. Parameter updating module; 2. Target frame detection unit; 201. Position analysis module; 202. Similarity calculation module; 203. Sample information deletion module; 3. Global position analysis unit; 301. Data frame sampling module; 302. Exit position analysis module; 303. Coordinate conversion module; 4. Impact degree judgment unit; 401. Obstacle impact value calculation module; 402. Exit impact value calculation module; 403. Crowd impact value calculation module; 404. Field value calculation module; 5. Evacuation path generation unit; 501. Moving direction optimization module; 502. Speed ​​analysis module; 503. Moving path simulation module; 6. Emergency handling unit; 601. Emergency value determination module; 602. Personnel dispatch module. DETAILED DESCRIPTION

[0032] 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.

[0033] See also Figure 1-6 ,The present invention provides a technical solution: an emergency site data perception system based on cloud-edge-end processing, comprising an evacuation path generation unit 5 and an emergency processing unit 6;

[0034] Recognition model building unit 1, recognition model building unit 1 obtains a sample data set of crowds, obstacles, dangerous objects and exit signs. Since each sample information in the data set contains multiple image data frames, a pixel point analysis algorithm is used to calculate the gradient amplitude and direction of each pixel in the image data frame, and the gradient feature vector of the image data frame is determined based on these data. The color feature vector is fused with the gradient feature vector, and a target recognition model is constructed using a kernel correlation filter and a regression model. All fusion results contained in each sample information are input into the target recognition model for analysis to obtain a response map corresponding to each frame;

[0035] The target frame detection unit 2 scans the image information contained in the frame according to the peak position of the response graph of each frame and the size of the target frame of the previous frame, outputs the target frame position and size corresponding to the current image data frame, determines the similarity between the target frame position and size of the image data frame contained in each sample information and the position and size of the identification frame, if the similarity is lower than the preset value, recalculates the peak value of the response graph corresponding to the image data frame, and updates the detection parameters, otherwise calculates the similarity between the target frame position and size of the current frame and the previous frame;

[0036] The global position analysis unit 3 divides the designated scene into multiple sub-areas, shoots the sub-areas with a camera, transmits the obtained video data to the edge server, sorts the data frames in each video data according to the time series, stores them in the sampling set, uses the target recognition model to analyze the local position information of the crowd, obstacles, dangerous objects and exits contained in the image data frame corresponding to each sub-area, and uses the coordinate optimization algorithm to convert the local position information involved in each sub-area to obtain the global position information of each crowd, obstacle, dangerous object and exit in the designated scene;

[0037] The impact degree judgment unit 4 divides the sub-area to generate multiple grid units, determines the position coordinates of each obstacle and dangerous object in the sub-area, and then uses the impact value determination algorithm to calculate the total obstacle impact value of each grid unit, calculates the total exit impact value of each grid unit according to the exit impact coefficient and the Euclidean distance between the center point of the grid unit and the exit, and calculates the total crowd impact value of each grid unit using the crowd impact coefficient and the Euclidean distance between the center point of the grid unit and the crowd. After accumulating the three, the field value of each grid unit is obtained, and these data are used to determine the moving direction corresponding to any center point.

[0038] The recognition model building unit 1 includes a sample information acquisition module 101 and a feature vector determination module 102. After the sample information acquisition module 101 obtains the sample data sets of the crowd, obstacles, dangerous objects and exit signs, a corresponding identification frame is set for the sample information in each sample data set. Each sample information contains multiple image data frames. The pixel point analysis algorithm is used to calculate the amplitude and direction of the gradient of each pixel point in the image data frame. The gradient feature vector determination module 102 divides the area involved in the image data frame to obtain multiple small units. According to the pixel point gradient amplitude and direction in each small unit, a corresponding nine-level gradient histogram is analyzed, and the histograms corresponding to the adjacent areas are counted. After the four-dimensional feature vector corresponding to each small unit is analyzed based on these data, the histograms of all small units are aggregated to obtain a nine-dimensional feature vector, and the corresponding eighteen-level gradient histogram is analyzed using the pixel point gradient amplitude and direction in each small unit, which is aggregated to obtain an eighteen-dimensional feature vector, and all feature vectors are associated to determine the final gradient feature vector of the image data frame. The pixel point analysis algorithm is specifically as follows:

[0039]

[0040] θ(x,y)=arctan(Gy(x,y) / Gx(x,y))

[0041] Among them, G(x,y) represents the gradient amplitude of the pixel at (x,y), θ(x,y) represents the gradient direction of the pixel at (x,y), and G x (x, y) represents the horizontal gradient of the pixel at (x, y), G y (x,y) represents the vertical gradient of the pixel at (x,y), and (x,y) represents the specific position corresponding to the pixel;

[0042] The recognition model construction unit 1 also includes a parameter updating module 103. After extracting the color feature vector of the image data frame, the parameter updating module 103 fuses it with the gradient feature vector, and uses the kernel correlation filter and the regression model to construct a target recognition model. All fusion results contained in each sample information are input into the target recognition model for analysis to obtain a response map corresponding to each frame. The accuracy corresponding to the model result is calculated according to the difference between the peak value of the response map of each frame and other points in the map. If the accuracy is lower than the threshold, the tracking is determined to be invalid, otherwise the tracking is determined to be valid. The filter parameters and the target template are optimized using the parameter updating algorithm. The kernel correlation filter is specifically a correlation filter based on the KCF algorithm, the regression model is specifically a ridge regression model, and the parameter updating algorithm is specifically:

[0043]

[0044] Among them, α represents the updated filter parameter, x represents the updated target template, and x t-1 represents the target template of the previous frame, x t represents the target template of the current frame, η represents the linear interpolation factor, α t Represents the filter parameters of the current frame, α t-1 Represents the filter parameters of the previous frame;

[0045] The target frame detection unit 2 includes a position analysis module 201, a similarity calculation module 202 and a sample information deletion module 203. If the tracking is effective, the position analysis module 201 uses the target recognition model to scan the image information contained in the frame according to the peak position of each frame response graph and the size of the target frame of the previous frame, and outputs the target frame position and size corresponding to the current image data frame. If the tracking is invalid, the image information contained in the frame is scanned one by one, and the target frame position and size corresponding to the current image data frame are output. The similarity calculation module 202 determines the image data frame target frame position and size contained in each sample information and the similarity calculation module 203. The similarity between the position and size of the identification frame is calculated. If the similarity is lower than the preset value, the peak value of the response graph corresponding to the image data frame is recalculated, and the detection parameters are updated. Otherwise, the similarity between the position and size of the target frame of the current frame and the previous frame is calculated. If the similarity between the current image data frame and the previous frame is greater than the average value, the current frame is deleted. If the value is less than or equal to the average value, the current frame is retained until the similarity of all image data frames in the sample information is determined. The number of image data frames included in the current sample information is counted. If the number is lower than the threshold, the sample information is deleted. Otherwise, no operation is performed.

[0046] The global position analysis unit 3 includes a data frame sampling module 301, an exit position parsing module 302 and a coordinate conversion module 303. The data frame sampling module 301 divides the specified scene into multiple sub-areas, numbers each sub-area, shoots the sub-area with a camera, transmits the obtained video data to the edge server, sets a sampling interval, collects the image data frames contained in each video data according to the sampling interval, sorts the data frames in each video data according to the time series, and stores them in the sampling set. The exit position parsing module 302 uses the target recognition model to sequentially sort the image data frames in the sampling set. The coordinate conversion module 303 scans the image data frame to obtain the local position information of the crowd, obstacles, dangerous objects and exit signs contained in the image data frame corresponding to each sub-region, and uses deep learning technology to analyze the exit local position information contained in the image data frame corresponding to each sub-region according to the content and local position information of the exit sign. The coordinate conversion module 303 transmits the local position information involved in each sub-region to the cloud server, and uses the coordinate optimization algorithm to convert the local position information involved in each sub-region to obtain the global position information of each crowd, obstacle, dangerous object and exit in the specified scene. The coordinate optimization algorithm is specifically as follows:

[0047]

[0048] in, represents the global position information of individual O in the scene, a represents the length of each sub-region, b represents the width of each sub-region, O represents the number information of the crowd, obstacles, dangerous objects and exits, (i, j) represents the number information of each sub-region, and (x, y) represents the local position information of individual O in the sub-region.

[0049] The impact degree judgment unit 4 includes an obstacle impact value calculation module 401, an exit impact value calculation module 402, a crowd impact value calculation module 403 and a field value calculation module 404. The obstacle impact value calculation module 401 analyzes all the passage paths according to the local position information of all exits in the sub-area, divides the area involved in the passage path, generates multiple grid units, determines the position coordinates of each obstacle and dangerous object in the sub-area, and uses the impact value determination algorithm to count the degree of influence of each obstacle and dangerous object on each grid unit, and calculates the total obstacle impact value of each grid unit according to the weights corresponding to the dangerous objects and obstacles. After the exit impact value calculation module 402 determines the local position coordinates of each exit in the sub-area, it calculates the total obstacle impact value of each grid unit according to the exit impact coefficient and the Euclidean distance between the center point of the grid unit and the exit. The degree to which each grid unit is affected by each exit is calculated, and the maximum exit influence degree is taken as the total exit influence value of the corresponding grid unit. The crowd influence value calculation module 403 obtains the local position coordinates of each crowd in the sub-area, and calculates the degree to which each grid unit is affected by the crowd at each location according to the crowd influence coefficient and the Euclidean distance between the center point of the grid unit and the crowd, and adds them up to obtain the total crowd influence value of the corresponding grid unit. The field value calculation module 404 counts the total obstacle influence value, the total exit influence value and the total crowd influence value corresponding to each grid unit, and after accumulating the three, obtains the field value of each grid unit. The path loss value from the center point of each grid unit to the exit position is calculated according to the field value, and the moving direction corresponding to any center point is determined using these data. The influence value determination algorithm is specifically as follows:

[0050]

[0051] Where (i, j) represents the coordinate position of the center point of the grid unit. If D a represents the coordinates of the dangerous object, then c a (i, j) represents the impact value of the dangerous object a on the grid unit of the position coordinate (i, j), m represents the impact coefficient of the dangerous object, l((i, j), D a ) represents the Euclidean distance between the center point of the grid unit and the dangerous object a, γ represents the dangerous object impact distance threshold, l represents the distance value, if D a represents the position coordinates of the obstacle, then c a (i, j) represents the impact value of obstacle a on the grid unit of position coordinate (i, j), m represents the impact coefficient of the obstacle, l((i, j), D a ) represents the Euclidean distance between the center point of the grid unit and the obstacle a, γ represents the obstacle influence distance threshold, and l represents the distance value;

[0052] The evacuation path generation unit 5 includes a moving direction optimization module 501, a speed analysis module 502 and a moving path simulation module 503. The moving direction optimization module 501 transmits the field value, the path loss value and the moving direction of the grid cells in each sub-area to the cloud server, calculates the global field value of each grid cell using the global coordinate information of the center point of the grid cells in each sub-area, and adjusts the moving direction of the center point, and returns these data to the edge server. The speed analysis module 502 calculates the density value corresponding to each grid cell according to the local position information of the crowd in the sub-area, and uses the density value to analyze the time when passing through each center point. The moving speed is transmitted to the cloud server, and the moving path and speed of each crowd evacuation are analyzed by the aggregation analysis algorithm to obtain the global passage path, which is returned to the edge server. The moving path simulation module 503 builds a real-time scene model according to all the global position information in the specified scene and the local position information of each sub-area through the simulation software, receives the moving path and speed corresponding to each crowd evacuation, and simulates it, and outputs the obtained results through a visual interface. The aggregation analysis algorithm is specifically the aggregation optimization artificial bee colony algorithm, the cloud server is specifically the Tencent cloud server, and the edge server is specifically the Atlas 500Pro edge server;

[0053] The emergency handling unit 6 includes an emergency value determination module 601 and a personnel scheduling module 602. The emergency value determination module 601 transmits the local position information of the temperature and humidity sensors, gas sensors and smoke sensors in each sub-area and the collected data to the edge server, defines multiple abnormal ranges for each data, and sets emergency values ​​for it. The distance between each dangerous object and each sensor is calculated according to the local position information of the dangerous objects and sensors in each sub-area. After determining the weight of the emergency value corresponding to each sensor in different dangerous objects according to the distance, the actual emergency value of each dangerous object in the sub-area is calculated. After receiving the actual emergency value of the dangerous object in each sub-area, the personnel scheduling module 602 transmits it to the cloud server, sorts the dangerous objects in the specified scene according to the actual emergency value, and the control center schedules and deploys personnel according to the global position information and arrangement order of the dangerous objects.

[0054] Working principle: The present invention uses the sample information acquisition module 101 in the recognition model construction unit 1 to analyze the gradient amplitude and direction of each pixel in the image data frame contained in the sample information, uses the feature vector determination module 102 to determine the gradient feature vector of the image data frame, and the parameter update module 103 optimizes the filter parameters and the target template. The position analysis module 201 in the target frame detection unit 2 outputs the target frame position and size corresponding to the current image data frame, and uses the similarity calculation module 202 to determine the similarity between the position and size of the target frame of the image data frame and the position and size of the identification frame. The sample information deletion module 203 counts the number of image data frames contained in the current sample information. If the number is lower than the threshold, the sample information is deleted. The data frame sampling module 301 in the global position analysis unit 3 is used to sort the data frames related to the sub-region according to the time series and store them in the sampling set. The exit position analysis module 302 analyzes the exit local position information contained in the image data frame corresponding to each sub-region, and the coordinate conversion module 303 converts the local position information involved in each sub-region. In exchange, the corresponding global position information in the specified scene is obtained, the obstacle impact value calculation module 401 in the impact degree judgment unit 4 calculates the total obstacle impact value of each grid unit, the exit impact value calculation module 402 determines the total exit impact value of the corresponding grid unit, the crowd impact value calculation module 403 obtains the total crowd impact value of the corresponding grid unit, and the field value calculation module 404 accumulates the obstacle impact total value, the exit impact total value and the crowd impact total value to obtain the field value of each grid unit, and the moving direction optimization module 501 in the evacuation path generation unit 5 adjusts the moving direction of the center point, the speed analysis module 502 analyzes the moving path and speed of each crowd evacuation to obtain the global passage path, and the moving path simulation module 503 builds a real-time scene model for simulation, and the obtained results are output through a visual interface, and the emergency value determination module 601 in the emergency processing unit 6 is used to calculate the actual emergency value of each dangerous object in the sub-area, and the personnel scheduling module 602 sorts the dangerous objects in the specified scene according to the actual emergency value, so as to facilitate the scheduling and deployment of personnel.

[0055] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0056] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An emergency scene data perception system based on cloud-edge-end processing, comprising an evacuation path generation unit (5) and an emergency processing unit (6), characterized in that: A recognition model construction unit (1), wherein the recognition model construction unit (1) obtains a sample data set of a crowd, an obstacle, a dangerous object, and an exit sign. Since each sample information in the data set contains a plurality of image data frames, a pixel point analysis algorithm is used to calculate the gradient amplitude and direction of each pixel point in the image data frame, a gradient feature vector of the image data frame is determined based on these data, a color feature vector is fused with a gradient feature vector, a target recognition model is constructed using a kernel correlation filter and a regression model, and all fusion results contained in each sample information are input into the target recognition model for analysis to obtain a response map corresponding to each frame; A target frame detection unit (2), wherein the target frame detection unit (2) scans the image information contained in the frame according to the peak position of the response graph of each frame and the size of the target frame of the previous frame, outputs the target frame position and size corresponding to the current image data frame, determines the similarity between the target frame position and size of the image data frame contained in each sample information and the position and size of the identification frame, and if the similarity is lower than a preset value, recalculates the peak value of the response graph corresponding to the image data frame and updates the detection parameters, otherwise calculates the similarity between the target frame position and size of the current frame and the previous frame; A global position analysis unit (3), wherein the global position analysis unit (3) divides a designated scene into a plurality of sub-areas, uses a camera to shoot the sub-areas, transmits the obtained video data to an edge server, sorts the data frames in each video data according to a time series, stores the data frames in the video data in a sampling set, uses a target recognition model to analyze the local position information of the crowd, obstacles, dangerous objects and exits contained in the image data frames corresponding to each sub-area, uses a coordinate optimization algorithm to convert the local position information involved in each sub-area, and obtains the global position information of each crowd, obstacle, dangerous object and exit in the designated scene; The impact degree judgment unit (4) divides the sub-area to generate a plurality of grid units, determines the position coordinates of each obstacle and dangerous object in the sub-area, and then uses an impact value determination algorithm to calculate the total obstacle impact value of each grid unit, calculates the total exit impact value of each grid unit based on the exit impact coefficient and the Euclidean distance between the center point of the grid unit and the exit, and calculates the total crowd impact value of each grid unit based on the crowd impact coefficient and the Euclidean distance between the center point of the grid unit and the crowd. After accumulating the three, the field value of each grid unit is obtained, and the moving direction corresponding to any center point is determined using these data.

2. The emergency scene data perception system based on cloud-edge processing according to claim 1 is characterized in that: The recognition model building unit (1) comprises a sample information acquisition module (101) and a feature vector determination module (102). After acquiring a sample data set of a crowd, an obstacle, a dangerous object and an exit sign, the sample information acquisition module (101) sets a corresponding identification frame for the sample information in each sample data set. Each sample information includes a plurality of image data frames. The pixel point analysis algorithm is used to calculate the gradient amplitude and direction of each pixel point in the image data frame. The gradient feature vector determination module (102) divides the area involved in the image data frame to obtain a plurality of small units. According to the gradient amplitude and direction of the pixel point in each small unit, a corresponding nine-level gradient histogram is analyzed, and the histograms corresponding to the adjacent areas are counted. After the four-dimensional feature vector corresponding to each small unit is analyzed according to these data, the histograms of all the small units are aggregated to obtain a nine-dimensional feature vector. The gradient amplitude and direction of the pixel point in each small unit are analyzed to obtain a corresponding eighteen-level gradient histogram, which is aggregated to obtain an eighteen-dimensional feature vector. All the feature vectors are associated to determine the final gradient feature vector of the image data frame.

3. The emergency scene data perception system based on cloud-edge-end processing according to claim 2 is characterized in that: The recognition model construction unit (1) also includes a parameter updating module (103). After extracting the color feature vector of the image data frame, the parameter updating module (103) fuses the color feature vector with the gradient feature vector, constructs a target recognition model using a kernel correlation filter and a regression model, inputs all fusion results contained in each sample information into the target recognition model for analysis, obtains a response graph corresponding to each frame, calculates the accuracy corresponding to the model result based on the difference between the peak value of the response graph of each frame and other points in the graph, and determines that the tracking is invalid if the accuracy is lower than a threshold value, otherwise it is determined that the tracking is valid, and optimizes the filter parameters and the target template using a parameter updating algorithm.

4. The emergency scene data perception system based on cloud-edge processing according to claim 1 is characterized in that: The target frame detection unit (2) comprises a position analysis module (201), a similarity calculation module (202) and a sample information deletion module (203). If the tracking is effective, the position analysis module (201) uses the target recognition model to scan the image information contained in the frame according to the peak position of each frame response graph and the size of the target frame of the previous frame, and outputs the position and size of the target frame corresponding to the current image data frame. If the tracking is invalid, the image information contained in the frame is scanned one by one, and the position and size of the target frame corresponding to the current image data frame are output. The similarity calculation module (202) determines the target frame of each sample information contained in the image data frame. The similarity between the position and size of the target frame and the position and size of the identification frame is calculated. If the similarity is lower than a preset value, the peak value of the response graph corresponding to the image data frame is recalculated and the detection parameters are updated. Otherwise, the similarity between the position and size of the target frame of the current frame and the previous frame is calculated. If the similarity between the current image data frame and the previous frame is greater than the average value, the current frame is deleted. If the value is less than or equal to the average value, the current frame is retained. After the similarity of all image data frames in the sample information is determined, the number of image data frames included in the current sample information is counted. If the number is lower than a threshold, the sample information is deleted. Otherwise, no operation is performed.

5. The emergency scene data perception system based on cloud-edge processing according to claim 1 is characterized in that: The global position analysis unit (3) comprises a data frame sampling module (301), an exit position analysis module (302) and a coordinate conversion module (303). The data frame sampling module (301) divides a specified scene into a plurality of sub-areas, numbers each sub-area, shoots the sub-area with a camera, transmits the obtained video data to an edge server, sets a sampling interval, collects image data frames contained in each video data according to the sampling interval, sorts the data frames in each video data according to a time series, and stores them in a sampling set. The exit position analysis module (302) uses a target recognition model to obtain the image data frames contained in each video data. The image data frames in the sampling set are scanned in sequence to obtain the local position information of the crowd, obstacles, dangerous objects and exit signs contained in the image data frames corresponding to each sub-region respectively. The local position information of the exit contained in the image data frames corresponding to each sub-region is analyzed according to the content and local position information of the exit sign by using deep learning technology. The coordinate conversion module (303) transmits the local position information involved in each sub-region to the cloud server, and uses the coordinate optimization algorithm to convert the local position information involved in each sub-region to obtain the global position information of each crowd, obstacle, dangerous object and exit in the specified scene.

6. The emergency scene data perception system based on cloud-edge processing according to claim 1 is characterized in that: The impact degree judgment unit (4) comprises an obstacle impact value calculation module (401), an exit impact value calculation module (402), a crowd impact value calculation module (403) and a field value calculation module (404). The obstacle impact value calculation module (401) analyzes all the passage paths according to the local position information of all the exits in the sub-area, divides the area involved in the passage path, generates a plurality of grid units, determines the position coordinates of each obstacle and dangerous object in the sub-area, and uses an impact value determination algorithm to count the degree of influence of each obstacle and dangerous object on each grid unit, and calculates the total obstacle impact value of each grid unit according to the weights corresponding to the dangerous objects and obstacles. After the exit impact value calculation module (402) determines the local position coordinates of each exit in the sub-area, it calculates the total obstacle impact value of each grid unit according to the exit impact coefficient and the grid unit. The Euclidean distance between the center point of the sub-area and the exit is used to calculate the degree to which each grid unit is affected by each exit, and the maximum exit influence degree is taken as the total exit influence value of the corresponding grid unit. The crowd influence value calculation module (403) obtains the local position coordinates of each crowd in the sub-area, and calculates the degree to which each grid unit is affected by each crowd according to the crowd influence coefficient and the Euclidean distance between the center point of the grid unit and the crowd, and accumulates them to obtain the total crowd influence value of the corresponding grid unit. The field value calculation module (404) counts the total obstacle influence value, the total exit influence value and the total crowd influence value corresponding to each grid unit, and accumulates the three to obtain the field value of each grid unit. The path loss value from the center point of each grid unit to the exit position is calculated according to the field value, and the moving direction corresponding to any center point is determined using these data.

7. The emergency scene data perception system based on cloud-edge processing according to claim 1 is characterized in that: The evacuation path generation unit (5) comprises a moving direction optimization module (501), a speed analysis module (502) and a moving path simulation module (503). The moving direction optimization module (501) transmits the field value, the passage path loss value and the moving direction of the grid unit in each sub-area to the cloud server, calculates the global field value of each grid unit using the global coordinate information of the center point of the grid unit in each sub-area, adjusts the moving direction of the center point, and returns these data to the edge server. The speed analysis module (502) calculates the density value corresponding to each grid unit according to the local position information of the crowd in the sub-area, analyzes the moving speed when passing through each center point using the density value, transmits it to the cloud server, analyzes the moving path and speed of each crowd evacuation by using the aggregation analysis algorithm, obtains the global passage path, and returns it to the edge server. The moving path simulation module (503) builds a real-time scene model according to all the global position information and the local position information of each sub-area in the specified scene through simulation software, simulates after receiving the moving path and speed corresponding to the evacuation of each crowd, and outputs the obtained results through a visual interface.

8. The emergency scene data perception system based on cloud-edge processing according to claim 1 is characterized in that: The emergency handling unit (6) comprises an emergency value determination module (601) and a personnel dispatching module (602). The emergency value determination module (601) transmits the local position information of the temperature and humidity sensor, the gas sensor and the smoke sensor in each sub-area and the collected data to the edge server, defines a plurality of abnormal ranges for each data, and sets an emergency value for it. The distance between each dangerous object and each sensor is calculated according to the local position information of the dangerous object and the sensor in each sub-area. After the weight of the emergency value corresponding to each sensor in different dangerous objects is determined according to the distance, the actual emergency value of each dangerous object in the sub-area is calculated. After receiving the actual emergency value of the dangerous object in each sub-area, the personnel dispatching module (602) transmits it to the cloud server, sorts the dangerous objects in the specified scene according to the actual emergency value, and the control center dispatches and deploys personnel according to the global position information and arrangement order of the dangerous objects.

Images