A vehicle overload data intelligent analysis management method and system

Abstract

The application relates to the technical field of traffic management, and provides a vehicle overload data intelligent analysis management method and system.The method comprises the following steps: when an intelligent automobile is started, a pressure sensor array is activated to collect seat pressure information; the vehicle seat is regionally divided according to the seat pressure information, and a pressure bearing region division result is obtained; region identification is performed on the pressure bearing region division result, and a characteristic region statistical quantity is obtained; it is judged whether the characteristic region statistical quantity meets a statistical quantity threshold value, wherein the statistical quantity threshold value is a vehicle load limit number; when the characteristic region statistical quantity meets the statistical quantity threshold value, a vehicle overload signal is generated and transmitted to a management terminal.The application solves the technical problem that the traditional overload supervision in the prior art is usually checked by traffic police to see whether the vehicle is overloaded, and the detection efficiency is low.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traffic management, in particular to a vehicle overload data intelligent analysis management method and system. BACKGROUND

[0002] With the rapid development of economy, basically every family has their own vehicles, so vehicle overload is very common in life. In addition to private cars, vehicles such as black cars and trucks also have overload behavior. Traditional overload supervision is usually checked by traffic police whether it is overloaded, which has the technical problem of low detection efficiency. SUMMARY

[0003] Therefore, it is necessary to provide a vehicle overload data intelligent analysis management method and system which can improve the safety of vehicle driving in view of the above technical problems.

[0004] In a first aspect, the present application provides a vehicle overload data intelligent analysis management method applied to a vehicle overload data intelligent analysis management system, the system and an intelligent automobile are in communication connection, the intelligent automobile includes a pressure sensor array arranged on a seat, and the method comprises the following steps: when the intelligent automobile starts, activating the pressure sensor array to collect seat pressure information; dividing the vehicle seat according to the seat pressure information to obtain a pressure area division result; traversing the pressure area division result to identify the area and obtain a statistical number of feature areas; judging whether the statistical number of feature areas meets a statistical number threshold value, wherein the statistical number threshold value is a vehicle load limit number; and when the statistical number of feature areas meets the statistical number threshold value, generating a vehicle overload signal and transmitting it to a management terminal.

[0005] In a second aspect, the application provides a vehicle overload data intelligent analysis management system, which is in communication connection with an intelligent vehicle, and the intelligent vehicle comprises a pressure sensor array arranged on a seat, and comprises: a seat pressure information acquisition module, which is configured to activate the pressure sensor array to collect seat pressure information when the intelligent vehicle starts; a pressure area division result acquisition module, which is configured to divide the vehicle seat into areas according to the seat pressure information, and acquire a pressure area division result; a feature area statistical quantity acquisition module, which is configured to traverse the pressure area division result to identify areas, and acquire a feature area statistical quantity; a feature area statistical quantity judgment module, which is configured to judge whether the feature area statistical quantity meets a statistical quantity threshold value, wherein the statistical quantity threshold value is a vehicle load limit number; and a vehicle overload signal generation and transmission module, which is configured to generate a vehicle overload signal and transmit the signal to a management terminal when the feature area statistical quantity meets the statistical quantity threshold value.

[0006] The one or more technical solutions provided in the application have at least the following technical effects or advantages:

[0007] First, when the intelligent vehicle starts, the pressure sensor array is activated to collect seat pressure information; second, the vehicle seat is divided into areas according to the seat pressure information, and a pressure area division result is acquired; third, the pressure area division result is traversed to identify areas, and a feature area statistical quantity is acquired; fourth, it is judged whether the feature area statistical quantity meets a statistical quantity threshold value, wherein the statistical quantity threshold value is a vehicle load limit number; and finally, when the feature area statistical quantity meets the statistical quantity threshold value, a vehicle overload signal is generated and transmitted to a management terminal. The application solves the technical problem of low detection efficiency of traditional overload supervision, which is usually checked by traffic police whether the vehicle is overloaded, and achieves the technical effect of improving the detection rate of vehicle overload.

[0008] The above description is only a summary of the technical solutions of the application. In order to more clearly understand the technical means of the application, the application can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the application more obvious and easy to understand, the following specific embodiments of the application are described. BRIEF DESCRIPTION OF DRAWINGS

[0009] Figure 1 It is a flowchart of a vehicle overload data intelligent analysis management method in an embodiment;

[0010] Figure 2 It is a flowchart of feature area statistical quantity statistics of a vehicle overload data intelligent analysis management method in an embodiment;

[0011] Figure 3 Figure 1 is a structural block diagram of a vehicle overload data intelligent analysis management system in one embodiment.

[0012] Reference signs: seat pressure information acquisition module 11, pressure area division result acquisition module 12, feature area statistical quantity acquisition module 13, feature area statistical quantity judgment module 14, vehicle overload signal generation and transmission module 15. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0014] After introducing the basic principles of the present application, the technical scheme in the present application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor are within the scope of protection of the present application. In addition, it should be noted that, for convenience of description, only parts related to the present application are shown in the drawings, not all.

[0015] Embodiment one

[0016] As shown in Figure 1 The present application provides a vehicle overload data intelligent analysis management method, applied to a vehicle overload data intelligent analysis management system, the system and an intelligent automobile are in communication connection, the intelligent automobile includes a pressure sensor array deployed on a seat, and the method comprises:

[0017] S100: when the intelligent automobile starts, activate the pressure sensor array to collect seat pressure information;

[0018] Specifically, with the rapid development of the economy, basically every family has their own vehicles, so vehicle overload is very common in life, in addition to private cars, such as black cars, trucks and other vehicles will also have overload behavior, based on this, the application provides a vehicle overload data intelligent analysis management method, applied to a vehicle overload data intelligent analysis management system, the system and the intelligent car are in communication connection, the intelligent car includes a pressure sensor array arranged on the seat. The weight of the vehicle is monitored by the pressure sensor installed at different positions of the vehicle, and the weight of the vehicle is obtained by analyzing whether the pressure data at different positions of the vehicle and the number of buttocks on the seat is less than the preset number of the vehicle, thereby avoiding traffic accidents caused by vehicle overload driving, and improving the safety of vehicle driving.

[0019] The intelligent car is a new generation of product more humanized than the ordinary car, is a comprehensive system integrating multiple functions, and is a typical high-tech complex; the pressure sensor is a sensor or instrument that converts input machine pressure into point output signal, and the pressure sensor array is a combination of multiple pressure sensor elements, generally in special geometric distribution, which can collect information more comprehensively; the seat pressure information refers to the information of the pressure borne by the seat of the vehicle, which is obtained by the pressure sensor array.

[0020] When the intelligent car is started, the vehicle overload data intelligent analysis management system activates the pressure sensor array to collect the information of the pressure borne by each seat of the vehicle.

[0021] S200: regionally dividing the vehicle seat according to the seat pressure information to obtain a pressure region division result;

[0022] Specifically, the regional division refers to dividing the surface of the seat according to different pressure values. The vehicle seat is regionally divided according to the seat pressure information to obtain a pressure division result.

[0023] Further, the application step includes:

[0024] S210: the seat pressure information includes pressure direction information and pressure position information;

[0025] S220: screening the pressure position information meeting the first direction according to the pressure direction information;

[0026] S230: clustering and analyzing the pressure position information to obtain a pressure distribution point cloud;

[0027] S240: regionally dividing according to the pressure distribution point cloud to obtain the pressure region division result.

[0028] Specifically, the pressure direction information refers to the direction from which the seat bears pressure, and the pressure position information refers to the position information of the seat bearing pressure; the first direction refers to the direction from which the seat bears pressure from above, for example, the pressure on the seat when a person sits on the seat; the cluster analysis refers to an analysis process of grouping a set of data objects into multiple classes composed of similar objects, for example, setting a pressure deviation value, and gathering the pressure position information into a region according to the size of the pressure deviation, and if a person sits on the seat, the seat will have a pressure-bearing region; and the pressure distribution point cloud refers to a mass of point sets of surface characteristics of the seat pressure-bearing region.

[0029] The seat pressure information includes pressure direction information and pressure position information, the pressure position information from which the seat bears pressure from above is screened according to the pressure direction information, cluster analysis is performed on the pressure position information, and a pressure distribution point cloud is obtained; and a region is segmented according to the pressure distribution point cloud, and a pressure-bearing region division result is obtained.

[0030] Further, the step of the application further includes:

[0031] S241: Setting a density analysis window, wherein the density analysis window is a circular window with a preset diameter;

[0032] S242: According to the density analysis window, traversing the pressure position information to perform pressure distribution density analysis, and obtaining multiple pressure distribution densities;

[0033] S243: According to the multiple pressure distribution densities, performing cluster analysis to obtain the pressure distribution point cloud.

[0034] Specifically, the density analysis window refers to a window for analyzing the seat pressure information, which can be set as a circular window with a preset diameter in the application, wherein the preset diameter is set by the staff, and is not limited here; the pressure density analysis refers to evaluating the pressure distribution density in the window through the density analysis window, traversing the pressure position information to obtain the density of all density analysis windows of the pressure position, and the cluster analysis refers to an analysis process of grouping a set of data objects into multiple classes composed of similar objects. A pressure deviation value is set, if the density is greater than the pressure deviation value, the pressure distribution point cloud is obtained, and if the density is less than the pressure deviation value and the pressure points are sparse, the density analysis window is not considered as the pressure distribution point cloud.

[0035] First, a density analysis window is set, wherein the density analysis window is a circular window with a preset diameter; second, according to the density analysis window, traversing the pressure position information to perform pressure distribution density analysis, and obtaining multiple pressure distribution densities; and finally, according to the multiple pressure distribution densities, performing cluster analysis to obtain the pressure distribution point cloud.

[0036] Further, the step of the application further comprises:

[0037] S244: According to the plurality of pressure distribution densities, a first pressure distribution density and a second pressure distribution density are obtained, wherein the first pressure distribution density and the second pressure distribution density are adjacent window pressure distribution densities;

[0038] S245: When the density distribution deviation of the first pressure distribution density and the second pressure distribution density is less than or equal to a density distribution deviation threshold value, the window regions of the first pressure distribution density and the second pressure distribution density are aggregated into the same point cloud;

[0039] S246: When the density distribution deviation of the first pressure distribution density and the second pressure distribution density is greater than the density distribution deviation threshold value, the window regions of the first pressure distribution density and the second pressure distribution density are aggregated into different point clouds;

[0040] S247: The plurality of pressure distribution densities are repeatedly traversed to obtain the pressure distribution point cloud.

[0041] Specifically, the first pressure distribution density refers to any one of the plurality of pressure distribution densities, denoted as the first pressure distribution density, and the second pressure distribution density is the same; the density distribution deviation refers to the difference value of adjacent window pressure distribution densities, and the density distribution deviation threshold value refers to the value set by the staff, which is determined according to experience and is not required here. If the density difference of adjacent windows is less than the density distribution deviation threshold value, the adjacent windows are aggregated into the same point cloud.

[0042] According to the plurality of pressure distribution densities, a first pressure distribution density and a second pressure distribution density are selected, wherein the first pressure distribution density and the second pressure distribution density are adjacent window pressure distribution densities; when the density distribution deviation of the first pressure distribution density and the second pressure distribution density is less than or equal to a density distribution deviation threshold value, the window regions of the first pressure distribution density and the second pressure distribution density are aggregated into the same point cloud; when the density distribution deviation of the first pressure distribution density and the second pressure distribution density is greater than the density distribution deviation threshold value, the window regions of the first pressure distribution density and the second pressure distribution density are aggregated into different point clouds; the plurality of pressure distribution densities are repeatedly traversed to obtain the pressure distribution point cloud.

[0043] Further, the step of the application further comprises:

[0044] S248: The edge of the pressure distribution point cloud is depicted to obtain a point cloud distribution contour feature image;

[0045] S249: Obtain a reference area, wherein the reference area represents a minimum area after the buttocks are seated;

[0046] S2410: Set an area of the point cloud distribution contour feature image greater than or equal to the reference area as the pressure-bearing area division result.

[0047] Specifically, edge delineation refers to delineating the contour of the pressure distribution point cloud; the reference area refers to the minimum area of the buttocks in contact with the seat after sitting on the seat.

[0048] The contour of the pressure distribution point cloud is delineated to obtain a point cloud distribution contour feature image; then a reference area is obtained, which represents the minimum area after the buttocks are seated; the area of the point cloud distribution contour feature image greater than or equal to the reference area is set as the pressure-bearing area division result. If the point cloud distribution contour feature image is less than the reference area, since the reference area is the minimum area after the buttocks are seated, the seat is not for a person to sit on, such as a cup, a bag, etc.

[0049] S300: Traverse the pressure-bearing area division result to perform region identification and obtain a feature region statistical quantity;

[0050] Specifically, region identification refers to the process of matching the reference image information and the regions of the pressure-bearing area division result, i.e., similarity evaluation; the feature region statistical quantity refers to the sum of the number of pressure-bearing areas with high similarity evaluation results after the similarity evaluation.

[0051] As shown in Figure 2 Further, the steps of the present application include:

[0052] S310: Obtain reference image information, wherein the reference image information is a plurality of sample contour images after the buttocks are seated;

[0053] S320: Traverse the reference image information and perform shape similarity evaluation with the pressure-bearing area division result to obtain a plurality of similarity evaluation results;

[0054] S330: When any one of the plurality of similarity evaluation results is greater than or equal to a similarity threshold, add a feature region, and increase the feature region statistical quantity by one.

[0055] Specifically, the reference image refers to a map coordinate or RPC information that must include a standard, and cannot be pixel coordinates, arbitrary coordinate information without projection information, and pseudo coordinates; the image to be registered has no strict constraints, but if there is no coordinate information, at least 3 homonymous points need to be manually selected, which in this application refers to multiple sample contour images after the buttocks are seated; the shape similarity evaluation refers to comparing the reference image information with the image of the pressure area division result to obtain multiple similarity evaluation results, i.e., evaluating the similarity of the reference image and the image of the pressure area division result; the similarity threshold is set by the staff, and is used to determine whether the pressure area division result is the area after the buttocks are seated; the feature area is the area on which a person sits on the seat in the pressure area division result of the seat, i.e., the feature area statistical quantity is the sum of the number of people sitting on the seat, i.e., the total number of people in the vehicle is obtained.

[0056] Obtain reference image information, which is multiple sample contour images after the buttocks are seated; traverse the reference image information and perform shape similarity evaluation with the pressure area division result to obtain multiple similarity evaluation results, wherein the shape similarity evaluation can be realized using a convolutional neural network, a convolutional neural network model can be constructed, two pictures are input, and after calculation by the convolutional neural network model, a similarity value is output, when the two pictures match, the output value is marked as 1, and if the two pictures do not match, the training data is marked as -1, and the data is stabilized by training the pressure area division result and the reference image information; set a similarity threshold, for example, it can be set to 0.9, when any one of the multiple similarity evaluation results is greater than or equal to 0.9, add it to the feature area, and the feature area statistical quantity is increased by one.

[0057] Further, the steps of the application further include:

[0058] S340: When the feature area statistical quantity does not satisfy the statistical quantity threshold, activate the vehicle-mounted weighing module to obtain vehicle load data;

[0059] S350: Perform vehicle load prediction according to the feature area statistical quantity to obtain vehicle load prediction results;

[0060] S360: When the vehicle load data is greater than the vehicle load prediction results, and the load deviation is greater than or equal to the preset deviation, activate the millimeter wave radar to collect in-vehicle human posture information;

[0061] S370: Perform personnel segmentation according to the in-vehicle human posture information to obtain vehicle-mounted personnel quantity information;

[0062] S380: When the vehicle personnel quantity information meets the statistical quantity threshold, the vehicle overload signal is generated and transmitted to the management terminal.

[0063] Specifically, if the number of buttocks of the seat is less than the preset number, but the load is abnormal, the number of personnel needs to be detected by the millimeter wave radar to avoid the existence of unseated overload. The millimeter wave radar refers to a radar sensor working in the millimeter wave frequency band that uses radio methods to find targets and measure their positions in space. The vehicle load-bearing module refers to an instrument for measuring the weight on the vehicle.

[0064] The vehicle load data refers to the real-time load of the vehicle; the vehicle load prediction result refers to the prediction based on the feature area statistical data, which can be regarded as the number of people on the vehicle; the preset deviation is set by the staff to judge whether the vehicle load data is greater than the vehicle load prediction result and is not caused by the error of individual body shape; collecting the posture information of the people in the vehicle is because according to the vehicle load data and the vehicle load prediction result, it is judged that there are people on the vehicle who are not sitting on the seat, such as standing or sitting on the steps, etc. When the number of buttocks of the seat is less than the preset number, but the load is abnormal, the number of personnel needs to be detected by the millimeter wave radar to avoid the existence of unseated overload, personnel segmentation refers to using a convolutional neural network to extract moving objects, and then filtering the posture of the moving objects according to a human posture feature module to obtain the postures of multiple different personnel distributions and count the number of personnel.

[0065] When the feature area statistical quantity does not meet the statistical quantity threshold, activate the vehicle load module to obtain vehicle load data; perform vehicle load prediction based on the feature area statistical quantity to obtain vehicle load prediction results; when the vehicle load data is greater than the vehicle load prediction result, and the load deviation is greater than or equal to the preset deviation, activate the millimeter wave radar to collect the posture information of the people in the vehicle; perform personnel segmentation based on the posture information of the people in the vehicle to obtain vehicle personnel quantity information; when the vehicle personnel quantity information meets the statistical quantity threshold, generate the vehicle overload signal and transmit it to the management terminal.

[0066] S400: Determine whether the feature area statistical quantity meets the statistical quantity threshold, wherein the statistical quantity threshold is the vehicle load limit number.

[0067] Specifically, the statistical quantity threshold refers to the vehicle load limit number, and whether the feature area statistical quantity meets the statistical quantity threshold.

[0068] S500: When the feature area statistical quantity meets the statistical quantity threshold, generate the vehicle overload signal and transmit it to the management terminal.

[0069] Specifically, when the feature region statistical quantity, i.e., the predicted number of people in the feature region, is greater than the statistical quantity threshold, the vehicle is overloaded, and a vehicle overload signal is generated and transmitted to a management terminal.

[0070] To sum up, the vehicle overload data intelligent analysis management method provided by the embodiments of the present application has at least the following technical effects:

[0071] 1. By intelligently analyzing the seat pressure data on the vehicle, the traditional overload supervision, which is usually checked by the traffic police to see if it is overloaded, has the technical problem of low detection efficiency, and the technical effect of improving the vehicle overload detection rate is achieved.

[0072] 2. By intelligently analyzing the vehicle load data on the vehicle, the traditional overload supervision, which is usually checked by the traffic police to see if it is overloaded, has the technical problem of low detection efficiency, and the technical effect of improving the vehicle overload detection rate is achieved.

[0073] Embodiment Two

[0074] As shown in Figure 3 The present application also provides a vehicle overload data intelligent analysis management system, which is in communication connection with the intelligent vehicle, and the intelligent vehicle includes a pressure sensor array arranged on the seat, comprising:

[0075] A seat pressure information acquisition module 11 is configured to activate the pressure sensor array to collect seat pressure information when the intelligent vehicle starts;

[0076] A pressure area division result acquisition module 12 is configured to divide the vehicle seat into areas according to the seat pressure information and acquire a pressure area division result;

[0077] A feature region statistical quantity acquisition module 13 is configured to traverse the pressure area division result to identify the areas and acquire a feature region statistical quantity;

[0078] A feature region statistical quantity judgment module 14 is configured to judge whether the feature region statistical quantity meets a statistical quantity threshold, wherein the statistical quantity threshold is the number of people allowed by the vehicle;

[0079] A vehicle overload signal generation and transmission module 15 is configured to generate a vehicle overload signal and transmit it to a management terminal when the feature region statistical quantity meets the statistical quantity threshold

[0080] Further, the embodiments of the present application also include:

[0081] seat pressure information content module, the seat pressure information content module is used for the seat pressure information to include pressure direction information and pressure position information;

[0082] pressure position information screening module, the pressure position information screening module is used for screening the pressure position information that satisfies the first direction according to the pressure direction information;

[0083] pressure distribution point cloud acquisition module, the pressure distribution point cloud acquisition module is used for clustering analysis to the pressure position information, obtains pressure distribution point cloud;

[0084] pressure area division result acquisition module, the pressure area division result acquisition module is used for according to the pressure distribution point cloud carries out regional segmentation, obtains the pressure area division result.

[0085] Further, the embodiment of the application further includes:

[0086] density analysis window setting module, the density analysis window setting module is used for setting density analysis window, wherein the density analysis window is the circular window with preset diameter;

[0087] pressure distribution density acquisition module, the pressure distribution density acquisition module is used for according to the density analysis window, traverses the pressure position information and carries out pressure distribution density analysis, obtains multiple pressure distribution densities;

[0088] pressure distribution cloud acquisition module, the pressure distribution cloud acquisition module is used for clustering analysis according to the multiple pressure distribution densities, obtains the pressure distribution point cloud.

[0089] Further, the embodiment of the application further includes:

[0090] pressure distribution density acquisition module, the pressure distribution density acquisition module is used for according to the multiple pressure distribution densities, obtains first pressure distribution density and second pressure distribution density, wherein the first pressure distribution density and the second pressure distribution density are adjacent window pressure distribution densities;

[0091] window area aggregation module, the window area aggregation module is used for when the density distribution deviation of the first pressure distribution density and the second pressure distribution density is less than or equal to density distribution deviation threshold, the window area of the first pressure distribution density and the second pressure distribution density is aggregated as same point cloud;

[0092] A different point cloud clustering module is configured to cluster window regions of the first pressure distribution density and the second pressure distribution density into different point clouds when a density distribution deviation of the first pressure distribution density and the second pressure distribution density is greater than the density distribution deviation threshold.

[0093] A pressure distribution point cloud acquisition module is configured to repeatedly traverse the plurality of pressure distribution densities to acquire the pressure distribution point cloud.

[0094] Further, the embodiment of the present application further comprises:

[0095] A point cloud distribution contour feature image acquisition module is configured to perform edge drawing on the pressure distribution point cloud to acquire a point cloud distribution contour feature image.

[0096] A reference area acquisition module is configured to acquire a reference area, wherein the reference area represents a minimum area after the buttocks are seated.

[0097] A pressure-bearing area division result setting module is configured to set a region of the point cloud distribution contour feature image that is greater than or equal to the reference area as the pressure-bearing area division result.

[0098] Further, the embodiment of the present application further comprises:

[0099] A reference image information acquisition module is configured to acquire reference image information, wherein the reference image information is a plurality of sample contour images after the buttocks are seated.

[0100] A reference image information traversal module is configured to traverse the reference image information, perform shape similarity evaluation on the pressure-bearing area division result, and acquire a plurality of similarity evaluation results.

[0101] A feature region adding module is configured to add a feature region when any one of the plurality of similarity evaluation results is greater than or equal to a similarity threshold, and the number of feature regions is incremented by one.

[0102] Further, the embodiment of the present application further comprises:

[0103] A vehicle load data acquisition module is configured to activate the vehicle-mounted weighing module to acquire vehicle load data when the number of feature regions does not satisfy the statistical number threshold.

[0104] The vehicle load prediction result acquisition module is configured to perform vehicle load prediction according to the feature region statistical quantity, and acquire a vehicle load prediction result.

[0105] The in-vehicle person posture information acquisition module is configured to activate the millimeter wave radar and acquire in-vehicle person posture information when the vehicle load data is greater than the vehicle load prediction result and the load deviation is greater than or equal to a preset deviation.

[0106] The vehicle load overload signal transmission module is configured to generate the vehicle load overload signal and transmit the signal to the management terminal when the vehicle personnel quantity information meets the statistical quantity threshold.

[0107] The vehicle load overload signal transmission module is configured to generate the vehicle load overload signal and transmit the signal to the management terminal when the vehicle personnel quantity information meets the statistical quantity threshold.

[0108] The specific embodiments of the vehicle overload data intelligent analysis management system can be seen in the embodiments of the vehicle overload data intelligent analysis management method described above, and will not be described here. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so that the processor can call and execute the operations of the above modules.

[0109] The technical features of the above embodiments can be combined in any way. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0110] The above embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be noted that for ordinary skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for intelligent analysis and management of vehicle overload data, characterized in that, An intelligent analysis and management system for vehicle overload data is applied, wherein the system is communicatively connected to an intelligent vehicle, and the intelligent vehicle includes an array of pressure sensors deployed in the seats, comprising: When the smart car starts, it activates a pressure sensor array to collect information about the pressure on the seats. Based on the seat pressure information, the vehicle seats are segmented into regions to obtain the pressure region division results; The pressure-bearing area division results are traversed to perform area identification and obtain the statistical number of characteristic areas, including: Acquire reference image information, wherein the reference image information consists of multiple sample contour images of the buttocks after sitting down; The reference image information is traversed, and a shape similarity evaluation is performed with the pressure-bearing area division result to obtain multiple similarity evaluation results; When any one of the multiple similarity evaluation results is greater than or equal to the similarity threshold, it is added to the feature region, and the number of the feature regions is incremented by one. Determine whether the statistical quantity of the feature region meets the statistical quantity threshold, wherein the statistical quantity threshold is the vehicle's passenger capacity limit; When the number of statistical counts in the feature regions meets the statistical count threshold, a vehicle overload signal is generated and transmitted to the management terminal. The intelligent vehicle also includes millimeter-wave radar and an on-board weighing module, including: When the number of statistical data in the feature region does not meet the statistical data threshold, the vehicle weighing module is activated to obtain vehicle load data. Based on the statistical count of the feature regions, vehicle load is predicted, and the vehicle load prediction result is obtained. When the vehicle load data is greater than the vehicle load prediction result, and the load deviation is greater than or equal to the preset deviation, the millimeter-wave radar is activated to collect the posture information of the people inside the vehicle. Based on the posture information of the people inside the vehicle, personnel are segmented to obtain the number of people in the vehicle. When the number of passengers in the vehicle meets the statistical threshold, an overload signal is generated and transmitted to the management terminal.

2. The method as described in claim 1, characterized in that, Based on the seat pressure information, the vehicle seats are segmented into regions to obtain the pressure region division results, including: The seat pressure-bearing information includes pressure direction information and pressure location information; Based on the pressure bearing direction information, filter the pressure bearing location information that satisfies the first direction; Cluster analysis is performed on the pressure-bearing location information to obtain a pressure distribution point cloud; The pressure distribution point cloud is used to segment the region and obtain the pressure-bearing region division result.

3. The method as described in claim 2, characterized in that, Hierarchical clustering analysis is performed on the pressure-bearing location information to obtain a pressure distribution point cloud, including: A density analysis window is set, wherein the density analysis window is a circular window with a preset diameter; Based on the density analysis window, pressure distribution density analysis is performed by traversing the pressure-bearing location information to obtain multiple pressure distribution densities; Cluster analysis is performed based on the multiple pressure distribution densities to obtain the pressure distribution point cloud.

4. The method as described in claim 3, characterized in that, Cluster analysis is performed based on the multiple pressure distribution densities to obtain the pressure distribution point cloud, including: Based on the plurality of pressure distribution densities, a first pressure distribution density and a second pressure distribution density are obtained, wherein the first pressure distribution density and the second pressure distribution density are adjacent window pressure distribution densities; When the density distribution deviation between the first pressure distribution density and the second pressure distribution density is less than or equal to the density distribution deviation threshold, the window regions of the first pressure distribution density and the second pressure distribution density are aggregated into the same point cloud. When the density distribution deviation between the first pressure distribution density and the second pressure distribution density is greater than the density distribution deviation threshold, the window regions of the first pressure distribution density and the second pressure distribution density are aggregated into different point clouds. Repeatedly traverse the multiple pressure distribution densities to obtain the pressure distribution point cloud.

5. The method as described in claim 2, characterized in that, Based on the pressure distribution point cloud, region segmentation is performed to obtain the pressure-bearing region division results, including: Edge delineation is performed on the pressure distribution point cloud to obtain a point cloud distribution contour feature image; Obtain a reference area, wherein the reference area represents the minimum area after the buttocks are seated; The region in the point cloud distribution contour feature image that is greater than or equal to the reference area is defined as the pressure-bearing region division result.

6. An intelligent analysis and management system for vehicle overload data, used to execute the method of claim 1, characterized in that, The system is communicatively connected to an intelligent vehicle, which includes an array of pressure sensors deployed in the seats, comprising: A seat pressure information acquisition module is used to activate a pressure sensor array to collect seat pressure information when the intelligent vehicle is started. The pressure-bearing area division result acquisition module is used to divide the vehicle seats into regions based on the seat pressure information and acquire the pressure-bearing area division result. The feature region statistics acquisition module is used to traverse the pressure-bearing area division results to identify the region and acquire the feature region statistics. The feature region statistical quantity judgment module is used to determine whether the statistical quantity of the feature region meets the statistical quantity threshold, wherein the statistical quantity threshold is the vehicle's passenger limit. A vehicle overload signal generation and transmission module is used to generate a vehicle overload signal and transmit it to a management terminal when the statistical quantity of the feature area meets the statistical quantity threshold.

Images