Remote monitoring and early warning system based on smart community

Abstract

The invention discloses a remote monitoring and early warning system based on a smart community, and the system carries out the emergency monitoring of the monitoring equipment with the highest monitoring quality in a monitoring region where the monitoring equipment is damaged through temporary calling under the condition that the monitoring equipment is damaged. Meanwhile, vehicles and on-duty personnel in the monitoring area where the monitoring equipment is damaged are called for auxiliary monitoring, so that it is ensured that the intelligent community can be early warned, prompted and recorded under the condition that the monitoring equipment is damaged; the operation parameters of the monitoring equipment are obtained through analysis of the temperature, the response duration and the picture quality evaluation value during operation of the monitoring equipment, the operation performance of the monitoring equipment is evaluated through the operation parameters of the monitoring equipment, and the picture shooting quality is compared with manual detection of the operation performance of the monitoring equipment. The accuracy of monitoring equipment detection is greatly improved, meanwhile, the operation performance of the monitoring equipment can be detected in time, and the increasingly aggravated damage degree of the monitoring equipment is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of remote monitoring of smart communities, and in particular to a remote monitoring and early warning system based on smart communities. Background Art

[0002] Remote monitoring and early warning of smart communities is an effective means of using intelligent technology to improve the quality of life of residents. It has played an important role in improving community safety, promoting smart construction, and improving the living environment of residents. However, there are also some problems.

[0003] Currently, if the monitoring equipment in a smart community fails, the monitoring work in the corresponding area will be unable to proceed or the quality will be reduced. In this case, if an unexpected situation occurs, it may not be possible to provide timely warnings, prompts and records. Smart communities usually use manual methods to detect the degree of wear and tear of monitoring equipment. However, this method is inefficient and inaccurate, and often leads to increasing damage to the monitoring equipment. Summary of the invention

[0004] The purpose of the present invention is to solve the problems that manual detection of monitoring equipment is inefficient and inaccurate, which often leads to increasing damage to the monitoring equipment and the inability to provide timely warnings, prompts and records when the monitoring equipment fails, and to propose a remote monitoring and early warning system based on a smart community.

[0005] The object of the present invention can be achieved through the following technical solutions: a remote monitoring and early warning system based on a smart community, including a cloud service platform and an analysis module; the analysis module compares the operating parameters of the monitoring device with the preset monitoring device damage threshold interval, and determines that the monitoring device is a monitoring interruption device or a faulty device, and at the same time, the cloud service platform generates a corresponding early warning signal and sends it to the terminal module; and also includes a terminal module; The terminal module dispatches maintenance personnel to perform maintenance based on the received warning signal, and generates corresponding level warning plans for the monitoring interrupted equipment or faulty equipment according to the monitoring equipment. The warning plans include level 1 warning plan and level 2 warning plan. If the monitoring device is a monitoring interruption device, the first-level warning plan is implemented, specifically: Level 1 early warning plan; The first step of the execution process: Obtain all monitoring equipment information in the smart community, by connecting the midpoint of the detection area with the monitoring equipment in the smart community, extracting the length of the connection, and presetting the standard monitoring distance. By comparing the length of the connection between the midpoint of the detection area and the corresponding monitoring equipment with the preset standard monitoring distance, extract the monitoring equipment whose length of the connection between the midpoint of the detection area and the corresponding monitoring equipment is less than the preset standard monitoring distance, and mark it as a reserve monitoring equipment, obtain the monitoring area of ​​the detection area by the reserve monitoring equipment, and the image quality evaluation value of the detection area, and perform normalized weighted processing to obtain the pre-inspection value of the reserve monitoring equipment for the detection area, compare the pre-inspection values ​​of all reserve monitoring equipment, and extract the reserve monitoring equipment with the largest pre-inspection value as the emergency monitoring equipment for the detection area; The second step of the execution process: By making the emergency monitoring equipment monitor and cover the detection area, extract the area that the emergency monitoring equipment cannot monitor and cover the detection area, and mark it as the area to be inspected, by dividing the area to be inspected into several sub-areas to be inspected, and numbering them, and detecting whether there are vehicles in the sub-areas to be inspected; If yes, obtain the information of the vehicle in the sub-area to be inspected, and connect the cloud service platform to the vehicle in the sub-area to be inspected through the Internet of Things, and then call the vehicle's driving recorder to monitor the sub-area to be inspected, obtain the monitoring area of ​​the corresponding vehicle in the sub-area to be inspected, extract the vehicle with the widest coverage of the sub-area to be inspected in the monitoring area of ​​the corresponding vehicle in the sub-area to be inspected, as the marked vehicle, and match the monitoring area of ​​the sub-area to be inspected with the corresponding sub-area to be inspected by the marked vehicle. If there is a complete match, the sub-area to be inspected is recorded as a matching sub-area, and the sub-area to be inspected is monitored by the marked vehicle. If there is an incomplete match, extract the area where the monitoring area of ​​the sub-area to be inspected by the marked vehicle does not match the corresponding sub-area to be inspected, and mark it as a blind sub-area. At this time, it is determined whether there are monitoring areas of other vehicles in the sub-area to be inspected that can cover the blind inspection sub-area. If so, the sub-area to be inspected is monitored by multiple vehicles in the sub-area to be inspected. If not, the area of ​​the blind inspection sub-area is calculated, and a monitoring level is preset. Each monitoring level corresponds to a monitoring area threshold interval. The monitoring level corresponding to the blind inspection sub-area is obtained by comparing the area of ​​the blind inspection sub-area with the monitoring area threshold interval corresponding to the preset monitoring level, and a monitoring level instruction is generated. The monitoring level instruction and the number of the sub-area to be inspected corresponding to the blind inspection sub-area are sent to the terminal module. The terminal module dispatches the number of on-duty personnel according to the monitoring level, and stands guard in the blind inspection sub-area corresponding to the sub-area to be inspected with the corresponding number. If the monitoring device is a faulty device, the secondary warning plan is executed, specifically: The second-level warning plan does not need to call emergency monitoring equipment to monitor and cover the detection area. That is, at this time, the detection area is monitored and covered by the faulty equipment, and the same steps as the second step of the first-level warning plan execution process are performed.

[0006] As a preferred embodiment of the present invention, the analysis module analysis process is specifically as follows: If the operating parameters of the monitoring device are greater than the maximum value in the preset monitoring device damage threshold interval, the monitoring device is marked as a monitoring interruption device; if the operating parameters of the monitoring device belong to the preset monitoring device damage threshold interval, the monitoring device is marked as a faulty device; if the operating parameters of the monitoring device are less than the minimum value in the preset monitoring device damage threshold interval, the monitoring device is marked as a normal monitoring device.

[0007] As a preferred embodiment of the present invention, it includes a device detection module; The equipment detection module obtains the operating parameters of the monitoring equipment in the smart community. The operating parameters of the monitoring equipment include the temperature, response time and picture quality evaluation value of the monitoring equipment during operation. The intelligent parameter value is obtained by analyzing the temperature and response time of the monitoring equipment during operation. The performance evaluation value of the monitoring equipment is obtained by analyzing the intelligent parameter value. The operating parameters of the internal monitoring equipment are obtained by analyzing the performance evaluation value and the picture quality evaluation value of the monitoring equipment. The specific process of obtaining the intelligent parameter value by analyzing the temperature and response time of the monitoring equipment during operation is as follows: By evenly distributing detection points on the monitoring equipment in the smart community, the thermal imaging images of each detection point corresponding to the operation of the monitoring equipment in the smart community are collected. The temperature chromaticity corresponding to each detection point is extracted from the thermal imaging image of each detection point. Based on the temperature chromaticity corresponding to each detection point, it is matched with the reference chromaticity threshold of the thermal imaging image corresponding to the preset high temperature. If the match is successful, it will be recorded as a high temperature point. The number of high temperature points is counted and summed to obtain the total high temperature value when the monitoring equipment in the smart community is running, which is marked as the smart temperature value. By detecting the response time of the monitoring equipment in the smart community, multiple detection cycles are set, each detection cycle includes ten detection operations, and the interval time from the input command to the response command of the monitoring equipment in the smart community in each detection operation is obtained. By summing the interval time of the ten detection operations corresponding to each detection cycle and taking the average, the average interval time from the input command to the response command of the monitoring equipment in the smart community corresponding to each detection cycle is obtained, which is marked as the smart device average time. By subtracting the smart device average time corresponding to each detection cycle from the preset reference time, if the smart device average time is less than or equal to the preset reference time, the detection cycle corresponding to the smart device average time is marked as a qualified detection cycle. If the smart device average time is greater than the preset reference time, the detection cycle corresponding to the smart device average time is marked as an unqualified detection cycle. The number of unqualified detection cycles is extracted and divided by the total number of detection cycles to obtain the unqualified rate of the response time of the monitoring equipment in the smart community, and marked as the smart device abnormality rate; The intelligent parameter value is obtained by comprehensively analyzing the intelligent setting temperature difference value and the intelligent setting difference rate.

[0008] As a preferred embodiment of the present invention, the specific process of obtaining the monitoring equipment performance evaluation value by analyzing the intelligent parameter value is as follows: Set a number of detection time periods, each detection time period corresponds to a detection duration, wherein the detection duration corresponding to each detection time period is the same, obtain the intelligence parameter value corresponding to each detection moment in the detection duration, obtain the fluctuation of the intelligence parameter value in the detection duration corresponding to each detection time period, obtain the maximum value of the intelligence parameter value in the fluctuation of the intelligence parameter value in the detection duration corresponding to each detection time period, and obtain the standard deviation of the intelligence parameter value in the fluctuation of the intelligence parameter value in the detection duration corresponding to each detection time period, mark the maximum value of the intelligence parameter value corresponding to each detection time period as D, mark the standard deviation of the intelligence parameter value as B, assign a weight of H1 to the maximum value D of the intelligence parameter value corresponding to each detection time period, assign a weight of H2 to the standard deviation B of the intelligence parameter value, wherein H2>H1, and obtain the intelligence parameter influence value of each detection time period by normalizing and weighting the maximum value D of the intelligence parameter value corresponding to each detection time period and the standard deviation B of the intelligence parameter value; Preset a blank line graph, with the horizontal axis being the detection period and the vertical axis being the intelligence parameter influence value. Connect the intelligence parameter influence values ​​corresponding to adjacent detection periods to obtain the intelligence parameter influence value change line. Preset the intelligence parameter influence threshold line. Extract the area where the intelligence parameter influence value change line exceeds the intelligence parameter influence threshold line, marked as the intelligence surpassing area, and extract the interval time between adjacent intelligence surpassing areas, marked as the threshold interval time. Count the sum of all intelligence surpassing areas to obtain the total intelligence surpassing product zcj. At the same time, extract all the threshold interval time and divide them by the number of threshold interval time to obtain the average threshold interval length yjc. Substitute the total intelligence surpassing product zcj and the average threshold interval length yjc into the formula The monitoring equipment performance evaluation value zcp is obtained, where d1 and d2 are preset weight factors, and △zcp is the reference value for the monitoring equipment performance evaluation in the smart community.

[0009] As a preferred implementation of the present invention, the specific process of analyzing the picture quality evaluation value is as follows: By installing reference objects at different distances within the monitoring area of ​​the monitoring device, each reference object is provided with a number of identification points; Extract the image containing the reference object in the captured picture and mark it as the reference object image. By enlarging the reference object image and identifying the number of identification points of the farthest reference object in the reference object image, the number of shots of the reference object identification points is obtained. The actual number of identification points in the corresponding reference object is extracted from the cloud service platform. The difference between the actual number of the corresponding reference object identification points and the number of shots of the reference object identification points is obtained to obtain the number of differences pcs. The reference image is divided into several recognition areas according to the distribution of recognition points, and the contours of the corresponding recognition points in the recognition areas are recognized and the contour area is calculated to obtain the contour shooting area of ​​the corresponding recognition points in the recognition areas. At the same time, the preset contour area of ​​the corresponding recognition points is extracted from the cloud service platform. The preset contour area of ​​the recognition points corresponding to the recognition areas is subtracted from the contour shooting area of ​​the recognition points to obtain the contour deviation area of ​​the recognition points corresponding to the recognition areas. The deviation areas of the recognition points corresponding to all the recognition areas are summed up to obtain the total deviation product pcz. The monitoring device is used to photograph the persons in the monitoring area to obtain the person images, and the person images are identified. The person images that can capture the center of the eyebrows of the face are recorded as pre-check images. The person in the pre-check image uses the center of the eyebrows of the face as a reference point and makes a horizontal plane parallel to the face, which is recorded as a pre-check plane. The center of the eyebrows of the face and the monitoring device are used as two reference points to connect the lines, which are recorded as detection lines. The angle between the detection lines and the projections of the detection lines on the detection plane is measured. The angle between the detection lines and the projections of the detection lines on the detection plane is matched with the preset angle interval between the face and the camera. If the match is successful, the person in the pre-check image is marked as a person facing the camera. Extract the facial contour image of the person facing the camera in the pre-check image and mark it as the detection image. Collect the number of people in the detection image and record it as the detection number. Match the facial contour features of the person in the detection image with the people stored in the cloud service platform, where the facial contour features of the person include eyes, nose, and mouth. Mark the successfully matched person as the recognized person and the unmatched person as the unrecognizable person. Count the number of unrecognizable persons and divide it by the detection number to get the proportion of unrecognizable persons and mark it as the detection error ratio jcb. By substituting the number of poor evaluations pcs, the total deviation product pcz, and the error detection ratio jcb into the preset model The image quality evaluation value tz is obtained, where p1, p2, and p3 are preset weight factors, and △s, △z, and △s are the preset reference difference number, total deviation product, and error detection ratio, respectively.

[0010] As a preferred embodiment of the present invention, the operating parameter analysis process of the monitoring device is as follows: By substituting the monitoring equipment performance evaluation value zcp and the picture quality evaluation value tz into the preset model The monitoring equipment operation parameter zyc is obtained, where z1 and z2 are the monitoring equipment operation proportional factors.

[0011] Compared with the prior art, the present invention has the following beneficial effects: 1. In the event of a damaged monitoring device, the highest-quality monitoring device in the nearby monitoring area where the monitoring device is damaged is temporarily called upon for emergency monitoring. At the same time, vehicles and on-duty personnel in the monitoring area where the monitoring device is damaged are called upon for auxiliary monitoring to ensure that the smart community can be warned, prompted and recorded even when the monitoring device is damaged.

[0012] 2. The intelligent parameter value is obtained by analyzing the temperature and response time of the monitoring equipment during operation. The performance evaluation value of the monitoring equipment is obtained by analyzing the intelligent parameter value. The operating parameters of the monitoring equipment are obtained by analyzing the performance evaluation value and the image quality evaluation value of the monitoring equipment. Compared with manual detection of the operating performance of the monitoring equipment, the accuracy of the detection of the monitoring equipment is greatly increased by evaluating the operating parameters of the monitoring equipment and the quality of the picture shooting. At the same time, the operating performance of the monitoring equipment can be detected in time to avoid the increasing damage to the monitoring equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0014] Figure 1 It is a principle block diagram of the present invention; Figure 2 It is a line graph of the change of the intelligent parameter influence value of the present invention. DETAILED DESCRIPTION

[0015] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0016] Embodiment 1

[0017] See also Figure 1-Figure 2 As shown in the figure, the remote monitoring and early warning system based on the smart community includes an equipment detection module, an analysis module, a cloud service platform and a terminal module.

[0018] The device detection module obtains the operating parameters of the monitoring equipment in the smart community to evaluate whether the monitoring equipment can continue to work. The operating parameters of the monitoring equipment include the temperature, response time and monitoring image quality of the monitoring equipment during operation, specifically: By evenly distributing detection points on the monitoring equipment in the smart community, the thermal imaging images of each detection point corresponding to the operation of the monitoring equipment in the smart community are collected, and the temperature chromaticity corresponding to each detection point is extracted from the thermal imaging image of each detection point. Based on the temperature chromaticity corresponding to each detection point, it is matched with the preset reference chromaticity threshold of the thermal imaging image corresponding to the high temperature. If the match is successful, it will be recorded as a high temperature point, and the number of high temperature points is counted and summed to obtain the total high temperature value when the monitoring equipment in the smart community is running, which is marked as the smart temperature value zsw; By detecting the response time of the monitoring equipment in the smart community, multiple detection cycles are set, each detection cycle includes ten detection operations, and the interval time from the input command to the response command of the monitoring equipment in the smart community in each detection operation is obtained. By summing the interval time of the ten detection operations corresponding to each detection cycle and taking the average, the average interval time from the input command to the response command of the monitoring equipment in the smart community corresponding to each detection cycle is obtained, which is marked as the smart device average time. By subtracting the smart device average time corresponding to each detection cycle from the preset reference time, if the smart device average time is less than or equal to the preset reference time, the detection cycle corresponding to the smart device average time is marked as a qualified detection cycle, and if the smart device average time is greater than the preset reference time, the detection cycle corresponding to the smart device average time is marked as an unqualified detection cycle, the number of unqualified detection cycles is extracted and divided by the total number of detection cycles to obtain the unqualified rate of the response time of the monitoring equipment in the smart community, and marked as the smart device abnormality rate zsl; By substituting the intelligent temperature difference value zsw and the intelligent temperature difference rate zsl into the formula The performance parameter values ​​of the monitoring equipment in the smart community are obtained and marked as the smart parameter value zc, where a1 and a2 are preset proportional factors, the formula is a weighted formula customized by the technician, and the sizes of a1 and a2 are customized settings, for example, the values ​​are 0.65 and 0.35 respectively.

[0019] Set a number of detection time periods, each detection time period corresponds to a detection duration, wherein the detection duration corresponding to each detection time period is the same, obtain the intelligence parameter value corresponding to each detection moment in the detection duration, obtain the fluctuation of the intelligence parameter value in the detection duration corresponding to each detection time period, obtain the maximum value of the intelligence parameter value in the fluctuation of the intelligence parameter value in the detection duration corresponding to each detection time period, and obtain the standard deviation of the intelligence parameter value in the fluctuation of the intelligence parameter value in the detection duration corresponding to each detection time period, mark the maximum value of the intelligence parameter value corresponding to each detection time period as D, mark the standard deviation of the intelligence parameter value as B, assign a weight of H1 to the maximum value D of the intelligence parameter value corresponding to each detection time period, assign a weight of H2 to the standard deviation B of the intelligence parameter value, wherein H2>H1, and obtain the intelligence parameter influence value of each detection time period by normalizing and weighting the maximum value D of the intelligence parameter value corresponding to each detection time period and the standard deviation B of the intelligence parameter value; Preset blank line chart, see Figure 2As shown, the horizontal axis is the detection period, the vertical axis is the intelligence parameter influence value, the intelligence parameter influence values ​​corresponding to adjacent detection periods are connected to obtain the intelligence parameter influence value change line, the intelligence parameter influence threshold line is preset, the area where the intelligence parameter influence value change line exceeds the intelligence parameter influence threshold line is extracted, marked as the intelligence surpassing area, and the interval time between adjacent intelligence surpassing areas is extracted, marked as the threshold interval time, the sum of all the intelligence surpassing areas is counted to obtain the total intelligence surpassing product zcj, and at the same time, all the threshold interval time lengths are extracted and divided by the number of threshold interval time lengths to obtain the threshold interval average length yjc, by substituting the total intelligence surpassing product zcj and the threshold interval average length yjc into the formula The monitoring equipment performance evaluation value zcp is obtained, where d1 and d2 are preset weight factors, △zcp is the reference value for the performance evaluation of monitoring equipment in the smart community, and the smaller the monitoring equipment performance evaluation value zcp is, the better the operating performance of the monitoring equipment in the smart community is, and vice versa, the larger the value is, the worse the operating performance is; wherein, the formula and weight factors are custom settings, such as d1 and d2 are 0.6 and 0.4 respectively.

[0020] The pictures taken by the monitoring equipment in the smart community are analyzed to obtain the picture quality evaluation values, as follows: By installing reference objects at different distances within the monitoring area of ​​the monitoring device, each reference object is provided with a number of identification points; The image containing the reference object is extracted from the captured picture and marked as the reference object image. The number of reference object identification points shot is obtained by enlarging the reference object image and identifying the number of identification points of the farthest reference object in the reference object image. The actual number of identification points in the corresponding reference object is extracted from the cloud service platform. The difference number pcs is obtained by subtracting the actual number of corresponding reference object identification points from the number of reference object identification points shot.

[0021] The reference image is divided into several recognition areas according to the distribution of recognition points, and the contours of the corresponding recognition points in the recognition areas are recognized and the area of ​​the contours is calculated to obtain the contour shooting area of ​​the corresponding recognition points in the recognition areas. At the same time, the preset contour area of ​​the corresponding recognition points is extracted from the cloud service platform. The contour deviation area of ​​the recognition points corresponding to the recognition areas is obtained by subtracting the preset contour area of ​​the recognition points corresponding to the recognition areas from the contour shooting area of ​​the recognition points. The deviation areas of the recognition points corresponding to all recognition areas are counted and summed to obtain the total deviation product pcz.

[0022] The monitoring device is used to photograph the persons in the monitoring area to obtain the person images, and the person images are identified. The person images that can capture the center of the eyebrows of the face are recorded as pre-check images. The person in the pre-check image uses the center of the eyebrows of the face as a reference point and makes a horizontal plane parallel to the face, which is recorded as a pre-check plane. The center of the eyebrows of the face and the monitoring device are used as two reference points to connect the lines, which are recorded as detection lines. The angle between the detection lines and the projections of the detection lines on the detection plane is measured. The angle between the detection lines and the projections of the detection lines on the detection plane is matched with the preset angle interval between the face and the camera. If the match is successful, the person in the pre-check image is marked as a person facing the camera. Extract the facial contour image of the person facing the camera in the pre-inspection image and mark it as the detection image. Collect the number of people in the detection image and record it as the detection number. Match the facial contour features of the people in the detection image with the people stored in the cloud service platform, where the facial contour features of the people include eyes, nose, and mouth. Mark the successfully matched people as recognized people, and mark the unmatched people as unrecognizable people. Count the number of unrecognizable people and divide it by the detection number to get the proportion of unrecognizable people, which is marked as the detection error ratio jcb.

[0023] By substituting the number of poor evaluations pcs, the total deviation product pcz, and the error detection ratio jcb into the preset model The image quality evaluation value tz is obtained, where p1, p2, and p3 are preset weight factors, and their sizes are custom settings. For example, the values ​​of p1, p2, and p3 are 0.3, 0.4, and 0.4, respectively. △s, △z, and △s are the preset reference evaluation difference number, total deviation product, and error detection ratio, respectively. The preset model is constructed by the technicians based on their accumulated experience. It should be noted that, the larger the image quality evaluation value tz is, the lower the clarity and accuracy of the image is, and thus the worse the quality of the image is.

[0024] By substituting the monitoring equipment performance evaluation value zcp and the picture quality evaluation value tz into the preset model Get the monitoring equipment operation parameter zyc, where z1 and z2 are the monitoring equipment operation scale factors, and the values ​​of z1 and z2 can be 2.5 and 2.7, respectively, which are customized according to actual use; It should be noted that, the larger the monitoring device operation parameter zyc is, the worse the operation quality of the monitoring device is and the greater the loss is.

[0025] The analysis module compares the monitoring device operation parameter zyc with the preset monitoring device damage threshold interval. If the monitoring device operation parameter zyc is greater than the maximum value in the preset monitoring device damage threshold interval, the monitoring device is marked as a monitoring interruption device, where the monitoring interruption device indicates that the monitoring device cannot perform monitoring work. If the monitoring device operation parameter zyc belongs to the preset monitoring device damage threshold interval, the monitoring device is marked as a faulty device, where the faulty device indicates that the monitoring device can still work, but the operating function is reduced. If the monitoring device operation parameter zyc is less than the minimum value in the preset monitoring device damage threshold interval, the monitoring device is marked as a normal monitoring device. When the monitoring device is a monitoring interruption device or a faulty device, the cloud service platform generates a corresponding warning signal and sends it to the terminal module. The terminal module dispatches maintenance personnel for maintenance and implements the corresponding level of warning plan at the same time. If the monitoring device is a monitoring interruption device, a first-level warning plan is implemented; if the monitoring device is a faulty device, a second-level warning plan is implemented.

[0026] Get the monitoring area of ​​the interrupted or faulty device, mark it as the detection area, and make corresponding prediction plans, specifically: Level 1 early warning plan; The first step of the execution process is Get all the monitoring equipment information in the smart community, connect the midpoint of the detection area with the monitoring equipment in the smart community, extract the connection length, preset the standard monitoring distance, compare the connection length between the midpoint of the detection area and the corresponding monitoring equipment with the preset standard monitoring distance, extract the monitoring equipment whose connection length between the midpoint of the detection area and the corresponding monitoring equipment is less than the preset standard monitoring distance, and mark it as a preliminary monitoring equipment, obtain the monitoring area js of the preliminary monitoring equipment for the detection area, and the image quality evaluation value tz of the detection area, and wait for it to be entered into the formula , get the pre-inspection value of the pre-monitoring equipment for the detection area, y1 and y2 are the preset weight ratios, and the values ​​are 0.54 and 0.46 respectively. The larger the pre-inspection value, the higher the detection quality of the pre-monitoring equipment for the detection area. The pre-inspection values ​​of all pre-monitoring equipment are compared, and the pre-monitoring equipment with the largest pre-inspection value is extracted as the emergency monitoring equipment for the detection area.

[0027] The second step of the execution process is By making the emergency monitoring equipment monitor and cover the detection area, extract the area that the emergency monitoring equipment cannot monitor and cover the detection area, and mark it as the area to be inspected, by dividing the area to be inspected into several sub-areas to be inspected, and numbering them, and detecting whether there are vehicles in the sub-areas to be inspected; If yes, obtain the information of the vehicle in the sub-area to be inspected, and connect the cloud service platform to the vehicle in the sub-area to be inspected through the Internet of Things, and then call the vehicle's driving recorder to monitor the sub-area to be inspected, obtain the monitoring area of ​​the corresponding vehicle in the sub-area to be inspected, extract the vehicle with the widest coverage of the sub-area to be inspected in the monitoring area of ​​the corresponding vehicle in the sub-area to be inspected, as the marked vehicle, and match the monitoring area of ​​the sub-area to be inspected with the corresponding sub-area to be inspected by the marked vehicle. If there is a complete match, the sub-area to be inspected is recorded as a matching sub-area, and the sub-area to be inspected is monitored by the marked vehicle. If there is an incomplete match, extract the area where the monitoring area of ​​the sub-area to be inspected by the marked vehicle does not match the corresponding sub-area to be inspected, and mark it as a blind sub-area. At this time, it is determined whether there are monitoring areas of other vehicles in the sub-area to be inspected that can cover the blind inspection sub-area. If so, the sub-area to be inspected is monitored by multiple vehicles in the sub-area to be inspected. If not, the area of ​​the blind inspection sub-area is calculated, and a monitoring level is preset. Each monitoring level corresponds to a monitoring area threshold interval. The monitoring level corresponding to the blind inspection sub-area is obtained by comparing the area of ​​the blind inspection sub-area with the monitoring area threshold interval corresponding to the preset monitoring level, and a monitoring level instruction is generated. The monitoring level instruction and the number of the sub-area to be inspected corresponding to the blind inspection sub-area are sent to the terminal module. The terminal module dispatches the number of on-duty personnel according to the monitoring level, and stands guard in the blind inspection sub-area corresponding to the sub-area to be inspected with the corresponding number. If there is no vehicle in the sub-area to be inspected, the monitoring area of ​​the sub-area to be inspected is extracted and compared with the preset monitoring level to obtain the corresponding monitoring level of the sub-area to be inspected, and a monitoring level instruction is generated. The monitoring level instruction and the number corresponding to the sub-area to be inspected are sent to the terminal module. The terminal module dispatches the number of on-duty personnel according to the monitoring level, and they stand guard and perform duty in the sub-area to be inspected with the corresponding number.

[0028] The second-level warning plan does not need to call emergency monitoring equipment to monitor and cover the detection area. That is, at this time, the detection area is monitored and covered by the faulty equipment, and the same steps as the second step of the first-level warning plan execution process are performed.

[0029] It should be noted that in the scenario where the monitoring equipment is damaged, the monitoring equipment with the highest monitoring quality in the nearby monitoring area where the monitoring equipment is damaged is temporarily called upon for emergency monitoring. At the same time, vehicles and on-duty personnel in the monitoring area where the monitoring equipment is damaged are called upon for auxiliary monitoring to ensure that the smart community can provide early warnings, prompts and records even when the monitoring equipment is damaged.

[0030] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. Remote monitoring and early warning system based on smart community, including cloud service platform and analysis module; The analysis module compares the operating parameters of the monitoring device with the preset monitoring device damage threshold interval, determines whether the monitoring device is a monitoring interruption device or a faulty device, and at the same time, the cloud service platform generates a corresponding warning signal and sends it to the terminal module; it is characterized in that: It also includes a terminal module; the terminal module dispatches maintenance personnel to perform maintenance based on the received warning signal, and generates a warning plan of corresponding level for the monitoring interruption device or faulty device according to the monitoring device, and the warning plan includes a first-level warning plan and a second-level warning plan; if the monitoring device executes the first-level warning plan for the monitoring interruption device, specifically: The first step of the execution process: obtain all the monitoring equipment information in the smart community, connect the midpoint of the detection area with the monitoring equipment in the smart community, extract the connection length, preset the standard monitoring distance, compare the connection length between the midpoint of the detection area and the corresponding monitoring equipment with the preset standard monitoring distance, extract the monitoring equipment whose connection length between the midpoint of the detection area and the corresponding monitoring equipment is less than the preset standard monitoring distance, and mark it as a reserve monitoring equipment, obtain the monitoring area of ​​the detection area by the reserve monitoring equipment, and the image quality evaluation value of the detection area, and perform normalized weighted processing to obtain the pre-inspection value of the reserve monitoring equipment for the detection area, compare the pre-inspection values ​​of all reserve monitoring equipment, and extract the reserve monitoring equipment with the largest pre-inspection value as the emergency monitoring equipment for the detection area; The second step of the execution process: by making the emergency monitoring equipment monitor and cover the detection area, extract the area that the emergency monitoring equipment cannot monitor and cover the detection area, and mark it as the area to be inspected, by dividing the area to be inspected into several sub-areas to be inspected, and numbering them, and detecting whether there are vehicles in the sub-areas to be inspected; If yes, obtain the information of the vehicle in the sub-area to be inspected, and connect the cloud service platform to the vehicle in the sub-area to be inspected through the Internet of Things, and then call the vehicle's driving recorder to monitor the sub-area to be inspected, obtain the monitoring area of ​​the corresponding vehicle in the sub-area to be inspected, extract the vehicle with the widest coverage of the sub-area to be inspected in the monitoring area of ​​the corresponding vehicle in the sub-area to be inspected, as the marked vehicle, and match the monitoring area of ​​the sub-area to be inspected with the corresponding sub-area to be inspected by the marked vehicle. If there is a complete match, the sub-area to be inspected is recorded as a matching sub-area, and the sub-area to be inspected is monitored by the marked vehicle. If there is an incomplete match, extract the area where the monitoring area of ​​the sub-area to be inspected by the marked vehicle does not match the corresponding sub-area to be inspected, and mark it as a blind sub-area. At this time, determine whether there are other vehicles' monitoring areas in the sub-area to be inspected that can cover the blind inspection sub-area. If so, the sub-area to be inspected is monitored by multiple vehicles in the sub-area to be inspected. If not, the area of ​​the blind inspection sub-area is calculated and a monitoring level is preset. Each monitoring level corresponds to a monitoring area threshold interval. The monitoring level corresponding to the blind inspection sub-area is obtained by comparing the area of ​​the blind inspection sub-area with the monitoring area threshold interval corresponding to the preset monitoring level, and a monitoring level instruction is generated. The monitoring level instruction and the number of the sub-area to be inspected corresponding to the blind inspection sub-area are sent to the terminal module. The terminal module dispatches the number of on-duty personnel according to the monitoring level, and they stand guard in the blind inspection sub-area corresponding to the sub-area to be inspected with the corresponding number.

2. According to claim 1, the remote monitoring and early warning system based on smart community is characterized in that: The analysis process of the analysis module is specifically as follows: If the operating parameters of the monitoring device are greater than the maximum value in the preset monitoring device damage threshold interval, the monitoring device is marked as a monitoring interruption device; if the operating parameters of the monitoring device belong to the preset monitoring device damage threshold interval, the monitoring device is marked as a faulty device; if the operating parameters of the monitoring device are less than the minimum value in the preset monitoring device damage threshold interval, the monitoring device is marked as a normal monitoring device.

3. According to claim 1, the remote monitoring and early warning system based on smart community is characterized in that: It also includes a device detection module; the device detection module obtains the operating parameters of the monitoring equipment in the smart community, the operating parameters of the monitoring equipment include the temperature, response time and image quality evaluation value of the monitoring equipment during operation, and obtains the intelligent parameter value by analyzing the temperature and response time of the monitoring equipment during operation, obtains the monitoring equipment performance evaluation value by analyzing the intelligent parameter value, and obtains the operating parameters of the internal monitoring equipment by analyzing the monitoring equipment performance evaluation value and the image quality evaluation value; the specific process of obtaining the intelligent parameter value by analyzing the temperature and response time of the monitoring equipment during operation is as follows: By evenly distributing detection points on the monitoring equipment in the smart community, the thermal imaging images of each detection point corresponding to the operation of the monitoring equipment in the smart community are collected, and the temperature chromaticity corresponding to each detection point is extracted from the thermal imaging image of each detection point. Based on the temperature chromaticity corresponding to each detection point, it is matched with the preset reference chromaticity threshold of the thermal imaging image corresponding to the high temperature. If the match is successful, it will be recorded as a high temperature point, and the number of high temperature points is counted and summed to obtain the total high temperature value when the monitoring equipment in the smart community is running, which is marked as the smart temperature value; By detecting the response time of the monitoring equipment in the smart community, multiple detection cycles are set, each detection cycle includes ten detection operations, and the interval time from the input instruction to the response instruction of the monitoring equipment in the smart community in each detection operation is obtained. By summing the interval time of the ten detection operations corresponding to each detection cycle and taking the average, the average interval time from the input instruction to the response instruction of the monitoring equipment in the smart community corresponding to each detection cycle is obtained, which is marked as the smart device average time. By subtracting the smart device average time corresponding to each detection cycle from the preset reference time, if the smart device average time is less than or equal to the preset reference time, the detection cycle corresponding to the smart device average time is marked as a qualified detection cycle, if the smart device average time is greater than the preset reference time, the detection cycle corresponding to the smart device average time is marked as an unqualified detection cycle, the number of unqualified detection cycles is extracted and divided by the total number of detection cycles to obtain the unqualified rate of the response time of the monitoring equipment in the smart community, and marked as the smart device abnormal rate; the smart device abnormal temperature value and the smart device abnormal rate are comprehensively analyzed to obtain the smart parameter value.

4. According to claim 3, the remote monitoring and early warning system based on smart community is characterized in that: The specific process of obtaining the monitoring equipment performance evaluation value by analyzing the intelligent parameter value is as follows: Set a number of detection time periods, each detection time period corresponds to a detection duration, wherein the detection duration corresponding to each detection time period is the same, obtain the intelligence parameter value corresponding to each detection moment in the detection duration, obtain the fluctuation of the intelligence parameter value in the detection duration corresponding to each detection time period, obtain the maximum value of the intelligence parameter value in the fluctuation of the intelligence parameter value in the detection duration corresponding to each detection time period, and obtain the standard deviation of the intelligence parameter value in the fluctuation of the intelligence parameter value in the detection duration corresponding to each detection time period, perform normalized weighted processing on the maximum value of the intelligence parameter value and the standard deviation of the intelligence parameter value corresponding to each detection time period, and obtain the intelligence parameter influence value of each detection time period; A blank line graph is preset, with the horizontal axis being the detection period and the vertical axis being the intelligent parameter influence value. The intelligent parameter influence values ​​corresponding to adjacent detection periods are connected to obtain an intelligent parameter influence value change line. An intelligent parameter influence threshold line is preset, and the area where the intelligent parameter influence value change line exceeds the intelligent parameter influence threshold line is extracted, marked as the intelligent exceeding area, and the interval duration between adjacent intelligent exceeding areas is extracted, marked as the inter-threshold duration. The sum of all the intelligent exceeding areas is counted to obtain the intelligent exceeding total product. At the same time, all the inter-threshold durations are extracted and divided by the number of inter-threshold durations to obtain the inter-threshold average length. The intelligent exceeding total product and the inter-threshold average length are analyzed to obtain the performance evaluation value of the monitoring equipment.

5. The remote monitoring and early warning system based on smart community according to claim 4 is characterized in that: The specific process of analyzing the image quality evaluation value is as follows: By installing reference objects at different distances within the monitoring area of ​​the monitoring device, each reference object is provided with a number of identification points; Extract the image containing the reference object in the captured picture and mark it as the reference object image. By enlarging the reference object image and identifying the number of identification points of the farthest reference object in the reference object image, the number of shots of the reference object identification points is obtained. The actual number of identification points in the corresponding reference object is extracted from the cloud service platform. The difference between the actual number of the corresponding reference object identification points and the number of shots of the reference object identification points is obtained to obtain the number of differences pcs. The reference image is divided into several recognition areas according to the distribution of recognition points, and the contours of the corresponding recognition points in the recognition areas are recognized, and the area of ​​the contours is calculated to obtain the contour shooting area of ​​the corresponding recognition points in the recognition areas. At the same time, the preset contour area of ​​the corresponding recognition points is extracted from the cloud service platform, and the preset contour area of ​​the recognition points corresponding to the recognition areas is subtracted from the contour shooting area of ​​the recognition points to obtain the contour deviation area of ​​the recognition points corresponding to the recognition areas. The deviation areas of the recognition points corresponding to all the recognition areas are summed up to obtain the total deviation product; The monitoring device is used to photograph the persons in the monitoring area to obtain the person images, and the person images are identified. The person images that can capture the center of the eyebrows of the face are recorded as pre-check images. The person in the pre-check image uses the center of the eyebrows of the face as a reference point and makes a horizontal plane parallel to the face, which is recorded as a pre-check plane. The center of the eyebrows of the face and the monitoring device are used as two reference points to connect the lines, which are recorded as detection lines. The angle between the detection lines and the projections of the detection lines on the detection plane is measured. The angle between the detection lines and the projections of the detection lines on the detection plane is matched with the preset angle interval between the face and the camera. If the match is successful, the person in the pre-check image is marked as a person facing the camera. Extract the facial contour image of the person facing the camera in the pre-check image and mark it as the detection image. Collect the number of people in the detection image and record it as the detection number. Match the facial contour features of the person in the detection image with the people stored in the cloud service platform, where the facial contour features of the person include eyes, nose, and mouth. Mark the successfully matched person as the recognized person and the unmatched person as the unrecognizable person. Count the number of unrecognizable persons and divide it by the detection number to get the proportion of unrecognizable persons and mark it as the error detection ratio. The image quality evaluation value is obtained by analyzing the number of poor ratings, total deviation product and error detection ratio.

6. The remote monitoring and early warning system based on smart community according to claim 5 is characterized in that: The operating parameter analysis process of the monitoring device is as follows: analyzing the performance evaluation value of the monitoring device and the image quality evaluation value to obtain the operating parameters of the monitoring device.

Images