Intelligent campus environment parameter comprehensive sensing method based on AIOT

Abstract

The invention relates to the technical field of video engines, in particular to a smart campus environment parameter comprehensive sensing method based on AIOT, and the method comprises the steps: obtaining the network bandwidth and alarm identification of each monitoring probe in a smart campus system at each moment, and the position coordinate and historical alarm vector of each monitoring probe, acquiring the actual cache length of each monitoring probe in real time through a video engine; obtaining an alarm association degree between each monitoring probe and other monitoring probes; calculating the query emergency degree of each monitoring probe at the current moment; determining the cache emergency degree of each monitoring probe at the current moment; determining the video cache length of each monitoring probe at the current moment; and comparing the actual cache length with the video cache length, and adjusting the video transmission code rates of different monitoring probes in real time. According to the method and the device, when different monitoring probes are called, sufficient video cache data are ensured to provide smooth videos for managers.

Description

Technical Field

[0001] The present application relates to the field of video engine technology, and specifically to a comprehensive perception method of smart campus environmental parameters based on AIOT. Background Art

[0002] In the smart campus system, a large number of video surveillance devices are deployed to collect campus surveillance data to achieve a comprehensive perception of the campus environment. These data are not only used for monitoring, but also can be used to identify potential dangerous situations and issue alarms in time through AI technology to assist campus safety management. After the AI ​​alarm is triggered, the manager needs to review the alarm to confirm whether it is a false alarm and formulate corresponding response strategies accordingly. In this process, it is crucial to provide managers with smooth video services so that they can view monitoring information in real time and make accurate judgments and responses. Due to the huge amount of video data involved in the smart campus system, video information is usually stored in the local storage of the video surveillance device and is called by the video engine of the smart campus system to provide online video services. This service requires adaptive bit rate adjustment according to the network status to ensure the smoothness of video playback.

[0003] However, when the network conditions are poor and managers need to switch multiple surveillance probes to determine the alarm situation in an area, the lack of an effective video caching mechanism causes video freezes when managers switch surveillance probes, resulting in poor robustness of the video engine. Summary of the invention

[0004] In order to solve the above technical problems, a comprehensive perception method of smart campus environmental parameters based on AIOT is provided to solve the existing problems.

[0005] The solution to the technical problem in this application is to provide a comprehensive perception method of smart campus environmental parameters based on AIOT, including the following steps:

[0006] Obtain the network bandwidth of each monitoring probe in the smart campus system at each time, as well as the location coordinates of each monitoring probe, and obtain the actual cache length of each monitoring probe in real time through the video engine;

[0007] Perform abnormal identification on the video information of each monitoring probe at each time, determine the alarm state of each monitoring probe at each time, and obtain the alarm identification of each monitoring probe at each time; based on the alarm situation of each monitoring probe in the historical period, obtain the historical alarm vector of each monitoring probe;

[0008] Obtaining the alarm correlation between each monitoring probe and the other monitoring probes through the spatial distance between each monitoring probe and the other monitoring probes and the similarity of the historical alarm vectors;

[0009] Using the alarm correlation, weight the average level of alarm identification of each monitoring probe at different times before the current time, and calculate the query urgency of each monitoring probe at the current time;

[0010] Analyze the average level of network bandwidth of each monitoring probe at different times before the current time, and determine the cache urgency of each monitoring probe at the current time in combination with the query urgency;

[0011] Based on the cache urgency, the video cache length of each monitoring probe at the current moment is determined; the actual cache length and the video cache length are compared, and the video transmission bit rates of different monitoring probes are adjusted in real time.

[0012] Preferably, the determining the alarm state of each monitoring probe at each moment and obtaining the alarm identification of each monitoring probe at each moment includes:

[0013] If there is an abnormality in the video information of each monitoring probe at each moment, the monitoring probe will immediately trigger an alarm. If each monitoring probe is in an alarm state at each moment, the alarm mark is 1, otherwise, the alarm mark is 0.

[0014] Preferably, the method for obtaining the historical alarm vector is:

[0015] The number of times the alarm identification of each monitoring probe is 1 in each time period is counted and recorded as the number of alarms; the number of alarms of each monitoring probe in multiple time periods is combined to form a historical alarm vector of each monitoring probe.

[0016] Preferably, the spatial distance is the Euclidean distance between the position coordinates of each monitoring probe and the remaining monitoring probes.

[0017] Preferably, the degree of similarity is the inverse of the Euclidean distance between the historical alarm vectors of each monitoring probe and the remaining monitoring probes.

[0018] Preferably, the alarm correlation degree is a ratio of the similarity degree to the spatial distance.

[0019] Preferably, the calculating of the query urgency of each monitoring probe at the current moment includes:

[0020] Normalizing the alarm correlation between each monitoring probe and all other monitoring probes, and using the normalized result as the alarm impact weight of each monitoring probe and the other monitoring probes;

[0021] The average value of the alarm identification of each monitoring probe at multiple moments before the current moment is used as the alarm value of each monitoring probe at the current moment;

[0022] Based on the alarm impact weight of each monitoring probe and the other monitoring probes, the alarm values ​​of the other monitoring probes at the current moment are weighted summed up, and the sum of the weighted summation result and the alarm value of each monitoring probe at the current moment is used as the query urgency of each monitoring probe at the current moment.

[0023] Preferably, determining the cache urgency of each monitoring probe at the current moment includes:

[0024] The average of the network bandwidth of each monitoring probe at multiple times before the current moment is used as the bandwidth characteristic value of each monitoring probe at the current moment;

[0025] The ratio of the query urgency to the bandwidth characteristic value is used as the cache urgency of each monitoring probe at the current moment.

[0026] Preferably, the determining of the video cache length of each monitoring probe at the current moment includes:

[0027] Normalize the cache urgency of all monitoring probes at the current moment, and use the normalized value as the cache weight of each monitoring probe at the current moment;

[0028] A video cache space of a preset duration is allocated to each monitoring probe; and the product of the cache weight and the preset duration is used as the video cache length of each monitoring probe at the current moment.

[0029] Preferably, the real-time adjustment of the video transmission bit rates of different monitoring probes includes:

[0030] For the video information corresponding to the monitoring probe whose actual cache length is smaller than the video cache length, the preset minimum transmission bit rate is used for compression transmission; otherwise, the preset maximum transmission bit rate is used for compression transmission.

[0031] This application has at least the following beneficial effects:

[0032] The present application calculates the alarm correlation, and its beneficial effect is that it takes into account the location distribution of different monitoring probes and the similarity of alarm information occurring in the historical period, reflects whether the monitoring areas between different monitoring probes are directly connected, and indicates the possibility of monitoring probes with connected monitoring areas being continuously called; calculates the query urgency of each monitoring probe at the current moment, and its beneficial effect is that it takes into account the situation that each monitoring probe may be called by video after an alarm occurs, and screens out monitoring probes that are easily called for query due to alarms, so that the subsequent video engine gives priority to video caching for these monitoring probes; determines the cache urgency of each monitoring probe at the current moment, and determines the video cache length of each monitoring probe at the current moment; compares the actual cache length with the video cache length, and adjusts the video transmission bit rate of different monitoring probes in real time, and its beneficial effect is that it takes into account the network status of the monitoring probe, and then allocates more video cache space to the monitoring probes that are more likely to be called and have worse network status, to ensure that different monitoring probes have sufficient video cache data when they are called to provide smooth video for management personnel, and adjusts the video transmission bit rate in real time according to the network status, avoiding the video freeze phenomenon caused by poor network status and uneven distribution of video cache resources in traditional video engines. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The following is a further detailed description of a comprehensive perception method of smart campus environmental parameters based on AIOT in this application in conjunction with the accompanying drawings.

[0034] Figure 1 A flowchart of a method for comprehensively perceiving environmental parameters of a smart campus based on AIOT provided in an embodiment of the present application;

[0035] Figure 2 A flowchart of the steps of a method for obtaining a video cache length provided in an embodiment of the present application. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solutions and advantages of this application more clear, the following is a further detailed description of a comprehensive perception method of smart campus environmental parameters based on AIOT proposed in this application in combination with the accompanying drawings and implementation examples. It should be understood that the specific embodiments described here are only used to explain this application and are not used to limit this application.

[0037] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0038] See also Figure 1 , which shows a flowchart of a method for comprehensive perception of smart campus environmental parameters based on AIOT provided by an embodiment of the present application, the method comprising the following steps:

[0039] Step 1: Obtain the network bandwidth, alarm identification, location coordinates and historical alarm vector of each monitoring probe in the smart campus system at each time, and obtain the actual cache length of each monitoring probe in real time through the video engine.

[0040] In the smart campus system, a comprehensive perception of the campus environment is achieved by deploying multiple monitoring probes, where each monitoring probe stores real-time monitoring video information in the IOT device, where each monitoring probe corresponds to an IOT device. The IOT device, i.e., the local system, is responsible for storing the video information of the corresponding monitoring probe, identifying the monitoring video information in the IOT device, and issuing an alarm for dangerous situations. Secondly, the smart campus system stores the geographic location information of each monitoring probe, as well as the monitoring video information of alarms at historical moments, so that management personnel can view them in real time.

[0041] When the smart campus system sounds an alarm, managers can view surveillance information by continuously switching surveillance probes. However, due to poor network conditions, the video cache mechanism will not be smooth, and video freezes may occur when managers switch surveillance probes to view surveillance videos.

[0042] Based on the above analysis, the network bandwidth of N monitoring probes at each moment is obtained in real time through the network traffic monitoring tool, and the video information monitored by each monitoring probe in real time is identified. Once an abnormal situation is detected, the monitoring probe immediately triggers an alarm and generates and stores alarm information. If each monitoring probe is in an alarm state at each moment, the alarm mark is 1, and if each monitoring probe is in a non-alarm state at each moment, the alarm mark is 0;

[0043] It should be noted that the method of identifying anomalies in video information is a well-known technology and will not be described in detail here.

[0044] In this embodiment, data is recorded once every 1 second. As other implementation methods, the implementer can set it according to the actual situation. Secondly, the network bandwidth indicates the network status and reflects the data transmission efficiency and capacity of the network. Secondly, there are 30 monitoring probes in the smart campus system. As other implementation methods, the implementer can set it according to the actual situation.

[0045] Secondly, the location coordinates of each monitoring probe are obtained, where the location coordinates are a coordinate point in a three-dimensional space, reflecting the coordinate position of the monitoring probe in the smart campus system.

[0046] Further, according to the stored alarm information, the number of times the alarm identification is 1 for each monitoring probe in each time period is counted, and recorded as the number of alarms; the number of alarms of each monitoring probe in multiple time periods is combined to form a historical alarm vector of each monitoring probe;

[0047] In this embodiment, the number of alarm flags of 1 for each monitoring probe in every minute is counted, that is, the number of seconds in every minute that the probe is in an alarm state; secondly, the length of the historical alarm vector is 14400, corresponding to the alarm information of the past 10 days. When the alarm information is less than 10 days, the corresponding historical alarm vector length is less than 14400. At this time, the historical alarm vector is filled with element value 0.

[0048] The actual cache length of each monitoring probe at the current moment is obtained through the API (Application Programming Interface) provided by the video engine in the smart campus system.

[0049] At this point, the network bandwidth and alarm identification of each monitoring probe at each time, as well as the location coordinates and historical alarm vector of each monitoring probe are obtained, and the actual cache length of each monitoring probe at the current time is obtained.

[0050] Step 2: Obtain the alarm correlation between each monitoring probe and the other monitoring probes through the spatial distance between each monitoring probe and the other monitoring probes and the similarity of the historical alarm vectors.

[0051] During the monitoring process of the entire campus, the alarm conditions of the surveillance probes usually have obvious correlation characteristics, mainly because the monitoring areas between the surveillance probes are directly connected, or even overlap. When campus managers use the video engine of the smart campus system to verify the alarm, they usually send video acquisition requests to other surveillance probes that have alarms and are connected to the same area in space, in addition to requesting to obtain the surveillance video of the alarming surveillance probe. This allows them to judge the alarm situation from multiple angles and form a comprehensive perception of the campus environment.

[0052] Therefore, the more obvious the correlation characteristics of the alarm conditions of the two surveillance probes are, the more likely it is that the administrator will continuously request the surveillance probes. When performing online video caching, when the administrator calls up the video of one of the surveillance probes, the video of the other surveillance probe can be cached synchronously to reduce the lag when switching videos.

[0053] Based on the above analysis, the alarm correlation is determined by the location distribution of different monitoring probes and the alarm identification to reflect the alarm correlation between monitoring probes, including:

[0054] Calculate the spatial distance between the position coordinates of each monitoring probe and the other monitoring probes;

[0055] In this embodiment, the Euclidean distance between the position coordinates of each monitoring probe and the other monitoring probes is calculated, wherein the calculation of the Euclidean distance is a well-known technique and will not be described in detail herein.

[0056] The smaller the spatial distance is, the closer the monitoring areas of the two monitoring probes are, and the more likely it is that the two monitoring probes will be called continuously by the management personnel. The spatial distance only considers the positional relationship of the monitoring probes in the three-dimensional space, and does not consider whether the areas monitored by the monitoring probes are connected. If the monitoring areas of the two monitoring probes are very close in space, but not directly connected, and are blocked by walls and other buildings, then the two monitoring probes may not be the two probes that the management personnel call continuously. Therefore, it is necessary to analyze the connectivity of the monitoring areas of the two monitoring probes based on historical alarm information.

[0057] Calculate the similarity between each monitoring probe and the historical alarm vectors of the remaining monitoring probes;

[0058] In this embodiment, the inverse of the Euclidean distance between each monitoring probe and the historical alarm vectors of the remaining monitoring probes is calculated. As other implementation methods, the implementer can adopt other methods of the prior art, such as the inverse of the DTW distance, cosine similarity, etc. This embodiment does not impose any special restrictions on this.

[0059] The ratio of the similarity to the spatial distance is used as the alarm correlation degree between each monitoring probe and the other monitoring probes;

[0060] It should be noted that, the greater the degree of similarity, the more similar the historical alarm information of the two monitoring probes, and the more likely it is that the monitoring areas of the two monitoring probes are directly connected; the greater the alarm correlation, the closer the spatial distance between the two monitoring probes, and the more often the two monitoring probes issue alarms at the same time during the historical monitoring period, the more directly connected and close the monitoring areas of the two monitoring probes are, the more likely the management personnel will continuously call the two monitoring probes for alarm review.

[0061] At this point, the alarm correlation between each monitoring probe and the other monitoring probes is obtained.

[0062] Step 3: using the alarm correlation, weighting the average level of alarm identification of each monitoring probe at different times before the current time, and calculating the query urgency of each monitoring probe at the current time.

[0063] Furthermore, when managers review alarms, they usually give priority to the surveillance probe at the location where the alarm was issued for video calls. Therefore, when the video engine caches the video, it should first select the surveillance probe at the alarm location and the surveillance probes around it for video caching to reduce the lag that occurs when managers switch surveillance probes.

[0064] Based on the above analysis, the query urgency is calculated to reflect the extent to which the surveillance probe may be called by video, so that the video engine prioritizes video caching for the surveillance probes, giving a higher cache length to the surveillance probes at the alarm location and the surrounding locations. The video engine will prioritize caching the surveillance videos of these surveillance probes.

[0065] Normalize the alarm correlation between each monitoring probe and all other monitoring probes, and use the normalized result as the alarm impact weight of each monitoring probe and the other monitoring probes;

[0066] In this embodiment, the normalization method adopted is: calculate the sum of the alarm correlation degrees of each monitoring probe and all other monitoring probes, record it as the first sum, and use the ratio of the alarm correlation degree to the first sum as the alarm impact weight of each monitoring probe and the other monitoring probes.

[0067] It should be noted that the greater the alarm impact weight, the more likely each monitoring probe is to become the next monitoring probe to be called due to the alarms of other monitoring probes.

[0068] The average value of the alarm identification of each monitoring probe at multiple moments before the current moment is used as the alarm value of each monitoring probe at the current moment;

[0069] In this embodiment, the average of the alarm flags of each monitoring probe at all times within 10 minutes before the current moment is used as the alarm value of each monitoring probe at the current moment. As other implementation methods, the implementer can set it according to the actual situation.

[0070] Based on the alarm impact weights of each monitoring probe and the rest of the monitoring probes, weighted sum is performed on the alarm values ​​of the rest of the monitoring probes at the current moment, and the sum of the weighted sum and the alarm value of each monitoring probe at the current moment is used as the query urgency of each monitoring probe at the current moment;

[0071] It should be noted that the weighted summation method is a well-known technique and will not be described in detail here.

[0072] In this embodiment, taking the nth monitoring probe at the current time t as an example, the calculation formula for the query urgency of the nth monitoring probe at the current time t is:

[0073]

[0074] Among them, U n,t is the query urgency of the nth monitoring probe at the current time t, Av n,t is the alarm value of the nth monitoring probe at the current time t, α n,ris the alarm impact weight of the nth monitoring probe and the rth monitoring probe, Av r,t is the alarm value of the rth monitoring probe at the current time t, and N is the number of all monitoring probes.

[0075] It should be noted that the larger the alarm value of the nth surveillance probe, the more serious the alarm situation of the nth surveillance probe itself in the past period of time, the more likely the surveillance video of the nth surveillance probe will be called; the larger the associated alarm value of the nth surveillance probe, the greater the alarm impact weight, the more serious the alarm situation of the surrounding surveillance probes that monitor the same area, the more likely the nth surveillance probe will be called for video; finally, the greater the query urgency, the more likely the nth surveillance probe is to be called for video, and the video engine should give priority to caching the video of the nth surveillance probe.

[0076] It should be noted that, since the values ​​of the alarm identifier are 0 and 1, the alarm value range of the nth monitoring probe is [0,1]; after weighted summation of multiple alarm values, the result range is also [0,1], so the query urgency range is [0,2].

[0077] At this point, the query urgency of each monitoring probe at the current moment is obtained.

[0078] Step 4, analyzing the average level of network bandwidth of each monitoring probe at different times before the current moment, and determining the cache urgency of each monitoring probe at the current moment in combination with the query urgency; determining the video cache length of each monitoring probe at the current moment based on the cache urgency; comparing the actual cache length with the video cache length, and adjusting the video transmission bit rate of different monitoring probes in real time.

[0079] Furthermore, the purpose of video caching in the video engine is to cope with the situation of poor network bandwidth. When the network bandwidth is poor, the video engine needs to increase the video cache length to ensure that the video will not be stuck. Therefore, the network bandwidth status of each monitoring probe is analyzed to adjust the video caching solution of the monitoring probe, specifically:

[0080] The average of the network bandwidth of each monitoring probe at multiple times before the current moment is used as the bandwidth characteristic value of each monitoring probe at the current moment;

[0081] In this embodiment, the average of the network bandwidth of each monitoring probe at all times within 10 minutes before the current moment is used as the bandwidth characteristic value of each monitoring probe at the current moment. As other implementation methods, implementers can set them according to actual conditions.

[0082] It should be noted that the larger the bandwidth characteristic value is, the better the network status of the monitoring probe is in the recent period of time, and the faster the data transmission rate is. When caching the video, a shorter video cache length can be set for it, and the transmission bit rate can be increased to improve the quality of the video cache, so that the video called by the management personnel has a better visual effect.

[0083] Furthermore, different video cache lengths are calculated for different surveillance probes. For surveillance probes that are more easily called and have worse network conditions, a longer video cache length is set to avoid freezes when administrators switch surveillance probes. The video cache length calculation method is:

[0084] The ratio of the query urgency to the bandwidth characteristic value is used as the cache urgency of each monitoring probe at the current moment;

[0085] In this embodiment, when calculating the ratio of the query urgency to the bandwidth characteristic value, in order to avoid the denominator being 0, a preset value greater than 0 is added to the denominator, wherein the preset value greater than 0 is 0.01. As other implementation methods, the implementer can set it according to the actual situation.

[0086] It should be noted that, the greater the query urgency and the smaller the bandwidth characteristic value, the more likely the monitoring probe is to be called, and the worse the network status is, the more the video engine needs to allocate more video cache space to it.

[0087] Further, based on the cache urgency, the video cache length is calculated, specifically:

[0088] Normalize the cache urgency of all monitoring probes at the current moment, and use the normalized value as the cache weight of each monitoring probe at the current moment;

[0089] In this embodiment, the normalization method adopted is: calculating the sum of the cache urgency of all monitoring probes at the current moment, recorded as the second sum, and taking the ratio of the cache urgency to the second sum as the cache weight of each monitoring probe at the current moment.

[0090] Allocate a video cache space of a preset length to each monitoring probe; multiply the cache weight by the preset length as the video cache length of each monitoring probe at the current moment;

[0091] In this embodiment, 10 seconds of video buffer space is allocated to each monitoring probe. As other implementation methods, implementers can set it according to actual conditions.

[0092] It should be noted that the larger the cache weight, the more likely the surveillance video of the corresponding surveillance probe is to be called, and the worse the network environment of the surveillance probe is. Therefore, in order to ensure that the video engine can call the cache data in time and provide smooth video services when the management personnel switch the surveillance probe, a longer video cache length is given to the surveillance probe; the step flow chart of the method for obtaining the video cache length provided in the embodiment of the present application is as follows Figure 2 shown.

[0093] Furthermore, for all surveillance probes, the video buffer length can avoid video freeze when the administrator switches the surveillance probes, so as to meet the video buffer condition of the surveillance probes and adjust the video transmission bit rate, specifically:

[0094] For the video information of the monitoring probe whose actual cache length is less than the video cache length, the preset minimum transmission bit rate is used for compression transmission; for the video information of the monitoring probe whose actual cache length is greater than or equal to the video cache length, the preset maximum transmission bit rate is used for compression transmission;

[0095] In this embodiment, the preset minimum bit rate is 0.5Mdps, and the preset maximum bit rate is 2Mdps. As other implementation methods, the implementer can set them according to actual conditions.

[0096] It should be noted that if the actual cache length is less than the video cache length, it means that the corresponding monitoring probe has problems such as network delay, and the video quality is reduced to ensure smooth video transmission. If the actual cache length is greater than or equal to the video cache length, it means that the network status of the corresponding monitoring probe is good and the data transmission is smooth. By increasing the video transmission bit rate, the video quality is guaranteed under the premise of smooth video.

[0097] It should be noted that adjusting the video transmission bit rate by using the buffer length is a well-known technology in the field of video engines and will not be described in detail here.

[0098] It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0099] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0100] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the present application. It should be pointed out that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present application without departing from the content of the technical solution of the present application, shall fall within the protection scope of the technical solution of the present application.

Claims

1. A comprehensive perception method of smart campus environmental parameters based on AIOT, characterized in that: The method comprises the following steps: Obtain the network bandwidth of each monitoring probe in the smart campus system at each time, as well as the location coordinates of each monitoring probe, and obtain the actual cache length of each monitoring probe in real time through the video engine; Perform abnormal identification on the video information of each monitoring probe at each time, determine the alarm state of each monitoring probe at each time, and obtain the alarm identification of each monitoring probe at each time; based on the alarm situation of each monitoring probe in the historical period, obtain the historical alarm vector of each monitoring probe; Obtaining the alarm correlation between each monitoring probe and the other monitoring probes through the spatial distance between each monitoring probe and the other monitoring probes and the similarity of the historical alarm vectors; Using the alarm correlation, weight the average level of alarm identification of each monitoring probe at different times before the current time, and calculate the query urgency of each monitoring probe at the current time; Analyze the average level of network bandwidth of each monitoring probe at different times before the current time, and determine the cache urgency of each monitoring probe at the current time in combination with the query urgency; Based on the cache urgency, the video cache length of each monitoring probe at the current moment is determined; the actual cache length and the video cache length are compared, and the video transmission bit rates of different monitoring probes are adjusted in real time.

2. The AIOT-based smart campus environmental parameter comprehensive perception method as claimed in claim 1, characterized in that: The step of determining the alarm state of each monitoring probe at each moment and obtaining the alarm identification of each monitoring probe at each moment includes: If there is an abnormality in the video information of each monitoring probe at each moment, the monitoring probe will immediately trigger an alarm. If each monitoring probe is in an alarm state at each moment, the alarm mark is 1, otherwise, the alarm mark is 0.

3. The AIOT-based smart campus environmental parameter comprehensive perception method as claimed in claim 2, characterized in that: The method for obtaining the historical alarm vector is: The number of times the alarm identification of each monitoring probe is 1 in each time period is counted and recorded as the number of alarms; the number of alarms of each monitoring probe in multiple time periods is combined to form a historical alarm vector of each monitoring probe.

4. The AIOT-based smart campus environmental parameter comprehensive perception method as claimed in claim 1, characterized in that: The spatial distance is the Euclidean distance between the position coordinates of each monitoring probe and the other monitoring probes.

5. The AIOT-based smart campus environmental parameter comprehensive perception method as claimed in claim 1, characterized in that: The degree of similarity is the inverse of the Euclidean distance between each monitoring probe and the historical alarm vectors of the remaining monitoring probes.

6. The AIOT-based smart campus environmental parameter comprehensive perception method as claimed in claim 1, characterized in that: The alarm correlation degree is the ratio of the similarity degree to the spatial distance.

7. The AIOT-based smart campus environmental parameter comprehensive perception method as claimed in claim 1 is characterized in that: The calculation of the query urgency of each monitoring probe at the current moment includes: Normalizing the alarm correlation between each monitoring probe and all other monitoring probes, and using the normalized result as the alarm impact weight of each monitoring probe and the other monitoring probes; The average value of the alarm identification of each monitoring probe at multiple moments before the current moment is used as the alarm value of each monitoring probe at the current moment; Based on the alarm impact weight of each monitoring probe and the other monitoring probes, the alarm values ​​of the other monitoring probes at the current moment are weighted summed up, and the sum of the weighted summation result and the alarm value of each monitoring probe at the current moment is used as the query urgency of each monitoring probe at the current moment.

8. The method for comprehensive perception of smart campus environmental parameters based on AIOT as claimed in claim 1, characterized in that: Determining the cache urgency of each monitoring probe at the current moment includes: The average of the network bandwidth of each monitoring probe at multiple times before the current moment is used as the bandwidth characteristic value of each monitoring probe at the current moment; The ratio of the query urgency to the bandwidth characteristic value is used as the cache urgency of each monitoring probe at the current moment.

9. The AIOT-based smart campus environmental parameter comprehensive perception method as claimed in claim 1, characterized in that: Determining the video cache length of each monitoring probe at the current moment includes: Normalize the cache urgency of all monitoring probes at the current moment, and use the normalized value as the cache weight of each monitoring probe at the current moment; A video cache space of a preset duration is allocated to each monitoring probe; and the product of the cache weight and the preset duration is used as the video cache length of each monitoring probe at the current moment.

10. The AIOT-based smart campus environmental parameter comprehensive perception method according to claim 1, characterized in that: The real-time adjustment of the video transmission bit rates of different monitoring probes includes: For the video information corresponding to the monitoring probe whose actual cache length is smaller than the video cache length, the preset minimum transmission bit rate is used for compression transmission; otherwise, the preset maximum transmission bit rate is used for compression transmission.

Images