An automated control system for video surveillance equipment in intelligent buildings

Abstract

The present invention relates to the field of intelligent video surveillance technology, and in particular to an automated control system for intelligent building video surveillance equipment, comprising an acquisition module, a determination module, a judgment module, a selection module, a generation module, an adjustment module, and a control module. The present invention optimizes building surveillance by collecting and analyzing multiple key data sets (crowd density, crowd speed, noise level, and camera workload) in real time and making intelligent adjustments based on the logical correlations between these data sets. Specifically, the system screens temporary floors using preset density and synchronization thresholds, and determines floors of interest based on a combination of crowd density and noise level. These data sets are interconnected, ensuring that the selected floors receive higher monitoring priority, effectively resolving the issues of slow response to sudden and unusual crowd situations and low monitoring quality caused by reliance on data storage and analysis delays.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent video monitoring, and in particular to an automatic control system for intelligent building video monitoring equipment. Background Art

[0002] With the continuous acceleration of urbanization and the increasing frequency of people moving around in buildings, traditional building video surveillance systems face immense pressure on storage and data processing to cope with the high-density and high-frequency video surveillance demands. At the same time, the security sector is facing an increasingly urgent demand for real-time monitoring, immediate response, and abnormal event handling. Improving the efficiency and flexibility of surveillance systems and optimizing security management have become pressing challenges. Against this backdrop, the automated and intelligent development of building video surveillance technology, particularly mechanisms that respond to crowd density and real-time dynamics, has become a key direction for improving building security management.

[0003] Patent document CN114979575A discloses a building video surveillance system, comprising a video front-end, a data platform, an early warning platform, a video terminal, and an inspection platform. The video front-end, serving as the acquisition end for the surveillance system's video data, collects and pre-processes personnel video data using video equipment installed at various locations within the building. The data platform, serving as the surveillance system's database, analyzes and stores the collected video data and provides access for query and management. The early warning platform, serving as the surveillance system's security center, identifies personnel entering the surveillance area, allocates video resources on demand based on their preset permissions, and issues timely alarms when abnormalities are detected. The video terminal, serving as the surveillance system's management center, freely manages, views, and schedules data within the data and early warning platforms, providing management personnel with access to the video surveillance system. The inspection platform, based on the video data collected and analyzed by the surveillance system and combined with early warning signals from the early warning platform, develops a cyclical inspection plan for daily abnormalities in the building, thereby achieving comprehensive and accurate security for the building.

[0004] It can be seen that the building video surveillance system has the following problems: the system relies on the data platform to analyze and store video data, but for high-frequency, high-real-time video surveillance scenarios, the storage and analysis of video data will cause delays in a high-density monitoring environment, affecting security efficiency; the system only relies on personnel identity recognition and abnormal alarms to handle security incidents, and has a low response speed to abnormal situations such as sudden excessive crowd density. Summary of the Invention

[0005] To this end, the present invention provides an intelligent building video surveillance equipment automation control system, which is used to overcome the problems in the prior art of slow response speed and low monitoring quality in the face of sudden abnormal crowd situations due to reliance on data storage and analysis delays through real-time dynamic scheduling and dynamic threshold adjustment.

[0006] To achieve the above-mentioned object, the present invention provides an intelligent building video surveillance equipment automation control system, comprising:

[0007] The acquisition module is used to collect real-time data on the noise level of each monitored floor in the building, the density and speed of people monitored by cameras running at a preset video bit rate on each monitored floor, and the workload value of the cameras;

[0008] a determination module connected to the acquisition module, configured to determine a number of temporary floors according to the crowd density and a preset density threshold;

[0009] a determination module, connected to the acquisition module and the determination module respectively, for determining a number of floors of interest based on the pedestrian flow speed, the noise level, and a preset synchronization threshold of each temporary floor;

[0010] a selection module connected to the acquisition module and the determination module, respectively, for selecting a number of key floors according to the crowd flow density of each of the focus floors, the crowd flow speed of another focus floor closest to it physically, and the workload values of the two focus floors;

[0011] a generating module, connected to the collecting module and the selecting module respectively, for generating a plurality of adjusted video bit rates according to the crowd density, the crowd speed and the preset video bit rate of each key floor;

[0012] an adjustment module, connected to the acquisition module, the determination module, the judgment module, and the generation module, respectively, for adjusting the preset density threshold according to the number of occurrences of the adjusted video bit rate within the preset adjustment duration to obtain an adjusted density threshold, or adjusting the preset synchronization threshold to obtain an adjusted synchronization threshold;

[0013] A control module is connected to the generating module and the adjusting module respectively, and is used to control the camera to operate at an adjusted video bit rate recalculated based on the adjusted density threshold or the adjusted synchronization threshold.

[0014] Furthermore, the determination module includes:

[0015] a first speed fluctuation calculation unit, configured to calculate a standard deviation of the pedestrian flow speed at each moment from an initial moment to a preset determination time period, and obtain a plurality of first speed fluctuation values;

[0016] a noise fluctuation calculation unit, configured to calculate a standard deviation of the noise level at each moment from an initial moment to the preset determination time length, to obtain a plurality of noise fluctuation values;

[0017] A determination unit is connected to the speed fluctuation calculation unit and the noise fluctuation calculation unit respectively, and is used to determine a number of focus floors according to all the first speed fluctuation values, all the noise fluctuation values and a preset synchronization threshold.

[0018] Furthermore, the determination unit includes:

[0019] a speed fluctuation curve drawing subunit, configured to draw a curve showing the first speed fluctuation value changing with time within the preset determination time period, to obtain a speed fluctuation curve;

[0020] A noise fluctuation drawing subunit is used to draw a curve showing the noise fluctuation value changing with time within the preset determination time period to obtain a noise fluctuation curve;

[0021] a synchronization degree calculation subunit, connected to the speed fluctuation curve drawing subunit and the noise fluctuation drawing subunit respectively, for calculating the cosine similarity of the speed fluctuation curve and the noise fluctuation curve to obtain a change synchronization degree;

[0022] The determination subunit is connected to the synchronization calculation subunit and is used to determine that the temporary floor is the focus floor when the change synchronization degree is greater than the preset synchronization degree threshold, so as to determine a number of focus floors.

[0023] Furthermore, the selection module includes:

[0024] a density fluctuation calculation unit, configured to calculate the standard deviation of the crowd density within a preset selected time period to obtain a density fluctuation value;

[0025] a second speed fluctuation calculation unit, configured to calculate a standard deviation of the pedestrian flow speed within the preset selected time period to obtain a second speed fluctuation value;

[0026] a fluctuation similarity calculation unit, connected to the density fluctuation calculation unit and the second speed fluctuation calculation unit, respectively, for calculating fluctuation similarity according to the density fluctuation value and the second speed fluctuation value;

[0027] A selection unit is connected to the fluctuation similarity calculation unit and is used to select a plurality of the key floors according to the fluctuation similarity and the workload values of the two focus floors.

[0028] Furthermore, the fluctuation similarity calculation unit includes:

[0029] a fluctuation normalization calculation subunit, configured to normalize the density fluctuation value according to a preset density fluctuation normalization range to obtain a density fluctuation normalization value, and to normalize the second speed fluctuation value according to a preset speed fluctuation normalization range to obtain a speed fluctuation normalization value;

[0030] The similarity calculation subunit is connected to the fluctuation normalization calculation subunit and is used to calculate the correlation coefficient between the density fluctuation normalization value and the speed fluctuation normalization value to obtain the fluctuation similarity.

[0031] Furthermore, the selection unit includes:

[0032] a load fluctuation calculation subunit, configured to calculate the standard deviation of the workload value of the single floor of interest within the preset selection time period when the fluctuation similarity is greater than a preset similarity threshold, to obtain a load fluctuation value;

[0033] a fluctuation deviation calculation subunit, connected to the load fluctuation calculation subunit, for calculating a relative deviation between the load fluctuation value of a single floor of interest and the load fluctuation value of another floor of interest that is physically closest to the floor of interest, to obtain a fluctuation deviation value;

[0034] The selection subunit is connected to the fluctuation deviation calculation subunit and is used to determine that the corresponding two focus floors are both the key floors when the fluctuation deviation value is greater than a preset deviation value, so as to select several key floors.

[0035] Furthermore, the generation module includes:

[0036] generating a normalization unit, configured to normalize the crowd density according to a preset density normalization range to obtain a crowd density normalization value, and to normalize the crowd speed according to a preset speed normalization range to obtain a crowd speed normalization value;

[0037] a factor calculation unit connected to the generating normalization unit, configured to calculate the product of the normalized value of the crowd density and a preset crowd density weight to obtain a crowd density factor, and to calculate the product of the normalized value of the crowd speed and a preset crowd speed weight to obtain a crowd speed factor;

[0038] an index calculation unit connected to the factor calculation unit, for calculating the sum of the crowd density factor and the crowd speed factor to obtain an adjustment index;

[0039] A generating unit is connected to the index calculating unit and is used to increase the preset video bit rate according to the relative deviation between the adjustment index and the preset index threshold and the preset adjustment coefficient when the adjustment index is greater than the preset index threshold, to obtain the adjusted video bit rate, so as to generate a plurality of adjusted video bit rates.

[0040] Furthermore, the adjustment module includes:

[0041] A number fluctuation calculation unit, used to calculate the standard deviation of the number of occurrences of adjusting the video bit rate to obtain a number fluctuation value;

[0042] An adjustment unit is connected to the number fluctuation calculation unit and is used to adjust the preset density threshold according to the number fluctuation value and the preset number fluctuation range to obtain the adjusted density threshold, or adjust the preset synchronization threshold to obtain the adjusted synchronization threshold.

[0043] Furthermore, the adjustment unit includes:

[0044] a synchronization threshold adjustment subunit, configured to, when the number fluctuation value is greater than the maximum value of the preset number fluctuation range, reduce the preset synchronization threshold according to a relative deviation between the number fluctuation value and the maximum value of the preset number fluctuation range and a preset first adjustment factor to obtain the adjusted synchronization threshold;

[0045] The density threshold adjustment subunit is used to increase the preset density threshold according to the relative deviation between the minimum value of the preset number fluctuation range and the number fluctuation value and the preset second adjustment factor when the number fluctuation value is less than the minimum value of the preset number fluctuation range, so as to obtain the adjusted density threshold.

[0046] Furthermore, the determining module includes:

[0047] a density comparison unit, configured to compare the crowd density with the preset density threshold to form a density comparison result;

[0048] A determination unit is connected to the density comparison unit and is used to determine that the monitored floor is a temporary floor when the density comparison result shows that the pedestrian density is greater than the preset density threshold, so as to determine a number of temporary floors.

[0049] Compared to existing technologies, the present invention offers the advantage of optimizing building surveillance by collecting and analyzing multiple key data points (people density, traffic speed, noise level, and camera workload) in real time and intelligently adjusting them based on the logical correlations between these data points. Specifically, the system uses preset density and synchronization thresholds to screen temporary floors and then determines the floors of interest based on traffic density and noise level. This correlation ensures that the selected floors receive higher monitoring priority, while also avoiding over-concentration of resources in certain areas and ensuring the proper allocation of monitoring resources. Furthermore, by weighting traffic density and speed information, the system dynamically optimizes camera workload based on the video bitrate of key floors. This process not only improves surveillance efficiency but also enables real-time response to environmental changes. For example, when density fluctuates significantly on certain floors, the system automatically adjusts the density threshold to accommodate higher traffic density, avoiding blind spots or data distortion. Furthermore, by adjusting the synchronization threshold and video bitrate, the system balances camera workload across different floors, ensuring surveillance quality while avoiding excessive resource consumption. Through these correlation adjustments, the system achieves efficient configuration of monitoring resources, improves the intelligent level of building management, reduces the need for manual intervention, and effectively solves the problems of slow response to sudden abnormal crowd situations and low monitoring quality due to reliance on data storage and analysis delays.

[0050] Furthermore, by correlating fluctuations in pedestrian speed and noise levels, it can be determined whether any floor anomalies exist. If the fluctuation trends are similar, this indicates that the floor may be experiencing high levels of dynamic change or instability, requiring special attention. By combining the synchronization of speed and noise fluctuations, the system can more accurately identify floors with potential safety risks or management issues. It can analyze floor status from multiple dimensions, thus avoiding the potential misjudgments that can arise from traditional monitoring based on a single indicator. Ultimately, this improves monitoring accuracy and resource utilization efficiency, ensuring more intelligent, timely, and precise building safety management.

[0051] Furthermore, by comparing the synchronization between speed and noise fluctuation curves, the system can accurately identify floors where pedestrian activity and noise fluctuations are synchronized, typically indicating significant dynamic changes or abnormal conditions on those floors. Cosine similarity, a method for calculating synchronization, effectively measures the degree of matching between the two changing trends, further improving the accuracy of the judgment. When the synchronization exceeds a preset threshold, the system can quickly and intelligently determine which floors require key monitoring, avoiding potential risks that may be overlooked by traditional monitoring methods.

[0052] Furthermore, by introducing fluctuation similarity calculation, the selection module can comprehensively consider changes in crowd density and crowd speed fluctuations, thereby identifying floors of interest with similar fluctuation patterns and helping the system to rationally allocate resources across multiple monitored floors. This fluctuation similarity analysis method improves the accuracy and flexibility of building monitoring, effectively screening floors that require special attention, thereby optimizing the monitoring system's response time and resource utilization efficiency. Furthermore, by taking into account workload values, it helps allocate more processing resources to floors with heavier loads, ensuring optimal monitoring results.

[0053] Furthermore, through normalization, fluctuation values of different ranges and units can be compared on a unified scale, eliminating the impact of scale differences and ensuring the accuracy and fairness of the fluctuation similarity calculation. The calculated fluctuation similarity effectively reflects the degree of synchronization between density fluctuations and velocity fluctuations, helping the system accurately identify floors with similar fluctuation characteristics, providing a reliable basis for subsequent floor selection.

[0054] Furthermore, by calculating the load fluctuation value and relative deviation, it is possible to screen out floors with large workload fluctuations and prioritize them as target floors for focus. This not only accurately identifies the floors that need the most attention, but also considers the impact between floors through the correlation of physical distance, avoiding the misjudgment that may be caused by considering floor load fluctuations alone, and improving the accuracy and responsiveness of the entire monitoring system.

[0055] Furthermore, through a multi-level calculation process, the video bitrate can be dynamically adjusted based on the actual monitoring situation to improve monitoring accuracy and response speed. Normalization ensures data comparability across floors and areas, allowing changes in crowd density and speed to be accurately captured. Factor and index calculations rationally weight the impact of different parameters on monitoring adjustments, thereby improving the scientific nature and stability of the overall judgment. Increasing the video bitrate based on the deviation between the adjustment index and the preset threshold can provide more detailed monitoring data in situations with high crowd density or large speed changes, effectively addressing monitoring needs in highly dynamic environments and improving the system's response capabilities to emergencies.

[0056] Furthermore, by calculating the fluctuations in the number of video bitrate adjustments, the stability of the adjustment operation can be accurately understood. This calculation of the fluctuation value can promptly capture potential fluctuations and instabilities in the system. By adjusting the preset density threshold and the preset synchronization threshold, it can prevent system misjudgments or delayed responses caused by unstable adjustments. Dynamic adjustment of the adjustment threshold can improve the system's flexibility and responsiveness, ensuring that the system can more accurately adapt to environmental changes under different operating conditions, optimizing operational results, and ultimately enhancing the reliability and accuracy of the entire system.

[0057] Furthermore, when fluctuations are large, reducing the synchronization threshold helps improve the system's responsiveness to rapid changes, allowing for timely detection and handling of anomalies. Conversely, when fluctuations are small, increasing the density threshold can reduce unnecessary sensitivity, thereby avoiding frequent system adjustments and maintaining stable operation. This dynamic adjustment method based on relative deviation and adjustment factors can more accurately respond to the needs of different scenarios, optimize the system's resource allocation and response strategies, and thus improve overall efficiency and reliability.

[0058] Furthermore, by determining that floors with a density greater than a preset threshold are temporary floors, the system can respond promptly to fluctuations in crowd density, dynamically identify floors that require temporary enhanced monitoring, effectively respond to sudden high-density crowds, avoid resource waste and improve management efficiency, ensure dynamic monitoring of floors, and enhance the flexibility and accuracy of the monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 Schematic diagram of the automated control system for the intelligent building video surveillance equipment of this embodiment;

[0060] Figure 2 This is a decision logic diagram for the decision subunit in this embodiment to determine the floor of interest;

[0061] Figure 3 This is a decision logic diagram for selecting a subunit to determine a key floor in this embodiment;

[0062] Figure 4 This is a decision logic diagram for adjusting the preset synchronization threshold or the preset density threshold by the adjustment unit in this embodiment. DETAILED DESCRIPTION

[0063] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0064] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0065] See also Figure 1 , which is a schematic diagram of the automatic control system of the intelligent building video surveillance equipment in this embodiment;

[0066] This embodiment provides an automated control system for video surveillance equipment in an intelligent building, including:

[0067] The acquisition module is used to collect real-time data on the noise level of each monitored floor in the building, the density and speed of people monitored by cameras running at a preset video bit rate on each monitored floor, and the workload value of the cameras;

[0068] a determination module connected to the acquisition module, configured to determine a number of temporary floors according to the crowd density and a preset density threshold;

[0069] a determination module, connected to the acquisition module and the determination module respectively, for determining a number of floors of interest based on the pedestrian flow speed, the noise level, and a preset synchronization threshold of each temporary floor;

[0070] a selection module connected to the acquisition module and the determination module, respectively, for selecting a number of key floors according to the crowd flow density of each of the focus floors, the crowd flow speed of another focus floor closest to it physically, and the workload values of the two focus floors;

[0071] a generating module, connected to the collecting module and the selecting module respectively, for generating a plurality of adjusted video bit rates according to the crowd density, the crowd speed and the preset video bit rate of each key floor;

[0072] an adjustment module, connected to the acquisition module, the determination module, the judgment module, and the generation module, respectively, for adjusting the preset density threshold according to the number of occurrences of the adjusted video bit rate within the preset adjustment duration to obtain an adjusted density threshold, or adjusting the preset synchronization threshold to obtain an adjusted synchronization threshold;

[0073] A control module is connected to the generating module and the adjusting module respectively, and is used to control the camera to operate at an adjusted video bit rate recalculated based on the adjusted density threshold or the adjusted synchronization threshold.

[0074] The acquisition module is one of the core components of the automated control system for intelligent building video surveillance equipment. It is responsible for collecting key data from each monitored floor in the building in real time for subsequent analysis and decision-making. Specifically, the acquisition module obtains the following parameters:

[0075] The noise level represents the ambient noise intensity on each monitored floor within a building, typically expressed in decibels (dB). Installed noise sensors (such as acoustic sensors and microphone arrays) monitor the ambient noise level on each floor in real time. These sensors connect to the system's data interface and provide real-time noise intensity feedback to the acquisition module. Noise data can be precisely collected by specific floor or area, helping to determine whether the ambient noise level on a given floor exceeds preset standards.

[0076] Crowd density indicates the number of people per unit area on a floor, typically expressed as "people per square meter." Floor-level surveillance cameras capture video data and, combined with image processing algorithms (such as object detection and behavior recognition), calculate the number of people within the camera's field of view during a specific time period. By analyzing pixel changes in the video stream and combining it with the floor's area information, the system can estimate the current density.

[0077] Crowd velocity refers to the speed of movement of people within a floor, typically expressed in meters per second. Crowd velocity is calculated using real-time video stream data captured by video surveillance. The system analyzes the movement trajectories of people in video frames and calculates the distance traveled per unit time. Using algorithms (optical flow and motion detection), the system accurately determines the average speed of crowd flow, reflecting the flow of people within a floor.

[0078] The camera's workload value refers to the degree of system resource usage generated by the camera's video acquisition and processing tasks per unit time. Its value is obtained by weighted calculation of multiple dimensions such as CPU usage, memory usage, video bit rate, and data upload rate. Specifically, by setting weights for each resource item and normalizing them, a comprehensive calculation is performed to obtain a standardized numerical indicator for measuring the camera's current working intensity. This standardized numerical indicator is a dimensionless normalized value (0 to 1) and is obtained by collecting and normalizing multiple resource usage indicators and then performing weighted calculation: W = α × (C / Cmax) + β × (M / Mmax) + γ × (F / Fmax) + δ × (T / Tmax), where W is the workload value (dimensionless, range [0, 1]), C is the CPU usage (%), C / Cmax∈[0, 1], M is the memory usage (%), M / Mmax∈[0, 1], F is the video bitrate (Mbps), F / Fmax∈[0, 1], T is the data upload rate (Mbps), T / Tmax∈[0, 1], Cmax is the maximum available CPU computing power, Mmax is the maximum memory capacity of the camera processing module, Fmax is the highest video bitrate supported by the device, and Tmax is the maximum uplink bandwidth capability of the camera. α, β, γ, and δ are the weight coefficients of each resource item, satisfying α + β + γ + δ = 1. In this embodiment: α=0.4, β=0.3, γ=0.2, δ=0.1.

[0079] In this example, in an office building, the acquisition module uses smart sensors and cameras distributed across each floor to collect real-time noise level and pedestrian flow data. The system uses this data to assess the monitoring needs of each floor, adjusting the camera's video bitrate to accommodate excessive human activity or adjusting the floor's noise control equipment to reduce environmental interference.

[0080] The preset video bitrate refers to the initial video data transmission rate used by the camera in normal monitoring mode. It is usually measured in bitrate (Mbps) and depends on the network bandwidth capacity, storage system write speed, and the required clarity of the monitoring image. It is usually set between 512 kbps and 8 Mbps. In this embodiment, the preset video bitrate is set to 2 Mbps. While ensuring the clarity of the monitoring image, it can effectively control network transmission delays and storage pressure, achieving efficient real-time monitoring and rapid response.

[0081] The preset density threshold is the standard value used by the system to determine floor density during monitoring. When the floor density exceeds this threshold, the system triggers appropriate monitoring adjustments or alarms. This threshold is typically set based on the building's usage and traffic conditions, typically between 0.5 and 2 people / square meter. In this example, it is set to 1.5 people / square meter, which accurately identifies high-traffic areas and allows for timely video bitrate adjustments or further monitoring measures.

[0082] The preset synchronization threshold is used by the system to measure the synchronization between noise fluctuations and pedestrian flow speed fluctuations within a floor. A higher synchronization indicates a more consistent trend between pedestrian flow speed and noise on a floor, indicating a more urgent need for monitoring on that floor. This threshold is typically set between 0.7 and 0.9, and in this example, 0.8. This threshold effectively identifies dynamic floor changes, allowing for timely response and adjustment of monitoring strategies to avoid missing areas of potential safety hazards.

[0083] Through the collaborative work of multiple modules, information such as noise levels, crowd density, crowd speed, and camera workload on each floor of the building is monitored in real time. First, the acquisition module obtains relevant data for each floor, and the determination module determines the temporary floor based on the crowd density and a preset density threshold. Then, the judgment module further determines the floors of interest based on the speed, noise, and synchronization threshold of the temporary floor. The selection module selects key floors based on the crowd density, relative crowd speed, and workload of each floor of interest. Next, the generation module adjusts the video bitrate according to the situation of the key floors, and the adjustment module adjusts the density threshold or synchronization threshold according to the frequency of changes in the video bitrate. Finally, the control module dynamically controls the camera to optimize monitoring efficiency and resource utilization.

[0084] By collecting and analyzing a variety of key data (people density, traffic speed, noise level, and camera workload) in real time and intelligently adjusting based on the logical correlations between these data, the system optimizes building surveillance. Specifically, the system uses preset density and synchronization thresholds to screen temporary floors, and then determines focus floors based on traffic density and noise levels. This correlation ensures that the selected floors receive higher surveillance priority, while also avoiding over-concentration of resources in certain areas and ensuring the proper allocation of surveillance resources. Furthermore, by weighting traffic density and speed information, the system dynamically optimizes camera workload based on the video bitrate of key floors. This process not only improves surveillance efficiency but also enables real-time response to environmental changes. For example, when traffic density fluctuates significantly on certain floors, the system automatically adjusts the density threshold to accommodate the higher density, avoiding blind spots or data distortion. Furthermore, by adjusting the synchronization threshold and video bitrate, the system balances the camera workload across different floors, ensuring surveillance quality while avoiding excessive resource consumption. Through these correlation adjustments, the system achieves efficient configuration of monitoring resources, improves the intelligent level of building management, reduces the need for manual intervention, and effectively solves the problems of slow response to sudden abnormal crowd situations and low monitoring quality due to reliance on data storage and analysis delays.

[0085] Specifically, the determination module includes:

[0086] a first speed fluctuation calculation unit, configured to calculate a standard deviation of the pedestrian flow speed at each moment from an initial moment to a preset determination time period, and obtain a plurality of first speed fluctuation values;

[0087] a noise fluctuation calculation unit, configured to calculate a standard deviation of the noise level at each moment from an initial moment to the preset determination time length, to obtain a plurality of noise fluctuation values;

[0088] A determination unit is connected to the speed fluctuation calculation unit and the noise fluctuation calculation unit respectively, and is used to determine a number of focus floors according to all the first speed fluctuation values, all the noise fluctuation values and a preset synchronization threshold.

[0089] The preset judgment duration is the time period used to calculate fluctuations in pedestrian flow and noise levels, depending on the characteristics of building activity and monitoring requirements. It's typically set between 10 minutes and 1 hour to accommodate different real-time monitoring scenarios and the changing cycles of floor activity. In this example, it's set to 30 minutes, which effectively captures fluctuations in floor pedestrian flow and noise levels, ensuring accurate identification and timely response to potential anomalies.

[0090] First, the first speed fluctuation calculation unit calculates the standard deviation of the pedestrian speed at each moment starting from the initial moment according to a preset judgment time, and obtains a number of first speed fluctuation values; then, the noise fluctuation calculation unit calculates the standard deviation of the noise level at each moment according to the same time period, and obtains a number of noise fluctuation values; finally, the judgment unit comprehensively considers all the first speed fluctuation values and noise fluctuation values, and combines them with a preset synchronization threshold to determine through comparative analysis whether there is a situation where the pedestrian flow and noise fluctuations are synchronized, thereby determining a number of floors that require special attention.

[0091] By correlating fluctuations in pedestrian speed and noise levels, the system can determine whether any floor anomalies exist. Similar fluctuation trends indicate that the floor may be experiencing high levels of dynamic change or instability, requiring special attention. By combining the synchronization of speed and noise fluctuations, the system can more accurately identify floors with potential safety risks or management issues. It can analyze floor status from multiple dimensions, thus avoiding the potential misjudgments that can arise from traditional monitoring based solely on a single indicator. Ultimately, this improves monitoring accuracy and resource utilization efficiency, ensuring more intelligent, timely, and precise building safety management.

[0092] Please continue reading Figure 2 As shown, it is a decision logic diagram of the decision subunit in this embodiment for deciding the floor of interest;

[0093] The determination unit includes:

[0094] a speed fluctuation curve drawing subunit, configured to draw a curve showing the first speed fluctuation value changing with time within the preset determination time period, to obtain a speed fluctuation curve;

[0095] A noise fluctuation drawing subunit is used to draw a curve showing the noise fluctuation value changing with time within the preset determination time period to obtain a noise fluctuation curve;

[0096] a synchronization degree calculation subunit, connected to the speed fluctuation curve drawing subunit and the noise fluctuation drawing subunit respectively, for calculating the cosine similarity of the speed fluctuation curve and the noise fluctuation curve to obtain a change synchronization degree;

[0097] The determination subunit is connected to the synchronization calculation subunit and is used to determine that the temporary floor is the focus floor when the change synchronization degree is greater than the preset synchronization degree threshold, so as to determine a number of focus floors.

[0098] First, the speed fluctuation curve plotting subunit plots the fluctuations of pedestrian speed over time based on a preset judgment period, generating a speed fluctuation curve. Next, the noise fluctuation plotting subunit plots the noise fluctuations over time based on the same time period, generating a noise fluctuation curve. The synchronization calculation subunit then analyzes these two curves and calculates their cosine similarity to measure their synchronization. Finally, the judgment subunit compares the results with a preset synchronization threshold. If the synchronization exceeds the threshold, the floor is identified as a focus floor, thereby identifying several floors of concern. By simultaneously comparing pedestrian speed fluctuations with ambient noise fluctuations, the system can distinguish between dynamic changes caused by true human activity and interference from a single factor. Rapid crowd movement (increased speed fluctuations) is often accompanied by increased noise levels from footsteps and conversations, while simple wind noise or air conditioning noise will not cause a significant change in pedestrian speed. Similarly, when high-speed moving objects (such as elevator door openings or cleaning robots) appear in the surveillance footage, speed fluctuations increase, but the noise fluctuations may not match. By calculating the cosine similarity of the two fluctuation curves, only when the speed and noise change synchronously at the same time can it be determined as a true "crowd dynamics" event, thereby accurately locking the floors where people are concentrated and there may be safety hazards, avoiding the false alarms and missed alarms caused by traditional reliance on a single indicator.

[0099] By comparing the synchronization of speed fluctuation curves with noise fluctuation curves, the system can accurately identify floors where pedestrian activity and noise fluctuations are synchronized, typically indicating significant dynamic changes or abnormal conditions on those floors. Cosine similarity, a method for calculating synchronization, effectively measures the degree of matching between the two changing trends, further improving the accuracy of the judgment. When the synchronization exceeds a preset threshold, the system can quickly and intelligently determine which floors require key monitoring, avoiding potential risks that may be overlooked by traditional monitoring methods.

[0100] To calculate the cosine similarity between the velocity and noise fluctuation curves, we first need to convert the two curves into vectors and then use the standard cosine similarity formula. Cosine similarity can help determine whether the shapes of the two curves are similar (i.e., whether their changing trends are consistent).

[0101] The curve represents: the speed fluctuation and noise fluctuation at each moment are regarded as the elements of two vectors respectively.

[0102] Calculate cosine similarity: Use the cosine similarity formula to calculate the similarity between the two vectors.

[0103] Cosine similarity formula: , where A is the vector of the speed fluctuation curve, which contains the speed fluctuation values at different times is the modulus of the vector of the velocity fluctuation curve; B is the vector of the noise fluctuation curve, which includes the noise fluctuation values at different times. is the modulus of the vector of the noise fluctuation curve; It is the dot product of the vector of the speed fluctuation curve and the vector of the noise fluctuation curve. The dot product is calculated in the existing technology by multiplying and summing each pair of elements at the same position, which will not be repeated here.

[0104] Specifically, the selection module includes:

[0105] a density fluctuation calculation unit, configured to calculate the standard deviation of the crowd density within a preset selected time period to obtain a density fluctuation value;

[0106] a second speed fluctuation calculation unit, configured to calculate a standard deviation of the pedestrian flow speed within the preset selected time period to obtain a second speed fluctuation value;

[0107] a fluctuation similarity calculation unit, connected to the density fluctuation calculation unit and the second speed fluctuation calculation unit, respectively, for calculating fluctuation similarity according to the density fluctuation value and the second speed fluctuation value;

[0108] A selection unit is connected to the fluctuation similarity calculation unit and is used to select a plurality of the key floors according to the fluctuation similarity and the workload values of the two focus floors.

[0109] The preset selection duration refers to the time interval used in the selection module to calculate fluctuations in crowd density and crowd speed. It depends on the actual monitoring needs and the characteristics of the building environment. It is usually set between 5 minutes and 2 hours. In this embodiment, it is set to 30 minutes. It can effectively balance the volatility of monitoring data and the response speed of the system, capture the changing trends of crowd flow and noise in a shorter period of time, thereby improving the accuracy of floor selection and monitoring efficiency.

[0110] By analyzing the fluctuations of the crowd density and crowd speed within a preset selection time period, the following steps are performed in sequence: first, the density fluctuation calculation unit calculates the standard deviation of the crowd density within the time period to obtain the density fluctuation value; second, the second speed fluctuation calculation unit calculates the standard deviation of the crowd speed within the time period to obtain the second speed fluctuation value; then, the fluctuation similarity calculation unit calculates the fluctuation similarity based on the density fluctuation value and the second speed fluctuation value to reflect the similarity of the fluctuation trends of the two; finally, the selection unit determines several key floors based on the fluctuation similarity and the workload values of the two focus floors, so as to carry out more refined monitoring and resource allocation on these floors.

[0111] By incorporating fluctuation similarity calculations, the selection module comprehensively considers fluctuations in both crowd density and crowd speed, identifying floors of interest with similar fluctuation patterns and enabling the system to optimally allocate resources across multiple monitored floors. This fluctuation similarity analysis method improves the accuracy and flexibility of building monitoring, effectively identifying floors requiring special attention and optimizing the monitoring system's response time and resource utilization. Furthermore, by incorporating workload considerations, it helps allocate more processing resources to floors with heavier loads, ensuring optimal monitoring results.

[0112] Specifically, the fluctuation similarity calculation unit includes:

[0113] a fluctuation normalization calculation subunit, configured to normalize the density fluctuation value according to a preset density fluctuation normalization range to obtain a density fluctuation normalization value, and to normalize the second speed fluctuation value according to a preset speed fluctuation normalization range to obtain a speed fluctuation normalization value;

[0114] The similarity calculation subunit is connected to the fluctuation normalization calculation subunit and is used to calculate the correlation coefficient between the density fluctuation normalization value and the speed fluctuation normalization value to obtain the fluctuation similarity.

[0115] The preset density fluctuation normalization range refers to the benchmark range for linearly mapping the fluctuation value of pedestrian density to a unified dimensional interval. Its setting depends on the statistical distribution characteristics of historical monitoring data and the physical space limitations of the scene. For office buildings, it is usually set between [0 people / m2, 5 people / m2] (representing the mapping relationship). In this embodiment, it is set to [0 people / m2, 4.2 people / m2], which can eliminate dimensional interference caused by differences in coverage area of different cameras.

[0116] The preset speed fluctuation normalization range is a baseline interval for linearly mapping pedestrian speed fluctuations to a uniform dimension. Its range depends on pedestrian movement patterns and sensor accuracy. It is typically set between [0 m / s and 2 m / s]. In this example, it is set to [0 m / s and 1.8 m / s] to suppress speed jump errors caused by sensor noise.

[0117] The normalization adopts the maximum and minimum normalization method, which normalizes the density fluctuation value according to the maximum and minimum values of the preset density fluctuation normalization range, and normalizes the second speed fluctuation value according to the maximum and minimum values of the preset speed fluctuation normalization range. The maximum and minimum normalization method is an existing technology and will not be repeated here.

[0118] First, the density fluctuation values and velocity fluctuation values are normalized separately by the Fluctuation Normalization Calculation Subunit. Density fluctuation values are normalized within a preset density fluctuation normalization range to obtain a density fluctuation normalized value; velocity fluctuation values are normalized within a preset velocity fluctuation normalization range to obtain a velocity fluctuation normalized value. Subsequently, the Similarity Calculation Subunit calculates the correlation coefficient between these two normalized values to determine the fluctuation similarity. This process quantifies the degree of similarity between density and velocity fluctuations, providing data support for subsequent floor selection.

[0119] Normalization allows fluctuation values of different ranges and units to be compared on a unified scale, eliminating the impact of scale differences and ensuring the accuracy and fairness of the fluctuation similarity calculation. The calculated fluctuation similarity effectively reflects the degree of synchronization between density and velocity fluctuations, helping the system accurately identify floors with similar fluctuation characteristics and providing a reliable basis for subsequent floor selection.

[0120] Please continue reading Figure 3 As shown, it is a decision logic diagram of the selection subunit for determining the key floor in this embodiment;

[0121] The selection unit includes:

[0122] a load fluctuation calculation subunit, configured to calculate the standard deviation of the workload value of the single floor of interest within the preset selection time period when the fluctuation similarity is greater than a preset similarity threshold, to obtain a load fluctuation value;

[0123] a fluctuation deviation calculation subunit, connected to the load fluctuation calculation subunit, for calculating a relative deviation between the load fluctuation value of a single floor of interest and the load fluctuation value of another floor of interest that is physically closest to the floor of interest, to obtain a fluctuation deviation value;

[0124] The selection subunit is connected to the fluctuation deviation calculation subunit and is used to determine that the corresponding two focus floors are both the key floors when the fluctuation deviation value is greater than a preset deviation value, so as to select several key floors.

[0125] The preset similarity threshold refers to the standard value used to determine whether there is a significant correlation between the load fluctuation similarity of two floors of interest. It depends on the specific needs of building monitoring, the functional correlation between different floors and the analysis results of historical monitoring data. It is usually set between 0.6 and 0.9. In this embodiment, it is set to 0.8, which can ensure that there is a high load fluctuation similarity between the selected floors of interest, reduce misjudgments caused by low similarity, and improve the accuracy and effectiveness of system monitoring.

[0126] The preset deviation value is a threshold used to determine whether there is a significant difference between the load fluctuations of two floors of interest. It depends on the range of variation of the load fluctuations between floors and the expected tolerance. It is usually set between 0 and 0.5. In this embodiment, it is set to 0.2. While ensuring the sensitivity of the system, it can avoid overly subtle fluctuations from affecting the selection results, thereby improving the stability and accuracy of the key floor selection.

[0127] First, when the fluctuation similarity exceeds a preset similarity threshold, the load fluctuation calculation subunit calculates the standard deviation of the workload values for each floor of interest within the preset selection duration to obtain a load fluctuation value. Next, the fluctuation deviation calculation subunit calculates the relative deviation between the load fluctuation value of each floor of interest and its closest physically closest floor of interest to obtain a fluctuation deviation value. Finally, the selection subunit determines whether to designate the two floors of interest as key floors by determining whether the fluctuation deviation value exceeds a preset deviation value.

[0128] By calculating the load fluctuation value and relative deviation, floors with large workload fluctuations can be screened out and prioritized as target floors for focus. This not only accurately identifies the floors that need the most attention, but also considers the impact between floors through the correlation of physical distance, avoiding the misjudgment that may be caused by considering floor load fluctuations alone, and improving the accuracy and responsiveness of the entire monitoring system.

[0129] Specifically, the generation module includes:

[0130] generating a normalization unit, configured to normalize the crowd density according to a preset density normalization range to obtain a crowd density normalization value, and to normalize the crowd speed according to a preset speed normalization range to obtain a crowd speed normalization value;

[0131] a factor calculation unit connected to the generating normalization unit, configured to calculate the product of the normalized value of the crowd density and a preset crowd density weight to obtain a crowd density factor, and to calculate the product of the normalized value of the crowd speed and a preset crowd speed weight to obtain a crowd speed factor;

[0132] an index calculation unit connected to the factor calculation unit, for calculating the sum of the crowd density factor and the crowd speed factor to obtain an adjustment index;

[0133] A generating unit is connected to the index calculating unit and is used for, when the adjustment index is greater than a preset index threshold, increasing the preset video bit rate according to a relative deviation between the adjustment index and the preset index threshold and a preset adjustment coefficient to obtain the adjusted video bit rate, so as to generate a plurality of adjusted video bit rates, F0'=F0×[1+j×(S-S0) / S0], where F0' is the adjusted video bit rate, F0 is the preset video bit rate, j is the preset adjustment coefficient, S is the adjustment index, and S0 is the preset index threshold.

[0134] The preset density normalization range linearly maps the raw crowd density value (unit: persons / m2) to a standardized range. This range depends on the maximum capacity of the camera's monitoring area and the characteristics of the scene type. It is typically set between [0 persons / m2, 6 persons / m2]. In this example, it is set to [0 persons / m2, 5 persons / m2] to eliminate the impact of area differences on density assessment.

[0135] The preset speed normalization range is a baseline interval for linearly mapping pedestrian speed (in m / s) to a standardized range. This range is determined by pedestrian movement characteristics and sensor accuracy. It is typically set between [0 m / s, 3 m / s]. In this example, it is set to [0 m / s, 2.2 m / s] to address speed measurement errors caused by different camera viewing angles.

[0136] The preset crowd density weight is the weight of the impact of crowd density on the final video bitrate adjustment. This weight typically depends on the importance of crowd density in the monitoring system. It is typically set between [0, 1]. In this example, it is set to 0.6, which gives more attention to high-density areas and improves monitoring accuracy.

[0137] The preset crowd speed weight is the weight of crowd speed in terms of its impact on monitoring results. This weight generally depends on the importance of crowd speed in the monitoring scenario. It is usually set between [0, 1], and in this example is set to 0.4 to properly balance the impact of density and speed, avoiding over-reliance on either.

[0138] The preset index threshold refers to the critical value that determines whether the video bit rate needs to be increased when calculating the adjustment index. It depends on the monitoring requirements and the system carrying capacity. It is usually set between [0, 1]. In this embodiment, it is set to 0.7. It can ensure that the video bit rate adjustment is triggered only when the crowd density and speed changes in the monitored area reach a certain threshold, thereby improving the dynamic response capability of the monitoring.

[0139] The preset adjustment coefficient refers to the coefficient that controls the adjustment range when deciding whether to increase the video bitrate based on the deviation between the adjustment index and the preset index threshold. It depends on the sensitivity requirement of the video bitrate adjustment and is usually set between [0.1, 0.5]. In this embodiment, it is set to 0.3, which can effectively balance the response speed and system stability, and avoid excessive system load or excessive video bitrate fluctuations due to excessive adjustment.

[0140] First, the generation and normalization unit normalizes both crowd density and crowd speed (this is a prior art technique and will not be further elaborated), converting them into a unified standard value range. Next, the factor calculation unit calculates the corresponding density factor and speed factor, respectively, based on preset crowd density and crowd speed weights. The index calculation unit then adds these two factors to generate an adjustment index, representing the overall degree of change in the current monitoring scene. Finally, based on the relative deviation of the adjustment index from the preset index threshold and the preset adjustment coefficient, the generation unit determines whether the video bitrate needs to be increased to more accurately capture the dynamic changes in the monitoring scene, thereby generating a new adjusted video bitrate.

[0141] Through a multi-level calculation process, the video bitrate can be dynamically adjusted based on the actual monitoring situation to improve monitoring accuracy and response speed. Normalization ensures data comparability across floors and areas, allowing changes in crowd density and speed to be accurately captured. Factor and index calculations rationally weight the impact of different parameters on monitoring adjustments, thereby improving the scientific nature and stability of the overall judgment. Increasing the video bitrate based on the deviation between the adjustment index and the preset threshold can provide more detailed monitoring data in situations with high crowd density or large speed changes, effectively addressing monitoring needs in highly dynamic environments and improving the system's response capabilities to emergencies.

[0142] Specifically, the adjustment module includes:

[0143] A number fluctuation calculation unit, used to calculate the standard deviation of the number of occurrences of adjusting the video bit rate to obtain a number fluctuation value;

[0144] An adjustment unit is connected to the number fluctuation calculation unit and is used to adjust the preset density threshold according to the number fluctuation value and the preset number fluctuation range to obtain the adjusted density threshold, or adjust the preset synchronization threshold to obtain the adjusted synchronization threshold.

[0145] The preset frequency fluctuation range refers to the fluctuation range of the number of times the video bit rate is adjusted during the adjustment process, which is set based on historical data or actual needs. It depends on the system's tolerance for video bit rate adjustment and the stability that needs to be achieved. It is usually set between 0 and 5 times to ensure that the system does not cause excessive fluctuations or unnecessary waste of resources due to frequent adjustments. In this embodiment, it is set to 0 to 3 times, which can ensure that the system maintains sufficient stability when adjusting the video bit rate, while avoiding the impact of too many frequent adjustments on system performance.

[0146] The frequency fluctuation calculation unit is used to calculate the standard deviation of the number of times the video bitrate is adjusted to obtain a frequency fluctuation value, which reflects the stability and consistency of the adjustment operation. The adjustment unit then compares the frequency fluctuation value with a preset frequency fluctuation range and, if necessary, adjusts the preset density threshold or preset synchronization threshold to obtain a new adjustment threshold.

[0147] By calculating the fluctuations in the number of video bitrate adjustments, we can accurately understand the stability of these adjustments. This calculation allows us to promptly detect potential fluctuations and instabilities in the system. By adjusting the preset density and synchronization thresholds, we can prevent system misjudgments or delayed responses caused by unstable adjustments. Dynamic adjustment of the thresholds improves system flexibility and responsiveness, ensuring that the system can more accurately adapt to environmental changes under different operating conditions, optimizing operational results and ultimately enhancing overall system reliability and accuracy.

[0148] Please continue reading Figure 4 As shown, it is a decision logic diagram of the adjustment unit of this embodiment adjusting the preset synchronization threshold or the preset density threshold;

[0149] The adjustment unit includes:

[0150] a synchronization threshold adjustment subunit, configured to, when the number fluctuation value is greater than the maximum value of the preset number fluctuation range, reduce the preset synchronization threshold according to a relative deviation between the number fluctuation value and the maximum value of the preset number fluctuation range and a preset first adjustment factor to obtain the adjusted synchronization threshold;

[0151] The density threshold adjustment subunit is used to increase the preset density threshold according to the relative deviation between the minimum value of the preset number fluctuation range and the number fluctuation value and the preset second adjustment factor when the number fluctuation value is less than the minimum value of the preset number fluctuation range, so as to obtain the adjusted density threshold.

[0152] The preset first adjustment factor refers to the coefficient used to adjust the synchronization threshold according to the relative deviation between the number fluctuation value and the maximum value of the preset number fluctuation range during the synchronization threshold adjustment process. It depends on the response sensitivity requirements of the system and the fluctuation amplitude in the actual application scenario. It is usually set between 0.1 and 1.0. In this embodiment, it is set to 0.5, which can provide sufficient synchronization threshold adjustment during large fluctuations, ensure the system's rapid response to changes, and avoid unnecessary misjudgment caused by excessive adjustment.

[0153] The preset second adjustment factor refers to the coefficient used to adjust the density threshold according to the relative deviation between the number fluctuation value and the minimum value of the preset number fluctuation range during the density threshold adjustment process. It depends on the system's tolerance for small fluctuations and the fluctuation stability requirements in the scenario. It is usually set between 0.05 and 0.3. In this embodiment, it is set to 0.2, which can reasonably increase the density threshold when the fluctuation is small, avoid frequent adjustments of the system due to small fluctuations, and thus improve the stability of the overall operation.

[0154] When the number of fluctuations exceeds the maximum value of the preset number of fluctuations, the synchronization threshold adjustment subunit reduces the synchronization threshold based on the relative deviation between the number of fluctuations and the maximum value, combined with a preset first adjustment factor, to increase the system's sensitivity to fluctuations and respond promptly to changes. When the number of fluctuations is less than the minimum value of the preset number of fluctuations, the density threshold adjustment subunit increases the density threshold based on the relative deviation between the number of fluctuations and the minimum value, combined with a preset second adjustment factor, to reduce overreaction to small fluctuations.

[0155] When fluctuations are large, reducing the synchronization threshold helps improve the system's responsiveness to rapid changes, allowing for timely detection and handling of anomalies. Conversely, when fluctuations are small, increasing the density threshold can reduce unnecessary sensitivity, thereby avoiding frequent system adjustments and maintaining stable operation. This dynamic adjustment method based on relative deviation and adjustment factors can more accurately respond to the needs of different scenarios, optimize the system's resource allocation and response strategies, and thus improve overall efficiency and reliability.

[0156] Specifically, the determination module includes:

[0157] a density comparison unit, configured to compare the crowd density with the preset density threshold to form a density comparison result;

[0158] A determination unit is connected to the density comparison unit and is used to determine that the monitored floor is a temporary floor when the density comparison result shows that the pedestrian density is greater than the preset density threshold, so as to determine a number of temporary floors.

[0159] The density comparison unit first compares the current crowd density with a preset density threshold to generate a density comparison result. If the crowd density exceeds the preset density threshold, the determination unit identifies the floor as a "temporary floor" and determines a number of temporary floors accordingly. This allows the system to flexibly adjust monitored floors based on changes in crowd density, ensuring real-time monitoring and management of floors with high temporary traffic.

[0160] By determining floors with a density greater than a preset threshold as temporary floors, the system can respond promptly to fluctuations in crowd density, dynamically identify floors that require temporary enhanced monitoring, effectively deal with sudden high-density crowds, avoid resource waste, and improve management efficiency, ensuring dynamic monitoring of floors and enhancing the flexibility and accuracy of the monitoring system.

[0161] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. An automated control system for video surveillance equipment in intelligent buildings, characterized in that: include: The acquisition module is used to collect real-time data on the noise level of each monitored floor in the building, the density and speed of people monitored by cameras running at a preset video bit rate on each monitored floor, and the workload value of the cameras; a determination module connected to the acquisition module, configured to determine a number of temporary floors according to the crowd density and a preset density threshold; a determination module, connected to the acquisition module and the determination module respectively, for determining a number of floors of interest based on the pedestrian flow speed, the noise level, and a preset synchronization threshold of each temporary floor; a selection module connected to the acquisition module and the determination module, respectively, for selecting a number of key floors according to the crowd flow density of each of the focus floors, the crowd flow speed of another focus floor closest to it physically, and the workload values of the two focus floors; a generating module, connected to the collecting module and the selecting module respectively, for generating a plurality of adjusted video bit rates according to the crowd density, the crowd speed and the preset video bit rate of each key floor; an adjustment module, connected to the acquisition module, the determination module, the judgment module, and the generation module, respectively, for adjusting the preset density threshold according to the number of occurrences of the adjusted video bit rate within the preset adjustment duration to obtain an adjusted density threshold, or adjusting the preset synchronization threshold to obtain an adjusted synchronization threshold; a control module, connected to the generation module and the adjustment module respectively, for controlling the camera to operate at an adjusted video bit rate recalculated based on the adjustment density threshold or the adjustment synchronization threshold; The determination module includes: a first speed fluctuation calculation unit, configured to calculate a standard deviation of the pedestrian flow speed at each moment from an initial moment to a preset determination time period, and obtain a plurality of first speed fluctuation values; a noise fluctuation calculation unit, configured to calculate a standard deviation of the noise level at each moment from an initial moment to the preset determination time length, to obtain a plurality of noise fluctuation values; a determination unit, connected to the speed fluctuation calculation unit and the noise fluctuation calculation unit, respectively, for determining a number of floors of interest based on all the first speed fluctuation values, all the noise fluctuation values, and a preset synchronization threshold; The determination unit includes: a speed fluctuation curve drawing subunit, configured to draw a curve showing the first speed fluctuation value changing with time within the preset determination time period, to obtain a speed fluctuation curve; A noise fluctuation drawing subunit is used to draw a curve showing the noise fluctuation value changing with time within the preset determination time period to obtain a noise fluctuation curve; a synchronization degree calculation subunit, connected to the speed fluctuation curve drawing subunit and the noise fluctuation drawing subunit respectively, for calculating the cosine similarity of the speed fluctuation curve and the noise fluctuation curve to obtain a change synchronization degree; The determination subunit is connected to the synchronization calculation subunit and is used to determine that the temporary floor is the focus floor when the change synchronization degree is greater than the preset synchronization degree threshold, so as to determine a number of focus floors.

2. The intelligent building video surveillance equipment automation control system according to claim 1, characterized in that: The selection module includes: a density fluctuation calculation unit, configured to calculate the standard deviation of the crowd density within a preset selected time period to obtain a density fluctuation value; a second speed fluctuation calculation unit, configured to calculate a standard deviation of the pedestrian flow speed within the preset selected time period to obtain a second speed fluctuation value; a fluctuation similarity calculation unit, connected to the density fluctuation calculation unit and the second speed fluctuation calculation unit, respectively, for calculating fluctuation similarity according to the density fluctuation value and the second speed fluctuation value; A selection unit is connected to the fluctuation similarity calculation unit and is used to select a plurality of the key floors according to the fluctuation similarity and the workload values of the two focus floors.

3. The intelligent building video surveillance equipment automation control system according to claim 2, characterized in that: The fluctuation similarity calculation unit includes: a fluctuation normalization calculation subunit, configured to normalize the density fluctuation value according to a preset density fluctuation normalization range to obtain a density fluctuation normalization value, and to normalize the second speed fluctuation value according to a preset speed fluctuation normalization range to obtain a speed fluctuation normalization value; The similarity calculation subunit is connected to the fluctuation normalization calculation subunit and is used to calculate the correlation coefficient between the density fluctuation normalization value and the speed fluctuation normalization value to obtain the fluctuation similarity.

4. The intelligent building video surveillance equipment automation control system according to claim 3, characterized in that: The selection unit includes: a load fluctuation calculation subunit, configured to calculate the standard deviation of the workload value of the single floor of interest within the preset selection time period when the fluctuation similarity is greater than a preset similarity threshold, to obtain a load fluctuation value; a fluctuation deviation calculation subunit, connected to the load fluctuation calculation subunit, for calculating a relative deviation between the load fluctuation value of a single floor of interest and the load fluctuation value of another floor of interest that is physically closest to the floor of interest, to obtain a fluctuation deviation value; The selection subunit is connected to the fluctuation deviation calculation subunit and is used to determine that the corresponding two focus floors are both the key floors when the fluctuation deviation value is greater than a preset deviation value, so as to select several key floors.

5. The intelligent building video surveillance equipment automation control system according to claim 4, characterized in that: The generation module includes: generating a normalization unit, configured to normalize the crowd density according to a preset density normalization range to obtain a crowd density normalization value, and to normalize the crowd speed according to a preset speed normalization range to obtain a crowd speed normalization value; a factor calculation unit connected to the generating normalization unit, configured to calculate the product of the normalized value of the crowd density and a preset crowd density weight to obtain a crowd density factor, and to calculate the product of the normalized value of the crowd speed and a preset crowd speed weight to obtain a crowd speed factor; an index calculation unit connected to the factor calculation unit, for calculating the sum of the crowd density factor and the crowd speed factor to obtain an adjustment index; A generating unit is connected to the index calculating unit and is used to increase the preset video bit rate according to the relative deviation between the adjustment index and the preset index threshold and the preset adjustment coefficient when the adjustment index is greater than the preset index threshold, to obtain the adjusted video bit rate, so as to generate a plurality of adjusted video bit rates.

6. The intelligent building video surveillance equipment automation control system according to claim 5, characterized in that: The adjustment module includes: A number fluctuation calculation unit, used to calculate the standard deviation of the number of occurrences of adjusting the video bit rate to obtain a number fluctuation value; An adjustment unit is connected to the number fluctuation calculation unit and is used to adjust the preset density threshold according to the number fluctuation value and the preset number fluctuation range to obtain the adjusted density threshold, or adjust the preset synchronization threshold to obtain the adjusted synchronization threshold.

7. The intelligent building video surveillance equipment automation control system according to claim 6, characterized in that: The adjustment unit includes: a synchronization threshold adjustment subunit, configured to, when the number fluctuation value is greater than the maximum value of the preset number fluctuation range, reduce the preset synchronization threshold according to a relative deviation between the number fluctuation value and the maximum value of the preset number fluctuation range and a preset first adjustment factor to obtain the adjusted synchronization threshold; The density threshold adjustment subunit is used to increase the preset density threshold according to the relative deviation between the minimum value of the preset number fluctuation range and the number fluctuation value and the preset second adjustment factor when the number fluctuation value is less than the minimum value of the preset number fluctuation range, so as to obtain the adjusted density threshold.

8. The intelligent building video surveillance equipment automation control system according to claim 1, characterized in that: The determination module includes: a density comparison unit, configured to compare the crowd density with the preset density threshold to form a density comparison result; A determination unit is connected to the density comparison unit and is used to determine that the monitored floor is a temporary floor when the density comparison result shows that the pedestrian density is greater than the preset density threshold, so as to determine a number of temporary floors.

Images