CT (Computed Tomography) self-power-taking video monitoring and early warning method and device based on environmental perception

Abstract

The invention discloses a CT (Computed Tomography) self-power-taking video monitoring and early warning method and device based on environmental perception. According to the method, historical working data of CT self-power-taking video monitoring in a target area is acquired, and a working task identification model is constructed based on a hidden Markov model; using the model to identify work tasks in a preset time period, analyzing electric quantity changes and evaluating work quality, and constructing a work task-electric quantity-quality data matrix; performing cluster division based on the matrix, and determining a monitoring task distribution scheme; and acquiring video monitoring data according to the scheme, identifying an abnormal event, and performing monitoring and early warning. The video monitoring task distribution is optimized, the monitoring efficiency and the early warning accuracy are improved, and the method is suitable for the field of intelligent monitoring and power management.

Description

Technical Field

[0001] The present invention relates to the technical field of video monitoring and early warning, and in particular to a CT self-collecting electric video monitoring and early warning method and device based on environment perception. Background Art

[0002] With the rapid development of intelligent monitoring technology, intelligent early warning systems based on video monitoring have been widely used in urban management, power inspection, security monitoring and other fields. Traditional video monitoring systems mainly rely on fixed power supplies and implement equipment status management through regular inspections or remote control. However, in some special application scenarios, such as remote areas, power facility monitoring, forest fire prevention, etc., the traditional power supply mode is difficult to meet the needs of long-term autonomous operation. Therefore, self-power technology has gradually become an important means to solve the power supply problem of monitoring equipment.

[0003] CT (current transformer) self-powering technology uses the electromagnetic induction principle in the transmission line to power the monitoring equipment, enabling it to achieve long-term stable operation without external power access. However, due to the fluctuations in grid load, environmental factors and the power consumption characteristics of the equipment itself, there is a certain degree of uncertainty in the power supply capacity of CT self-powered video monitoring equipment, which may cause fluctuations in the operating status of the equipment and thus affect the execution quality of the monitoring task. How to reasonably allocate video monitoring tasks under the condition of limited power supply and ensure monitoring quality and early warning reliability has become an important research direction for the optimization of current intelligent monitoring systems.

[0004] In the existing technology, some intelligent monitoring systems have basic task management and anomaly detection functions, but they usually lack comprehensive perception of environmental factors and power status, and cannot dynamically adjust task allocation according to the remaining power of the monitoring equipment, resulting in some equipment being unable to perform high-energy consumption tasks due to insufficient power, or monitoring blind spots appearing during task execution, reducing monitoring coverage and early warning accuracy. In addition, traditional anomaly detection methods are mostly based on fixed threshold judgments or simple pattern matching, which do not fully combine the characteristics of monitoring tasks with environmental change factors, and are prone to false alarms or missed alarms, affecting the accurate identification and rapid response of abnormal events.

[0005] In view of the above problems, there is an urgent need for a CT self-collecting video monitoring and early warning method and device based on environmental perception. Through intelligent task identification and allocation strategies, the energy utilization efficiency of the video surveillance system can be improved, the ability to identify abnormal events can be enhanced, and efficient and accurate monitoring and early warning can be achieved. Summary of the invention

[0006] In order to solve at least one of the above technical problems, the present invention proposes a CT self-collected electric video monitoring and early warning method and device based on environmental perception.

[0007] The first aspect of the present invention provides a CT self-collected electric video monitoring and early warning method based on environmental perception, comprising: Obtaining historical working data of each CT self-collecting video surveillance in the target area, analyzing the historical working data based on a hidden Markov model, and constructing a working task recognition model for video surveillance; According to the work task identification model, work tasks are identified for each video surveillance within a preset time period, power change data of the video surveillance within the preset time period is obtained, and the work quality under each work task of the video surveillance is evaluated to construct a work task-power-quality data matrix; Clustering each video monitoring according to the work task-power-quality data matrix, determining the monitoring task of each monitoring cluster, and obtaining a monitoring task allocation plan; The video surveillance data of the target area is acquired according to the monitoring task allocation plan, abnormal events are identified according to the video surveillance data, and monitoring and early warning operations are performed according to the abnormal event identification results.

[0008] In this solution, the historical working data of each CT self-collecting video surveillance in the target area is obtained, and the historical working data is analyzed based on the hidden Markov model to construct a working task recognition model for video surveillance, specifically: Obtain the historical working data of each CT self-collecting video surveillance in the target area, wherein the historical working data includes the working current and voltage data, the processor load status, the camera motion trajectory parameters and the work task labels marked at the corresponding time during the video surveillance operation, wherein the work task labels include target tracking and anomaly detection; Performing timestamp alignment and missing value interpolation preprocessing on the historical working data, dividing it into continuous time slot segments using a sliding window, normalizing the working current and voltage data, processor load status, and camera motion trajectory parameters, and generating an observation sequence of the hidden Markov model input data type; Define the hidden state set of the hidden Markov model as the various types of work tasks marked in the work task label, and import the observation sequence into the hidden Markov model as the observation state and hidden state set of the hidden Markov model; The initial state transition probability matrix and observation probability matrix of the hidden Markov model are calculated by the forward-backward algorithm, the true hidden state of each time slot segment is supervised and constrained by the labeled task labels, and the distribution parameters of the state transition probability and observation probability are iteratively optimized by the label-corrected Baum-Welch algorithm. When the path matching rate between the hidden state sequence generated by the model and the actual labeled work task sequence increases less than the preset threshold for three consecutive iterations, the training is terminated and a work task recognition model that integrates the video surveillance work data features and work task association rules is output.

[0009] In this solution, the work task identification model is used to identify the work task of each video surveillance within the preset time period, obtain the power change data of the video surveillance within the preset time period, and evaluate the work quality under each work task of the video surveillance to construct a work task-power-quality data matrix, which is specifically: Acquire the real-time working data of each video surveillance within a preset time, import the real-time working data into the work task identification model, and determine the work task change data of each video surveillance within the preset time period, wherein the work task change data includes the work task name and the duration of each work task; Obtaining power change data of each video surveillance within a preset time period and target recognition data under different work tasks, wherein the power change data includes charge and discharge data, and the target recognition data includes target detection box selection data or abnormal detection result data under the corresponding work task; Determine the target recognition data for each video frame of the monitored video within a preset time period according to the target recognition data, and determine the moving trajectory of the target detection frame according to the target recognition data for each video frame; For the target tracking task, the target selection accuracy and tracking trajectory continuity are determined according to the moving trajectory, and the anomaly detection accuracy of the anomaly detection task within a preset time period is determined according to the anomaly detection result data; Determine the work quality of each video monitoring task based on the target selection accuracy, tracking trajectory continuity, and anomaly detection accuracy; The work task changes, power change data, and work quality within the preset time period are aligned in time series to construct a work task-power-quality data matrix.

[0010] In this solution, each video monitoring is clustered according to the work task-power-quality data matrix, the monitoring task of each monitoring cluster is determined, and the monitoring task allocation scheme is obtained, which is specifically: Determine the influence of different power on the work quality of each work task according to the work task-power-quality data matrix, and obtain influence data, wherein the influence data includes a mapping relationship between each power threshold interval and the corresponding work quality compliance rate; Monitor the current remaining power of each video surveillance in real time, match the set of work tasks that are allowed to be executed in the corresponding power threshold interval in the impact data according to the current remaining power, and build a candidate task pool for each video surveillance; Acquire the environmental perception data of the target area at the current moment, trigger the target tracking mode when a moving target is detected, calculate the azimuth angle between each video surveillance camera and the target motion trajectory, and determine the quality influence coefficient of the current remaining power on the target tracking task according to the influence data; Generate a comprehensive scoring result of the orientation matching degree and the power guarantee degree according to the orientation angle and the quality influence coefficient, and obtain the applicability score of each video monitoring; Video surveillance with a fitness score lower than the preset threshold is removed from the target tracking cluster, and the top N video surveillances are dynamically assigned to the target tracking cluster according to the score ranking, and the remaining surveillances are assigned to the anomaly detection cluster; When the remaining power of any video monitoring drops to a first critical threshold, the work task type with the highest quality compliance rate under the remaining power is determined according to the impact data, and the video monitoring is reallocated to the corresponding task cluster to obtain a monitoring task allocation plan; The power consumption rate and work quality compliance rate of each cluster task are continuously collected during execution. When it is detected that the average quality compliance rate of a cluster is lower than the second critical threshold, the suitability scores of all monitoring in the area are recalculated and the monitoring task allocation plan is adjusted until the cluster task quality is restored to within the safety threshold range.

[0011] In this solution, the influence of different power on the work quality of each work task is determined according to the work task-power-quality data matrix to obtain the influence data, which is specifically: Based on the work task-power-quality data matrix, the work quality data of each video surveillance executing each work task under different power states during the historical operation period are extracted, the power data of the continuous time series are divided into power change segments through a sliding time window, and the power values ​​in each segment are clustered and analyzed to divide multiple power threshold intervals representing the power level; For each work task type, the proportion of samples with work quality that meet the standards in each power threshold interval to the total number of samples in the interval is counted to generate an initial mapping relationship between the power threshold interval and the quality compliance rate; The probability density estimation method is used to fit the probability distribution of the quality compliance rate within each power threshold interval, and the significance difference degree of the work quality distribution between different power intervals is calculated according to the probability distribution. If the difference in the work quality distribution of adjacent power intervals does not reach the preset significance level, the power threshold intervals are merged; Based on the merged power threshold intervals, the mean and variance of the work quality compliance rate in each interval are recalculated, the abnormal intervals whose variance exceeds the stability threshold are eliminated, and the power threshold intervals and their corresponding quality compliance rates that meet the confidence conditions are retained; A dynamic matching relationship is established between the finally divided power threshold interval and the quality compliance rate, and a mapping table of the preset power threshold interval and the work quality compliance rate is generated as the influencing data.

[0012] In this solution, the video surveillance data of the target area is obtained according to the monitoring task allocation plan, abnormal events are identified according to the video surveillance data, and monitoring and early warning operations are performed according to the abnormal event identification results, specifically: Based on the monitoring cluster task types divided in the monitoring task allocation scheme, the video monitoring devices in each cluster are dynamically scheduled to collect real-time video stream data of the target area, and the video stream data is input into a preset abnormal event recognition model, wherein the abnormal event recognition model is generated based on historical abnormal event sample training, and its input features include dynamic target features in the video frame, environmental change patterns, and spatiotemporal correlation of target motion trajectories; The abnormal event recognition model is used to perform feature matching on the video stream data. When an abnormal pattern whose matching degree exceeds a threshold value in the preset abnormal feature library is detected to appear continuously in the video frame sequence, the time window, spatial distribution and feature intensity of the abnormal event are extracted to generate an abnormal event determination result; According to the determination result, if the abnormal event feature intensity is lower than the first risk threshold, it is marked as a potential abnormal event and the acquisition frame rate and target tracking parameters of the corresponding monitoring cluster are adjusted to continuously verify the abnormal features; If the feature intensity exceeds the first risk threshold, an alarm signal is generated according to the type of abnormal event, the time window data, spatial coordinates and enhanced video clips of the abnormal event are simultaneously uploaded to the cloud platform, and the directional warning function of the sound and light alarm device in the target area is activated; During the duration of the alarm signal, the spatial diffusion trend and characteristic intensity changes of abnormal events are monitored in real time. If the diffusion trend exceeds the preset safety range or the characteristic intensity reaches the second risk threshold, the emergency resource scheduling path is determined based on the type and location of the abnormal event.

[0013] The second aspect of the present invention also provides a CT self-service electricity video monitoring and early warning device based on environmental perception, the system comprising: a memory, a processor, the memory comprising a CT self-service electricity video monitoring and early warning method program based on environmental perception, the CT self-service electricity video monitoring and early warning method program based on environmental perception when executed by the processor, implements the following steps: Obtaining historical working data of each CT self-collecting video surveillance in the target area, analyzing the historical working data based on a hidden Markov model, and constructing a working task recognition model for video surveillance; According to the work task identification model, work tasks are identified for each video surveillance within a preset time period, power change data of the video surveillance within the preset time period is obtained, and the work quality under each work task of the video surveillance is evaluated to construct a work task-power-quality data matrix; Clustering each video monitoring according to the work task-power-quality data matrix, determining the monitoring task of each monitoring cluster, and obtaining a monitoring task allocation plan; The video surveillance data of the target area is acquired according to the monitoring task allocation plan, abnormal events are identified according to the video surveillance data, and monitoring and early warning operations are performed according to the abnormal event identification results.

[0014] The present invention discloses a CT self-collecting power video monitoring and early warning method and device based on environmental perception. The method acquires the historical working data of CT self-collecting power video monitoring in the target area, and constructs a work task identification model based on the hidden Markov model; uses the model to identify the work tasks within a preset time period, analyzes the power changes and evaluates the work quality, and constructs a work task-power-quality data matrix; performs cluster division based on the matrix, and determines the monitoring task allocation plan; obtains video monitoring data according to the plan, identifies abnormal events, and performs monitoring and early warning. The present invention optimizes the allocation of video monitoring tasks, improves monitoring efficiency and early warning accuracy, and is suitable for the fields of intelligent monitoring and power management. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A flow chart of a CT self-collected electric and video monitoring and early warning method based on environment perception of the present invention is shown; Figure 2 A flow chart of obtaining influence data according to the present invention is shown; Figure 3 A flow chart showing monitoring and early warning operations of the present invention is shown; Figure 4 The block diagram of the CT self-collecting electric video monitoring and early warning device based on environment perception of the present invention is shown. DETAILED DESCRIPTION

[0016] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0017] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0018] Figure 1 The present invention shows a flow chart of a CT self-collected electric and video monitoring and early warning method based on environment perception.

[0019] like Figure 1 As shown, the first aspect of the present invention provides a CT self-collected electric video monitoring and early warning method based on environment perception, comprising: S102, obtaining historical working data of each CT self-collecting video surveillance in the target area, analyzing the historical working data based on a hidden Markov model, and constructing a working task recognition model for video surveillance; S104, identifying the work task of each video surveillance within the preset time period according to the work task identification model, obtaining the power change data of the video surveillance within the preset time period, and evaluating the work quality under each work task of the video surveillance, and constructing a work task-power-quality data matrix; S106, clustering each video monitoring according to the work task-power-quality data matrix, determining the monitoring task of each monitoring cluster, and obtaining a monitoring task allocation plan; S108, acquiring video surveillance data of the target area according to the monitoring task allocation plan, identifying abnormal events according to the video surveillance data, and performing monitoring and early warning operations according to the abnormal event identification results.

[0020] It should be noted that by constructing a work task recognition model based on the hidden Markov model, the problem of inaccurate task type recognition caused by dynamic changes in the environment in traditional video surveillance systems is effectively solved. The correlation between the equipment operating status and the task type can be mined from complex historical work data, and the intelligent level of monitoring task classification can be improved. By establishing a work task-power-quality data matrix, the limitation of the separation analysis of power consumption and task execution quality in the existing technology is broken through, and the quantitative evaluation of the impact of dynamic power changes on task execution efficiency is realized, providing data support for subsequent resource optimization configuration. The matrix-based clustering method overcomes the defect of unbalanced equipment load in the fixed task allocation mode. By dynamically matching the relationship between the remaining power of the equipment and the task quality requirements, an adaptive monitoring task allocation scheme is formed, which significantly improves the collaborative work efficiency of the equipment cluster in low-power scenarios. Finally, combined with the abnormal recognition and graded warning mechanism of environmental perception, the problem of missed detection and delayed response of abnormal events caused by the limited perspective of a single device in the traditional monitoring system is solved. Through cluster collaborative data fusion analysis, the accurate positioning of abnormal events and the dynamic evaluation of risk levels are realized, thereby effectively improving the real-time monitoring and early warning and the accuracy of emergency response in complex environments while ensuring the endurance of the equipment.

[0021] According to an embodiment of the present invention, the historical working data of each CT self-collecting video surveillance in the target area is obtained, the historical working data is analyzed based on a hidden Markov model, and a working task recognition model of video surveillance is constructed, specifically: Obtain the historical working data of each CT self-collecting video surveillance in the target area, wherein the historical working data includes the working current and voltage data, the processor load status, the camera motion trajectory parameters and the work task labels marked at the corresponding time during the video surveillance operation, wherein the work task labels include target tracking and anomaly detection; Performing timestamp alignment and missing value interpolation preprocessing on the historical working data, dividing it into continuous time slot segments using a sliding window, normalizing the working current and voltage data, processor load status, and camera motion trajectory parameters, and generating an observation sequence of the hidden Markov model input data type; Define the hidden state set of the hidden Markov model as the various types of work tasks marked in the work task label, and import the observation sequence into the hidden Markov model as the observation state and hidden state set of the hidden Markov model; The initial state transition probability matrix and observation probability matrix of the hidden Markov model are calculated by the forward-backward algorithm, the true hidden state of each time slot segment is supervised and constrained by the labeled task labels, and the distribution parameters of the state transition probability and observation probability are iteratively optimized by the label-corrected Baum-Welch algorithm. When the path matching rate between the hidden state sequence generated by the model and the actual labeled work task sequence increases less than the preset threshold for three consecutive iterations, the training is terminated and a work task recognition model that integrates the video surveillance work data features and work task association rules is output.

[0022] It should be noted that the dynamic relationship between the multi-dimensional operating parameters of video surveillance equipment (such as current, voltage, processor load, camera motion trajectory) and the work task label is probabilistically represented by using the modeling ability of the hidden Markov model for time series data, so as to achieve accurate identification of the equipment work task. Specifically, by defining the work task type as a hidden state and the equipment operation parameters as an observed state, the hidden Markov model can learn the typical characteristic distribution of equipment operation parameters under different work tasks (such as high processor load and frequent camera movement corresponding to the target tracking task), and capture the state transition law when the work task is switched (such as the transition probability of triggering target tracking after the anomaly detection task is completed). In the model training process, through the supervised correction mechanism with annotated labels, combined with the joint optimization of the forward-backward algorithm and the Baum-Welch algorithm, the misjudgment problem caused by the fuzzy association between the observed data and the hidden state in the traditional unsupervised hidden Markov model in task identification is effectively solved, and the path matching accuracy of the model for the actual work task sequence is significantly improved. The work task identification model generated in this way can not only analyze the implicit task types in the equipment operation data in real time, but also adapt to parameter fluctuations caused by hardware differences or environmental interference of different devices, and ultimately realize dynamic perception and highly robust classification of work task types in complex scenarios, providing reliable task status input for subsequent cluster collaborative scheduling based on power and task quality. Supervised constraints refer to the use of annotated work task labels to forcibly guide the authenticity of hidden states during the training process of hidden Markov models. By taking the known time slot work task labels as the true values ​​of hidden states, the parameter update direction of the model in the calculation of state transition probability and observation probability is directly corrected, thereby breaking through the limitations of the traditional unsupervised Baum-Welch algorithm that relies on pure statistical learning; the Baum-Welch algorithm with label correction is an improvement on the classic algorithm based on supervised constraints. During the iteration of the expectation maximization (EM) algorithm, when calculating the probability of state sequence through the forward-backward algorithm, the hidden state path corresponding to the annotated label is injected into the parameter estimation link as prior knowledge, forcing the probability weight of the wrong transfer path in the state transition matrix to be adjusted. At the same time, when optimizing the observation probability matrix, the observed value distribution of the equipment operation parameters (such as current fluctuation, camera motion trajectory) is corrected in a targeted manner according to the real work task type corresponding to the label, so that the model parameter update not only depends on the statistical characteristics of the observed data, but also deeply integrates the deterministic laws of known task labels.This hybrid training mechanism that integrates supervision and unsupervised training can significantly improve the model's ability to capture the implicit correlation between equipment work tasks and operating parameters, and effectively solve the problems of large differences in parameter distribution of similar tasks and strong randomness in task switching timing caused by equipment heterogeneity in traditional methods, ultimately achieving high-precision convergence and strong generalization ability of the work task identification model; the distribution parameters of the state transition probability include the state transition probability matrix elements between each work task type, and the distribution parameters of the observation probability include the normalized sensor data quantization level probability, the processor load level probability, and the camera motion trajectory discrete angular velocity interval probability.

[0023] According to an embodiment of the present invention, the work task identification is performed on each video surveillance within a preset time period according to the work task identification model, the power change data of the video surveillance within the preset time period is obtained, and the work quality under each work task of the video surveillance is evaluated to construct a work task-power-quality data matrix, specifically: Acquire the real-time working data of each video surveillance within a preset time, import the real-time working data into the work task identification model, and determine the work task change data of each video surveillance within the preset time period, wherein the work task change data includes the work task name and the duration of each work task; Obtaining power change data of each video surveillance within a preset time period and target recognition data under different work tasks, wherein the power change data includes charge and discharge data, and the target recognition data includes target detection box selection data or abnormal detection result data under the corresponding work task; Determine the target recognition data for each video frame of the monitored video within a preset time period according to the target recognition data, and determine the moving trajectory of the target detection frame according to the target recognition data for each video frame; For the target tracking task, the target selection accuracy and tracking trajectory continuity are determined according to the moving trajectory, and the anomaly detection accuracy of the anomaly detection task within a preset time period is determined according to the anomaly detection result data; Determine the work quality of each video monitoring task based on the target selection accuracy, tracking trajectory continuity, and anomaly detection accuracy; The work task changes, power change data, and work quality within the preset time period are aligned in time series to construct a work task-power-quality data matrix.

[0024] It should be noted that in the target tracking task, the target detection frame movement trajectory analysis between consecutive video frames can effectively identify the tracking jitter or target loss caused by insufficient device power, so as to accurately evaluate the trajectory continuity quality of the tracking task; in the anomaly detection task, the anomaly detection results are compared with the real scene to verify and quantify the quality indicators such as the false alarm rate and missed detection rate of the device in a specific power range; by aligning the task type, duration, power change curve and quality evaluation results in the time dimension, the constructed three-dimensional data matrix can intuitively reflect the quality attenuation law of various types of tasks under different power thresholds, such as identifying It can identify the characteristics of a sharp increase in the probability of trajectory fracture when the device performs a target tracking task when the remaining power is lower than a certain critical value, or discover the operating characteristics of anomaly detection tasks that maintain a high accuracy rate in a medium power range, thereby providing a data-driven decision-making basis for subsequent dynamic task allocation, effectively avoiding the problem of system reliability degradation caused by the forced execution of high-precision tasks under low power conditions by the traditional system due to the lack of task-power-quality correlation analysis. At the same time, through the prediction of the quality attenuation law, the preventive adjustment of the equipment working mode can be achieved, which significantly improves the task execution success rate and the timeliness of abnormal event handling of the self-power monitoring system under limited energy conditions.

[0025] According to an embodiment of the present invention, each video monitoring is clustered according to the work task-power-quality data matrix, the monitoring task of each monitoring cluster is determined, and a monitoring task allocation scheme is obtained, which is specifically: Determine the influence of different power on the work quality of each work task according to the work task-power-quality data matrix, and obtain influence data, wherein the influence data includes a mapping relationship between each power threshold interval and the corresponding work quality compliance rate; Monitor the current remaining power of each video surveillance in real time, match the set of work tasks that are allowed to be executed in the corresponding power threshold interval in the impact data according to the current remaining power, and build a candidate task pool for each video surveillance; Acquire the environmental perception data of the target area at the current moment, trigger the target tracking mode when a moving target is detected, calculate the azimuth angle between each video surveillance camera and the target motion trajectory, and determine the quality influence coefficient of the current remaining power on the target tracking task according to the influence data; Generate a comprehensive scoring result of the orientation matching degree and the power guarantee degree according to the orientation angle and the quality influence coefficient, and obtain the applicability score of each video monitoring; Video surveillance with a fitness score lower than the preset threshold is removed from the target tracking cluster, and the top N video surveillances are dynamically assigned to the target tracking cluster according to the score ranking, and the remaining surveillances are assigned to the anomaly detection cluster; When the remaining power of any video monitoring drops to a first critical threshold, the work task type with the highest quality compliance rate under the remaining power is determined according to the impact data, and the video monitoring is reallocated to the corresponding task cluster to obtain a monitoring task allocation plan; The power consumption rate and work quality compliance rate of each cluster task are continuously collected during execution. When it is detected that the average quality compliance rate of a cluster is lower than the second critical threshold, the suitability scores of all monitoring in the area are recalculated and the monitoring task allocation plan is adjusted until the cluster task quality is restored to within the safety threshold range.

[0026] It should be noted that the fixed task allocation mode often leads to unstable task execution quality due to fluctuations in device power and dynamic changes in the environment. For example, when low-power devices continue to perform high-energy tracking tasks, problems such as target loss and missed anomaly detection are prone to occur. When an abnormal event occurs in the environment, the optimal monitoring cluster cannot be quickly formed due to the fixed device tasks, resulting in waste of monitoring resources and low response efficiency. Therefore, by establishing a power-task quality association model and a dynamic cluster division mechanism, efficient coordination of monitoring equipment in resource-constrained scenarios is achieved: first, based on historical data, the constraints of different power intervals on the quality of various tasks are mined, and dynamic matching rules between power thresholds and task quality are constructed to provide equipment with a candidate task pool that is power-adapted; secondly, by combining real-time environmental perception data (such as the direction of the moving target) and the dual evaluation of the remaining power of the equipment, through the fusion score of spatial coverage (direction angle) and power support (quality impact coefficient), the equipment cluster that can both guarantee the quality of the task and have the optimal spatial layout in the current environment is dynamically screened; when the power of the equipment drops to the critical threshold, it is automatically switched to the task type with the highest quality compliance rate under the current power level to avoid the systemic risks caused by low-power equipment forcing high-precision tasks; at the same time, through closed-loop monitoring and dynamic redistribution of the execution quality of cluster tasks, the load balancing of equipment is continuously optimized, and the problem of overall cluster efficiency decline caused by environmental mutations or equipment performance degradation in traditional systems is effectively solved, and finally, the task execution success rate and abnormal event response speed of the monitoring system are improved simultaneously under limited energy supply, extending the equipment life cycle while ensuring the stability of monitoring and early warning. Environmental perception data refers to the characteristic information reflecting the dynamic changes of the monitoring scene obtained in real time through video monitoring equipment and related sensors, including the motion trajectory of the mobile target, speed change, direction deviation, environmental occlusion, lighting condition fluctuations and other multi-dimensional parameters related to the target behavior pattern and environmental interference. When determining the quality impact coefficient of the current remaining power on the target tracking task, firstly, based on the pre-established mapping relationship between the power threshold interval and the quality compliance rate, the interval range to which the current remaining power belongs is located, and the historical average quality compliance rate of the target tracking task in this interval is obtained as the benchmark value; then, combined with the dynamic interference factors in the real-time environmental perception data (such as the intensity of the target movement and the frequency of occlusion), the additional loss weight of environmental interference on the quality of task execution is quantified through the preset environmental complexity evaluation model, such as high-speed movement or frequent occlusion will trigger the quality attenuation factor; finally, the baseline quality compliance rate is dynamically coupled with the attenuation factor caused by environmental interference to generate a composite quality impact coefficient that comprehensively reflects the current power support capacity and the degree of environmental challenges.

[0027] Figure 2 A flow chart of obtaining influence data according to the present invention is shown.

[0028] According to an embodiment of the present invention, the influence of different electric quantities on the work quality of each work task is determined according to the work task-electric quantity-quality data matrix to obtain the influence data, specifically: S202, based on the work task-power-quality data matrix, extract the work quality data of each video surveillance executing each work task under different power states during the historical operation period, divide the power data of the continuous time series into power change segments through a sliding time window, perform cluster analysis on the power value in each segment, and divide multiple power threshold intervals representing the power level; S204, for each work task type, counting the proportion of the number of samples that meet the work quality standards within each power threshold interval to the total number of samples in the interval, and generating an initial mapping relationship between the power threshold interval and the quality compliance rate; S206, using a probability density estimation method to perform probability distribution fitting on the quality compliance rate within each power threshold interval, and calculating the significance difference of the work quality distribution between different power intervals according to the probability distribution, and merging the power threshold intervals if the difference in the work quality distribution between adjacent power intervals does not reach a preset significance level; S208, recalculating the mean and variance of the work quality compliance rate in each interval based on the merged power threshold intervals, eliminating abnormal intervals whose variance exceeds the stability threshold, and retaining the power threshold intervals and their corresponding quality compliance rates that meet the confidence condition; S210, establishing a dynamic matching relationship between the finally divided power threshold interval and the quality compliance rate, and generating a mapping table of preset power threshold intervals and work quality compliance rates as influencing data.

[0029] It should be noted that, based on the sliding time window and cluster analysis technology, multiple threshold intervals that can characterize the typical power status of the equipment are identified from the continuously changing power data, overcoming the empirical bias that may exist in the artificial setting of fixed power segments; then, by statistically analyzing the distribution law of the task quality compliance rate in each power interval, a preliminary correlation between the power level and the task quality is established; then, using probability density estimation and significance difference test, the initial divided intervals are scientifically verified and merged and optimized to eliminate statistical noise caused by random data sampling or too fine intervals, ensuring that the internal quality compliance rate of each retained power threshold interval has statistically significant differences and distribution consistency; finally, through variance analysis and confidence screening, the intervals with excessive fluctuations caused by individual differences in equipment or abnormal working conditions are eliminated, and the power intervals with stable quality characterization capabilities are retained, thereby generating a dynamically matched power threshold-quality compliance rate mapping table. This process, through multi-level data cleaning and statistical verification, not only avoids the over-simplification of the complex nonlinear relationship between electricity and quality by simple threshold segmentation in traditional methods, but also ensures the robustness of the influencing data under equipment heterogeneity and environmental fluctuations, and finally forms influencing data that can accurately reflect the law of changes in task execution efficiency under different electricity states, providing a reliable electricity constraint model for dynamic task allocation. The calculation of the confidence is realized by combining probability density estimation with hypothesis testing: first, based on the historical quality compliance rate samples within each electricity threshold interval, a probability distribution model of the quality compliance rate is constructed by using parameter estimation (such as the mean variance model under normal distribution) or non-parametric kernel density estimation method; then, by calculating the confidence interval range corresponding to the preset confidence level (such as 95%) under the distribution, the probability that the true value of the quality compliance rate falls within this interval is determined. The calculation depends on the sample mean, standard deviation and sample size (such as the critical value of t distribution or Z score), and finally forms a confidence index that characterizes the reliability of interval estimation. The confidence condition is that the width of the confidence interval is less than the preset value.

[0030] Figure 3 A flow chart of monitoring and early warning operations of the present invention is shown.

[0031] According to an embodiment of the present invention, the acquisition of video surveillance data of the target area according to the monitoring task allocation scheme, the identification of abnormal events according to the video surveillance data, and the monitoring and early warning operation according to the abnormal event identification result are specifically as follows: S302, based on the monitoring cluster task types divided in the monitoring task allocation scheme, dynamically dispatch the video monitoring devices in each cluster to collect real-time video stream data of the target area, and input the video stream data into a preset abnormal event recognition model, wherein the abnormal event recognition model is generated based on historical abnormal event sample training, and its input features include dynamic target features in the video frame, environmental change patterns, and spatiotemporal correlation of target motion trajectories; S304, performing feature matching on the video stream data through the abnormal event recognition model, and when detecting that abnormal patterns with a matching degree exceeding a threshold value appear continuously in the video frame sequence with those in the preset abnormal feature library, extracting the time window, spatial distribution and feature intensity of the abnormal event, and generating an abnormal event determination result; S306, according to the determination result, if the abnormal event feature intensity is lower than the first risk threshold, it is marked as a potential abnormal event and the acquisition frame rate and target tracking parameters of the corresponding monitoring cluster are adjusted to continuously verify the abnormal features; S308, if the feature intensity exceeds the first risk threshold, an alarm signal is generated according to the type of abnormal event, the time window data, spatial coordinates and enhanced video clips of the abnormal event are simultaneously uploaded to the cloud platform, and the directional warning function of the sound and light alarm device in the target area is activated; S310: During the duration of the alarm signal, the spatial diffusion trend and characteristic intensity changes of abnormal events are monitored in real time. If the diffusion trend exceeds the preset safety range or the characteristic intensity reaches the second risk threshold, the emergency resource scheduling path is determined according to the type of abnormal event and the location of the abnormal event.

[0032] It should be noted that the multi-dimensional feature analysis of video stream data (dynamic targets, environmental changes, and temporal and spatial correlations) based on the pre-trained anomaly recognition model can effectively capture hidden abnormal patterns that are difficult to identify with traditional single-frame detection methods (such as slowly spreading leakage events or intermittent suspicious behaviors), and reduce the misjudgment rate by matching abnormal features of continuous frame sequences; when potential anomalies are detected, the acquisition frame rate and tracking parameters of the monitoring cluster are adaptively adjusted to achieve continuous high-precision tracking of suspicious targets, avoiding the problem of feature loss caused by insufficient resolution in the traditional fixed parameter mode; differentiated early warning strategies are initiated for abnormal events of different risk levels, and low-risk Events trigger the optimization and reorganization of monitoring resources to verify features, and high-risk events link the cloud and sound and light alarm devices to achieve multi-modal warnings, ensuring real-time synchronization and rapid response of key information; in addition, by real-time monitoring of the spatial diffusion trend and intensity changes of abnormal events, dynamic generation of resource scheduling paths can accurately match the needs of event evolution (such as giving priority to dispatching surrounding fire-fighting resources when a fire spreads), overcoming the response lag and resource mismatch problems of traditional plan-based scheduling, thereby reducing the system's false alarm rate while comprehensively improving the closed-loop disposal efficiency from abnormality perception to resource scheduling, and achieving coordinated optimization of the monitoring and early warning system in event identification accuracy, response real-time, and resource utilization efficiency. Abnormal modes include abnormal behavioral characteristics of dynamic targets in video scenes (such as sudden acceleration, reverse movement or group gathering), abnormal changes in environmental parameters (such as abnormal temperature gradient, regional color difference changes caused by smoke diffusion or liquid leakage), and abnormal spatiotemporal correlation of target motion trajectories (such as wandering paths exceeding preset safety routes, abnormal stays in specific areas or high-frequency returns), and also cover abnormal correlations between interactive behaviors of multiple targets (such as illegal transfer of objects, abnormal shortening of following distance); target tracking parameters include camera gimbal steering speed, optical zoom ratio, video acquisition frame rate, trajectory prediction model parameters in the tracking algorithm (such as Kalman filter coefficients, motion speed weights), target feature matching thresholds (such as color histogram similarity, contour recognition accuracy) and multi-target tracking priority rules (such as priority locking of near-field targets and continuous focus on high-threat targets).

[0033] Figure 4 The block diagram of the CT self-collecting electric video monitoring and early warning device based on environment perception of the present invention is shown.

[0034] The second aspect of the present invention further provides a CT self-service electricity video monitoring and early warning device 4 based on environmental perception, the system comprising: a memory 41, a processor 42, the memory comprising a CT self-service electricity video monitoring and early warning method program based on environmental perception, the CT self-service electricity video monitoring and early warning method program based on environmental perception when executed by the processor, implements the following steps: Obtaining historical working data of each CT self-collecting video surveillance in the target area, analyzing the historical working data based on a hidden Markov model, and constructing a working task recognition model for video surveillance; According to the work task identification model, work tasks are identified for each video surveillance within a preset time period, power change data of the video surveillance within the preset time period is obtained, and the work quality under each work task of the video surveillance is evaluated to construct a work task-power-quality data matrix; Clustering each video monitoring according to the work task-power-quality data matrix, determining the monitoring task of each monitoring cluster, and obtaining a monitoring task allocation plan; The video surveillance data of the target area is acquired according to the monitoring task allocation plan, abnormal events are identified according to the video surveillance data, and monitoring and early warning operations are performed according to the abnormal event identification results.

[0035] The present invention discloses a CT self-collecting power video monitoring and early warning method and device based on environmental perception. The method acquires the historical working data of CT self-collecting power video monitoring in the target area, and constructs a work task identification model based on the hidden Markov model; uses the model to identify the work tasks within a preset time period, analyzes the power changes and evaluates the work quality, and constructs a work task-power-quality data matrix; performs cluster division based on the matrix, and determines the monitoring task allocation plan; obtains video monitoring data according to the plan, identifies abnormal events, and performs monitoring and early warning. The present invention optimizes the allocation of video monitoring tasks, improves monitoring efficiency and early warning accuracy, and is suitable for the fields of intelligent monitoring and power management.

[0036] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0037] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0038] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0039] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0040] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0041] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A CT self-collected video monitoring and early warning method based on environmental perception, characterized in that: The following steps are involved: Obtaining historical working data of each CT self-collecting video surveillance in the target area, analyzing the historical working data based on a hidden Markov model, and constructing a working task recognition model for video surveillance; According to the work task identification model, work tasks are identified for each video surveillance within a preset time period, power change data of the video surveillance within the preset time period is obtained, and the work quality under each work task of the video surveillance is evaluated to construct a work task-power-quality data matrix; Clustering each video monitoring according to the work task-power-quality data matrix, determining the monitoring task of each monitoring cluster, and obtaining a monitoring task allocation plan; The video surveillance data of the target area is acquired according to the monitoring task allocation plan, abnormal events are identified according to the video surveillance data, and monitoring and early warning operations are performed according to the abnormal event identification results.

2. The method for monitoring and early warning of CT self-collected electric video based on environment perception according to claim 1 is characterized in that: The method of obtaining the historical working data of each CT self-collecting video surveillance in the target area, analyzing the historical working data based on the hidden Markov model, and constructing a working task recognition model for video surveillance is specifically as follows: Obtain the historical working data of each CT self-collecting video surveillance in the target area, wherein the historical working data includes the working current and voltage data, the processor load status, the camera motion trajectory parameters and the work task labels marked at the corresponding time during the video surveillance operation, wherein the work task labels include target tracking and anomaly detection; Performing timestamp alignment and missing value interpolation preprocessing on the historical working data, dividing it into continuous time slot segments using a sliding window, normalizing the working current and voltage data, processor load status, and camera motion trajectory parameters, and generating an observation sequence of the hidden Markov model input data type; Define the hidden state set of the hidden Markov model as the various types of work tasks marked in the work task label, and import the observation sequence into the hidden Markov model as the observation state and hidden state set of the hidden Markov model; The initial state transition probability matrix and observation probability matrix of the hidden Markov model are calculated by the forward-backward algorithm, the true hidden state of each time slot segment is supervised and constrained by the labeled task labels, and the distribution parameters of the state transition probability and observation probability are iteratively optimized by the label-corrected Baum-Welch algorithm. When the path matching rate between the hidden state sequence generated by the model and the actual labeled work task sequence increases less than the preset threshold for three consecutive iterations, the training is terminated and a work task recognition model that integrates the video surveillance work data features and work task association rules is output.

3. The method for monitoring and early warning of CT self-collected electric video based on environment perception according to claim 1 is characterized in that: The work task identification model is used to identify each video surveillance within a preset time period, obtain the power change data of the video surveillance within the preset time period, and evaluate the work quality under each work task of the video surveillance to construct a work task-power-quality data matrix, specifically: Acquire the real-time working data of each video surveillance within a preset time, import the real-time working data into the work task identification model, and determine the work task change data of each video surveillance within the preset time period, wherein the work task change data includes the work task name and the duration of each work task; Obtaining power change data of each video surveillance within a preset time period and target recognition data under different work tasks, wherein the power change data includes charge and discharge data, and the target recognition data includes target detection box selection data or abnormal detection result data under the corresponding work task; Determine the target recognition data for each video frame of the monitoring video within a preset time period according to the target recognition data, and determine the moving trajectory of the target detection frame according to the target recognition data for each video frame; For the target tracking task, the target selection accuracy and tracking trajectory continuity are determined according to the moving trajectory, and the anomaly detection accuracy of the anomaly detection task within a preset time period is determined according to the anomaly detection result data; Determine the work quality of each video monitoring task based on the target selection accuracy, tracking trajectory continuity, and anomaly detection accuracy; The work task changes, power change data, and work quality within the preset time period are aligned in time series to construct a work task-power-quality data matrix.

4. The method for monitoring and early warning of CT self-collected electric video based on environment perception according to claim 1 is characterized in that: The method of clustering each video monitoring according to the work task-power-quality data matrix, determining the monitoring task of each monitoring cluster, and obtaining a monitoring task allocation scheme is as follows: Determine the influence of different power on the work quality of each work task according to the work task-power-quality data matrix, and obtain influence data, wherein the influence data includes a mapping relationship between each power threshold interval and the corresponding work quality compliance rate; Monitor the current remaining power of each video surveillance in real time, match the set of work tasks that are allowed to be executed in the corresponding power threshold interval in the impact data according to the current remaining power, and build a candidate task pool for each video surveillance; Acquire environmental perception data of the target area at the current moment, trigger the target tracking mode when a moving target is detected, calculate the azimuth angle between each video surveillance camera and the target motion trajectory, and determine the quality influence coefficient of the current remaining power on the target tracking task according to the influence data; Generate a comprehensive scoring result of the orientation matching degree and the power guarantee degree according to the orientation angle and the quality influence coefficient, and obtain the applicability score of each video monitoring; Video surveillance with a fitness score lower than the preset threshold is removed from the target tracking cluster, and the top N video surveillances are dynamically assigned to the target tracking cluster according to the score ranking, and the remaining surveillances are assigned to the anomaly detection cluster; When the remaining power of any video monitoring drops to a first critical threshold, the work task type with the highest quality compliance rate under the remaining power is determined according to the impact data, and the video monitoring is reallocated to the corresponding task cluster to obtain a monitoring task allocation plan; The power consumption rate and work quality compliance rate of each cluster task are continuously collected during execution. When it is detected that the average quality compliance rate of a cluster is lower than the second critical threshold, the suitability scores of all monitoring in the area are recalculated and the monitoring task allocation plan is adjusted until the cluster task quality is restored to within the safety threshold range.

5. The method for monitoring and early warning of CT self-collected electric and video signals based on environment perception according to claim 4 is characterized in that: The influence of different power on the work quality of each work task is determined according to the work task-power-quality data matrix to obtain the influence data, specifically: Based on the work task-power-quality data matrix, the work quality data of each video surveillance executing each work task under different power states during the historical operation period are extracted, the power data of the continuous time series are divided into power change segments through a sliding time window, and the power values ​​in each segment are clustered and analyzed to divide multiple power threshold intervals representing the power level; For each work task type, the proportion of samples with work quality that meet the standards in each power threshold interval to the total number of samples in the interval is counted to generate an initial mapping relationship between the power threshold interval and the quality compliance rate; The probability density estimation method is used to fit the probability distribution of the quality compliance rate within each power threshold interval, and the significance difference degree of the work quality distribution between different power intervals is calculated according to the probability distribution. If the difference in the work quality distribution of adjacent power intervals does not reach the preset significance level, the power threshold intervals are merged; Based on the merged power threshold intervals, the mean and variance of the work quality compliance rate in each interval are recalculated, the abnormal intervals whose variance exceeds the stability threshold are eliminated, and the power threshold intervals and their corresponding quality compliance rates that meet the confidence conditions are retained; A dynamic matching relationship is established between the finally divided power threshold interval and the quality compliance rate, and a mapping table of the preset power threshold interval and the work quality compliance rate is generated as the influencing data.

6. The method for monitoring and early warning of CT self-collected electric video based on environment perception according to claim 1 is characterized in that: The acquiring of video surveillance data of the target area according to the monitoring task allocation scheme, identifying abnormal events according to the video surveillance data, and performing monitoring and early warning operations according to the abnormal event identification results are specifically as follows: Based on the monitoring cluster task types divided in the monitoring task allocation scheme, the video monitoring devices in each cluster are dynamically scheduled to collect real-time video stream data of the target area, and the video stream data is input into a preset abnormal event recognition model, wherein the abnormal event recognition model is generated based on historical abnormal event sample training, and its input features include dynamic target features in the video frame, environmental change patterns, and spatiotemporal correlation of target motion trajectories; The abnormal event recognition model is used to perform feature matching on the video stream data. When an abnormal pattern whose matching degree exceeds a threshold value in the preset abnormal feature library is detected to appear continuously in the video frame sequence, the time window, spatial distribution and feature intensity of the abnormal event are extracted to generate an abnormal event determination result; According to the determination result, if the abnormal event feature intensity is lower than the first risk threshold, it is marked as a potential abnormal event and the acquisition frame rate and target tracking parameters of the corresponding monitoring cluster are adjusted to continuously verify the abnormal features; If the feature intensity exceeds the first risk threshold, an alarm signal is generated according to the type of abnormal event, the time window data, spatial coordinates and enhanced video clips of the abnormal event are simultaneously uploaded to the cloud platform, and the directional warning function of the sound and light alarm device in the target area is activated; During the duration of the alarm signal, the spatial diffusion trend and characteristic intensity changes of abnormal events are monitored in real time. If the diffusion trend exceeds the preset safety range or the characteristic intensity reaches the second risk threshold, the emergency resource scheduling path is determined based on the type and location of the abnormal event.

7. A CT self-collecting electric video monitoring and early warning device based on environmental perception, characterized in that: The CT self-service electricity video monitoring and early warning device based on environment perception includes a storage device and a processor. The storage device includes a CT self-service electricity video monitoring and early warning method program based on environment perception. When the CT self-service electricity video monitoring and early warning method program based on environment perception is executed by the processor, the following steps are implemented: Obtaining historical working data of each CT self-collecting video surveillance in the target area, analyzing the historical working data based on a hidden Markov model, and constructing a working task recognition model for video surveillance; According to the work task identification model, work tasks are identified for each video surveillance within a preset time period, power change data of the video surveillance within the preset time period is obtained, and the work quality under each work task of the video surveillance is evaluated to construct a work task-power-quality data matrix; Clustering each video monitoring according to the work task-power-quality data matrix, determining the monitoring task of each monitoring cluster, and obtaining a monitoring task allocation plan; The video surveillance data of the target area is acquired according to the monitoring task allocation plan, abnormal events are identified according to the video surveillance data, and monitoring and early warning operations are performed according to the abnormal event identification results.

Images