Intelligent monitoring method, system and device for floating population

Abstract

The application relates to the technical field of community security management, and discloses a floating population intelligent monitoring method, system and equipment. The method comprises the following steps: determining floating population data flow according to behavior event information in monitoring image data of a preset monitoring area collected; obtaining personal trajectory data of the floating population data flow by dynamically tracking the floating population data flow based on a preset trajectory algorithm; analyzing the personal trajectory data by a preset outlier detection abnormal behavior algorithm to obtain abnormal behavior data of the floating population data flow; and pushing early warning information when the abnormal behavior data meets an abnormal behavior early warning threshold. In the application, the monitoring video of the area where the floating population is located can be analyzed, the activity trajectory of the floating population can be recorded, the dynamic trajectory can be described, the personal trajectory data can be analyzed and counted for abnormal behavior by the preset outlier detection abnormal behavior algorithm, and early warning can be performed when the early warning threshold is exceeded, so that early warning can be timely and accurately sent out.

Description

Technical Field

[0001] This invention relates to the field of community security management technology, and in particular to a method, system and equipment for intelligent monitoring of the floating population. Background Technology

[0002] With increasing economic globalization and population mobility, more and more people are choosing to leave their hometowns to work, study, or travel in other cities, provinces, or countries. These migrant populations include people who use internet cafes, stay in hotels, and use logistics and express delivery services.

[0003] Existing surveillance systems often have limited functionality, lack intelligent analysis capabilities, require inefficient manual monitoring, and are unable to process and analyze large amounts of data to extract useful information. They are also ineffective in monitoring dynamic scenarios. With the development of the internet and the widespread availability of surveillance equipment, almost every internet cafe, hotel, postal and logistics center, and residence permit area is now equipped with surveillance devices. Therefore, how to efficiently and accurately monitor and warn of transient populations has become an urgent problem to be solved.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide a method, system, and device for intelligent monitoring of the floating population, aiming to solve at least one of the technical problems existing in the prior art.

[0006] To achieve the above objectives, the present invention provides an intelligent monitoring method for the floating population, the method comprising:

[0007] Collect surveillance video data of the preset monitoring area;

[0008] The flow of mobile population data is determined based on behavioral event information in the surveillance video data.

[0009] The data stream of the floating population is dynamically tracked based on a preset trajectory algorithm to obtain the individual trajectory data of the floating population data stream;

[0010] The personal trajectory data is analyzed by a preset outlier detection algorithm to obtain abnormal behavior data of the floating population data stream.

[0011] When the abnormal behavior data meets the abnormal behavior warning threshold, a warning message is pushed.

[0012] In some embodiments, determining the mobile population data stream based on behavioral event information in the surveillance video data includes:

[0013] Facial identity information is obtained from the surveillance video data based on a preset recognition algorithm;

[0014] Behavioral event information corresponding to the facial identity information is extracted from the surveillance video data; wherein, the behavioral event information includes the location of the event, the activity performed, and the number of times the image was captured;

[0015] A data stream of the floating population is constructed based on the behavioral event information.

[0016] In some embodiments, obtaining facial identity information based on the surveillance video data using a preset recognition algorithm includes:

[0017] The monitoring image data is subjected to feature extraction using a preset feature extraction algorithm to obtain the quantitative features of the monitoring image data;

[0018] Select facial features from the quantified features;

[0019] Obtain the corresponding facial identity information based on the facial features.

[0020] In some embodiments, the dynamic tracking of the migrant population data stream based on a preset trajectory algorithm to obtain individual trajectory data of the migrant population data stream includes:

[0021] Based on the visual tracking algorithm, the real-time location information and real-time movement information of the mobile population data stream are obtained by visually tracking the surveillance image data.

[0022] The personal trajectory data of the mobile population data stream is constructed based on the real-time location information and real-time movement information.

[0023] In some embodiments, the step of analyzing the personal trajectory data using a preset outlier detection algorithm to obtain abnormal behavior data of the migrant population data stream includes:

[0024] A box plot of the individual trajectory data is constructed using a preset outlier detection algorithm.

[0025] The upper and lower beards of the box plot are used as the boundaries of the distribution of the individual trajectory data.

[0026] Based on the boundary, abnormal data values ​​in the personal trajectory data are determined;

[0027] The abnormal behavior data of the floating population data stream is constructed based on the abnormal data values.

[0028] In some embodiments, constructing a box plot of the personal trajectory data using a preset outlier detection algorithm includes:

[0029] Quartiles are obtained by using a pre-defined algorithm to detect outliers and abnormal behavior.

[0030] The individual trajectory data is graphically described based on the quartiles to obtain a box plot of the individual trajectory data.

[0031] In some embodiments, the method further includes:

[0032] Obtain the minimum, first quantile, median, third quantile, and maximum value of the box plot of the individual trajectory data;

[0033] The interquartile interval is determined based on the difference between the first quantile and the third quantile.

[0034] Accordingly, determining the abnormal data values ​​in the personal trajectory data based on the boundary includes:

[0035] Abnormal data values ​​in the personal trajectory data are determined based on the interquartile range and the boundary.

[0036] In some embodiments, determining the outlier values ​​in the personal trajectory data based on the interquartile range and the boundary includes:

[0037] The first boundary value is obtained based on the difference between the first quantile and the interquartile range of a preset multiple;

[0038] The second boundary value is obtained by summing the third quantile with the interquartile range of a preset multiple;

[0039] The upper beard of the box plot is used as the third boundary value;

[0040] The lower beard of the box plot is used as the fourth boundary value;

[0041] Data points in the personal trajectory data that are lower than the first boundary value or the fourth boundary value are considered as abnormal data values.

[0042] and / or;

[0043] Data points in the personal trajectory data that are higher than the second boundary value or the third boundary value are considered as abnormal data values.

[0044] Furthermore, to achieve the above objectives, the present invention also proposes an intelligent monitoring system for the floating population, the system comprising:

[0045] The video data acquisition module is used to acquire surveillance video data of a preset monitoring area;

[0046] The event association module is used to determine the mobile population data stream based on behavioral event information in the surveillance video data;

[0047] The dynamic tracking module is used to dynamically track the migrant population data stream based on a preset trajectory algorithm in order to obtain the individual trajectory data of the migrant population data stream.

[0048] The outlier detection module is used to analyze the personal trajectory data through a preset outlier detection abnormal behavior algorithm to obtain abnormal behavior data of the floating population data stream.

[0049] The personnel early warning module is used to push early warning information when the abnormal behavior data meets the abnormal behavior early warning threshold.

[0050] Furthermore, to achieve the above objectives, the present invention also proposes an intelligent monitoring device for the floating population, the intelligent monitoring device for the floating population comprising: a memory, a processor, and an intelligent monitoring program for the floating population stored in the memory and executable on the processor, the intelligent monitoring program for the floating population being configured to implement the intelligent monitoring method for the floating population as described in the above embodiments.

[0051] This invention collects surveillance video data from a preset monitoring area; determines a flow of transient population data based on behavioral event information in the surveillance video data; dynamically tracks the transient population data stream based on a preset trajectory algorithm to obtain individual trajectory data of the transient population data stream; analyzes the individual trajectory data using a preset outlier detection algorithm to obtain abnormal behavior data of the transient population data stream; and pushes an early warning message when the abnormal behavior data meets the abnormal behavior warning threshold. This invention can analyze surveillance video of the area where the transient population is located, record the transient population's activity trajectory, depict the transient population's dynamic trajectory, and analyze and statistically analyze abnormal behavior of individuals using a preset outlier detection algorithm, issuing warnings when exceeding warning thresholds, thus enabling timely and accurate early warnings and preventing problems before they occur. Attached Figure Description

[0052] Figure 1 This is a schematic diagram of the structure of a smart monitoring device for mobile population in the hardware operating environment of an embodiment of the present invention.

[0053] Figure 2 This is a flowchart illustrating the first embodiment of the intelligent monitoring method for the floating population of the present invention.

[0054] Figure 3 This is a flowchart illustrating the second embodiment of the intelligent monitoring method for the floating population of the present invention.

[0055] Figure 4 This is a first schematic diagram of the box plot in the intelligent monitoring method for the floating population of the present invention;

[0056] Figure 5This is a second schematic diagram of the box plot in the intelligent monitoring method for the floating population of the present invention;

[0057] Figure 6 This is a schematic diagram of outliers in the box plot of the intelligent monitoring method for the floating population of the present invention.

[0058] Figure 7 This is a structural block diagram of the first embodiment of the intelligent monitoring system for the floating population of the present invention.

[0059] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0060] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0061] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0062] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention. It should be understood that the specific embodiments described herein are only for explaining the invention and are not intended to limit the invention.

[0063] Reference Figure 1 , Figure 1 This is a schematic diagram of the structure of a mobile population intelligent monitoring device in the hardware operating environment of an embodiment of the present invention.

[0064] like Figure 1As shown, the intelligent monitoring device for the floating population may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0065] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on intelligent monitoring equipment for the floating population, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0066] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a mobile population intelligent monitoring program.

[0067] exist Figure 1 In the intelligent monitoring device for the floating population shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the intelligent monitoring device for the floating population of the present invention can be set in the intelligent monitoring device for the floating population. The intelligent monitoring device for the floating population calls the intelligent monitoring program for the floating population stored in the memory 1005 through the processor 1001 and executes the intelligent monitoring method for the floating population provided in the embodiment of the present invention.

[0068] This invention proposes a method, system, and equipment for intelligent monitoring of the floating population.

[0069] This invention provides an intelligent monitoring method for the floating population, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of an intelligent monitoring method for mobile population according to the present invention.

[0070] like Figure 2 As shown, the intelligent monitoring method for the floating population includes:

[0071] Step S100: Collect monitoring image data of the preset monitoring area;

[0072] Step S200: Determine the mobile population data stream based on the behavioral event information in the surveillance video data;

[0073] Step S300: Dynamically track the migrant population data stream based on a preset trajectory algorithm to obtain the individual trajectory data of the migrant population data stream;

[0074] Step S400: Analyze the personal trajectory data using a preset outlier detection algorithm to obtain abnormal behavior data of the floating population data stream;

[0075] Step S500: When the abnormal behavior data meets the abnormal behavior warning threshold, push the warning information.

[0076] It should be noted that the executing entity in this embodiment can be a smart monitoring device for the floating population. This smart monitoring device for the floating population can be a computer device with data processing function, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment, a computer device is used as an example for explanation.

[0077] In one embodiment, surveillance video data of a preset monitoring area is collected. It is understood that the transient population includes people using internet cafes, staying in hotels, and using logistics and express delivery services. Exemplarily, the preset monitoring area includes, but is not limited to, internet cafes, hotels, logistics and express delivery stations, and places where residence permits are issued. This embodiment does not limit the scope of the preset monitoring area.

[0078] Specifically, in this embodiment, surveillance videos from areas such as internet cafe check-in, hotel accommodation, postal and logistics stations, and residence permit processing areas can be collected to obtain surveillance video data.

[0079] In one embodiment, determining the floating population data stream based on behavioral event information in the surveillance video data includes: obtaining facial identity information based on the surveillance video data using a preset recognition algorithm; extracting behavioral event information corresponding to the facial identity information based on the surveillance video data; wherein the behavioral event information includes the location of the event, the activity performed, and the number of times the image was captured; and constructing the floating population data stream based on the behavioral event information.

[0080] Specifically, the monitoring image data of the above-mentioned preset monitoring area is summarized and analyzed, and facial identity information is collected by facial recognition based on the monitoring image data according to the preset recognition algorithm. The preset recognition algorithm includes, but is not limited to, facial recognition algorithms.

[0081] For example, behavioral event information corresponding to the facial identity information is extracted from the surveillance video data; wherein, the behavioral event information includes, but is not limited to, the location of the event, the activity performed, and the number of times the image was captured; a data stream is formed by extracting the above-mentioned behavioral event information to obtain a mobile population data stream. This embodiment does not limit the scope of the behavioral event information.

[0082] In one embodiment, obtaining facial identity information based on the surveillance video data using a preset recognition algorithm includes: extracting features from the surveillance video data using a preset feature extraction algorithm to obtain quantized features of the surveillance video data; selecting facial features from the quantized features; and obtaining corresponding facial identity information based on the facial features.

[0083] It is understood that this embodiment uses a facial feature-based recognition algorithm as an example for illustration, and this embodiment does not limit the specific type of the preset recognition algorithm. Specifically, the feature extraction algorithm is used to extract features from the surveillance video data, converting the surveillance video data into quantifiable features. The identity information obtained from the facial features is summarized and aggregated to obtain the corresponding facial identity information, thereby realizing the classification, recognition, and analysis of the surveillance video data. For example, when monitoring people in an internet cafe, facial features can be extracted using the feature extraction algorithm to achieve the recognition and analysis of people in the internet cafe.

[0084] For example, the facial recognition algorithm for obtaining facial identity information may include one or more of the following: facial feature point-based recognition algorithm, whole-image-based recognition algorithm, template-based recognition algorithm, and neural network-based recognition algorithm. Facial features may include facial feature information, facial curve information, etc.

[0085] In one embodiment, the mobile population data stream is dynamically tracked based on a preset trajectory algorithm to obtain individual trajectory data of the mobile population data stream, including: using a visual tracking algorithm to visually track the surveillance video data to obtain real-time location information and real-time action information of the mobile population data stream; and constructing individual trajectory data of the mobile population data stream based on the real-time location information and real-time action information.

[0086] Specifically, based on the analyzed data flow of the floating population, dynamic tracking is performed to generate individual trajectory data. For example, an individual trajectory algorithm is used to visually track surveillance video data, enabling real-time tracking and monitoring of the floating population. For instance, when monitoring people in public places, visual tracking algorithms can be used to track the location and movement information of individuals in real time.

[0087] It should be noted that visual tracking algorithms include, but are not limited to, correlation filtering target tracking algorithms. Target tracking algorithms include particle filtering, edge contour-based tracking, and template-based target modeling, etc. This embodiment does not limit the specific type of visual tracking algorithm.

[0088] In one embodiment, the personal trajectory data is analyzed using a preset outlier detection algorithm to obtain abnormal behavior data of the migrant population data stream. This includes: constructing a box plot of the personal trajectory data using the preset outlier detection algorithm; using the upper and lower beards of the box plot as the boundaries of the personal trajectory data distribution; determining abnormal data values ​​in the personal trajectory data based on the boundaries; and constructing abnormal behavior data of the migrant population data stream based on the abnormal data values.

[0089] For example, various abnormal behavior algorithms, such as outlier detection, are used to statistically analyze the abnormal behaviors of individuals, and warnings are issued when these behaviors exceed a warning threshold. Specifically, quartiles are obtained using a preset outlier detection algorithm; the individual trajectory data is then graphically described based on the quartiles to obtain a box plot of the individual trajectory data. The upper and lower whiskers of the box plot are used as the boundaries of the individual trajectory data distribution; abnormal data values ​​in the individual trajectory data are determined based on these boundaries; and abnormal behavior data of the floating population data stream is constructed based on these abnormal data values.

[0090] In one embodiment, an early warning message is pushed when the abnormal behavior data meets the abnormal behavior early warning threshold. For example, an early warning can be determined by whether the number of abnormal behaviors in the abnormal behavior data exceeds the abnormal behavior frequency early warning threshold, or by whether the type of activity involved in the abnormal behavior in the abnormal behavior data meets the abnormal behavior activity threshold. This embodiment does not limit the specific content of the early warning determination.

[0091] This embodiment collects surveillance video data from a preset monitoring area; determines a flow of mobile population data based on behavioral event information in the surveillance video data; dynamically tracks the mobile population data stream based on a preset trajectory algorithm to obtain individual trajectory data of the mobile population data stream; analyzes the individual trajectory data using a preset outlier detection algorithm to obtain abnormal behavior data of the mobile population data stream; and pushes an early warning message when the abnormal behavior data meets the abnormal behavior warning threshold. In this embodiment, surveillance video of the area where the mobile population is located can be analyzed to record the activity trajectory of the mobile population, depict their dynamic trajectory, and perform abnormal behavior analysis and statistics on the individual trajectory data of individuals with abnormal behavior using a preset outlier detection algorithm. If the abnormal behavior exceeds the warning threshold, an early warning is issued, thus enabling timely and accurate warnings to prevent problems before they occur.

[0092] In one embodiment, such as Figure 3 As shown, based on the first embodiment, a second embodiment of the intelligent monitoring method for the floating population of the present invention is proposed. Step S400 includes:

[0093] Step S401: Construct a box plot of the personal trajectory data using a preset outlier detection algorithm;

[0094] Step S402: Use the upper and lower beards of the box plot as the boundaries of the distribution of the personal trajectory data;

[0095] Step S403: Determine the abnormal data values ​​in the personal trajectory data based on the boundary;

[0096] Step S404: Construct abnormal behavior data of the floating population data stream based on the abnormal data values.

[0097] In one embodiment, constructing a box plot of the personal trajectory data using a preset outlier detection algorithm includes: obtaining quartiles using the preset outlier detection algorithm; and graphically describing the personal trajectory data based on the quartiles to obtain a box plot of the personal trajectory data.

[0098] It should be noted that various abnormal behavior algorithms, such as outlier detection, are used to statistically analyze the abnormal behavior of individuals, and warnings are issued when these behaviors exceed a certain threshold. (Reference) Figure 4 This embodiment uses the boxplot in the outlier detection algorithm as an example for illustration. Figure 4As shown, box plots graphically describe numerical data using quantiles, providing a very simple yet effective way to visualize outliers. The upper and lower whiskers are considered the boundaries of the data distribution. Any data point appearing above or below the whiskers can be considered an outlier. In this embodiment, quartiles are used to graphically describe personal trajectory data.

[0099] In one embodiment, the method further includes: obtaining the minimum value, first quantile, median, third quantile, and maximum value of the box plot of the personal trajectory data; determining the interquartile range based on the difference between the first quantile and the third quantile; correspondingly, determining the abnormal data values ​​in the personal trajectory data based on the boundary includes: determining the abnormal data values ​​in the personal trajectory data based on the interquartile range and the boundary.

[0100] Specifically, the concept of interquartile range (IQR) is used to construct box plots. IQR is a statistical concept that measures statistical dispersion and data variability by dividing a dataset into quartiles. Simply put, any dataset or set of observations is divided into four defined intervals based on the values ​​of the data and their comparison with the whole dataset. Quartiles divide the data into three points and four intervals. Reference Figure 5 This embodiment uses quartiles to graphically describe individual trajectory data, obtaining the minimum value of the box plot (e.g., Figure 5 Minimum (as shown), first quantile (as shown) Figure 5 First Quarter (as shown), median (e.g.) Figure 5 The second quartile or median shown), the third quartile (as shown) Figure 5 The ThirdQuartile (as shown) and the maximum value (as shown) Figure 5 (Maximum shown).

[0101] In one embodiment, determining abnormal data values ​​in the personal trajectory data based on the interquartile range and the boundary includes: obtaining a first boundary value based on the difference between a first quantile and a preset multiple of the interquartile range; obtaining a second boundary value based on the sum of a third quantile and a preset multiple of the interquartile range; using the upper beard of the box plot as a third boundary value; using the lower beard of the box plot as a fourth boundary value; identifying data points in the personal trajectory data that are lower than the first boundary value or the fourth boundary value as abnormal data values; and / or; identifying data points in the personal trajectory data that are higher than the second boundary value or the third boundary value as abnormal data values.

[0102] Specifically, refer to Figure 6In this embodiment, individual trajectory data is graphically described using quartiles to obtain the first quartile of the box plot (e.g., Figure 6 As shown in Q1), median (e.g.) Figure 6 The Median shown) and the third quartile (as shown) Figure 6 As shown in Q3). The first boundary value (Q1 - 1.5 * IQR) is obtained based on the difference between the first quantile Q1 and a preset multiple, such as 1.5 times the interquartile range IQR; the second boundary value (Q3 + 1.5 * IQR) is obtained based on the sum of the third quantile Q3 and a preset multiple, such as 1.5 times the interquartile range IQR; the upper whisker of the boxplot is used as the third boundary value; the lower whisker of the boxplot is used as the fourth boundary value; data points in the personal trajectory data that are lower than the first boundary value (Q1 - 1.5 * IQR) or the fourth boundary value (boxplot lower whisker) are considered outlier values; and / or; data points in the personal trajectory data that are higher than the second boundary value (Q3 + 1.5 * IQR) or the third boundary value (boxplot upper whisker) are considered outlier values.

[0103] For example, the interquartile range (IQR) is used to define outliers. The interquartile range (IQR) is the difference between the third quartile Q3 and the first quartile Q1, i.e., IQR = Q3 - Q1. In this case, outliers are defined as observations that are below (Q1 - 1.5 * IQR) or below the boxplot threshold, or above (Q3 + 1.5 * IQR) or above the boxplot threshold.

[0104] This embodiment constructs a box plot of the individual trajectory data using a preset outlier detection algorithm; the upper and lower beards of the box plot are used as the boundaries of the individual trajectory data distribution; outlier data values ​​in the individual trajectory data are determined based on the boundaries; and outlier behavior data of the mobile population data stream is constructed based on the outlier data values. In this embodiment, the preset outlier detection algorithm statistically analyzes outlier behavior in the individual trajectory data, issuing warnings when values ​​exceed a warning threshold. The box plot in the preset outlier detection algorithm uses quantiles to graphically describe numerical data, providing a simple and effective visualization of outliers, thus enabling timely and accurate warnings and preventing potential problems.

[0105] Reference Figure 7 , Figure 7 This is a structural block diagram of the first embodiment of the intelligent monitoring system for the floating population of the present invention.

[0106] like Figure 7 As shown, the intelligent monitoring system for the floating population includes:

[0107] The video data acquisition module 10 is used to acquire monitoring video data of a preset monitoring area;

[0108] Event association module 20 is used to determine the floating population data stream based on behavioral event information in the surveillance video data;

[0109] The dynamic tracking module 30 is used to dynamically track the migrant population data stream based on a preset trajectory algorithm in order to obtain the personal trajectory data of the migrant population data stream.

[0110] The outlier detection module 40 is used to analyze the personal trajectory data through a preset outlier detection abnormal behavior algorithm to obtain abnormal behavior data of the floating population data stream.

[0111] The personnel early warning module 50 is used to push early warning information when the abnormal behavior data meets the abnormal behavior early warning threshold.

[0112] In one embodiment, surveillance video data of a preset monitoring area is collected. It is understood that the transient population includes people using internet cafes, staying in hotels, and using logistics and express delivery services. Exemplarily, the preset monitoring area includes, but is not limited to, internet cafes, hotels, logistics and express delivery stations, and places where residence permits are issued. This embodiment does not limit the scope of the preset monitoring area.

[0113] Specifically, in this embodiment, surveillance videos from areas such as internet cafe check-in, hotel accommodation, postal and logistics stations, and residence permit processing areas can be collected to obtain surveillance video data.

[0114] In one embodiment, determining the floating population data stream based on behavioral event information in the surveillance video data includes: obtaining facial identity information based on the surveillance video data using a preset recognition algorithm; extracting behavioral event information corresponding to the facial identity information based on the surveillance video data; wherein the behavioral event information includes the location of the event, the activity performed, and the number of times the image was captured; and constructing the floating population data stream based on the behavioral event information.

[0115] Specifically, the monitoring image data of the above-mentioned preset monitoring area is summarized and analyzed, and facial identity information is collected by facial recognition based on the monitoring image data according to the preset recognition algorithm. The preset recognition algorithm includes, but is not limited to, facial recognition algorithms.

[0116] For example, behavioral event information corresponding to the facial identity information is extracted from the surveillance video data; wherein, the behavioral event information includes, but is not limited to, the location of the event, the activity performed, and the number of times the image was captured; a data stream is formed by extracting the above-mentioned behavioral event information to obtain a mobile population data stream. This embodiment does not limit the scope of the behavioral event information.

[0117] In one embodiment, obtaining facial identity information based on the surveillance video data using a preset recognition algorithm includes: extracting features from the surveillance video data using a preset feature extraction algorithm to obtain quantized features of the surveillance video data; selecting facial features from the quantized features; and obtaining corresponding facial identity information based on the facial features.

[0118] It is understood that this embodiment uses a facial feature-based recognition algorithm as an example for illustration, and this embodiment does not limit the specific type of the preset recognition algorithm. Specifically, the feature extraction algorithm is used to extract features from the surveillance video data, converting the surveillance video data into quantifiable features. The identity information obtained from the facial features is summarized and aggregated to obtain the corresponding facial identity information, thereby realizing the classification, recognition, and analysis of the surveillance video data. For example, when monitoring people in an internet cafe, facial features can be extracted using the feature extraction algorithm to achieve the recognition and analysis of people in the internet cafe.

[0119] For example, the facial recognition algorithm for obtaining facial identity information may include one or more of the following: facial feature point-based recognition algorithm, whole-image-based recognition algorithm, template-based recognition algorithm, and neural network-based recognition algorithm. Facial features may include facial feature information, facial curve information, etc.

[0120] In one embodiment, the mobile population data stream is dynamically tracked based on a preset trajectory algorithm to obtain individual trajectory data of the mobile population data stream, including: using a visual tracking algorithm to visually track the surveillance video data to obtain real-time location information and real-time action information of the mobile population data stream; and constructing individual trajectory data of the mobile population data stream based on the real-time location information and real-time action information.

[0121] Specifically, based on the analyzed data flow of the floating population, dynamic tracking is performed to generate individual trajectory data. For example, an individual trajectory algorithm is used to visually track surveillance video data, enabling real-time tracking and monitoring of the floating population. For instance, when monitoring people in public places, visual tracking algorithms can be used to track the location and movement information of individuals in real time.

[0122] It should be noted that visual tracking algorithms include, but are not limited to, correlation filtering target tracking algorithms. Target tracking algorithms include particle filtering, edge contour-based tracking, and template-based target modeling, etc. This embodiment does not limit the specific type of visual tracking algorithm.

[0123] In one embodiment, the personal trajectory data is analyzed using a preset outlier detection algorithm to obtain abnormal behavior data of the migrant population data stream. This includes: constructing a box plot of the personal trajectory data using the preset outlier detection algorithm; using the upper and lower beards of the box plot as the boundaries of the personal trajectory data distribution; determining abnormal data values ​​in the personal trajectory data based on the boundaries; and constructing abnormal behavior data of the migrant population data stream based on the abnormal data values.

[0124] For example, various abnormal behavior algorithms, such as outlier detection, are used to statistically analyze the abnormal behaviors of individuals, and warnings are issued when these behaviors exceed a warning threshold. Specifically, quartiles are obtained using a preset outlier detection algorithm; the individual trajectory data is then graphically described based on the quartiles to obtain a box plot of the individual trajectory data. The upper and lower whiskers of the box plot are used as the boundaries of the individual trajectory data distribution; abnormal data values ​​in the individual trajectory data are determined based on these boundaries; and abnormal behavior data of the floating population data stream is constructed based on these abnormal data values.

[0125] In one embodiment, an early warning message is pushed when the abnormal behavior data meets the abnormal behavior early warning threshold. For example, an early warning can be determined by whether the number of abnormal behaviors in the abnormal behavior data exceeds the abnormal behavior frequency early warning threshold, or by whether the type of activity involved in the abnormal behavior in the abnormal behavior data meets the abnormal behavior activity threshold. This embodiment does not limit the specific content of the early warning determination.

[0126] This embodiment collects surveillance video data from a preset monitoring area; determines the flow of mobile population data based on behavioral event information in the surveillance video data; dynamically tracks the flow of mobile population data based on a preset trajectory algorithm to obtain individual trajectory data of the flow of mobile population data; analyzes the individual trajectory data using a preset outlier detection algorithm to obtain abnormal behavior data of the flow of mobile population data; and pushes a warning message when the abnormal behavior data meets the abnormal behavior warning threshold.

[0127] This embodiment proposes an intelligent monitoring system for the floating population, comprising: a video data acquisition module 10 for acquiring monitoring video data of a preset monitoring area; an event association module 20 for determining the floating population data stream based on behavioral event information in the monitoring video data; a dynamic tracking module 30 for dynamically tracking the floating population data stream based on a preset trajectory algorithm to obtain individual trajectory data of the floating population data stream; an outlier detection module 40 for analyzing the individual trajectory data using a preset outlier detection abnormal behavior algorithm to obtain abnormal behavior data of the floating population data stream; and a personnel early warning module 50 for pushing early warning information when the abnormal behavior data meets the abnormal behavior early warning threshold. In this embodiment, monitoring videos of the area where the floating population is located can be analyzed to record the activity trajectory of the floating population, depict their dynamic trajectory, and perform abnormal behavior analysis and statistics on the individual trajectory data of individuals with abnormal behavior using a preset outlier detection abnormal behavior algorithm. If the behavior exceeds the early warning threshold, an early warning can be issued, thus enabling timely and accurate early warnings and preventing problems before they occur.

[0128] In addition, for technical details not described in detail in this embodiment of the intelligent monitoring system for the floating population, please refer to the application of the intelligent monitoring method for the floating population as described above provided in any embodiment of the present invention, which will not be repeated here.

[0129] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solution of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0130] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0131] Furthermore, it should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0132] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0133] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory (ROM) / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0134] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for intelligent monitoring of floating population, characterized in that, The method includes: Collect surveillance video data of the preset monitoring area; The flow of mobile population data is determined based on behavioral event information in the surveillance video data. The data stream of the floating population is dynamically tracked based on a preset trajectory algorithm to obtain the individual trajectory data of the floating population data stream; The personal trajectory data is analyzed by a preset outlier detection algorithm to obtain abnormal behavior data of the floating population data stream. When the abnormal behavior data meets the abnormal behavior warning threshold, a warning message is pushed. The personal trajectory data is analyzed using a preset outlier detection algorithm to obtain abnormal behavior data of the migrant population data stream. This includes: constructing a box plot of the personal trajectory data using the preset outlier detection algorithm; using the upper and lower beards of the box plot as the boundaries of the personal trajectory data distribution; determining abnormal data values ​​in the personal trajectory data based on the boundaries; and constructing abnormal behavior data of the migrant population data stream based on the abnormal data values. Constructing a box plot of the personal trajectory data using a preset outlier detection algorithm includes: obtaining quartiles using the preset outlier detection algorithm; and graphically describing the personal trajectory data based on the quartiles to obtain a box plot of the personal trajectory data. The method further includes: obtaining the minimum value, first quantile, median, third quantile, and maximum value of the box plot of the personal trajectory data; determining the interquartile range based on the difference between the first quantile and the third quantile; correspondingly, determining the abnormal data values ​​in the personal trajectory data based on the boundary includes: determining the abnormal data values ​​in the personal trajectory data based on the interquartile range and the boundary. Determining outlier values ​​in the personal trajectory data based on the interquartile range and the boundaries includes: obtaining a first boundary value based on the difference between the first quartile and a preset multiple of the interquartile range; obtaining a second boundary value based on the sum of the third quartile and a preset multiple of the interquartile range; using the upper beard of the box plot as the third boundary value; using the lower beard of the box plot as the fourth boundary value; identifying data points in the personal trajectory data below the first or fourth boundary value as outlier values; and / or; identifying data points in the personal trajectory data above the second or third boundary value as outlier values; wherein, the personal trajectory data is graphically described using quartiles to obtain the first quartile of the box plot. The first boundary value is Q1 - 1.5 * IQR, calculated from the difference between the first quantile Q1 and the interquartile range IQR (a preset multiple of 1.5). The second boundary value is Q3 + 1.5 * IQR, calculated from the sum of the third quantile Q3 and the preset interquartile range IQR (a preset multiple of 1.5). The upper beard of the box plot is used as the third boundary value. The lower beard of the box plot is used as the fourth boundary value. Data points in the personal trajectory data that are lower than the first boundary value Q1 - 1.5 * IQR or the fourth boundary value are considered outlier values. Alternatively, data points in the personal trajectory data that are higher than the second boundary value Q3 + 1.5 * IQR or the third boundary value are considered outlier values.

2. The intelligent monitoring method for the floating population as described in claim 1, characterized in that, The step of determining the mobile population data stream based on behavioral event information in the surveillance video data includes: Facial identity information is obtained from the surveillance video data based on a preset recognition algorithm; Behavioral event information corresponding to the facial identity information is extracted from the surveillance video data; wherein, the behavioral event information includes the location of the event, the activity performed, and the number of times the image was captured; A data stream of the floating population is constructed based on the behavioral event information.

3. The intelligent monitoring method for the floating population as described in claim 2, characterized in that, The step of obtaining facial identity information based on the surveillance video data using a preset recognition algorithm includes: The monitoring image data is subjected to feature extraction using a preset feature extraction algorithm to obtain the quantitative features of the monitoring image data; Select facial features from the quantified features; Obtain the corresponding facial identity information based on the facial features.

4. The intelligent monitoring method for the floating population as described in claim 1, characterized in that, The dynamic tracking of the migrant population data stream based on a preset trajectory algorithm to obtain individual trajectory data of the migrant population data stream includes: Based on the visual tracking algorithm, the real-time location information and real-time movement information of the mobile population data stream are obtained by visually tracking the surveillance image data. The personal trajectory data of the mobile population data stream is constructed based on the real-time location information and real-time movement information.

5. A mobile population intelligent monitoring system based on the method described in any one of claims 1 to 4, characterized in that, The system includes: The video data acquisition module is used to acquire surveillance video data of a preset monitoring area; The event association module is used to determine the mobile population data stream based on behavioral event information in the surveillance video data; The dynamic tracking module is used to dynamically track the migrant population data stream based on a preset trajectory algorithm in order to obtain the individual trajectory data of the migrant population data stream. The outlier detection module is used to analyze the personal trajectory data through a preset outlier detection abnormal behavior algorithm to obtain abnormal behavior data of the mobile population data stream. The personnel early warning module is used to push early warning information when the abnormal behavior data meets the abnormal behavior early warning threshold.

6. A smart monitoring device for transient population, characterized in that, The intelligent monitoring device for the floating population includes: a memory, a processor, and an intelligent monitoring program for the floating population stored in the memory and executable on the processor, wherein the intelligent monitoring program for the floating population is configured to implement the intelligent monitoring method for the floating population as described in any one of claims 1 to 4.

Images