Monitoring method and system based on equatorial plane projection

Abstract

The present application relates to a monitoring method and system based on equatorial plane projection. The method comprises the following steps: on the basis of a target monitoring area, converting the position of a target monitored object in video data into coordinates on a spherical surface centered on a pan-tilt-zoom camera, converting the spherical coordinate data into coordinate data on an equatorial plane where the pan-tilt-zoom camera is located, and acquiring two-dimensional equatorial projection image data.

Description

Monitoring Methods and Systems Based on Equatorial Plane Projection

[0001] Related applications

[0002] This application claims priority to Chinese patent application No. 202410835545.8, filed on June 26, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of image surveillance technology, and in particular to a surveillance method and system based on equatorial plane projection. Background Technology

[0004] The field of image surveillance technology encompasses various techniques and systems for real-time or non-real-time monitoring of environments or specific locations using video equipment. Aimed at monitoring and recording environments and activities through various forms of video capture devices, image surveillance technology is widely used in public safety, traffic monitoring, industrial automation, home security, and commercial security, among other areas. With technological advancements, image surveillance has evolved from simple video recording to include intelligent functions such as motion detection, facial recognition, and behavior analysis, significantly improving monitoring efficiency and accuracy.

[0005] Surveillance methods are a series of techniques used to observe and record specific areas, objects, or individuals. These methods typically include setting the location and angle of cameras, controlling camera movement, and processing and analyzing the captured video data. Surveillance methods have a wide range of applications, primarily for security and protection, such as monitoring illegal activities and ensuring personnel safety in public places, residential areas, and commercial facilities. In addition, surveillance methods are also applied to traffic monitoring, industrial production process monitoring, and behavioral research to improve operational efficiency and safety management levels.

[0006] Traditional monitoring methods face challenges in processing and analyzing surveillance data due to their complexity and long response times. Relying on fixed or preset camera angles, these methods introduce blind spots or inaccurate data capture when adjustments are needed. Furthermore, they lack highly flexible and adaptive monitoring mechanisms for identifying movement and analyzing behavioral patterns, making it difficult to accurately assess and respond to abnormal behavior in real time, thus creating vulnerabilities in security monitoring. For example, in public safety monitoring, the inability to effectively identify or predict abnormal behavior patterns prevents timely detection and prevention of security incidents, impacting monitoring effectiveness and overall security performance. Summary of the Invention

[0007] The purpose of this application is to address the shortcomings of existing technologies by proposing a monitoring method and system based on equatorial plane projection.

[0008] To achieve the above objectives, this application adopts the following technical solution: a monitoring method based on equatorial plane projection, comprising the following steps:

[0009] S1: Based on the target monitoring area, the video image data of the monitoring area is captured in real time through the PTZ camera. The position of the target monitoring object in the video data is converted into spherical coordinates centered on the PTZ camera to obtain spherical coordinate data. The spherical coordinate data is then transformed into equatorial plane projection data to obtain two-dimensional equatorial projection image data.

[0010] S2: Based on the two-dimensional equatorial projection image data, analyze the moving speed and moving duration of the target monitored object, calculate the deviation of the target monitored object from the normal moving speed and moving duration, evaluate the moving deviation index, and obtain the moving deviation information;

[0011] S3: Based on the two-dimensional equatorial projection image data, analyze the movement path and behavior pattern of the target monitoring object, identify the abnormal behavior pattern of the target monitoring object, calculate the abnormal behavior risk index, assess the risk of the abnormal behavior pattern, and obtain the abnormal behavior identification result.

[0012] S4: Based on the movement deviation information and abnormal behavior recognition results, calculate the overall abnormal risk level of the target object, implement corresponding early warning measures according to the abnormal risk level, adjust the angle of the PTZ camera, continuously monitor the target monitoring object information, and obtain safety early warning detection information.

[0013] In one embodiment, the step of obtaining the spherical coordinate data is as follows:

[0014] S111: Based on the target monitoring area, the video image data of the monitoring area is captured in real time by the pan-tilt camera, and the pixel coordinates of the target object in the image are identified.

[0015] S112: Based on the pixel coordinates of the target object in the image, using the formula:

[0016] Convert the pixel coordinates into spherical coordinates centered on the gimbal camera to obtain spherical coordinate data;

[0017] Where θ is the latitude angle in spherical coordinates, φ is the longitude angle in spherical coordinates, x and y are the pixel coordinates of the target object, x0 and y0 are the pixel coordinates of the image center, and f x and f y These are the focal lengths of the camera in the x and y directions, respectively, d x and d y It is the optical distortion adjustment factor.

[0018] In one embodiment, the step of acquiring the two-dimensional equatorial projection image data is as follows:

[0019] S121: Based on the spherical coordinate data, extract the latitude angle θ and longitude angle φ from the spherical coordinates;

[0020] S122: Based on the latitude angle θ and longitude angle φ, using the formula:

[0021] Calculate the equatorial plane coordinate data, convert the spherical coordinate data into the equatorial plane coordinate data of the pan-tilt camera, and obtain two-dimensional equatorial projection image data;

[0022] Where R is the radius of the sphere, α is the tilt angle between the pan-tilt camera and the ground, θ is the latitude angle in spherical coordinates, φ is the longitude angle in spherical coordinates, and x... eq and y eq These are the two-dimensional coordinates of the target object projected onto the equatorial plane.

[0023] In one embodiment, the step of obtaining the movement deviation information is as follows:

[0024] S211: Based on the two-dimensional equatorial projection image data, extract the positional change of the target object between two consecutive frames and obtain the actual moving speed v. act and travel time t act ;

[0025] S212: Based on the actual moving speed v act and travel time t act , compared to the preset normal moving speed v norm and travel time t norm Compare and calculate the speed deviation Δv and duration deviation Δt, and use the formula:

[0026] Calculate the moving deviation index P, assess the degree of moving deviation based on the value of the moving deviation index P, and obtain moving deviation information;

[0027] Among them, v act It is the actual moving speed, t act It is the actual duration of movement, v norm and t norm These are the preset normal movement speed and movement time, respectively. Δv and Δt represent the deviations in speed and time, respectively. v and w t These are the weighting coefficients for speed and duration deviations, respectively, and P is the movement deviation index.

[0028] In one embodiment, the method for identifying abnormal behavior patterns of the target monitored object is as follows:

[0029] S311: Based on the two-dimensional equatorial projection image data, extract the movement path information of the target object, including the target's position coordinates in consecutive time frames, using the formula:

[0030] Calculate the matching score M between the current behavior pattern and the abnormal behavior pattern of the target monitored object;

[0031] Among them, w i λ is the weight of the i-th point. i It is the sensitivity factor, τ is the tolerance threshold, and d i M is the distance between the actual path point and the preset pattern point, n is the matching score, n is the total number of data points, and e is the base of the natural logarithm.

[0032] S312: Based on the matching score M, compare the matching score M with a preset matching threshold, and mark behaviors where M exceeds the matching threshold as abnormal behaviors to obtain the abnormal behavior type of the target object.

[0033] In one embodiment, the step of obtaining the abnormal behavior identification result is as follows:

[0034] S321: Based on the abnormal behavior type of the target object, extract the matching score M corresponding to the abnormal behavior type. j ;

[0035] S322: Based on the matching score M j Through the formula:

[0036] Calculate the abnormal behavior risk index R, assess the abnormal behavior risk of the target object based on the value of the abnormal behavior risk index R, and obtain the abnormal behavior identification result;

[0037] Where k is the total number of matched abnormal behavior patterns, and M j w is the matching score for the j-th behavior pattern. j It is the risk weight of the j-th behavior pattern, α j τ is the sensitivity coefficient for the j-th behavioral pattern. j R is the threshold for the j-th behavior pattern, and R is the abnormal behavior risk index.

[0038] In one embodiment, the method for implementing the corresponding early warning measures is as follows:

[0039] S411: Based on the aforementioned movement deviation information and abnormal behavior identification results, extract the movement deviation index P and the abnormal behavior risk index R, using the formula:

[0040] Calculate the overall anomaly risk level E of the target object;

[0041] Where P is the movement deviation index, R is the abnormal behavior risk index, γ is the weighting coefficient for adjusting the impact of movement deviation, δ is the weighting coefficient for adjusting the impact of behavior risk, ε is the overall weighting coefficient, and E is the overall abnormal risk level.

[0042] S412: Based on the overall abnormal risk level E, compare the overall abnormal risk level E with the preset abnormal standard and implement corresponding early warning measures.

[0043] To achieve the above objectives, this application also proposes a monitoring system based on equatorial plane projection, the system comprising:

[0044] The video data capture module captures real-time video image data based on the target monitoring area through a PTZ camera, converts the position of the target monitoring object in the video data into spherical coordinates centered on the PTZ camera, and generates a real-time spherical coordinate set.

[0045] Based on the real-time spherical coordinate set, the equatorial projection conversion module should convert the spherical coordinate data to the equatorial plane coordinate data of the pan-tilt camera to obtain the equatorial plane projection image data.

[0046] The behavior speed analysis module analyzes the movement speed and duration of the monitored object based on the equatorial plane projection image data, compares it with a preset standard, calculates the deviation, and generates a movement deviation index.

[0047] The abnormal behavior pattern matching module compares the behavior patterns of the monitored object with the preset abnormal behavior pattern database based on the equatorial plane projection image data, identifies the abnormal behavior type, calculates the abnormal behavior risk index, and obtains abnormal behavior pattern risk information.

[0048] Based on the movement deviation index and abnormal behavior pattern risk information, the abnormal behavior risk assessment module calculates the overall abnormal risk level, implements matching early warning measures, adjusts the angle of the PTZ camera, continuously monitors the target monitoring object information, and obtains safety early warning detection information.

[0049] Compared with the prior art, the advantages and positive effects of this application are as follows:

[0050] In this application, video images are captured in real time by a pan-tilt camera. The position of the target monitoring object in the image is converted into spherical coordinates and then projected onto the equatorial plane. This ensures that the scene observed from any viewpoint is converted into the absolute position on the equatorial plane, maintaining the invariance of the scene's position. This facilitates subsequent analysis and monitoring, enhances the stability and accuracy of monitoring, and reduces data redundancy and processing complexity. By comparing the deviation of the target monitoring object's movement speed and duration from preset standards, and analyzing the matching degree between the behavior pattern and the abnormal behavior pattern database, the abnormal behavior risk of the monitored object can be accurately identified and assessed, thereby implementing precise early warning measures. This optimizes the accuracy and real-time performance of behavior analysis, enabling the monitoring system to more effectively prevent and manage potential security risks. Attached Figure Description

[0051] Figure 1 is a flowchart of the method of this application;

[0052] Figure 2 is a flowchart of the process for obtaining spherical coordinate data in this application;

[0053] Figure 3 is a flowchart of the process for obtaining two-dimensional equatorial projection image data in this application;

[0054] Figure 4 is a flowchart of the process for obtaining movement deviation information in this application;

[0055] Figure 5 is a flowchart illustrating the identification of abnormal behavior patterns of the target monitored object in this application;

[0056] Figure 6 is a flowchart of the process for obtaining abnormal behavior identification results in this application;

[0057] Figure 7 is a flowchart of the corresponding early warning measures implemented in this application. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0059] In the description of this application, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Furthermore, in the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0060] Example

[0061] Please refer to Figure 1. This application provides a technical solution: a monitoring method based on equatorial plane projection, comprising the following steps:

[0062] S1: Based on the target monitoring area, the video image data of the monitoring area is captured in real time through the PTZ camera. The position of the target monitoring object in the video data is converted into spherical coordinates centered on the PTZ camera to obtain spherical coordinate data. The spherical coordinate data is then transformed into equatorial plane projection data to obtain two-dimensional equatorial projection image data.

[0063] S2: Based on two-dimensional equatorial projection image data, analyze the moving speed and moving time of the target monitoring object, compare it with the preset normal moving speed and moving time, calculate the deviation of the target monitoring object from the normal moving speed and moving time, evaluate the moving deviation index, and obtain the moving deviation information;

[0064] S3: Based on two-dimensional equatorial projection image data, analyze the movement path and behavior pattern of the target monitoring object, compare the movement path of the target monitoring object with the preset abnormal behavior pattern database, calculate the matching degree between the current behavior pattern of the target monitoring object and the abnormal behavior pattern, identify the abnormal behavior pattern of the target monitoring object, calculate the abnormal behavior risk index, assess the risk of the abnormal behavior pattern, and obtain the abnormal behavior identification result.

[0065] S4: Based on the movement deviation information and abnormal behavior recognition results, calculate the overall abnormal risk level of the target object, implement corresponding early warning measures according to the abnormal risk level, adjust the angle of the PTZ camera, continuously monitor the target monitoring object information, and obtain safety early warning detection information;

[0066] The two-dimensional equatorial projection image data includes the two-dimensional position coordinates of the target monitoring object and the corresponding timestamp; the movement deviation information includes the change in the movement speed and the duration of movement of the target monitoring object; the abnormal behavior identification results include the risk score and abnormality type of the abnormal behavior; and the safety early warning detection information includes the corresponding early warning measures and the adjustment information of the PTZ camera.

[0067] Please refer to Figure 2. The steps for obtaining spherical coordinate data are as follows:

[0068] S111: Based on the target monitoring area, the video image data of the monitoring area is captured in real time by the pan-tilt camera, and the pixel coordinates of the target object in the image are identified.

[0069] S112: Based on the pixel coordinates of the target object in the image, using the formula:

[0070] Convert the pixel coordinates into spherical coordinates centered on the gimbal camera to obtain spherical coordinate data;

[0071] Where θ is the latitude angle in spherical coordinates, φ is the longitude angle in spherical coordinates, x and y are the pixel coordinates of the target object, x0 and y0 are the pixel coordinates of the image center, and f x and f y These are the focal lengths of the camera in the x and y directions, respectively, d x and d y It is the optical distortion adjustment factor.

[0072] formula:

[0073] Parameter details and acquisition methods:

[0074] Pixel coordinates x and y: These are the coordinates obtained after identifying a target object from an image captured by a camera using image recognition technology. They represent the target object's position in the image. These coordinates can be extracted directly from the video stream in real time using image processing software or algorithms, such as the image recognition function in the OpenCV library.

[0075] Image center coordinates x0 and y0: These are typically half the image resolution. For example, if using a 1920x1080 HD camera, x0 is 960 and y0 is 540. These coordinates are used to determine the center point of the image and are an inherent property of the image resolution.

[0076] Focal length f x and f y These parameters are typically provided by the camera manufacturer or can be obtained through an optical calibration process. They represent the camera's focal length on the x and y axes, which is part of the camera's optical characteristics.

[0077] Optical distortion adjustment factor d x and d y The coefficient is used to correct pixel position distortion caused by lens curvature and other optical distortions. The coefficient can be obtained through optical calibration procedures, such as taking multiple shots using a checkerboard pattern and analyzing the results to determine the value, or it can be preset by an expert.

[0078] Calculation example:

[0079] Parameters and assumed values: Target object pixel coordinates x = 1000 and y = 800; Image center coordinates x0 = 960, y0 = 540 (focal length); f x =1000 pixels, f y =1000 pixels; distortion adjustment factor d x =1.05, d y =0.95.

[0080] Calculate latitude angle θ:

[0081] Substitute the given values:

[0082] The formula used to calculate the longitude angle φ is:

[0083] The calculation results θ≈15.5° and φ≈2.18° indicate that, in the view captured by the gimbal camera, the target object is located approximately 15.5 degrees above the center of the image and approximately 2.18 degrees to the right.

[0084] Please refer to Figure 3. The steps for obtaining two-dimensional equatorial projection image data are as follows:

[0085] S121: Extract the latitude angle θ and longitude angle φ from the spherical coordinate data;

[0086] S122: Based on latitude angle θ and longitude angle φ, using the formula:

[0087] Calculate the equatorial plane coordinate data, convert the spherical coordinate data into the equatorial plane coordinate data of the pan-tilt camera, and obtain two-dimensional equatorial projection image data;

[0088] Where R is the radius of the sphere, α is the tilt angle between the pan-tilt camera and the ground, θ is the latitude angle in spherical coordinates, φ is the longitude angle in spherical coordinates, and x... eq and y eq These are the two-dimensional coordinates of the target object projected onto the equatorial plane.

[0089] formula:

[0090] Parameter details and acquisition methods:

[0091] Latitude angle θ and longitude angle φ: obtained through previous steps.

[0092] Sphere radius R: In most monitoring applications, the radius of the sphere can be assumed to be unit 1 to simplify calculations and for standardization in calculations and conversions.

[0093] The tilt angle α between the PTZ camera and the ground is an actual measurement determined by the physical tilt angle of the camera during installation. It can be obtained from specifications provided by the installation engineer or by direct measurement using a tilt sensor.

[0094] Calculation example:

[0095] Assumption:

[0096] θ = 30° (latitude angle)

[0097] φ = 45° (longitude angle)

[0098] R = 1 (radius of the sphere, normalized)

[0099] α = 10° (camera tilt angle)

[0100] Conversion process and calculation formula:

[0101] Convert θ and φ to radians for calculation:

[0102] Calculate the equatorial plane coordinates using the formula:

[0103] Specific calculations:

[0104] therefore

[0105] The calculated equatorial plane coordinates are as follows:

[0106] Calculated x eq and y eq The coordinates represent the position of the target object on the equatorial plane.

[0107] Please refer to Figure 4. The steps for obtaining the movement deviation information are as follows:

[0108] S211: Based on two-dimensional equatorial projection image data, extract the positional change of the target monitoring object between two consecutive frames and obtain the actual moving speed v. act and travel time t act ;

[0109] S212: Based on actual movement speed v act and travel time t act , compared to the preset normal moving speed v norm and travel time t norm Compare and calculate the speed deviation Δv and duration deviation Δt, and use the formula:

[0110] Calculate the moving deviation index P, assess the degree of moving deviation based on the value of the moving deviation index P, and obtain moving deviation information;

[0111] Among them, v act It is the actual moving speed, t act It is the actual duration of movement, v norm and t norm These are the preset normal movement speed and movement time, respectively. Δv and Δt represent the deviations in speed and time, respectively. v and w t These are the weighting coefficients for speed and duration deviations, respectively, and P is the movement deviation index.

[0112] formula:

[0113] Parameter details and acquisition methods:

[0114] Actual moving speed v act This is obtained by measuring the change in the target's position between two consecutive frames from two-dimensional equatorial projection image data and dividing by the time difference. act It is calculated by measuring the pixel distance of the target between two frames and converting it into an actual distance, then dividing by the time interval between the two frames.

[0115] Actual travel time t act This is determined by recording the time between when the target starts moving and when it stops moving. It is usually obtained directly from the timestamps of the video surveillance system.

[0116] Preset normal movement speed v norm and travel time t norm : This is based on previously observed or desired behavioral parameters. The parameters are set by the system administrator or through historical data analysis.

[0117] Speed ​​deviation Δv and duration deviation Δt: Speed ​​deviation is determined by Δv = v act -v norm The calculated time deviation is obtained through Δt = t act -t norm The calculations show that the deviation indicates the difference between the actual observed value and the expected standard.

[0118] weight w v and w t The weighting coefficients are pre-set based on the specific needs of the monitoring scenario. They reflect the relative importance of speed and time deviation when evaluating the total deviation index.

[0119] Calculation example:

[0120] Assume the following parameters:

[0121] v act = 5 m / s, t act =120 seconds, v norm = 4 m / s (preset normal speed), t norm =100 seconds (default normal duration), w v =0.6, w t =0.4.

[0122] Calculation process:

[0123] Calculate the speed deviation and duration deviation: Δv = 5 - 4 = 1 m / s Δt = 120 - 100 = 20 seconds

[0124] Calculate the deviation index P:

[0125] The obtained deviation index P≈0.332 indicates that the target's movement speed and duration show slight anomalies relative to the preset standard.

[0126] Please refer to Figure 5. The method for identifying abnormal behavior patterns of the target monitoring object is as follows:

[0127] S311: Based on two-dimensional equatorial projection image data, extract the movement path information of the monitored target, including the target's position coordinates in consecutive time frames, using the formula:

[0128] Calculate the matching score M between the current behavior pattern and the abnormal behavior pattern of the target monitored object;

[0129] Among them, w i λ is the weight of the i-th point. i It is the sensitivity factor, τ is the tolerance threshold, and d i M is the distance between the actual path point and the preset pattern point, n is the matching score, n is the total number of data points, and e is the base of the natural logarithm.

[0130] S312: Based on the matching score M, compare the matching score M with the preset matching threshold, mark behaviors where M exceeds the matching threshold as abnormal behaviors, and obtain the abnormal behavior type of the target object.

[0131] formula:

[0132] Parameter details and acquisition methods:

[0133] d i The distance between the actual path point and the preset pattern point is calculated as: d i =|D i -Q i |, where D i Q represents the position of the actual observed target in the image at time point i. This position is extracted directly from the surveillance video using image processing techniques. i This is the expected location at the i-th time point in the pre-defined abnormal behavior pattern database. The data is pre-defined based on past abnormal behavior cases or theoretical models.

[0134] w i The weight of each point is predetermined based on its importance in the behavioral pattern. For example, key turning points in the behavioral pattern will be given higher weights.

[0135] λ iThe sensitivity factor for each point is used to adjust for the influence of distance bias. A high sensitivity factor means that even small biases can lead to large score differences.

[0136] τ: Tolerance threshold, used to define what level of deviation is acceptable. Deviation exceeding this threshold will significantly reduce the matching score.

[0137] Calculation example:

[0138] Assume the following parameters and points:

[0139] P = {(2,3),(3,4),(5,5)} Actual path points

[0140] Q = {(2,2),(3,5),(5,6)} Preset pattern points

[0141] w = {0.5, 1, 0.5} weight

[0142] λ = {1,1,1} sensitivity factor

[0143] τ = 1 tolerance threshold

[0144] Calculation process:

[0145] Calculate the distance deviation d for each point. i : d1=|(2-2,3-2)|=1 d2=|(3-3,4-5)|=1 d3=|(5-5,5-6)|=1

[0146] Application matching degree calculation formula:

[0147] A calculated matching score M = 1.0 indicates that the actual observed path has a high degree of consistency with the preset abnormal behavior pattern, meaning that the monitored object exhibits the preset abnormal behavior type.

[0148] Please refer to Figure 6. The steps for obtaining the abnormal behavior identification results are as follows:

[0149] S321: Based on the abnormal behavior type of the target object, extract the matching score M corresponding to the abnormal behavior type. j ;

[0150] S322: Based on matching score M j Through the formula:

[0151] Calculate the abnormal behavior risk index R, assess the abnormal behavior risk of the target object based on the value of the abnormal behavior risk index R, and obtain the abnormal behavior identification result;

[0152] Where k is the total number of matched abnormal behavior patterns, and M jw is the matching score for the j-th behavior pattern. j It is the risk weight of the j-th behavior pattern, α j τ is the sensitivity coefficient for the j-th behavioral pattern. j R is the threshold for the j-th behavior pattern, and R is the abnormal behavior risk index.

[0153] Parameter details and acquisition methods:

[0154] Matching score M j This indicates the degree of matching between the behavior of the target monitored object and the preset abnormal behavior pattern, which is calculated through previous steps.

[0155] weight w j : Indicates the weight corresponding to the risk level of each behavioral pattern. The weight is based on historical data, expert opinions, or presuppositions about the severity of the behavioral consequences, with the aim of emphasizing behavioral patterns that are more likely to lead to serious consequences in risk assessment.

[0156] Sensitivity coefficient α j Controlling the impact of the matching score on risk assessment. A high coefficient value means that even a slightly higher matching score will significantly increase the risk assessment value, and it is usually adjusted according to the specific risk sensitivity of the pattern.

[0157] Threshold τ j This is the minimum threshold for determining an abnormal behavioral pattern based on its matching score. If the matching score of a behavioral pattern is below this value, its contribution to the risk index is relatively small.

[0158] Calculation example:

[0159] Assuming there are three behavior modes, the corresponding parameter settings are as follows:

[0160] Matching score M = {0.8, 0.5, 0.9}

[0161] Weights w = {0.5, 1.0, 0.7}

[0162] Sensitivity coefficient α = {1.5, 1.0, 2.0}

[0163] Threshold τ = {0.6, 0.5, 0.7}

[0164] Calculation process:

[0165] The risk contribution for each mode is calculated using the following formula:

[0166] Calculate for each pattern:

[0167] For the first pattern:

[0168] For the second mode:

[0169] For the third mode:

[0170] Calculate the abnormal behavior risk index R: R = R1 + R2 + R3 = 0.183 + 0.125 + 0.339 = 0.647

[0171] The calculation result R = 0.647 indicates that, based on the current behavioral data and the matching with the preset abnormal patterns, the overall behavioral pattern of the target monitored object shows a medium to high risk of abnormal behavior.

[0172] Please refer to Figure 7. The method for implementing the corresponding early warning measures is as follows:

[0173] S411: Based on movement deviation information and abnormal behavior identification results, extract the movement deviation index P and the abnormal behavior risk index R, using the formula:

[0174] Calculate the overall anomaly risk level E of the target object;

[0175] Where P is the movement deviation index, R is the abnormal behavior risk index, γ is the weighting coefficient for adjusting the impact of movement deviation, δ is the weighting coefficient for adjusting the impact of behavior risk, ∈ is the overall weighting coefficient, and E is the overall abnormal risk level.

[0176] S412: Based on the overall anomaly risk level E, compare the overall anomaly risk level E with the preset anomaly standard and implement corresponding early warning measures.

[0177] formula:

[0178] Parameter details and acquisition methods:

[0179] The movement deviation index P is calculated through the previous steps.

[0180] Abnormal behavior risk index R: Calculated through previous steps.

[0181] Weighting coefficient γ: Used to adjust the influence of the movement deviation index P in the overall risk level calculation. The weight is usually set by the system administrator based on specific monitoring needs and historical data, reflecting the importance of abnormal movement speed in the overall risk.

[0182] The weighting coefficient δ is used to adjust the influence of the abnormal behavior risk index R in the overall risk level calculation. The weights are set based on monitoring needs and historical data, reflecting the importance of abnormal behavioral patterns in the overall risk.

[0183] The weighting coefficient ∈ is used to adjust the combined influence of the movement deviation and abnormal behavior risk indices on the overall risk level. The weights are used to balance the relationship between movement deviation and behavioral risk, ensuring that their combined impact is appropriately considered.

[0184] Calculation example:

[0185] Assumption:

[0186] The moving deviation index P = 0.4

[0187] The risk index for abnormal behavior, R, is 0.6.

[0188] Weighting coefficient γ = 0.3

[0189] Weighting coefficient δ = 0.4

[0190] Weighting coefficient ∈ = 0.3

[0191] Calculation process:

[0192] Calculate the contribution of each part: γ·P 2 =0.3·0.4 2 =0.3·0.16=0.048 δ·R 2 =0.4·0.6 2 =0.4·0.36=0.144 ε·log(1+P+R)=0.3·log(1+0.4+0.6) =0.3·log(2) ≈0.3·0.3010 =0.0903

[0193] Calculate the overall anomaly risk level E:

[0194] The calculated result E≈0.5314 indicates that the overall anomaly risk level of the target object is moderate. This value provides a quantitative risk assessment result, which can be used to determine whether early warning measures or further monitoring adjustments are needed.

[0195] A monitoring system based on equatorial plane projection, comprising:

[0196] The video data capture module captures real-time video image data based on the target monitoring area through a PTZ camera, converts the position of the target monitoring object in the video data into spherical coordinates centered on the PTZ camera, and generates a real-time spherical coordinate set.

[0197] The equatorial projection conversion module is based on a real-time spherical coordinate set. It should convert the spherical coordinate data to the equatorial plane coordinate data of the pan-tilt camera to obtain the equatorial plane projection image data.

[0198] The behavior speed analysis module analyzes the movement speed and duration of the monitored object based on equatorial plane projection image data, compares it with preset standards, calculates the deviation, and generates a movement deviation index.

[0199] The abnormal behavior pattern matching module compares the behavior patterns of monitored objects with a preset abnormal behavior pattern database based on equatorial plane projection image data, identifies the types of abnormal behavior, calculates the abnormal behavior risk index, and obtains abnormal behavior pattern risk information.

[0200] The abnormal behavior risk assessment module calculates the overall abnormal risk level based on the movement deviation index and abnormal behavior pattern risk information, implements matching early warning measures, adjusts the angle of the PTZ camera, continuously monitors the target monitoring object information, and obtains safety early warning detection information.

[0201] The above are merely embodiments of this application and are not intended to limit this application in any other way. Any person skilled in the art may use the above-disclosed technical content to make changes or modifications to equivalent embodiments and apply them to other fields. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of this application without departing from the content of the technical solution of this application shall still fall within the protection scope of the technical solution of this application.

Claims

1. A monitoring method based on equatorial plane projection, wherein, The method includes the following steps: Based on the target monitoring area, video image data of the monitoring area is captured in real time through a PTZ camera. The position of the target monitoring object in the video data is converted into spherical coordinates centered on the PTZ camera to obtain spherical coordinate data. The spherical coordinate data is then transformed into equatorial plane projection data to obtain two-dimensional equatorial projection image data. Based on the two-dimensional equatorial projection image data, the moving speed and moving duration of the target monitored object are analyzed, the deviation of the target monitored object from the normal moving speed and moving duration is calculated, the moving deviation index is evaluated, and the moving deviation information is obtained. The steps for obtaining the movement deviation information are as follows: Based on the two-dimensional equatorial projection image data, the positional change of the target object between two consecutive frames is extracted, and the actual moving speed v is obtained. act and travel time t act ; Based on the actual moving speed v act and travel time t act , compared to the preset normal moving speed v norm and travel time t norm Compare and calculate the speed deviation Δv and duration deviation Δt, and use the formula: Calculate the moving deviation index P, assess the degree of moving deviation based on the value of the moving deviation index P, and obtain moving deviation information; Among them, v act It is the actual moving speed, t act It is the actual duration of movement, v norm and t norm These are the preset normal movement speed and movement time, respectively. Δv and Δt represent the deviations in speed and time, respectively. v and w t These are the weighting coefficients for speed and duration deviations, respectively, and P is the movement deviation index; Based on the two-dimensional equatorial projection image data, the movement path and behavior pattern of the target monitored object are analyzed, abnormal behavior patterns of the target monitored object are identified, and an abnormal behavior risk index is calculated to assess the risk of abnormal behavior patterns and obtain abnormal behavior identification results. Based on the movement deviation information and abnormal behavior recognition results, the overall abnormal risk level of the target object is calculated. According to the abnormal risk level, corresponding early warning measures are implemented, and the angle of the PTZ camera is adjusted to continuously monitor the target object information and obtain safety early warning detection information.

2. The monitoring method based on equatorial plane projection according to claim 1, wherein, The steps for obtaining the spherical coordinate data are as follows: Based on the target monitoring area, video image data of the monitoring area is captured in real time by a PTZ camera, and the pixel coordinates of the target objects in the image are identified. Based on the pixel coordinates of the target object in the image, using the formula: Convert the pixel coordinates into spherical coordinates centered on the gimbal camera to obtain spherical coordinate data; Where θ is the latitude angle in spherical coordinates, φ is the longitude angle in spherical coordinates, x and y are the pixel coordinates of the target object, x0 and y0 are the pixel coordinates of the image center, and f x and f y These are the focal lengths of the camera in the x and y directions, respectively, d x and d y It is the optical distortion adjustment factor.

3. The monitoring method based on equatorial plane projection according to claim 2, wherein, The steps for acquiring the two-dimensional equatorial projection image data are as follows: Based on the spherical coordinate data, extract the latitude angle θ and longitude angle φ from the spherical coordinates; Based on the latitude angle θ and longitude angle φ, using the formula: Calculate the equatorial plane coordinate data, convert the spherical coordinate data into the equatorial plane coordinate data of the pan-tilt camera, and obtain two-dimensional equatorial projection image data; Where R is the radius of the sphere, α is the tilt angle between the pan-tilt camera and the ground, θ is the latitude angle in spherical coordinates, φ is the longitude angle in spherical coordinates, and x... eq and y eq These are the two-dimensional coordinates of the target object projected onto the equatorial plane.

4. The monitoring method based on equatorial plane projection according to claim 1, wherein, The method for identifying abnormal behavior patterns of the target monitored object is as follows: Based on the two-dimensional equatorial projection image data, the movement path information of the target object is extracted, including the target's position coordinates in consecutive time frames, using the formula: Calculate the matching score M between the current behavior pattern and the abnormal behavior pattern of the target monitored object; Among them, w i λ is the weight of the i-th point. j It is the sensitivity factor, τ is the tolerance threshold, and d i M is the distance between the actual path point and the preset pattern point, n is the matching score, n is the total number of data points, and e is the base of the natural logarithm. Based on the matching score M, the matching score M is compared with a preset matching threshold. Behaviors where M exceeds the matching threshold are marked as abnormal behaviors, thus obtaining the abnormal behavior type of the target object.

5. The monitoring method based on equatorial plane projection according to claim 4, wherein, The steps for obtaining the abnormal behavior identification results are as follows: Based on the abnormal behavior type of the target object, extract the matching score M corresponding to the abnormal behavior type. j ; Based on the matching score M j Through the formula: Calculate the abnormal behavior risk index R, assess the abnormal behavior risk of the target object based on the value of the abnormal behavior risk index R, and obtain the abnormal behavior identification result; Where k is the total number of matched abnormal behavior patterns, and M j w is the matching score for the j-th behavior pattern. j It is the risk weight of the j-th behavior pattern, α j τ is the sensitivity coefficient for the j-th behavioral pattern. j R is the threshold for the j-th behavior pattern, and R is the abnormal behavior risk index.

6. The monitoring method based on equatorial plane projection according to claim 1, wherein, The method for implementing the corresponding early warning measures is as follows: Based on the movement deviation information and abnormal behavior identification results, the movement deviation index P and the abnormal behavior risk index R are extracted, using the formula: Calculate the overall anomaly risk level E of the target object; Where P is the movement deviation index, R is the abnormal behavior risk index, γ is the weighting coefficient for adjusting the impact of movement deviation, δ is the weighting coefficient for adjusting the impact of behavior risk, ε is the overall weighting coefficient, and E is the overall abnormal risk level. Based on the overall anomaly risk level E, the overall anomaly risk level E is compared with the preset anomaly standard, and corresponding early warning measures are implemented.

7. A monitoring system based on equatorial plane projection, executed according to any one of claims 1-6, wherein, The system includes: The video data capture module captures real-time video image data based on the target monitoring area through a PTZ camera, converts the position of the target monitoring object in the video data into spherical coordinates centered on the PTZ camera, and generates a real-time spherical coordinate set. Based on the real-time spherical coordinate set, the equatorial projection conversion module should convert the spherical coordinate data to the equatorial plane coordinate data of the pan-tilt camera to obtain the equatorial plane projection image data. The behavior speed analysis module analyzes the movement speed and duration of the monitored object based on the equatorial plane projection image data, compares it with a preset standard, calculates the deviation, and generates a movement deviation index. The method for calculating the movement deviation index is as follows: Based on the two-dimensional equatorial projection image data, the positional change of the target object between two consecutive frames is extracted, and the actual moving speed v is obtained. act and travel time t act ; Based on the actual moving speed v act and travel time t act , compared to the preset normal moving speed v norm and travel time t norm Compare and calculate the speed deviation Δv and duration deviation Δt, and use the formula: Calculate the moving deviation index P; Among them, v act It is the actual moving speed, t act It is the actual duration of movement, v norm and t norm These are the preset normal movement speed and movement time, respectively. Δv and Δt represent the deviations in speed and time, respectively. v and w t These are the weighting coefficients for speed and duration deviations, respectively, and P is the movement deviation index; The abnormal behavior pattern matching module compares the behavior patterns of the monitored object with the preset abnormal behavior pattern database based on the equatorial plane projection image data, identifies the abnormal behavior type, calculates the abnormal behavior risk index, and obtains abnormal behavior pattern risk information. Based on the movement deviation index and abnormal behavior pattern risk information, the abnormal behavior risk assessment module calculates the overall abnormal risk level, implements matching early warning measures, adjusts the angle of the PTZ camera, continuously monitors the target monitoring object information, and obtains safety early warning detection information.

Images