System and method for supervising parking lot based on remote seat

By combining cloud computing platforms and deep learning models, the problems of false alarms and missed alarms in abnormal behavior detection in complex scenarios have been solved, improving the efficiency of parking lot management and the flexibility of emergency response, and achieving efficient and accurate parking lot supervision.

CN119028166AActive Publication Date: 2024-11-26CHONG QING YI LIAN XIN XI KE JI YOU XIAN GONG SI
View PDF 11 Cites 0 Cited by

Patent Information

Application Number
CN202411069752.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-11-26
Estimated Expiration
2044-08-06

AI Technical Summary

Technical Problem

Existing technologies are prone to false alarms and missed alarms in abnormal behavior detection in complex scenarios. The real-time performance and reliability of data transmission in remote monitoring systems are insufficient, affecting the efficiency and accuracy of parking lot management.

Method used

Deep learning models are trained using a cloud computing platform, and background subtraction and feature extraction are performed using an adaptive Gaussian mixture model. Anomaly detection is performed using an AutoEncoder model, and abnormal behavior is identified through self-supervised learning. Emergency response is achieved by combining deep learning with a decision-making support system and an intelligent customer service system.

Benefits of technology

It has achieved efficient and accurate parking management, improved the accuracy of abnormal behavior detection and the real-time nature of data transmission, and enhanced the flexibility of emergency response and user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119028166A_ABST
    Figure CN119028166A_ABST
Patent Text Reader

Abstract

The invention provides a system and method for supervising a parking lot based on a remote seat, and aims to improve the efficiency and safety of parking lot management through remote monitoring and automation technologies. The system mainly comprises an image acquisition device, a remote seat center, a background subtraction module, a motion feature extraction module and an anomaly detection module. And the data processing module preprocesses the image data by using background subtraction and an optical flow method to extract foreground and motion features, and performs abnormal behavior and fire detection in combination with an anomaly detection algorithm. The remote seat center receives and analyzes the processed data through a network, carries out real-time monitoring and early warning on abnormal behaviors in combination with a deep learning algorithm, and provides remote emergency processing suggestions at the same time, so that managers can take actions in time. According to the system, efficient abnormal behavior detection and emergency processing are realized through a deep learning technology, and the safety and management efficiency of the parking lot are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention provides a parking lot supervision method, and in particular relates to a system and method for supervising a parking lot based on a remote seat. Background Art

[0002] With the acceleration of urbanization and the rapid growth of the number of motor vehicles, the problem of parking difficulties has become increasingly prominent and has become an important challenge for urban traffic management. Remote seat supervision technology refers to real-time monitoring and management of parking lot operations through remote monitoring and management centers. The core of this technology is to use sensors, cameras, data transmission networks and other equipment to transmit real-time data of parking lots to remote monitoring centers for real-time monitoring and management by seat personnel. Remote seat supervision technology can significantly improve the efficiency and accuracy of parking lot management, reduce manual intervention, and improve user experience.

[0003] Deep learning and image processing technologies have been widely used in intelligent parking systems. By acquiring real-time images of parking lots through cameras and using deep learning algorithms for image processing and analysis, functions such as vehicle recognition, license plate recognition, and parking space detection can be realized. The application of these technologies can not only improve the automation level of parking lots, but also provide accurate real-time data support for remote seat supervision.

[0004] Although the intelligent parking system has made significant progress in some aspects, the existing technology still has some shortcomings. For example, the traditional abnormal behavior detection method is prone to false positives and false negatives in complex scenarios; the existing remote seat supervision system still has room for improvement in terms of real-time and reliability of data transmission; this urgently requires technical personnel in this field to solve the corresponding technical problems. Summary of the invention

[0005] The present invention aims to at least solve the technical problems existing in the prior art, and in particular innovatively proposes a system and method for remote seat supervision of a parking lot.

[0006] In order to achieve the above-mentioned object of the present invention, the present invention provides a system for supervising a parking lot based on a remote seat, comprising:

[0007] Cloud computing platform: upload image data obtained by image acquisition devices to the cloud for deep learning model training and more complex analysis.

[0008] First, abnormal behavior judgment is performed. Before abnormal behavior judgment, the background image needs to be subtracted;

[0009] Background subtraction is used to remove static background in video and highlight moving objects. Adaptive mixed Gaussian model is used to identify the gray value of the background for subsequent background subtraction.

[0010]

[0011] Among them: B t+1 (x, y) is the background value at position (x, y) at time t+1; α t and β t is the dynamic learning rate, the subscript t is the current time, which determines the update weight of the image grayscale value of the background model at time t;

[0012] I t (x,y) is the grayscale value of the pixel at position (x,y) at time t;

[0013] B t (x+i, y+j) is the grayscale value of the background model at position (x+i, y+j); i is the movement value of the image pixel's horizontal coordinate x, and j is the movement value of the image pixel's vertical coordinate y;

[0014] w ij is the Gaussian weight, and m is the window size, which is used to set according to the background object.

[0015] Dynamic learning rate α at time t t , dynamic learning rate β for background position t And the background position Gaussian weight w ij The calculation method is:

[0016]

[0017]

[0018] Among them, B t (x,y) is the background value at position (x,y) at time t,

[0019] The initial learning rate at time t is α0 and the initial learning rate at the background position is β0, and α0+β0=1. M is the total number of pixels in the image, which is used for normalization after difference summation.

[0020] represents pixel I at time t t (x, y) and the background value B at time t t The average of the global differences between (x,y),

[0021] is the local variance term, is the variance of the image grayscale value of the background model at position (x, y),

[0022] I represents time t t (x, y) and the image gray value B of the background model tThe difference between (x, y) in the local binary pattern LBP, which is a texture descriptor used to capture local texture features.

[0023] λ is a parameter that controls the change of weights.

[0024] Index term Represents the similarity between the pixel at position (x+i,y+j) and position (x,y). The similarity is measured by the square of the difference between the two, then multiplied by negative λ and exponentially taken.

[0025] Normalization term The similarity index of all neighborhood pixels is summed up and used to normalize the weights to ensure that the sum of all weights is 1.

[0026] The background subtraction module also includes using the foreground mask to subtract the redundant static content of the background.

[0027]

[0028] in,

[0029] I t (x,y) represents the gray value of the pixel at position (x,y) at time t,

[0030] B t (x,y) represents the background value at position (x,y) at time t,

[0031] Threshold: A preset threshold used to determine the current pixel gray value I t (x, y) and the image gray value B of the background model t Is the difference between (x,y) significant?

[0032] F t (x,y) is the foreground mask, F t (x, y) = 1 means that at the position (x, y) at time t, the image gray value I t (x, y) and the image gray value B of the background model t If the difference between (x, y) is greater than the preset threshold, the pixel is considered to belong to the foreground, that is, there is a moving object or change at the position (x, y) at time t.

[0033] F t (x, y) = 0 means that at the position (x, y) at time t, the image gray value I t (x, y) and the image gray value B of the background model t If the difference between (x, y) is less than or equal to the preset threshold, the pixel is considered to belong to the background, that is, there is no significant change at the position (x, y) at time t.

[0034] Feature extraction:

[0035] After background subtraction is completed, feature extraction begins to analyze the behavioral content of parking lot parking images.

[0036] In the foreground mask F t In the area where (x,y)=1, the optical flow field is used to describe the changes of image pixels over time:

[0037] I F (x,y,t) is the foreground mask F t In the region where (x, y) = 1, the grayscale value of the pixel image at the position (x, y) at time t;

[0038] Through Taylor expansion, we can get

[0039]

[0040] and is the spatial gradient of the image grayscale value, is the time gradient of the image gray value;

[0041] (x,y) is the image coordinate, t is the time, u and v are the components of the optical flow in the x and y directions respectively;

[0042] Calculate the magnitude of the motion vector:

[0043]

[0044] Calculate the direction of the motion vector:

[0045]

[0046] For the calculated motion features magnitude and θ, the feature vector is extracted as f i ,

[0047] f i =(magnitude,θ)

[0048] The probability distribution of normal behavior can be expressed as

[0049]

[0050] in, is the kth Gaussian distribution, calculated as:

[0051]

[0052] μ kis the mean of each motion vector magnitude and each motion vector direction θ, ∑k is the covariance matrix of each motion vector magnitude and each motion vector direction θ, is the inverse matrix of the covariance matrix ∑k, K is the total number of Gaussian distributions, and T represents the transpose; f i is the feature vector of the i-th input;

[0053] π k is the weight of the kth Gaussian distribution;

[0054] Gaussian distribution weight π k The update method is:

[0055]

[0056] is the weight of the k-th Gaussian distribution in the t-th iteration, is the weight of the kth Gaussian distribution in the t+1th iteration, is the expected value of the number of data points generated by the k-th Gaussian distribution in the t-th iteration, γ is a dynamic adjustment parameter, δ is a regularization parameter, K is the total number of Gaussian distributions, η is the learning rate, which is used to adjust the step size of gradient descent, is the gradient of the loss function with respect to the weights, N represents the total number of data points, and in each iteration, the number of all data points remains unchanged.

[0057] The anomaly detection module includes using self-supervised learning methods to train the model so that it can identify unseen abnormal behaviors. The AutoEncoder-based model can learn the characteristics of normal behavior, and when abnormal behavior is detected, there will be a higher reconstruction error, which is calculated as:

[0058] Encoder:

[0059] h=f(W e f i +b e )

[0060] Decoder:

[0061]

[0062] Mixed reconstruction error:

[0063]

[0064] Among them, f i is the feature vector of the i-th input, h is the encoded feature, is the reconstructed feature vector after the i-th decoding, and n is the dimension of the feature vector;

[0065] f() and g() are the function representations of the encoder and decoder respectively, W e and W d are the weight matrices of the encoder and decoder, respectively, and b e and b d are the bias vectors of the encoder and decoder respectively;

[0066] is the mean square error term, is the log-likelihood term,

[0067] is the weight parameter used to adjust the weight between the mean square error term and the log likelihood term, σ 2 is the variance of the Gaussian distribution;

[0068] L e It is the reconstruction error, which is used to measure the difference between the input data and the reconstructed data. The reconstruction error of the new feature vector is calculated in the inference phase. If the isomorphism error is greater than the threshold τ, it is judged as an abnormality.

[0069] When the isomorphism error L e >τ, the system will be judged as abnormal behavior. The setting of the threshold τ is determined by the mean and variance of the reconstruction error:

[0070]

[0071] in,

[0072] is the reconstruction error L e The mean of

[0073] is the reconstruction error L e The standard deviation of

[0074] χ is a constant used to adjust the sensitivity of the threshold;

[0075] About the reconstruction error L e The mean and standard deviation The calculation methods are:

[0076]

[0077] in, is the i-th reconstruction error, and P represents the number of all samples involved in calculating the reconstruction error;

[0078] When the image recognition system detects abnormal behavior, the system will provide an alarm signal to the abnormal behavior subject and the staff of the remote monitoring center to facilitate the response to the abnormality.

[0079] Measures to deal with abnormal behavior:

[0080] Real-time alert system: When abnormal behavior is detected, the edge device immediately triggers an alert and notifies the monitoring center through the network.

[0081] The system can automatically execute some preset emergency measures, such as closing gates and turning on warning lights.

[0082] Deep learning aids decision-making: Use deep learning models to analyze historical emergency event data and optimize emergency plans. The model can predict the effects of different emergency measures and help formulate the best emergency strategy.

[0083] Dynamic emergency response plan: Dynamically adjust the emergency response plan based on real-time monitoring data and the prediction results of the deep learning model to improve the flexibility and effectiveness of emergency response.

[0084] For example, after the model detects a fire hazard, it notifies remote staff to respond. Different levels of emergency needs correspond to different degrees of alarms and emergency response measures.

[0085] Intelligent customer service system: When abnormal behavior is detected, the system can generate automated notifications through NLP technology and communicate with users through voice or text to provide guidance and assistance.

[0086] Emergency response team collaboration: Through the cloud platform, abnormal behavior detection results and emergency handling suggestions are shared in real time to ensure that the emergency response team can quickly collaborate to handle emergencies.

[0087] In summary, due to the adoption of the above technical solution, the intelligent parking system based on remote seat supervision of the present invention, combined with deep learning technology, realizes efficient and accurate parking lot management, which has important practical significance and application value.

[0088] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0090] Figure 1 It is an overall schematic diagram of the present invention. DETAILED DESCRIPTION

[0091] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0092] The present invention provides a method for supervising a parking lot based on a remote seat. Figure 1 As shown, including the following:

[0093] Cloud computing platform: upload image data obtained by image acquisition devices to the cloud for deep learning model training and more complex analysis.

[0094] First, abnormal behavior judgment is performed. Before abnormal behavior judgment, the background image needs to be subtracted;

[0095] Background subtraction is used to remove static backgrounds in videos and highlight moving objects. The grayscale value of the background is identified using an adaptive mixed Gaussian model for subsequent background subtraction.

[0096]

[0097] Among them: B t+1 (x, y) is the background value at position (x, y) at time t+1; α t and β t is the dynamic learning rate, the subscript t is the current time, which determines the update weight of the image grayscale value of the background model at time t;

[0098] I t (x,y) is the grayscale value of the pixel at position (x,y) at time t;

[0099] B t (x+i, y+j) is the grayscale value of the background model at position (x+i, y+j); i is the movement value of the image pixel's horizontal coordinate x, and j is the movement value of the image pixel's vertical coordinate y;

[0100] w ij is the Gaussian weight, and m is the window size, which is used to set according to the background object.

[0101] Dynamic learning rate α at time t t , dynamic learning rate β for background position t And the background position Gaussian weight w ij The calculation method is:

[0102]

[0103] Among them, B t(x,y) is the background value at position (x,y) at time t,

[0104] The initial learning rate at time t is α0 and the initial learning rate at the background position is β0, and α0+β0=1. M is the total number of pixels in the image, which is used for normalization after difference summation.

[0105] represents pixel I at time t t (x, y) and the background value B at time t t The average of the global differences between (x,y),

[0106] is the local variance term, is the variance of the image grayscale value of the background model at position (x, y),

[0107] I represents time t t (x, y) and the image gray value B of the background model t The difference between (x, y) in the local binary pattern LBP, which is a texture descriptor used to capture local texture features.

[0108] λ is a parameter that controls the change of weight.

[0109] Index term Represents the similarity between the pixel at position (x+i,y+j) and position (x,y). The similarity is measured by the square of the difference between the two, then multiplied by negative λ and exponentially taken.

[0110] Normalization term The similarity index of all neighborhood pixels is summed up and used to normalize the weights to ensure that the sum of all weights is 1.

[0111] Use the foreground mask to remove the redundant static content of the background.

[0112]

[0113] in,

[0114] I t (x,y) represents the gray value of the pixel at position (x,y) at time t,

[0115] B t (x,y) represents the background value at position (x,y) at time t,

[0116] Threshold: A preset threshold used to determine the current pixel gray value I t (x, y) and the image gray value B of the background model t Is the difference between (x,y) significant?

[0117] F t (x,y) is the foreground mask, F t (x, y) = 1 means that at the position (x, y) at time t, the image gray value I t (x, y) and the image gray value B of the background model t If the difference between (x, y) is greater than the preset threshold, the pixel is considered to belong to the foreground, that is, there is a moving object or change at the position (x, y) at time t.

[0118] F t (x, y) = 0 means that at the position (x, y) at time t, the image gray value I t (x, y) and the image gray value B of the background model t If the difference between (x, y) is less than or equal to the preset threshold, the pixel is considered to belong to the background, that is, there is no significant change at the position (x, y) at time t.

[0119] For example, the gray value of the image at time t is I t (x,y) is

[0120]

[0121] The image gray value B of the background model t (x,y) is

[0122]

[0123] Assume that the threshold at the current time t is 5 and the foreground mask F t The calculation result of (x,y) is

[0124]

[0125] Feature extraction:

[0126] After background subtraction is completed, feature extraction begins to analyze the behavioral content of parking lot parking images.

[0127] In the foreground mask F t In the area where (x,y)=1, the optical flow field is used to describe the changes of image pixels over time:

[0128] I F (x,y,t) is the foreground mask F t In the region where (x, y) = 1, the grayscale value of the pixel image at the position (x, y) at time t

[0129] Through Taylor expansion, we can get

[0130]

[0131] and is the spatial gradient of the image grayscale value, is the time gradient of the image gray value;

[0132] (x,y) is the image coordinate, t is the time, u and v are the components of the optical flow in the x and y directions respectively;

[0133] Calculate the magnitude of the motion vector:

[0134]

[0135] Calculate the direction of the motion vector:

[0136]

[0137] For the calculated motion features magnitude and θ, the feature vector is extracted as f i ,

[0138] f i =(magnitude,θ)

[0139] The probability distribution of normal behavior can be expressed as:

[0140]

[0141] in, is the kth Gaussian distribution, calculated as,

[0142]

[0143] μ k is the mean of each motion vector magnitude and each motion vector direction θ, ∑k is the covariance matrix of each motion vector magnitude and each motion vector direction θ, is the inverse matrix of the covariance matrix ∑k, K is the total number of Gaussian distributions, and T represents the transpose; f i is the feature vector of the i-th input;

[0144] π k is the weight of the kth Gaussian distribution;

[0145] Gaussian distribution weight π k The update method is:

[0146]

[0147] is the weight of the k-th Gaussian distribution in the t-th iteration, is the weight of the kth Gaussian distribution in the t+1th iteration, is the expected value of the number of data points generated by the k-th Gaussian distribution in the t-th iteration, γ is a dynamic adjustment parameter, δ is a regularization parameter, K is the total number of Gaussian distributions, η is the learning rate, which is used to adjust the step size of gradient descent, is the gradient of the loss function with respect to the weights, N represents the total number of data points, and in each iteration, the number of all data points remains unchanged.

[0148] The anomaly detection module includes using self-supervised learning methods to train the model so that it can identify unseen abnormal behaviors. The AutoEncoder-based model can learn the characteristics of normal behavior, and when abnormal behavior is detected, there will be a higher reconstruction error, which is calculated as:

[0149] Encoder:

[0150] h=f(W e f i +b e )

[0151] Decoder:

[0152]

[0153] Mixed reconstruction error:

[0154]

[0155] Among them, f i is the feature vector of the i-th input, h is the encoded feature, is the reconstructed feature vector after the i-th decoding, and n is the dimension of the feature vector;

[0156] f() and g() are the function representations of the encoder and decoder respectively, W e and W d are the weight matrices of the encoder and decoder, respectively, and b e and b d are the bias vectors of the encoder and decoder respectively;

[0157] is the mean square error term, is the log-likelihood term,

[0158] is the weight parameter used to adjust the weight between the mean square error term and the log likelihood term, σ 2 is the variance of the Gaussian distribution;

[0159] L eIt is the reconstruction error, which is used to measure the difference between the input data and the reconstructed data. The reconstruction error of the new feature vector is calculated in the inference phase. If the isomorphism error is greater than the threshold τ, it is judged as an abnormality.

[0160] When the isomorphism error L e >τ, the system will be judged as abnormal behavior. The setting of the threshold τ is determined by the mean and variance of the reconstruction error:

[0161]

[0162] in,

[0163] is the reconstruction error L e The mean of

[0164] is the reconstruction error L e The standard deviation of

[0165] χ is a constant used to adjust the sensitivity of the threshold;

[0166] About the reconstruction error L e The mean and standard deviation The calculation methods are:

[0167]

[0168] in, is the i-th reconstruction error, and P represents the number of all samples involved in calculating the reconstruction error;

[0169] When the image recognition system detects abnormal behavior, the system will provide an alarm signal to the abnormal behavior subject and the staff of the remote monitoring center to facilitate the response to the abnormality.

[0170] Measures to deal with abnormal behavior:

[0171] Real-time alert system: When abnormal behavior is detected, the edge device immediately triggers an alert and notifies the monitoring center through the network.

[0172] The system can automatically execute some preset emergency measures, such as closing gates and turning on warning lights.

[0173] Deep learning aids decision-making: Use deep learning models to analyze historical emergency event data and optimize emergency plans. The model can predict the effects of different emergency measures and help formulate the best emergency strategy.

[0174] Dynamic emergency response plan: Dynamically adjust the emergency response plan based on real-time monitoring data and the prediction results of the deep learning model to improve the flexibility and effectiveness of emergency response.

[0175] For example, after the model detects a fire hazard, it notifies remote staff to respond. Different levels of emergency needs correspond to different degrees of alarms and emergency response measures.

[0176] Intelligent customer service system: When abnormal behavior is detected, the system can generate automated notifications through NLP technology and communicate with users through voice or text to provide guidance and assistance.

[0177] Emergency response team collaboration: Through the cloud platform, abnormal behavior detection results and emergency handling suggestions are shared in real time to ensure that the emergency response team can quickly collaborate to handle emergencies.

[0178] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

Claims

1. A system based on remote seat supervision of parking lots, characterized in that: include: A background subtraction module separates the background from the foreground using a background subtraction algorithm on the image data acquired by the image acquisition device; The motion feature extraction module uses the optical flow method to calculate the motion vector in the foreground area and extract the motion features; The anomaly detection module uses a self-supervised learning method to train the model and uses the isomorphic error to measure the difference between the input data and the reconstructed data to determine whether it is an anomaly.

2. The system based on remote seat supervision of parking lot according to claim 1 is characterized in that: The background subtraction module comprises: Use the adaptive mixed Gaussian model to identify the gray value of the background for subsequent background subtraction. Among them: B t+1 (x, y) is the background value at position (x, y) at time t+1; α t and β t is the dynamic learning rate, the subscript t is the current time, which determines the update weight of the image grayscale value of the background model at time t; I t (x,y) is the grayscale value of the pixel at position (x,y) at time t; B t (x+i, y+j) is the grayscale value of the background model at position (x+i, y+j); i is the movement value of the image pixel's horizontal coordinate x, and j is the movement value of the image pixel's vertical coordinate y; w ij is the Gaussian weight, and m is the window size, which is used to set according to the background object.

3. The system based on remote seat supervision of parking lot according to claim 2 is characterized in that: The dynamic learning rate α at time t t , dynamic learning rate β for background position t And the background position Gaussian weight w ij include: Dynamic learning rate α at time t t , dynamic learning rate β for background position t And the background position Gaussian weight w ij The calculation method is: Among them, B t (x,y) is the background value at position (x,y) at time t, The initial learning rate at time t is α0 and the initial learning rate at the background position is β0, and α0+β0=1. M is the total number of pixels in the image, which is used for normalization after difference summation. represents pixel I at time t t (x, y) and the background value B at time t t The average of the global differences between (x,y), is the local variance term, is the variance of the image grayscale value of the background model at position (x, y), I represents time t t (x, y) and the image gray value B of the background model t The difference between (x, y) in the local binary pattern LBP, which is a texture descriptor used to capture local texture features. λ is a parameter that controls the change of weight. Index term Represents the similarity between the pixel at position (x+i,y+j) and position (x,y). The similarity is measured by the square of the difference between the two, then multiplied by negative λ and exponentially taken. Normalization term The similarity index of all neighborhood pixels is summed up and used to normalize the weights to ensure that the sum of all weights is 1.

4. The system based on remote seat supervision of parking lot according to claim 1 is characterized in that: The background subtraction module comprises: Use the foreground mask to remove the redundant static content of the background. in, I t (x,y) represents the gray value of the pixel at position (x,y) at time t, B t (x,y) represents the background value at position (x,y) at time t, Threshold represents a preset threshold value, which is used to determine the current pixel gray value I t (x, y) and the image gray value B of the background model t Is the difference between (x,y) significant? F t (x,y) is the foreground mask, F t (x, y) = 1 means that at the position (x, y) at time t, the image gray value I t (x, y) and the image gray value B of the background model t The difference between (x, y) is greater than the preset threshold, then the pixel is considered to belong to the foreground, that is, there is a moving object or change at the position (x, y) at time t; F t (x, y) = 0 means that at the position (x, y) at time t, the image gray value I t (x, y) and the image gray value B of the background model t If the difference between (x, y) is less than or equal to the preset threshold, the pixel is considered to belong to the background, that is, there is no change at the position (x, y) at time t.

5. The system based on remote seat supervision of parking lot according to claim 1 is characterized in that: The motion feature extraction module comprises: In the foreground mask F t In the area where (x,y)=1, the optical flow field is used to describe the changes of image pixels over time: I F (x,y,t) is the foreground mask F t In the region where (x, y) = 1, the grayscale value of the pixel image at the position (x, y) at time t; Through Taylor expansion, we can get: and isI F (x,y,t) in the foreground mask F t In the region where (x, y) = 1, the spatial gradient of the grayscale value of the pixel image at the position (x, y) at time t, isI F (x,y,t) in the foreground mask F t The time gradient of the grayscale value of the pixel image at the position (x, y) at time t in the region where (x, y) = 1; (x,y) is the image coordinate, t is the time, u and v are the components of the optical flow in the x and y directions respectively; Calculate the magnitude of the motion vector, Calculate the direction of the motion vector, For the calculated motion features magnitude and θ, the feature vector is extracted as f i , f i =(magnitude,θ) The probability distribution of normal behavior can be expressed as, in, is the kth Gaussian distribution, calculated as, μ k is the mean of each motion vector magnitude and each motion vector direction θ, ∑k is the covariance matrix of each motion vector magnitude and each motion vector direction θ, is the inverse matrix of the covariance matrix ∑k, K is the total number of Gaussian distributions, and T represents the transpose; f i is the feature vector of the i-th input; π k is the weight of the kth Gaussian distribution; Gaussian distribution weight π k The update method is: is the weight of the k-th Gaussian distribution in the t-th iteration, is the weight of the kth Gaussian distribution in the t+1th iteration, is the expected value of the number of data points generated by the k-th Gaussian distribution in the t-th iteration, γ is a dynamic adjustment parameter, δ is a regularization parameter, K is the total number of Gaussian distributions, η is the learning rate, which is used to adjust the step size of gradient descent, is the gradient of the loss function with respect to the weights, N represents the total number of data points, and in each iteration, the number of all data points remains unchanged.

6. The system based on remote seat supervision of parking lot according to claim 1 is characterized in that: The anomaly detection module comprises: The model is trained using a self-supervised learning method to enable it to identify abnormal behavior. The AutoEncoder-based model can learn the characteristics of normal behavior. When abnormal behavior is detected, there will be a higher reconstruction error, which is calculated as follows: Encoder: h=f(W e f i +b e ) Decoder: Mixed reconstruction error: Among them, f i is the feature vector of the i-th input, h is the encoded feature, is the reconstructed feature vector after the i-th decoding, and n is the dimension of the feature vector; f() and g() are the function representations of the encoder and decoder respectively, W e and W d are the weight matrices of the encoder and decoder, respectively, and b e and b d are the bias vectors of the encoder and decoder respectively; is the mean square error term, is the log-likelihood term, is the weight parameter used to adjust the weight between the mean square error term and the log likelihood term, σ 2 is the variance of the Gaussian distribution; L e It is the reconstruction error, which is used to measure the difference between the input data and the reconstructed data. The reconstruction error of the new feature vector is calculated in the inference phase. If the isomorphism error is greater than the threshold τ, it is judged as an abnormality.

7. The system for remote seat monitoring of parking lots according to claim 5 is characterized in that: The calculation method of the threshold τ includes: When the isomorphism error L e >τ, the system will be judged as abnormal behavior. The setting of the threshold τ is determined by the mean and variance of the reconstruction error: in, is the reconstruction error L e The mean of is the reconstruction error L e The standard deviation of χ is a constant used to adjust the sensitivity of the threshold; About the reconstruction error L e The mean and standard deviation The calculation methods are: in, is the i-th reconstruction error, and P represents the number of all samples involved in calculating the reconstruction error; When the image recognition system detects abnormal behavior, the system will provide an alarm signal to the abnormal behavior subject and the staff of the remote monitoring center to facilitate the response to the abnormality.

8. A method for monitoring a parking lot based on a remote seat, characterized in that: The following steps are involved: S1, separating the background from the foreground using a background subtraction algorithm on the image data acquired by the image acquisition device; S2, using the optical flow method to calculate the motion vector in the foreground area and extract the motion features; S3 uses self-supervised learning methods to train the model and uses isomorphism error to measure the difference between input data and reconstructed data to determine whether it is an anomaly.

Citation Information

Patent Citations

  • Rapid detection identification method for specified pedestrian or vehicle in video monitoring network

    CN104166841A

  • Superpixel and three-dimensional self-organizing background subtraction algorithm-combined foreground extraction method

    CN105809716A

  • Traffic-video-based moving vehicle detection method

    CN106780548A

  • Adaptive elimination method for moving vehicle shadows in road monitoring video

    CN107220949A

  • Tracking research method based on dynamic / static target detection and real-time compressive sensing

    CN108038872A