A smart garage gate control system and method using image analysis technology

Abstract

The present invention discloses a smart garage gate control system and method using image analysis technology, which belongs to the field of image analysis technology. The present invention comprises the following steps: collecting images, obtaining grayscale images, and analyzing comprehensive grayscale values ​​corresponding to different colors; extracting the outline of the vehicle in the grayscale image, and training a deep learning model; collecting images of vehicles to be entered into the garage when they arrive at the gate position, and obtaining grayscale images; analyzing and recording vehicle information of the vehicles and controlling the gate to open, and the vehicles to enter the garage; each camera in the garage collects images of passing vehicles, and determines whether the passing vehicles in the images collected by each camera are the same vehicle; determining whether the passing vehicles are leaving the garage and predicting the time when the vehicles arrive at the gate, and controlling the gate to open in advance, and the vehicles leaving the garage; the present invention improves the accuracy of recognition by further restricting the recognition of vehicles, predicts the time when the vehicles leave the garage, and improves the efficiency of vehicle passage.

Description

Technical Field

[0001] The present invention relates to the field of image analysis technology, and in particular to a smart garage door gate control system and method using image analysis technology. Background Art

[0002] As people's living standards improve, the number of cars is increasing. The garage gate control system is an important part of the intelligent parking system. It is mainly used to control the entry and exit of vehicles in the garage and improve the efficiency and safety of vehicle management.

[0003] Garage gates use cameras to identify the license plates of vehicles entering and exiting and to raise and lower the gates. However, the cameras usually require vehicles to be a certain distance away from the gates before they can be recognized. This often results in slow or inaccurate recognition, causing traffic congestion. This not only reduces the efficiency of vehicle travel and brings inconvenience to vehicles, but also interferes with the garage's vehicle management due to inaccurate recognition, reducing the practicality of the gates.

[0004] Therefore, people are in urgent need of an intelligent garage door control system that applies image analysis technology to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide a smart garage door control system using image analysis technology to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] A method for controlling a smart garage door gate using image analysis technology, the method comprising the following steps:

[0008] S1. Collect images of different vehicle models at different angles according to vehicle models, perform grayscale processing on the images, and obtain grayscale images; analyze the comprehensive grayscale values ​​corresponding to different colors based on the color of the vehicle in each image and the grayscale values ​​of the pixels in each grayscale image;

[0009] S2. Use image analysis technology to extract the outline of the vehicle in the grayscale image and build a deep learning model. Take the image shooting angle and the outline of the vehicle as input and the corresponding vehicle model in the image as output to train the deep learning model.

[0010] S3. Capture an image of the vehicle arriving at the gate, perform grayscale processing on the image, and obtain a grayscale image; analyze the grayscale image using optical character recognition technology to obtain the vehicle's license plate number; extract the vehicle's outline from the grayscale image, and determine the vehicle's model based on the image's shooting angle using a deep learning model; obtain the vehicle's comprehensive grayscale value from the grayscale image and match the vehicle's color; record the vehicle's information and control the gate to open, allowing the vehicle to enter the warehouse. The vehicle information includes the license plate number, model, and color.

[0011] S4, each camera in the garage collects images of passing vehicles, analyzes vehicle information of the passing vehicles in the images collected by each camera, and determines whether the passing vehicles in the images collected by each camera are the same vehicle;

[0012] S5. Based on the time when each camera collects images and the distance between the corresponding camera and the gate, determine whether the passing vehicle is leaving the warehouse and predict the time when the vehicle arrives at the gate, control the gate to open in advance, and the vehicle leaves the warehouse.

[0013] According to the above technical solution, the specific process of step S1 is as follows:

[0014] S1-1. Establish a coordinate system with the center of the vehicle as the origin, the straight line along the vehicle's central axis as the x-axis, the straight line perpendicular to the x-axis and passing through the origin as the y-axis, and the straight line perpendicular to the x-axis and y-axis and passing through the origin as the z-axis. The angle between the camera and the origin in the coordinate system is used as the shooting angle.

[0015] S1-2, collect N1 images, record the ath image as T a，b，θ , T a，b，θ Indicates that the ath image is an image of the bth type of vehicle taken at a shooting angle of θ; N1 is a positive integer; a∈[1, N2], N2 are positive integers; b∈[1, N3], N3 are positive integers; θ∈[-2π, -2π];

[0016] T a，b，θ The intensity value of the red channel of the c-th pixel in is recorded as T a，b，θ The intensity value of the green channel of the c-th pixel in is recorded as T a，b，θ The intensity value of the blue channel of the c-th pixel in is recorded as N4 is a positive integer;

[0017] T a，b，θ Perform grayscale processing to obtain the grayscale image of the a-th image, recorded as Tgary a，b，θ , Tgary a，b，θ The grayscale image of the a-th image is the grayscale image of the image of the b-th vehicle model taken at a shooting angle of θ;

[0018] Calculate the grayscale value of a pixel in a grayscale image according to the following formula:

[0019]

[0020] in, Indicates Tgary a，b，θ The grayscale value of the cth pixel in ; α1, α2 and α3 are fixed parameters preset by the system;

[0021] S1-3, the color of the vehicle in the ath image is the dth color, d∈[1,N5], N5 is a positive integer;

[0022] To Tgary a，b，θ The gray value of each pixel in the filter is filtered to select Tgary a，b，θ The most frequent occurrences As the grayscale value corresponding to the dth color;

[0023] Get the grayscale value corresponding to the dth color in the N1 images collected, and take the average of the grayscale values ​​corresponding to the dth color in each image as the comprehensive grayscale value corresponding to the dth color, recorded as Igary d ;

[0024] Since the main color of the vehicle occupies the largest area of ​​the vehicle body, the grayscale value that appears the most times is selected as the grayscale value corresponding to the color. In addition, there is a small deviation in the grayscale value of the same color in different pictures, so it is more accurate to use the comprehensive grayscale value for judgment.

[0025] According to the above technical solution, the specific process of step S2 is as follows:

[0026] S2-1. Using image recognition technology to extract Tgary a，b，θ The contour of the vehicle in the grayscale image of the ath image is obtained, which is recorded as the set

[0027] S2-2, build a deep learning model, and transform θ and As input, the bth car model is used as output to train the deep learning model;

[0028] By analyzing different shooting angles of vehicles of the same model and integrating the contour features of the vehicle at different angles, different cameras can capture images of the vehicle at different angles, and the vehicle model can be accurately identified through a deep learning network.

[0029] According to the above technical solution, the specific process of step S3 is as follows:

[0030] S3-1, the time when the waiting vehicle arrives at the gate is recorded as time t1; the waiting vehicle arriving at the gate at time t1 is recorded as car t1 ; The image taken at time t1 is recorded as The shooting angle is recorded as right Perform grayscale processing to obtain a grayscale image, which is recorded as

[0031] S3-2, using optical character recognition technology Perform analysis and obtain car t1 The license plate number is recorded as

[0032] S3-3. Extraction car t1 The outline of Combine Get car through deep learning model t1 The model of

[0033] S3-4, pass The intensity values ​​of the red, green, and blue channels of each pixel in The gray value of each pixel in The gray value of each pixel in the filter is filtered to select The gray value that appears most times in the t1 The comprehensive gray value of

[0034] like satisfy car t1 The color is the dth color; α4 is a fixed parameter preset by the system;

[0035] like Dissatisfied car t1 The color of is not the dth color;

[0036] S3-5, record car t1 of and color and control the gate opening.

[0037] According to the above technical solution, the specific process of step S4 is as follows:

[0038] S4-1. Each camera in the garage collects images of passing vehicles and arranges the cameras in descending order according to the time of collection.

[0039] The time when the e-th camera captures the image of the passing vehicle is recorded as t2 e , e∈[1, N6], N6 is a positive integer;

[0040] According to t2 e Arrange the cameras from the earliest to the last moment;

[0041] Filter out cameras that meet the following conditions:

[0042]

[0043] Among them, α5 and α6 are fixed parameters preset by the system;

[0044] The time when the fth camera captures the image of the passing vehicle is recorded as t3 f , f∈[1, N7], N7 is a positive integer and N7≤N6; t3 f The vehicle passing the fth camera at time is recorded as T3 f The image captured by the fth camera at time is recorded as The shooting angle is recorded as

[0045] S4-2. Acquisition middle of and color, among which, express license plate number; express Model of car;

[0046] Will of and color, and car t1 of and color matching;

[0047] like of and color are the same as car t1 of If the color is the same as the image captured by the camera with car t1 It’s the same car;

[0048] Filter out the collected cars t1 The cameras of the images are rearranged in the order of acquisition time from earliest to latest;

[0049] The g-th camera captures the image to car t1 The moment of the image is recorded as t4 g , g∈[1,N8], N8 is a positive integer and N8≤N7;

[0050] Increase the judgment of vehicle model and color, effectively prevent photo deception. At the same time, the vehicle model and color are significant visual features. Combined with license plate information, it can greatly improve the accuracy of recognition and reduce misjudgment and missed judgment.

[0051] According to the above technical solution, the specific process of step S5 is as follows:

[0052] S5-1. The distance between the g-th camera and the gate is recorded as L g ;

[0053] If L g >L g+1 , then the passing vehicle leaves the warehouse;

[0054] If L g ≤L g+1 , then the passing vehicles will not leave the warehouse;

[0055] Among them, the N8+1th camera represents the camera at the gate and L N8+1 =0;

[0056] S5-2. Predict the time when the vehicle arrives at the gate according to the following formula:

[0057]

[0058] in, Indicates car t1 Predicted time of arrival at the gate;

[0059] S5-3, control the gate in advance When it is turned on, the vehicle leaves the warehouse.

[0060] An intelligent garage gate control system using image analysis technology is characterized in that the system includes an information acquisition module, an information processing module and an execution module;

[0061] The information acquisition module is used to acquire information required by the system; the information processing module is used to store, analyze and transmit information of each module; and the execution module is used to execute the information of the information processing module.

[0062] According to the above technical solution, the information collection module includes a vehicle information unit and a garage information unit;

[0063] The vehicle information unit is used to collect data information of the vehicle, and the garage information unit is used to collect data information of the camera in the garage.

[0064] According to the above technical solution, the information processing module includes an information storage unit, an information analysis unit and an information transmission unit;

[0065] The information storage unit is used to store the information acquired by the information acquisition module; the information analysis unit is used to analyze the information acquired by the information acquisition module; and the information transmission unit is used for information transmission among various modules in the system.

[0066] According to the above technical solution, the information display module includes a display unit and a gate control unit;

[0067] The display unit is used to display information about vehicles entering and exiting the garage, and the gate control unit is used to control the raising and lowering of the garage gate.

[0068] Compared with the prior art, the present invention has the following beneficial effects:

[0069] The present invention analyzes the image of the vehicle and, when identifying the vehicle, not only identifies the license plate number of the vehicle, but also identifies the model and color of the vehicle, further restricts the identification of the vehicle, improves the accuracy and safety of identification, and by identifying the movement path of the vehicle, predicts the vehicle's departure time, and controls the opening of the gate in advance, thereby improving the efficiency of vehicle passage and enhancing the management of the garage and the practicality of the gate. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0071] Figure 1 This is a flow chart of a smart garage gate control method using image analysis technology according to the present invention;

[0072] Figure 2 This is a structural diagram of a smart garage gate control system that uses image analysis technology in the present invention. DETAILED DESCRIPTION

[0073] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0074] See also Figure 1 , the present invention provides a technical solution:

[0075] S1. Collect images of different vehicle models at different angles according to vehicle models, perform grayscale processing on the images, and obtain grayscale images; analyze the comprehensive grayscale values ​​corresponding to different colors based on the color of the vehicle in each image and the grayscale values ​​of the pixels in each grayscale image;

[0076] The specific process of step S1 is as follows:

[0077] S1-1. Establish a coordinate system with the center of the vehicle as the origin, the straight line along the vehicle's central axis as the x-axis, the straight line perpendicular to the x-axis and passing through the origin as the y-axis, and the straight line perpendicular to the x-axis and y-axis and passing through the origin as the z-axis. The angle between the camera and the origin in the coordinate system is used as the shooting angle.

[0078] Define the shooting angle to provide a unified analysis standard for subsequent data collection and analysis, thereby improving the accuracy of data analysis;

[0079] S1-2, collect N1 images, record the ath image as T a，b，θ , T a，b，θ Indicates that the ath image is an image of the bth type of vehicle taken at a shooting angle of θ; N1 is a positive integer; a∈[1, N2], N2 are positive integers; b∈[1, N3], N3 are positive integers; θ∈[-2π, -2π];

[0080] T a，b，θ The intensity value of the red channel of the c-th pixel in is recorded as T a，b，θ The intensity value of the green channel of the c-th pixel in is recorded as T a，b，θ The intensity value of the blue channel of the c-th pixel in is recorded as N4 is a positive integer;

[0081] T a，b，θ Perform grayscale processing to obtain the grayscale image of the a-th image, recorded as Tgary a，b，θ , Tgary a，b，θ The grayscale image of the a-th image is the grayscale image of the image of the b-th vehicle model taken at a shooting angle of θ;

[0082] Calculate the grayscale value of a pixel in a grayscale image according to the following formula:

[0083]

[0084] in, Indicates Tgary a，b，θ The grayscale value of the cth pixel in ; α1, α2 and α3 are fixed parameters preset by the system;

[0085] For example:

[0086] T a，b，θ The intensity value of the red channel of the c-th pixel in is recorded as T a，b，θ The intensity value of the green channel of the c-th pixel in is recorded as T a，b，θ The intensity value of the blue channel of the c-th pixel in is recorded as α1=0.299; α2=0.587; α3=0.114;

[0087] Calculate the grayscale value of a pixel in a grayscale image according to the following formula:

[0088]

[0089] get

[0090] S1-3, the color of the vehicle in the ath image is the dth color, d∈[1,N5], N5 is a positive integer;

[0091] To Tgary a，b，θ The gray value of each pixel in the filter is filtered to select Tgary a，b，θ The most frequent occurrences As the grayscale value corresponding to the dth color;

[0092] Get the grayscale value corresponding to the dth color in the N1 images collected, and take the average of the grayscale values ​​corresponding to the dth color in each image as the comprehensive grayscale value corresponding to the dth color, recorded as Igary d ;

[0093] Since the main color of the vehicle occupies the largest area of ​​the vehicle body, the grayscale value that appears the most times is selected as the grayscale value corresponding to the color. In addition, there is a small deviation in the grayscale value of the same color in different pictures, so it is more accurate to use the comprehensive grayscale value for judgment.

[0094] S2. Use image analysis technology to extract the outline of the vehicle in the grayscale image and build a deep learning model. Take the image shooting angle and the outline of the vehicle as input and the corresponding vehicle model in the image as output to train the deep learning model.

[0095] The specific process of step S2 is as follows:

[0096] S2-1. Using image recognition technology to extract Tgary a，b，θ The contour of the vehicle in the grayscale image of the ath image is obtained, which is recorded as the set

[0097] S2-2, build a deep learning model, and transform θ and As input, the bth car model is used as output to train the deep learning model;

[0098] By analyzing different shooting angles of vehicles of the same model and integrating the contour features of the vehicle at different angles, different cameras can capture images of the vehicle at different angles, and the vehicle model can be accurately identified through a deep learning network.

[0099] S3. Capture an image of the vehicle arriving at the gate, perform grayscale processing on the image, and obtain a grayscale image; analyze the grayscale image using optical character recognition technology to obtain the vehicle's license plate number; extract the vehicle's outline from the grayscale image, and determine the vehicle's model based on the image's shooting angle using a deep learning model; obtain the vehicle's comprehensive grayscale value from the grayscale image and match the vehicle's color; record the vehicle's information and control the gate to open, allowing the vehicle to enter the warehouse. The vehicle information includes the license plate number, model, and color.

[0100] The specific process of step S3 is as follows:

[0101] S3-1, the time when the waiting vehicle arrives at the gate is recorded as time t1; the waiting vehicle arriving at the gate at time t1 is recorded as car t1 ; The image taken at time t1 is recorded as The shooting angle is recorded as right Perform grayscale processing to obtain a grayscale image, which is recorded as

[0102] S3-2, using optical character recognition technology Perform analysis and obtain car t1 The license plate number is recorded as

[0103] S3-3. Extraction car t1 The outline of Combine Get car through deep learning model t1 The model of

[0104] S3-4, pass The intensity values ​​of the red, green, and blue channels of each pixel in The gray value of each pixel in The gray value of each pixel in the filter is filtered to select The gray value that appears most times in the t1The comprehensive gray value of

[0105] The images captured by the camera at the gate are used to analyze and record the vehicle information of incoming vehicles, providing data support for subsequent vehicle exits and prediction of vehicle arrival time at the gate.

[0106] like satisfy car t1 The color is the dth color; α4 is a fixed parameter preset by the system;

[0107] like Dissatisfied car t1 The color of is not the dth color;

[0108] S3-5, record car t1 of and color and control the gate opening.

[0109] S4, each camera in the garage collects images of passing vehicles, analyzes vehicle information of the passing vehicles in the images collected by each camera, and determines whether the passing vehicles in the images collected by each camera are the same vehicle;

[0110] The specific process of step S4 is as follows:

[0111] S4-1. Each camera in the garage collects images of passing vehicles and arranges the cameras in descending order according to the time of collection.

[0112] The time when the e-th camera captures the image of the passing vehicle is recorded as t2 e , e∈[1, N6], N6 is a positive integer;

[0113] According to t2 e Arrange the cameras from the earliest to the last moment;

[0114] Filter out cameras that meet the following conditions:

[0115]

[0116] Among them, α5 and α6 are fixed parameters preset by the system;

[0117] The time when the fth camera captures the image of the passing vehicle is recorded as t3 f , f∈[1, N7], N7 is a positive integer and N7≤N6; t3 f The vehicle passing the fth camera at time is recorded as T3 f The image captured by the fth camera at time is recorded as The shooting angle is recorded as

[0118] S4-2. Acquisition middle of and color, among which, express license plate number; express Model of car;

[0119] Will of and color, and car t1 of and color matching;

[0120] like of and color are the same as car t1 of If the color is the same as the image captured by the camera with car t1 It’s the same car;

[0121] Filter out the collected cars t1 The cameras of the images are rearranged in the order of acquisition time from earliest to latest;

[0122] The g-th camera captures the image to car t1 The moment of the image is recorded as t4 g , g∈[1,N8], N8 is a positive integer and N8≤N7;

[0123] Increase the judgment of vehicle model and color, effectively prevent photo deception. At the same time, the vehicle model and color are significant visual features. Combined with license plate information, it can greatly improve the accuracy of recognition and reduce misjudgment and missed judgment.

[0124] S5. Based on the time when each camera collects images and the distance between the corresponding camera and the gate, determine whether the passing vehicle is leaving the warehouse and predict the time when the vehicle arrives at the gate, control the gate to open in advance, and the vehicle leaves the warehouse;

[0125] The specific process of step S5 is as follows:

[0126] S5-1. The distance between the g-th camera and the gate is recorded as L g ;

[0127] If L g >L g+1 , then the passing vehicle leaves the warehouse;

[0128] If L g ≤Lg+1 , then the passing vehicles will not leave the warehouse;

[0129] Among them, the N8+1th camera represents the camera at the gate and L N8+1 =0;

[0130] S5-2. Predict the time when the vehicle arrives at the gate according to the following formula:

[0131]

[0132] in, Indicates car t1 Predicted time of arrival at the gate;

[0133] S5-3, control the gate in advance When it is turned on, the vehicle leaves the warehouse;

[0134] For example:

[0135] t N8 =10:20:30;t41=10:20:00;L 1＝8 =200;L N8 =100;

[0136] The time it takes for a vehicle to arrive at the gate is predicted using the following formula:

[0137]

[0138] get

[0139] Control the gate in advance When it is turned on, the vehicle leaves the warehouse.

[0140] See also Figure 2 ,A smart garage gate control system using image analysis technology, characterized by : the system includes an information acquisition module, an information processing module, and an execution module;

[0141] The information acquisition module is used to acquire information required by the system; the information processing module is used to store, analyze and transmit information of each module; and the execution module is used to execute the information of the information processing module.

[0142] According to the above technical solution, the information collection module includes a vehicle information unit and a garage information unit;

[0143] The vehicle information unit is used to collect data information of the vehicle, and the garage information unit is used to collect data information of the camera in the garage.

[0144] According to the above technical solution, the information processing module includes an information storage unit, an information analysis unit and an information transmission unit;

[0145] The information storage unit is used to store the information acquired by the information acquisition module; the information analysis unit is used to analyze the information acquired by the information acquisition module; and the information transmission unit is used for information transmission among various modules in the system.

[0146] According to the above technical solution, the information display module includes a display unit and a gate control unit;

[0147] The display unit is used to display information about vehicles entering and exiting the garage, and the gate control unit is used to control the raising and lowering of the garage gate.

[0148] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0149] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A smart garage door control method using image analysis technology, characterized by: The method comprises the following steps: S1. Collect images of different vehicle models at different angles according to vehicle models, perform grayscale processing on the images, and obtain grayscale images; analyze the comprehensive grayscale values ​​corresponding to different colors based on the color of the vehicle in each image and the grayscale values ​​of the pixels in each grayscale image; S2. Use image analysis technology to extract the outline of the vehicle in the grayscale image and build a deep learning model. Take the image shooting angle and the outline of the vehicle as input and the corresponding vehicle model in the image as output to train the deep learning model. S3. Capture an image of the vehicle arriving at the gate, perform grayscale processing on the image, and obtain a grayscale image; analyze the grayscale image using optical character recognition technology to obtain the vehicle's license plate number; extract the vehicle's outline from the grayscale image, and determine the vehicle's model based on the image's shooting angle using a deep learning model; obtain the vehicle's comprehensive grayscale value from the grayscale image and match the vehicle's color; record the vehicle's information and control the gate to open, allowing the vehicle to enter the warehouse. The vehicle information includes the license plate number, model, and color. S4, each camera in the garage collects images of passing vehicles, analyzes vehicle information of the passing vehicles in the images collected by each camera, and determines whether the passing vehicles in the images collected by each camera are the same vehicle; S5. Based on the time when each camera collects images and the distance between the corresponding camera and the gate, determine whether the passing vehicle is leaving the warehouse and predict the time when the vehicle arrives at the gate, control the gate to open in advance, and the vehicle leaves the warehouse; The specific process of step S1 is as follows: S1-1. Establish a coordinate system with the center of the vehicle as the origin, the straight line along the vehicle's central axis as the x-axis, the straight line perpendicular to the x-axis and passing through the origin as the y-axis, and the straight line perpendicular to the x-axis and y-axis and passing through the origin as the z-axis. The angle between the camera and the origin in the coordinate system is used as the shooting angle. S1-2, collect N1 images, record the ath image as T a，b，θ , T a，b，θ Indicates that the ath image is an image of the bth type of vehicle taken at a shooting angle of θ; N1 is a positive integer; a∈[1, N2], N2 are positive integers; b∈[1, N3], N3 are positive integers; θ∈[-2π, -2π]; T a，b，θ The intensity value of the red channel of the c-th pixel in is recorded as T a，b，θ The intensity value of the green channel of the c-th pixel in is recorded as T a，b，θ The intensity value of the blue channel of the c-th pixel in is recorded as N4 is a positive integer; T a，b，θ Perform grayscale processing to obtain the grayscale image of the a-th image, recorded as Tgary a，b，θ , Tgary a，b，θ The grayscale image of the a-th image is the grayscale image of the image of the b-th vehicle model taken at a shooting angle of θ; Calculate the grayscale value of a pixel in a grayscale image according to the following formula: in, Indicates Tgary a，b，θ The grayscale value of the cth pixel in ; α1, α2 and α3 are fixed parameters preset by the system; S1-3, the color of the vehicle in the ath image is the dth color, d∈[1,N5], N5 is a positive integer; To Tgary a，b，θ The gray value of each pixel in the filter is filtered to select Tgary a，b，θ The most frequent occurrences As the grayscale value corresponding to the dth color; Get the grayscale value corresponding to the dth color in the N1 images collected, and take the average of the grayscale values ​​corresponding to the dth color in each image as the comprehensive grayscale value corresponding to the dth color, recorded as Igary d .

2. The intelligent garage door gate control method using image analysis technology according to claim 1, characterized in that: The specific process of step S2 is as follows: S2-1. Using image recognition technology to extract Tgary a，b，θ The contour of the vehicle in the grayscale image of the ath image is obtained, which is recorded as the set S2-2, build a deep learning model, and transform θ and As input, the bth car model is used as output to train the deep learning model.

3. The intelligent garage door gate control method using image analysis technology according to claim 2 is characterized by: The specific process of step S3 is as follows: S3-1, the time when the waiting vehicle arrives at the gate is recorded as time t1; the waiting vehicle arriving at the gate at time t1 is recorded as car t1 ; The image taken at time t1 is recorded as The shooting angle is recorded as right Perform grayscale processing to obtain a grayscale image, which is recorded as S3-2, using optical character recognition technology Perform analysis and obtain car t1 The license plate number is recorded as S3-3. Extraction car t1 The outline of Combine Get car through deep learning model t1 The model of S3-4, pass The intensity values ​​of the red, green, and blue channels of each pixel in The gray value of each pixel in The gray value of each pixel in the filter is filtered to select The gray value that appears most times in the t1 The comprehensive gray value of like satisfy car t1 The color is the dth color; α4 is a fixed parameter preset by the system; like Dissatisfied car t1 The color of is not the dth color; S3-5, record car t1 of and color and control the gate opening.

4. The intelligent garage door gate control method using image analysis technology according to claim 3 is characterized by: The specific process of step S4 is as follows: S4-1. Each camera in the garage collects images of passing vehicles and arranges the cameras in descending order according to the time of collection. The time when the e-th camera captures the image of the passing vehicle is recorded as t2 e , e∈[1, N6], N6 is a positive integer; According to t2 e Arrange the cameras from the earliest to the last moment; Filter out cameras that meet the following conditions: Among them, α5 and α6 are fixed parameters preset by the system; The time when the fth camera captures the image of the passing vehicle is recorded as t3 f , f∈[1, N7], N7 is a positive integer and N7≤N6; set t3 f The vehicle passing the fth camera at time is recorded as T3 f The image captured by the fth camera at time is recorded as The shooting angle is recorded as S4-2. Acquisition middle of and color, among which, express license plate number; express Model of car; Will of and color, and car t1 of and color matching; like of and color are the same as car t1 of If the color is the same as the image captured by the camera with car t1 It’s the same car; Filter out the collected cars t1 The cameras of the images are rearranged in the order of acquisition time from earliest to latest; The g-th camera captures the image to car t1 The moment of the image is recorded as t4 g , g∈[1,N8], N8 is a positive integer and N8≤N7.

5. The intelligent garage door gate control method using image analysis technology according to claim 4 is characterized by: The specific process of step S5 is as follows: S5-1. The distance between the g-th camera and the gate is recorded as L g ; If L g >L g+1 , then the passing vehicle leaves the warehouse; If L g ≤L g+1 , then the passing vehicles will not leave the warehouse; Among them, the N8+1th camera represents the camera at the gate and L N8+1 =0; S5-2. Predict the time when the vehicle arrives at the gate according to the following formula: in, Indicates car t1 Predicted time of arrival at the gate; S5-3, control the gate in advance When it is turned on, the vehicle leaves the warehouse.

6. A smart garage gate control system using image analysis technology, such as the smart garage gate control method using image analysis technology according to any one of claims 1 to 5, characterized in that: The system includes an information collection module, an information processing module and an execution module; The information acquisition module is used to acquire information required by the system; the information processing module is used to store, analyze and transmit information of each module; and the execution module is used to execute the information of the information processing module.

7. The intelligent garage door control system using image analysis technology according to claim 6, characterized in that: The information collection module includes a vehicle information unit and a garage information unit; The vehicle information unit is used to collect data information of the vehicle, and the garage information unit is used to collect data information of the camera in the garage.

8. The intelligent garage door control system using image analysis technology according to claim 6, characterized in that: The information processing module includes an information storage unit, an information analysis unit and an information transmission unit; The information storage unit is used to store the information acquired by the information acquisition module; the information analysis unit is used to analyze the information acquired by the information acquisition module; and the information transmission unit is used for information transmission among various modules in the system.

9. The intelligent garage door control system using image analysis technology according to claim 6, characterized in that: The information display module includes a display unit and a gate control unit; The display unit is used to display information about vehicles entering and exiting the garage, and the gate control unit is used to control the opening of the garage gate.

Images