A monitoring system and an elevator for preventing electric vehicles from being carried by the elevator

Abstract

The present invention relates to the technical field of elevator safety monitoring, and specifically provides a monitoring device and an elevator for preventing electric vehicles from being carried in the elevator. The system includes a target detection module, a contour matching module, a trajectory capture module, an early warning trigger module, and an elevator control module. In the present invention, by fusing image edge gradients, morphological features, and pixel contact features, the target contour is accurately extracted to reduce environmental interference. Using structural matching analysis, the edges of natural human features are eliminated to improve the accuracy of electric vehicle recognition. The trajectory capture combines the displacement of human key points and the trajectory change rate, sets a path continuity threshold, stabilizes the target form, and avoids the influence of occlusion or angle changes on recognition. Based on the data of the contour ratio and the staying duration, the alarm is triggered only when the illegal behavior is clear, reducing false alarm interference. The elevator control system links the alarm signal, dynamically sets the locking time to execute the stop operation instruction, and uploads the intrusion record to form traceable management, improving the safety supervision ability.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator safety monitoring, and particularly to a monitoring system and an elevator for preventing the carriage of electric vehicles in an elevator. Background Art

[0002] The technical field of elevator safety monitoring includes an integrated management system for elevator operating status, fault detection, abnormal behavior monitoring, and safety protection. The core content of this technical field involves aspects such as real-time monitoring of elevators, data collection and analysis, identification of illegal behaviors, automatic alarm, and safety warning. The system usually consists of sensing devices, video monitoring, data transmission, intelligent analysis devices, etc., aiming to improve the safety of elevators and prevent illegal use, elevator accidents, and abnormal situations. The elevator safety monitoring technology is further extended to the prevention and management of the carriage behavior of electric vehicles to ensure the safety of elevator passengers and the building environment.

[0003] Among them, the monitoring system for preventing the carriage of electric vehicles in an elevator refers to a safety monitoring system specifically used to identify, detect, and intervene in the entry of electric vehicles into the elevator. This device usually includes detection methods such as image recognition, weight detection, and infrared induction to determine whether there is an electric vehicle in the elevator. When an electric vehicle is detected entering the elevator, the system gives a reminder or stops it through methods such as voice alarms, warning lights, and remote control signals. Some devices also combine with the elevator access control system to prevent electric vehicles from entering the elevator or prevent the elevator from starting. In addition, this device can use the image recognition technology of the internal camera of the elevator and analyze the characteristics of electric vehicles using a deep learning model to achieve automatic recognition. By comprehensively using a variety of monitoring means, this device can effectively improve the safety of elevator carriage and avoid potential safety hazards caused by the illegal entry of electric vehicles into the elevator.

[0004] In the existing elevator management process, during the detection of electric vehicles, limited by a single detection method, it is easily interfered by environmental factors, resulting in insufficient recognition accuracy. For example, weight detection is affected by multiple passengers in the elevator and it is difficult to accurately distinguish an electric vehicle from other large pieces of luggage; infrared induction is easily affected by external temperature changes, resulting in false alarms or missed alarms. In traditional solutions, the image recognition method mostly uses simple feature matching methods, which have weak adaptability to the structure of electric vehicles. In the case of complex light, partial occlusion, or diverse forms of electric vehicles, it is easy to have recognition failures or misjudgments. Some solutions combine with the elevator access control system for management and control, but only based on static detection, triggering an alarm only after the electric vehicle enters the elevator, lacking the ability to predict illegal behaviors, resulting in a lag in response and being unable to effectively prevent the entry of electric vehicles. In addition, the alarm trigger logic of the existing system is relatively single, without fully considering factors such as the intrusion time, contour ratio, and staying duration of electric vehicles for multi-dimensional comprehensive judgment, which easily leads to frequent alarms or missed illegal behaviors, making the safety prevention effect difficult to reach an ideal level. Summary of the Invention

[0005] The object of the present invention is to solve the disadvantages existing in the prior art, and a monitoring system and an elevator for preventing an electric vehicle from being carried by an elevator are proposed.

[0006] To achieve the above object, the present invention adopts the following technical solutions: A monitoring system for preventing an electric vehicle from being carried by an elevator includes:

[0007] The target detection module obtains the image edge gradient, morphological features and pixel contact features, calculates the gradient change of adjacent pixels and establishes a global gradient mapping, analyzes the strongly continuous edge region as a candidate contour, calculates the curvature and screens the electric vehicle contour region to obtain a target contour candidate area;

[0008] The contour matching module screens the rigid structure area according to the target contour candidate area, and eliminates the edge area that conforms to the natural undulation characteristics of the human body based on the comparison of the electric vehicle component and human clothing characteristics to obtain a structure matching contour area;

[0009] The trajectory capture module, based on the structure matching contour area, combines the displacement of human key points and the trajectory change rate, sets a path continuity threshold, and screens the region with stable morphological changes to obtain an independent electric vehicle contour area;

[0010] The early warning trigger module judges whether the electric vehicle enters the elevator door according to the independent electric vehicle contour area, the contour ratio and the residence duration data, sets the alarm condition according to the intrusion time, calculates the priority and triggers an audible and visual alarm to generate an intrusion alarm signal;

[0011] The elevator control module, based on the intrusion alarm signal, executes elevator control, sets the elevator locking time, executes the stop operation instruction and uploads the intrusion record to obtain an elevator blocking instruction.

[0012] As a further solution of the present invention, the target contour candidate area includes a strongly continuous edge region, a global gradient mapping, and the calculation result of the candidate contour curvature; the structure matching contour area includes a rigid structure area, an electric vehicle component feature area, and the eliminated human edge area; the independent electric vehicle contour area includes a region with stable morphological changes, a region screened by the trajectory change rate, and a path continuity threshold region; the intrusion alarm signal includes the contour ratio data, the residence duration data, the intrusion time threshold, and the alarm priority; the elevator blocking instruction includes the elevator locking time, the stop operation instruction, and the uploaded intrusion record data.

[0013] As a further solution of the present invention, the target detection module includes:

[0014] The edge gradient calculation sub-module obtains the gray values of image pixels, calculates the gray change rate of adjacent pixels, determines the gradient direction and amplitude, filters the gradient amplitude pixels that meet the threshold, extracts the gradient mutation points, calculates the curvature, contrast change rate, and edge direction consistency, and generates gradient mutation feature parameters;

[0015] The global gradient mapping sub-module calculates the pixel gradient direction distribution based on the gradient mutation feature parameters, constructs a gradient direction histogram, calculates the change in the average gradient of adjacent regions, generates a global gradient change matrix, sets a dynamic threshold for the pixels of the global gradient change matrix, filters the regions with prominent gradient changes, and generates a global gradient mapping matrix;

[0016] The target contour screening sub-module extracts the contour of the gradient change region based on the global gradient mapping matrix, calculates the boundary curvature and contrast change rate, filters the contours with stable curvature and prominent contrast change, calculates the edge continuity and pixel contact characteristics, and filters the contour regions that meet the morphological characteristics to obtain the target contour candidate region.

[0017] As a further solution of the present invention, the contour matching module includes:

[0018] The target contour extraction sub-module obtains the target contour candidate region, calculates the edge gradient change amount of the pixel region, filters the boundary pixels whose change amount meets the gradient threshold, connects the continuous boundary pixels to form a preliminary contour, calculates the curvature change rate of the preliminary contour, and filters the contour segments whose curvature change rate is greater than the curvature threshold to obtain the high-curvature target contour region;

[0019] The symmetry screening sub-module calculates the symmetry offset of the internal pixel distribution of the contour region based on the high-curvature target contour region, filters the regions with an offset less than the set threshold, removes the non-rigid structure regions with an offset exceeding the set threshold, calculates the average offset of the morphological symmetry axis, and filters the regions with an average offset less than the average threshold to obtain the rigid structure contour region;

[0020] The structure matching optimization sub-module detects the edge curvature change trend based on the rigid structure contour region, calculates the local curvature change amount, filters the edge regions with a change amount greater than the standard threshold, calculates the matching degree coefficient, and filters the regions with a matching degree coefficient greater than the reference threshold to obtain the structure matching contour region.

[0021] As a further solution of the present invention, the formula for calculating the region with an offset less than the set threshold is specifically:

[0022]

[0023] Calculate the average offset of the morphological symmetry axis and filter the regions with an average offset less than the average threshold;

[0024] Among them, S represents the offset mean of the morphological symmetry axis, N represents the number of pixel points within the contour area, P i,x and P i,y respectively represent the positions of the i-th pixel point on the x-axis and y-axis, and respectively represent the positions of the i-th pixel point on the x-axis and y-axis within the reference area.

[0025] As a further aspect of the present invention, the trajectory capture module includes:

[0026] The trajectory rate analysis sub-module obtains the displacement information of the human key points, calculates the displacement distance within adjacent time frames, screens the high change rate areas based on the motion path continuity threshold, calls the time series distribution of the trajectory change rate calculation, and performs sequence analysis in combination with the time frames to obtain the trajectory change rate distribution data;

[0027] The target area screening sub-module, based on the trajectory change rate distribution data, detects the areas with sharp rate changes within a short time, calculates their proportion in the global trajectory, analyzes the time series continuity, and screens the stable motion trend areas to obtain the stable motion area distribution data;

[0028] The independent contour extraction sub-module, based on the stable motion area distribution data and combined with the rigid structure data of the electric vehicle, performs morphological analysis, extracts the consistent structure feature areas, calculates the boundary change of the areas, screens the areas with stable morphological changes, and establishes the independent contour area of the electric vehicle.

[0029] As a further aspect of the present invention, the warning trigger module includes:

[0030] The contour detection sub-module obtains the data of the electric vehicle contour area, detects the pixel distribution in the areas inside and outside the elevator door, extracts the contour feature of the target area, calculates the proportion of the contour area, calls the elevator door status information, compares with the contour proportion threshold, and determines whether the electric vehicle is close to or partially enters the elevator door area, generating a contour proportion parameter;

[0031] The trajectory analysis sub-module, based on the contour proportion parameter, extracts the electric vehicle trajectory data, calculates the staying time near the elevator door, analyzes the trajectory offset in combination with the motion trajectory, compares with the staying duration threshold, and determines whether there is a continuous intrusion trend to obtain a trajectory staying duration parameter;

[0032] The alarm trigger sub-module, based on the trajectory staying duration parameter and combined with the elevator door status data, analyzes whether the intrusion time exceeds the reference threshold, determines whether the alarm trigger condition is met, and if the alarm trigger condition is met, activates the audible and visual alarm to generate an intrusion alarm signal.

[0033] As a further aspect of the present invention, the specific calculation formula for extracting the contour feature of the target area is:

[0034]

[0035] Calculate the contour occupancy ratio, C ratio Represent the contour occupancy ratio, P i Represent the contour pixel value of the i-th pixel point, |P i | represents P i The absolute value of, A i Represent the area of the region corresponding to the i-th pixel point, N represents the total number of pixel points within the contour region, A total Represent the total area of the elevator door area.

[0036] As a further aspect of the present invention, the elevator control module includes:

[0037] The alarm signal processing sub-module acquires the intrusion alarm signal, detects the signal source and level, sets the locking parameters, invokes the elevator control data, matches the elevator floor and running state, calculates the deviation value between the elevator running parameters and the locking parameters, screens the executable locking duration, and obtains the elevator locking duration data;

[0038] The elevator operation control sub-module, based on the elevator locking duration data, compares the current running state of the elevator, determines whether it is in an adjustable range, calculates the stop trigger condition, compares the current position, target floor and scheduling information of the elevator, screens the stop method, and generates an elevator scheduling stop instruction;

[0039] The access prohibition instruction execution sub-module, based on the elevator scheduling stop instruction, detects the elevator response state, confirms the stop, collects the intrusion alarm signal and stop time data, integrates the log to record the stop parameters, uploads them to the intrusion record database, and generates an elevator lockdown instruction.

[0040] Based on the same inventive concept, an elevator for preventing electric vehicles from being carried by the elevator is also proposed, and the elevator is equipped with the above monitoring system.

[0041] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0042] In the present invention, by fusing image edge gradient, morphological features and pixel contact features, the target contour is accurately extracted to reduce environmental interference. Using structure matching analysis, the edges of human natural features are removed to improve the accuracy of electric vehicle recognition. The trajectory capture combines the displacement and trajectory change rate of human key points, sets the path continuity threshold, stabilizes the target form, and avoids the influence of occlusion or angle change on recognition. Based on the contour occupancy ratio and residence duration data, the alarm is triggered only when the illegal behavior is clear, reducing false alarm interference. The elevator control system is linked with the alarm signal, dynamically sets the locking time to execute the stop operation instruction, and uploads the intrusion record to form traceable management, improving the safety supervision ability. Description of the Drawings

[0043] Figure 1 This is the system flowchart of the present invention.

[0044] Figure 2 This is the flowchart of the sub-module of the present invention.

[0045] Figure 3 This is the flowchart of the target detection module of the present invention.

[0046] Figure 4 This is the flowchart of the contour matching module of the present invention.

[0047] Figure 5 This is the flowchart of the trajectory capture module of the present invention.

[0048] Figure 6 This is the flowchart of the early warning trigger module of the present invention.

[0049] Figure 7 This is the flowchart of the elevator control module of the present invention. Detailed implementation manners

[0050] In order to make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, in the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0052] Please refer to Figure 1 , a monitoring system for preventing electric vehicles from being carried by elevators includes:

[0053] The target detection module obtains the image edge gradient, morphological features and pixel contact features, calculates the gradient change of adjacent pixel points, establishes a global gradient mapping, sets a dynamic change threshold, performs vector analysis on the edge region, screens the candidate regions of the electric vehicle contour, and combines the curvature and contrast change rate to obtain the candidate region of the target contour. The contour matching module analyzes the morphological symmetry of the pixel region according to the candidate region of the target contour, screens the rigid structure region, and eliminates the edge regions that conform to the natural undulation characteristics of human clothing to obtain the structure matching contour region.

[0054] The trajectory capture module combines the displacement information of human body key points, analyzes the trajectory change rate, sets the continuity threshold of the motion path, screens the target areas with drastic changes in a short time, eliminates the target areas that do not conform to the human motion law, combines the rigid structure data of the electric vehicle, selects the stable shape change area, and obtains the independent contour area of the electric vehicle. The warning trigger module, based on the independent contour area of the electric vehicle, combines the alarm rules, calculates the contour ratio, the trajectory stay duration, and the elevator door status data, determines whether the electric vehicle enters the elevator door, sets the alarm activation condition according to the intrusion time, triggers the audible and visual alarm, and obtains the intrusion alarm signal.

[0055] According to the intrusion alarm signal, the elevator control module calls the elevator control system data, sets the elevator locking time, executes the stop operation instruction, and uploads the intrusion record to obtain the elevator blocking instruction.

[0056] The target contour candidate area includes the strong continuity edge area, the global gradient mapping, and the calculation result of the candidate contour curvature; the structure matching contour area includes the rigid structure area, the electric vehicle component feature area, and the eliminated human body edge area; the independent contour area of the electric vehicle includes the stable shape change area, the trajectory change rate screening area, and the path continuity threshold area; the intrusion alarm signal includes the contour ratio data, the stay duration data, the intrusion time threshold, and the alarm priority; the elevator blocking instruction includes the elevator locking time, the stop operation instruction, and the uploaded intrusion record data.

[0057] Please refer to Figure 3 and Figure 2 , the target detection module includes:

[0058] The edge gradient calculation sub-module obtains the gray values of the image pixels, calculates the gray change rate of adjacent pixels, determines the gradient direction and amplitude, screens the gradient amplitude pixels that meet the threshold, extracts the gradient mutation points, calculates the curvature, the contrast change rate, and the edge direction consistency, and generates the gradient mutation feature parameters.

[0059] The steps to obtain the grayscale values of image pixels first require extracting image data through corresponding image processing software or tools. Each pixel point has a grayscale value, usually ranging from 0 to 255, where 0 represents black and 255 represents white. Next, calculate the grayscale change rate of adjacent pixels, which can be achieved through a simple difference calculation method. For example, calculate the grayscale difference between adjacent pixels in the horizontal, vertical, or diagonal directions, expressed as: ΔI = I(x,y) - I(x+1,y), where I(x,y) represents the grayscale value at position (x,y) in the image. Using these differences, the magnitude of the grayscale change between adjacent pixels can be judged. Then, according to a predetermined threshold (for example, set to 15, that is, when the grayscale difference between adjacent pixels exceeds 15, the area is considered an edge), filter out the pixels with larger changes. These pixels with larger changes represent the edge regions in the image. Then, extract the mutation points of these edges. Edge detection algorithms such as the Sobel operator can be used to further calculate the gradient magnitude and select the most prominent edge part. Next, combining the curvature and the contrast change rate, use mathematical formulas to evaluate the degree of curvature of the edge and the prominence of the brightness change. Filter the qualified regions through the set thresholds (for example, the curvature is greater than 0.5 and the contrast change rate is greater than 0.3). The calculation of the curvature is based on the degree of curvature of the edge in the image. Usually, if the curvature value is greater than 0.5, it indicates that the change of the edge is relatively significant, so it is set as a reasonable threshold.

[0060] The calculation method of the contrast change rate is: contrast change rate = (Imax - Imin) / Iavg, where Imax and Imin are the maximum and minimum grayscale values within the contour region respectively, and Iavg is the average grayscale value of this region. If the contrast change rate is greater than 0.3, then the region is considered to have a prominent contrast change. Finally, calculate and generate gradient mutation feature parameters based on these features. These parameters include information such as the direction and intensity of the edge mutation, providing basic data for subsequent global gradient mapping.

[0061] The global gradient mapping sub-module calculates the pixel gradient direction distribution based on the gradient mutation feature parameters, constructs a gradient direction histogram, calculates the change in the average gradient of adjacent regions, generates a global gradient change matrix, sets a dynamic threshold for the pixels in the global gradient change matrix, filters out the regions with prominent gradient changes, and generates a global gradient mapping matrix. Based on the gradient mutation feature parameters, the pixel gradient direction distribution is constructed. This process aggregates the gradient direction data of each pixel into a direction histogram, similar to dividing the gradient direction of each pixel point (such as the gradient direction calculated by the Sobel operator) into multiple intervals, and each interval represents a certain angular range. For example, it is divided into 0°-45°, 45°-90°, etc., so that a histogram representing the gradient direction distribution of the image can be obtained. Next, the change in the average gradient of adjacent regions is calculated. The sliding window method can be used. Assuming the window size is 3x3 pixels, for each pixel within the window, its average gradient value is calculated and compared with the surrounding regions. If the change exceeds the set dynamic threshold (such as set to 0.2), it is considered that the gradient change in this region is large. In this way, a global gradient change matrix is obtained, which represents the gradient change situation in different regions of the entire image. Then, for each pixel in the global gradient change matrix, a dynamic threshold is set to filter out the regions with prominent gradient changes. For example, the dynamic threshold can be set by calculating the change value at each position in the matrix and the standard deviation of the neighborhood. If the gradient change of a certain pixel exceeds this threshold (such as set to 2 times the standard deviation), then this pixel is marked as a prominent region. Finally, a global gradient mapping matrix is generated, which shows all the regions with significant gradient changes in the image, providing data support for the subsequent target contour screening.

[0062] Based on the global gradient mapping matrix, the target contour screening sub-module extracts the contours of the gradient change regions, calculates the boundary curvature and the contrast change rate, filters out the contours with stable curvature and prominent contrast changes, calculates the edge continuity and the pixel contact characteristics, and filters out the contour regions that meet the morphological characteristics to obtain the target contour candidate area.

[0063] Based on the global gradient mapping matrix, the target contour screening sub-module first extracts the contours of the regions with relatively obvious gradient changes. This step can be completed by an image segmentation algorithm, such as Canny edge detection. Through this algorithm, the coordinates of all edge points in the image are extracted and connected into contours. Then, the boundary curvature of the contour is calculated. The calculation formula for curvature is: k = (d 2 y / dx 2 ) / (1+(dy / dx) 2 )^(3 / 2), where dy / dx is the tangent slope of the contour, d 2 y / dx 2is the second derivative, representing the curvature of the curve. If the calculated curvature value is greater than 0.5, it is considered that the contour has a large curvature. If the threshold is set to 0.5, it means to select those regions with more significant edge mutations. For example, if the curvature value within a certain contour region is greater than 0.5, the edge change in this region is obvious and meets the target screening conditions. Next, calculate the contrast change rate of the contour, defined as contrast change rate = (Imax - Imin) / Iavg, where Imax and Imin are the maximum and minimum gray values within the contour region respectively, and Iavg is the average gray value of this region. If the contrast change rate is greater than the preset threshold (e.g., set to 0.3), the contour has a significant change in contrast. Next, screen out those contours with stable curvature and prominent contrast change. These contours are more likely to be the edges of the target. Calculate the continuity of the edge, that is, by checking whether the contour is continuous. The distance threshold method is used to judge. If the distance between two adjacent edge points is less than 2 pixels, it is considered that the edge is continuous. This setting is based on the edge characteristics of typical target images. When the gray value change between adjacent pixels is large, usually the pixel distance between them is small. Therefore, 2 pixels are set as a reasonable threshold, indicating that these edges should be continuous parts belonging to the same target. Finally, combined with the pixel contact characteristics, screen out the contour regions that meet the morphological characteristics. For example, through morphological operations such as erosion and dilation, further refine the target contour, and finally obtain the target contour candidate regions. These regions may contain the target object and serve as the basic data for subsequent recognition and tracking.

[0064] Please refer to Figure 4 and Figure 2 , the contour matching module includes:

[0065] The target contour extraction sub-module obtains the target contour candidate regions, calculates the edge gradient change amount of the pixel region, screens out the boundary pixels whose change amount meets the gradient threshold, connects the continuous boundary pixels to form a preliminary contour, calculates the curvature change rate of the preliminary contour, screens out the contour segments whose curvature change rate is greater than the curvature threshold, removes the low-curvature boundaries, and obtains the high-curvature target contour region.

[0066] The target contour extraction sub-module forms a preliminary contour by obtaining the target contour candidate regions, calculating the edge gradient change amount of the pixel region, screening out the boundary pixels whose change amount meets the gradient threshold, and connecting the continuous boundary pixels, calculates the curvature change rate of the preliminary contour, screens out the contour segments whose curvature change rate is greater than the curvature threshold, and obtains the high-curvature target contour region. First, the target contour extraction sub-module performs edge detection on the input image and analyzes the edge characteristics of the image by calculating the edge gradient change amount of the pixel region. In practical applications, considering the gray value change of the image, the edge intensity of the image can be reflected by calculating the gradient value of each pixel point. For example, the Sobel operator is used to perform edge detection on the image. The formula for calculating the gradient change amount is:

[0067]

[0068] Among them, G is the gradient value, I is the image gray value, and are the partial derivatives of the image in the x and y directions respectively. By setting a gradient threshold, boundary pixels with a change amount greater than the threshold can be screened out, and then the boundary contour in the image can be obtained. Next, by connecting continuous boundary pixels to form a preliminary contour, the curvature change rate of the preliminary contour is further calculated. The curvature calculation formula is:

[0069]

[0070] Among them, K is the curvature, dθ is the change amount of the tangent angle, |dθ| represents the absolute value of dθ, and ds is the change amount of the arc length. By setting a curvature threshold, contour segments with a curvature change rate greater than the threshold are screened out, and finally a high-curvature target contour area is formed. For example, assuming that the edge gradient change amount in the image is 10 and the curvature change rate is 0.5, by setting the gradient threshold to 8 and the curvature threshold to 0.3, the target contour area that meets the conditions is screened out. At this time, the output high-curvature target contour area is the area with significant curvature changes, which is convenient for subsequent target recognition and processing.

[0071] Based on the high-curvature target contour area, the symmetry screening sub-module calculates the symmetry offset of the pixel distribution inside the contour area, screens out the areas with an offset less than the standard threshold, removes the non-rigid structure areas with an offset exceeding the threshold, calculates the average offset of the morphological symmetry axis, and screens out the areas with an average offset less than the reference threshold to obtain the rigid structure contour area.

[0072] Screen out the areas with an offset setting the standard threshold, and use the formula:

[0073]

[0074] Calculate the average offset of the morphological symmetry axis, and screen out the areas with an average offset averaging the reference threshold;

[0075] Among them, S represents the average offset of the morphological symmetry axis, N represents the number of pixel points in the contour area, P i,x and P i,y represent the positions of the i-th pixel point on the x and y axes respectively, and represent the positions of the i-th pixel point on the x and y axes in the reference area respectively;

[0076] The parameter definitions in the formula are as follows:

[0077] S: The average offset of the morphological symmetry axis, representing the average degree of symmetry offset between the contour region and the reference region. It is obtained by statistically analyzing the offset of each pixel position.

[0078] N: The number of pixels in the contour region. It is calculated by segmenting the contour region through image processing methods to obtain the number of pixels in this region.

[0079] P i,x and P i,y : The position coordinates of the i-th pixel on the x and y axes. It is obtained by extracting the coordinates of the pixels in the contour region.

[0080] and The position coordinates of the i-th pixel on the x and y axes in the reference region. The reference region is the reference image region selected by comparing with the contour region, and its coordinates are obtained through image registration methods. Quantification process:

[0081] N (number of pixels): The contour region is extracted through an image processing algorithm, and the number of pixels in this region is statistically analyzed. Assuming there are 1000 pixels in the contour region, then N = 1000.

[0082] P i,x and P i,y (Coordinates of each pixel in the contour region): For the first pixel in the contour region, its position is determined through the image coordinate system. Assuming the coordinates of the 1st pixel are P 1,x = 150 and P 1,y = 300.

[0083] and (Coordinates of each pixel in the reference region): The position of this pixel in the reference region is obtained through image registration of the reference region. Assuming the coordinates of this pixel in the reference region are and For the first pixel, calculate the offset of its position:

[0084]

[0085] Sum and take the square root of these two offsets to obtain the offset of this pixel:

[0086]

[0087] And so on, calculate the offsets of all 1000 pixels and find the average value. Assuming the sum of the offsets of all 1000 pixels is 7000. [[ID=5�]]

[0088] Divide the sum of all offsets by N to obtain the average offset S of the morphological symmetry axis:

[0089]

[0090] The calculated S = 7, indicating that the overall offset mean between the contour region and the reference region is 7 unit lengths. This value reflects the deviation of the symmetry of the contour region from the reference region. The larger the value, the more serious the offset, and the smaller the value, the better the symmetry of the contour region.

[0091] Based on the rigid structure contour region, the structure matching optimization sub-module detects the change trend of the edge curvature, calculates the curvature change amount in the local region, filters out the edge regions where the change amount is greater than the set threshold, removes the flexible deformation edges with high change amount, calculates the matching degree coefficient, filters out the regions where the matching degree coefficient is greater than the average threshold, and obtains the structure matching contour region.

[0092] Based on the rigid structure contour region, the structure matching optimization sub-module detects the change trend of the edge curvature, calculates the curvature change amount in the local region, filters out the edge regions where the change amount is greater than the set threshold, calculates the matching degree coefficient, filters out the regions where the matching degree coefficient is greater than the average threshold, and obtains the structure matching contour region. First, the structure matching optimization sub-module analyzes the edges of the rigid structure contour region to detect the change trend of the curvature. In order to capture the curvature change in the local region, a calculation method of local curvature change amount is adopted, and the local curvature change amount can be obtained by calculating the curvature change between different points in this region. The calculation formula is:

[0093] ΔK = |K1 - K2|;

[0094] where ΔK is the local curvature change amount, and K1 and K2 are the curvature values of two adjacent points. By setting a curvature change amount threshold, the edge regions where the change amount is greater than this threshold are filtered out for further analysis and processing. Then, the matching degree coefficient is calculated to judge the regional matching degree, and the calculation formula of the matching degree coefficient is as follows:

[0095]

[0096] where K 1,i and K 2,i are the curvature values of the two regions at the i-th position, and n is the number of pixel points in this region. By calculating the matching degree coefficient and comparing it with the set average threshold, the regions where the matching degree coefficient is greater than this threshold are filtered out, and finally the structure matching contour region is obtained. Assume that the threshold of the matching degree coefficient is set to 0.8. When the matching degree coefficient of a certain region is 0.9, then this region is the structure matching contour region. These regions show structures with strong consistency in practical applications and are suitable for further processing.

[0097] Please refer to Figure 5 and Figure 2 , the trajectory capture module includes:

[0098] The trajectory rate analysis sub-module obtains the displacement information of human key points, calculates the displacement distance within adjacent time frames, screens out the high change rate regions based on the motion path continuity threshold, calls the trajectory change rate to calculate its time series distribution, and combines multiple time frames for sequence analysis to obtain the trajectory change rate distribution data;

[0099] The trajectory rate analysis sub-module calculates the displacement distance within adjacent time frames by obtaining the displacement information of human key points, and screens out the high change rate regions according to the continuity threshold of the motion path. First, use the sensor device to capture the key point positions of human motion to form continuous time series data, and then calculate the displacement of the key points within each time frame. The displacement formula is:

[0100]

[0101] where x t and y t are the abscissa and ordinate of the key point at time frame t respectively. Through this formula, the displacement of the human key points at each time point is calculated. Subsequently, calculate the displacement change rate between adjacent time frames:

[0102] For example, assume that between the 1st frame and the 2nd frame, the key point displacement is 5 cm and the time interval is 0.1 second, then the change rate is 50 cm / s. According to the preset motion path continuity threshold (such as 0.3 m / s), screen out the regions where the rate exceeds this threshold. These regions are the parts where rapid changes may occur. By combining with the time series, the specific trajectory change rate distribution data is further determined.

[0103] The target region screening sub-module, based on the trajectory change rate distribution data, detects the regions where the rate changes violently in a short time, calculates its proportion in the global trajectory, analyzes the time series continuity, eliminates the regions that do not conform to the human motion law, and screens out the regions with stable motion trends to obtain the stable motion region distribution data.

[0104] The target area screening sub-module detects the areas where the speed changes drastically within a short time based on the trajectory change rate distribution data, and calculates the proportion of these areas in the global trajectory. By comparing the change rates in adjacent time frames, if the speed change exceeds the set threshold (e.g., 10 cm / s) within a short time, the area is determined as an area with drastic speed change. Further analyze the proportion of these areas in the global trajectory. For example, if the total length of the trajectory is 100 m and the length of a certain area with drastic change rate is 5 m, then the proportion of this area is 5%. Combining with the analysis of time series continuity, it can be found that the movement trends of some areas are relatively stable, so these areas are screened as stable movement areas. The screening process of these stable areas is to determine that their speed changes are stable (the change rate fluctuation is less than the set value, e.g., 1 cm / s), and then obtain the distribution data of the stable movement areas. For example, if the speed change of a certain area does not exceed the fluctuation range of 0.5 cm / s within 1 second, this area can be considered stable.

[0105] Based on the stable movement area distribution data and combined with the rigid structure data of the electric vehicle, the independent contour extraction sub-module performs morphological analysis, extracts the areas with consistent structural features, calculates the boundary change of the areas, screens the areas with stable morphological changes, and establishes an independent contour shape to obtain the independent contour area of the electric vehicle.

[0106] Based on the stable movement area distribution data and combined with the rigid structure data of the electric vehicle, the independent contour extraction sub-module performs morphological analysis, extracts the areas with consistent structural features, calculates the boundary change of the areas, and screens out the areas with stable morphological changes. Through in-depth analysis of the stable movement area data and combined with the rigid structure model of the electric vehicle (such as data based on geometric modeling), calculate the degree of morphological change within the area. For example, if the boundary change of the area does not exceed the set value (e.g., 0.5 mm) within a certain period of time, it indicates that the morphology of the area is stable. Use a mathematical model to fit the overall morphology of the electric vehicle to obtain the structural feature areas, and by comparing with the actual data, screen out those areas with smaller boundary changes, and the stability of these areas is higher. Finally, based on this analysis, construct the independent contour area of the electric vehicle, and through system identification and screening, identify the independent contour areas that meet the standards to ensure the stability and consistency of the electric vehicle structure.

[0107] Please refer to Figure 6 and Figure 2 , the warning trigger module includes:

[0108] The contour detection sub-module obtains the electric vehicle contour area data, detects the pixel distribution in the areas inside and outside the elevator door, extracts the contour features of the target area, calculates the proportion of the contour area, calls the elevator door status information, compares with the contour proportion threshold, determines whether the electric vehicle is close to or partially enters the elevator door area, and generates the contour proportion parameter.

[0109] Extract the contour features of the target area, using the formula:

[0110]

[0111] Calculate the contour ratio, C ratio Represents the contour ratio, P i Represents the contour pixel value of the i-th pixel point, |P i | represents P i The absolute value of A i Represents the area of the region corresponding to the i-th pixel, N represents the total number of pixels in the contour area, A total Represents the total area of the elevator door area.

[0112] This value is obtained through image processing algorithms. Each pixel of the image is marked as a contour pixel (value 1) or a non-contour pixel (value 0) after thresholding. In this example, it is assumed that there are a total of 2000 pixels detected in the elevator door area, of which 1000 pixels belong to the electric car contour area. The corresponding P i The value is 1. The remaining 1000 pixels are the background or the elevator door area, and the corresponding P i The value is 0.

[0113] Each pixel of the electric vehicle outline occupies a certain area, which is usually converted using the actual image resolution. Assuming the image resolution is 1mm2 / pixel, the area of each pixel is 1mm2. In this example, all P i Each pixel with a value of 1 (i.e., 1000 contour pixels) has an area of 1 mm2, so A i =1mm2. In the above example, the number of pixels within the electric vehicle outline area is 1000, so N = 1000.

[0114] The total area of the elevator door can be calculated by actual measurement or the number of pixels in the image. Assuming that the total area of the elevator door is 2000 mm2 (corresponding to 2000 pixels), therefore, A total =2000mm2.

[0115] Summation part: For each pixel, P i With A i The product of and is the area contributed by the pixel point. i The value is 1, A i The value is 1mm2, so each pixel contributes 1mm2 of area. For 1000 contour pixels, the sum is:

[0116]

[0117] Calculate the contour ratio: divide the sum of the areas occupied by all contour pixels by the total area A of the elevator door areatotal , the outline ratio C is obtained ratio :

[0118]

[0119] This result indicates that the outline area of the electric vehicle occupies half of the elevator door area, that is, 50%.

[0120] Based on the outline ratio parameter, the trajectory analysis sub-module extracts the electric vehicle trajectory data, calculates the residence time near the elevator door, analyzes the trajectory deviation in combination with the movement trajectory, compares the residence duration threshold, and determines whether there is a continuous intrusion trend to obtain the trajectory residence duration parameter.

[0121] The execution process of the trajectory analysis sub-module starts with the acquisition of the aforementioned outline ratio parameters. Through these parameters, the system can extract the trajectory data of the electric vehicle. The trajectory of the electric vehicle is obtained by tracking the movement path of the electric vehicle outline in the elevator door area. Specifically, the system needs to calculate the movement trajectory of the electric vehicle according to the position change of the electric vehicle in the video stream or consecutive captured images. To ensure the accuracy of the trajectory, the system applies the optical flow method (Optical Flow) or object detection algorithm to track the movement path of the electric vehicle through the comparison of consecutive frames. After processing the trajectory data, the system further calculates the residence time of the electric vehicle near the elevator door. If the electric vehicle stays in the elevator door area for more than the preset time threshold, the system will consider that it may have a continuous intrusion trend. For further judgment, the system analyzes the deviation of the electric vehicle's movement trajectory in combination with the movement trajectory. By comparing the change between the current trajectory and the previous trajectory, the trajectory deviation amount is calculated. When the trajectory deviation amount is greater than the set threshold and the residence time of the electric vehicle in the elevator door area exceeds the set residence duration threshold, the system determines that the electric vehicle may have a trend of continued intrusion, obtains the trajectory residence duration parameter, and prepares to further trigger an alarm.

[0122] Based on the trajectory residence duration parameter, the alarm trigger sub-module combines the elevator door status data, analyzes whether the intrusion time exceeds the reference threshold, determines whether the alarm trigger condition is met, and activates the audible and visual alarm to generate an intrusion alarm signal if the alarm trigger condition is met.

[0123] The execution process of the alarm trigger sub-module starts from obtaining the trajectory stay duration parameter. First, the system combines the status data of the elevator door to analyze whether the intrusion time exceeds the reference threshold. The status of the elevator door is obtained through the connection with the elevator control system. When the elevator door is in the open state and the staying time of the electric vehicle in the elevator door area exceeds the set reference threshold, the system will determine that the intrusion event meets the alarm trigger condition. The setting of the reference threshold is comprehensively considered according to historical data and scenario requirements. Usually, this value will be dynamically adjusted according to the opening time of the elevator door and the behavior pattern of the electric vehicle. For example, within 10 seconds after the elevator door opens, if the electric vehicle stays for more than 5 seconds, the system will determine that there may be danger and trigger an alarm. If this condition is met, the system will activate the audible and visual alarm device to send out an intrusion alarm signal. This signal not only notifies the elevator control system to take actions (such as automatically closing the elevator door), but also can notify the surrounding people through external alarm devices, so as to prevent potential accidents from occurring.

[0124] Please refer to Figure 7 and Figure 2 , the elevator control module includes:

[0125] The alarm signal processing sub-module obtains the intrusion alarm signal, detects the signal source and level, sets the locking parameter, calls the elevator control system data, matches the elevator floor and running status, calculates the deviation value between the elevator running parameter and the locking parameter, screens the executable locking duration, and obtains the elevator locking duration data.

[0126] The alarm signal processing submodule acquires intrusion alarm signals. First, the system receives intrusion alarm signals from sensors or monitoring devices. These signals typically include information such as the time, location, and signal strength of the intrusion. The system then analyzes the signal source to determine whether it is an external intrusion or a false alarm from an internal device. This analysis may involve analyzing the signal frequency and duration. By matching these signals with pre-set intrusion pattern data, the system determines whether they conform to normal intrusion signal characteristics. Next, the system determines the alarm level. Lower-level alarms may not trigger subsequent elevator control measures, while higher-level alarms trigger the activation of elevator safety measures. After confirming the level, the system sets lockout parameters, which include the elevator's operating mode, floor range, and predetermined elevator operating status. Lockout parameters are adjusted based on the specific alarm level. For example, a high-level alarm may trigger a full-elevator floor lockout mode, preventing the elevator from continuing to operate or stopping at certain floors when a threat is encountered. During this process, the system combines the elevator's current operating status, pre-set safety rules, and actual floor information to perform calculations. The system compares the elevator's current location with the target floor, calculates the elevator's current operating parameters, and compares them with the set lockout parameters to determine if there are any deviations. The greater the deviation between the elevator's operating parameters and the lockout parameters, the more necessary the lockout measures are. The system then further screens the available lockout durations. Assuming the lockout duration can be set between 10 and 30 minutes, the system determines the most appropriate duration based on the elevator's current location, floor, operating status, and alarm level, ultimately calculating the elevator's lockout duration. This data is then used by the subsequent elevator operation control submodule to ensure that the elevator executes necessary shutdown measures within the set safety time, protecting it from external intrusion threats.

[0127] The elevator operation control submodule compares the elevator's current operating status based on the elevator lock duration data, determines whether it is in the adjustable range, calculates the stop trigger condition, compares the elevator's current position, target floor and scheduling information, screens the stop method, and generates the elevator scheduling stop instruction.

[0128] The elevator operation control submodule is based on the elevator lock duration data. First, the elevator control module analyzes the current operating status of the elevator to check whether the elevator is in an adjustable state range. Assuming that the elevator is currently running on a high floor, whether its current operating state is in a state where it can stop needs to calculate the stop trigger condition. This condition may include the elevator's speed, acceleration, and the distance between the operating floor and the target floor. Specifically, the system uses an algorithm to calculate the relationship between the distance between the elevator and the target floor and the elevator's current speed and acceleration, using the formula:

[0129]

[0130] Among them, D is the distance where the elevator needs to stop, v0 is the initial speed of the elevator, a is the acceleration of the elevator, and t is the running time of the elevator. When the speed and acceleration of the elevator meet the set standards, the elevator is considered to be in a stoppable state. On this basis, the information of the elevator's target floor and current position is input into the system, and the elevator scheduling information is transmitted to the operation control sub-module. The sub-module screens out the most appropriate stopping method according to these data. For example, if the elevator is far from the target floor, it may adopt a deceleration stopping strategy, while if it is at a closer floor, it may directly trigger an emergency stop. The screening of these stopping methods combines the running trajectory of the elevator and the required time to determine the most suitable execution time. During this process, the elevator control sub-module also needs to analyze the elevator scheduling information to ensure that the appropriate stopping mode is triggered according to the current operating condition of the elevator, and finally generates an elevator scheduling shutdown instruction to ensure that the elevator can stop quickly and safely after the alarm is triggered. The no-entry instruction execution sub-module, based on the elevator scheduling shutdown instruction, detects the elevator response status, confirms the shutdown, collects the intrusion alarm signal and shutdown time data, integrates the log to record the shutdown parameters, uploads them to the intrusion record database, and generates an elevator lockdown instruction.

[0131] Based on the elevator scheduling shutdown instruction, first of all, the system needs to detect the response status of the elevator and check whether the elevator has stopped successfully. This process may include confirmation through the communication signal between the control system and the elevator. If the elevator does not stop as expected, the system will repeatedly check its status and output an alarm. At this time, the elevator may execute alternative shutdown measures until it is confirmed that the elevator has stopped completely. After the shutdown is successful, the system will collect and record data such as the intrusion alarm signal and shutdown time to ensure a complete log record of the shutdown process, and these data will be sorted into shutdown parameters. The shutdown data may include the start time of the shutdown, the duration of the shutdown, the intensity of the alarm signal, etc., for subsequent analysis and traceability. After logging, the system uploads it to the intrusion record database to ensure the secure storage and audit tracking of the data. In addition, the no-entry instruction execution sub-module will also generate an elevator lockdown instruction to ensure that the elevator will not restart or continue to run when under serious threat. Once the no-entry instruction is issued, the elevator will enter the no-entry mode according to the set conditions until it is manually lifted.

[0132] Based on the same inventive concept, the present invention also proposes an elevator for preventing electric vehicles from being carried in the elevator, and the elevator is equipped with the above monitoring system.

[0133] The above are only the preferred embodiments of the present invention, and do not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. A monitoring system for preventing electric vehicles from being carried by elevators, characterized in that, include: The target detection module obtains image edge gradients, morphological features, and pixel contact features, calculates the gradient changes of adjacent pixels and establishes a global gradient map, analyzes strong continuous edge regions as candidate contours, calculates curvature, and filters the electric vehicle contour region to obtain the target contour candidate region; The contour matching module selects the rigid structure area based on the target contour candidate area, and eliminates the edge area that conforms to the natural undulation characteristics of the human body based on the comparison of the characteristics of the electric vehicle parts and human clothing to obtain the structural matching contour area; The contour matching module includes: The target contour extraction submodule obtains the target contour candidate area, calculates the gradient change of the pixel area edge, selects the boundary pixels whose change meets the gradient threshold, connects the continuous boundary pixels to form a preliminary contour, calculates the curvature change rate of the preliminary contour, selects the contour segments whose curvature change rate is greater than the curvature threshold, and obtains the high curvature target contour area; The symmetry screening submodule calculates the symmetry offset of the pixel distribution within the contour area based on the high curvature target contour area, screens the areas where the offset is less than a set threshold, removes the non-rigid structure areas where the offset exceeds the set threshold, calculates the mean offset of the morphological symmetry axis, and screens the areas where the mean offset is less than the average threshold to obtain the rigid structure contour area; The structural matching optimization submodule detects the edge curvature change trend based on the rigid structure contour area, calculates the curvature change of the local area, screens the edge areas with the change greater than the standard threshold, calculates the matching coefficient, screens the areas with the matching coefficient greater than the reference threshold, and obtains the structural matching contour area; The trajectory capture module sets a path continuity threshold based on the structure matching contour area, combines the displacement of key points of the human body and the trajectory change rate, and screens the stable morphological change area to obtain the independent contour area of the electric vehicle; The trajectory capture module includes: The trajectory rate analysis submodule obtains the displacement information of key points of the human body, calculates the displacement distance in adjacent time frames, filters the high change rate area based on the path continuity threshold, calls the trajectory change rate to calculate the time series distribution, and performs sequence analysis based on the time frame to obtain the trajectory change rate distribution data; The target area screening submodule detects areas with drastic rate changes in a short period of time based on the trajectory change rate distribution data, calculates their proportion in the global trajectory, analyzes the continuity of the time series, and screens stable motion trend areas according to the change rate fluctuation threshold to obtain stable motion area distribution data; The independent contour extraction submodule performs morphological analysis based on the stable motion area distribution data and the rigid structure data of the electric vehicle, extracts the consistent structural feature area, calculates the regional boundary changes, and screens the stable morphological change area according to the set threshold to establish the independent contour area of the electric vehicle; The early warning trigger module determines whether the electric vehicle has entered the elevator door based on the electric vehicle's independent contour area, contour ratio and residence time data, sets alarm conditions based on the intrusion time, calculates the priority and triggers the sound and light alarm to generate an intrusion alarm signal; The elevator control module executes elevator control based on the intrusion alarm signal, sets the elevator locking time, executes the stop operation instruction and uploads the intrusion record, and obtains the elevator blocking instruction.

2. The monitoring system for preventing electric vehicles from being carried by elevators according to claim 1, wherein: The target contour candidate area includes a strongly continuous edge area, a global gradient map, and a calculation result of candidate contour curvature; the structure matching contour area includes a rigid structure area, an electric vehicle component feature area, and a removed human body edge area; the electric vehicle independent contour area includes a morphologically stable area, a trajectory change rate screening area, and a path continuity threshold area; the intrusion alarm signal includes contour ratio data, residence duration data, intrusion time threshold, and alarm priority; the elevator lockdown instruction includes elevator lock time, stop operation instruction, and upload intrusion record data.

3. The monitoring system for preventing electric vehicles from being carried by elevators according to claim 1, wherein: The target detection module includes: The edge gradient calculation sub-module obtains the gray values of image pixels, calculates the gray change rate of adjacent pixels, determines the gradient direction and amplitude, screens the gradient amplitude pixels that meet the threshold, extracts the gradient mutation points, calculates the curvature, contrast change rate, and edge direction consistency, and generates gradient mutation feature parameters; The global gradient mapping sub-module calculates the pixel gradient direction distribution based on the gradient mutation feature parameters, constructs a gradient direction histogram, calculates the change of the gradient mean value in adjacent regions, generates a global gradient change matrix, sets a dynamic threshold for the pixels of the global gradient change matrix, screens the regions with prominent gradient changes, and generates a global gradient mapping matrix; The target contour screening sub-module extracts the contour of the gradient change region based on the global gradient mapping matrix, calculates the boundary curvature and contrast change rate, screens the contours with stable curvature and prominent contrast change according to the set threshold, calculates the edge continuity and pixel contact characteristics, and screens the contour regions that meet the morphological characteristics to obtain the target contour candidate area.

4. The monitoring system for preventing electric vehicles from being carried by elevators according to claim 1, wherein: The specific formula for screening the area where the offset is less than the set threshold is: Calculate the offset mean value of the morphological symmetry axis and screen the areas where the offset mean value is less than the average threshold; Among them, S represents the average offset of the morphological symmetry axis, N represents the number of pixel points in the contour area, P i,x and P i,y respectively represent the positions of the i-th pixel point on the x-axis and y-axis, and respectively represent the positions of the i-th pixel point on the x-axis and y-axis in the reference area.

5. The monitoring system for preventing electric vehicles from being carried by elevators according to claim 1, wherein: The early warning trigger module includes: The contour detection sub-module obtains the electric vehicle contour area data, detects the pixel distribution in the areas inside and outside the elevator door, extracts the contour feature of the target area, calculates the contour area ratio, calls the elevator door state information, compares the contour ratio threshold, and determines whether the electric vehicle is close to or partially enters the elevator door area to generate the contour ratio parameter; The trajectory analysis sub-module extracts the electric vehicle trajectory data based on the contour ratio parameter, calculates the residence time near the elevator door, analyzes the trajectory offset in combination with the movement trajectory, compares the residence duration threshold, and determines whether there is a continuous intrusion trend to obtain the trajectory residence duration parameter; The alarm trigger sub-module analyzes whether the intrusion time exceeds the reference threshold based on the trajectory residence duration parameter in combination with the elevator door state data, determines whether the alarm trigger condition is met, and activates the audible and visual alarm if the alarm trigger condition is met to generate an intrusion alarm signal.

6. The monitoring system for preventing electric vehicles from being carried by elevators according to claim 5, wherein: The specific formula for extracting the contour feature of the target area is: Calculate the contour proportion, where C ratio represents the contour proportion, P i represents the contour pixel value of the i-th pixel point, |P i | represents the absolute value of P i , A i represents the area of the region corresponding to the i-th pixel point, N represents the total number of pixel points in the contour region, A total represents the total area of the elevator door region.

7. The monitoring system for preventing electric vehicles from being carried by elevators according to claim 1, wherein: The elevator control module includes: The alarm signal processing sub-module obtains the intrusion alarm signal, detects the signal source and level, sets the locking parameter, calls the elevator control data, matches the elevator floor and running state, calculates the deviation value between the elevator running parameter and the locking parameter, and screens the executable locking duration to obtain the elevator locking duration data; Based on the elevator locking duration data, the elevator operation control sub-module compares the current operation state of the elevator, determines whether it is in the adjustable range, calculates the stop trigger condition, compares the current position of the elevator, the target floor and the scheduling information, filters the stop mode, and generates an elevator scheduling stop instruction. Based on the elevator scheduling stop instruction, the restricted access instruction execution sub-module detects the elevator response status, confirms the stop, collects the intrusion alarm signal and the stop time data, integrates the log to record the stop parameters, uploads them to the intrusion record database, and generates an elevator blocking instruction.

8. An elevator for preventing electric vehicles from being carried in the elevator, characterized in that: The elevator is equipped with the monitoring system according to any one of claims 1 to 7 above.

Images