A method for identifying elevator non-level door opening faults based on computer vision

Abstract

The invention discloses a method for identifying an elevator non-level door opening fault based on computer vision, and relates to the technical field of elevator fault identification. The technical key points are: using infrared technology to complete the effective judgment of the elevator non-level door opening fault, and combining with a binocular camera unit, using stereo vision technology to identify fault information to ensure the accuracy of obtaining the height difference between the elevator and the corresponding floor, so as to facilitate the subsequent issuance of corresponding instructions according to the situation; using a stereo matching algorithm to calculate and obtain the height difference generated in the non-level door opening state, building a data calculation model based on the height difference and the original initial length of a slope adjustment mechanism, and generating the required elongation estimate or shortening estimate of the slope adjustment mechanism, so as to facilitate the rapid and effective adjustment of the longitudinal cylinder in the slope adjustment mechanism according to the corresponding estimate, so that the elevator can be used in an emergency and the safety of passengers is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator fault identification, and in particular to a computer vision-based elevator non-level door opening fault identification method. Background Art

[0002] Elevator fault identification refers to identifying and judging possible problems in the elevator system by monitoring abnormal conditions or fault signals that occur during elevator operation. These problems may involve the mechanical components, electrical systems, control systems, etc. of the elevator. The fault identification process usually includes the following aspects: abnormal monitoring, fault signal identification, fault classification, and fault location. Abnormal monitoring: The elevator system will monitor the operating status of the elevator in real time through sensors or monitoring devices, including the speed, acceleration, position, door opening and closing status, etc. of the elevator. When data that does not match the normal situation is detected, the system will mark it as abnormal. Fault signal identification: The elevator system will identify the abnormal data detected through the preset fault signal pattern. These patterns may be pre-defined rules, models, or algorithms trained based on machine learning, artificial intelligence, and other technologies. Fault classification: After identifying the fault signal, the system will classify it and determine which type of fault it belongs to. This will help with subsequent maintenance and processing. Fault location: After determining the type of fault, the system will further locate the specific location of the fault. This may require further detection and troubleshooting, or use the system's own self-diagnosis function to complete.

[0003] The existing application publication number is: CN112801072A, and the technical solution pointed out in the document named A device and method for identifying non-level door opening faults of elevators based on computer vision includes: a video acquisition module for collecting elevator sill images; an acceleration monitoring module for monitoring the acceleration of the elevator operation to predict whether the elevator enters a deceleration and stopping state; a model training module, including a sill groove target detection model training unit and a non-level door opening classification model training unit, which are used to train the model; a detection and recognition module, including an image illumination adaptive correction unit, a sill groove detection unit, an image angle adaptive correction unit, and a non-level door opening recognition unit; in this solution, when the device finds that the elevator is about to stop, it loads the detection and recognition model, analyzes the target images of the car door and the sill groove of the hall door, detects the elevator door opening state and amplitude, and can detect and identify the elevator non-level door opening fault in real time, efficiently and accurately by classifying the target image into level door opening and non-level door opening, but the solution does not adjust the fault or perform emergency maintenance.

[0004] In combination with the above documents and existing technologies, if an elevator has a non-level door opening failure, computer vision recognition technology is usually used to analyze the image, and then other algorithms are combined to determine the non-level door opening failure. Usually, when it is determined that the failure has occurred, the elevator will be shut down for maintenance. If the passengers in the elevator want to exit the elevator, they need to pass through the step surface. The height difference between the elevator and the ground of the corresponding floor caused by the failure is the so-called step surface. Passengers will be at risk of falling or falling when passing through the step surface. If the elevator needs to be used for emergency purposes, the step surface formed is not conducive to the use of passengers, which increases the danger of using the elevator. Summary of the invention

[0005] 1. Technical issues to be solved

[0006] In view of the shortcomings of the prior art, the present invention provides a method for identifying an elevator non-level door opening fault based on computer vision, which uses infrared technology to effectively determine the elevator non-level door opening fault, and combines a binocular camera unit to identify fault information using stereo vision technology to ensure the accuracy of obtaining the height difference between the elevator and the corresponding floor, so as to facilitate subsequent corresponding instructions according to the situation; a stereo matching algorithm is used to calculate the height difference generated in the non-level door opening state, and a data calculation model is built based on the height difference and the original initial length of the slope adjustment mechanism, and the required elongation estimate or shortening estimate of the slope adjustment mechanism is generated, so that the longitudinal cylinder in the slope adjustment mechanism can be quickly and effectively adjusted according to the corresponding estimate, so that the elevator can be used in an emergency, thereby ensuring the safety of passengers and solving the problems raised in the background technology.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] A computer vision-based elevator non-level door opening fault recognition method comprises the following steps:

[0010] S1. Install a slope adjustment mechanism at the bottom of the elevator, and equip an infrared detection unit at a position where the slope adjustment mechanism and the corresponding floor are flush with each other. After the elevator arrives at the corresponding floor, determine whether the infrared signal in the infrared detection unit is received. If the infrared signal can be received, no response action is taken; otherwise, an early warning signal is issued;

[0011] S2. Upon receiving the warning signal, trigger the binocular camera unit, use stereo vision technology to identify the fault information, and obtain the height difference between the elevator and the corresponding floor;

[0012] S3, comparing the height difference between the obtained elevator and the corresponding floor with the preset standard threshold, if the absolute value of the height difference exceeds the standard threshold, a warning signal is issued; otherwise, an emergency adjustment instruction is triggered;

[0013] S4. Execute the emergency adjustment command. According to the established rule engine, when it is determined that the height difference between the elevator and the corresponding floor obtained in real time is a positive number, an extension signal is sent to the slope adjustment mechanism. According to the height difference between the elevator and the corresponding floor, a data calculation model is established to generate an estimated extension amount L of the slope adjustment mechanism. 长 ;

[0014] When it is determined that the height difference between the elevator and the corresponding floor obtained in real time is negative, a shortening signal is sent to the slope adjustment mechanism. According to the height difference between the elevator and the corresponding floor and the collected initial length of the slope adjustment mechanism, a data calculation model is built to generate an estimated shortening amount L of the slope adjustment mechanism. 短 .

[0015] Furthermore, the slope adjustment mechanism includes a longitudinal cylinder and a transition plate; the longitudinal cylinder is installed in the elevator floor, and the longitudinal cylinder is always located below the transition plate, the output end of the longitudinal cylinder is hinged to the lower surface of the transition plate, and one end of the transition plate is connected to both sides of the inner wall of the elevator floor by setting a rotating shaft, and the other end of the transition plate faces the floor.

[0016] Furthermore, the infrared detection unit includes an infrared transmitter and an infrared receiver. The infrared generator is arranged on the surface of the corresponding floor, and the infrared receiver is embedded in the end surface of the transition plate facing the floor. Whenever the elevator arrives at the corresponding floor, the infrared generator sends out an infrared signal. If the infrared receiver receives the infrared signal, it means that the elevator and the floor are flush with each other. If the infrared receiver does not receive the infrared signal, it means that there is a fault that the elevator opens the door at a non-level floor.

[0017] Furthermore, the triggered binocular camera unit is a binocular camera installed on the top of the elevator, and the shooting surface of the binocular camera covers the elevator door and the horizontal ground of the floor, obtaining images of the elevator door and the horizontal ground of the floor, the elevator door represents the left image, and the horizontal ground of the stairs represents the right image.

[0018] Furthermore, the process of obtaining the height difference between the elevator and the corresponding floor is as follows:

[0019] Stereo vision matching: stereo matching is performed on the images collected by the binocular camera unit, that is, the corresponding pixel points in the left and right images are matched to obtain the disparity information between them. The disparity information indicates the position difference of the object in the left and right images. The depth information of the corresponding object from the camera in the left and right images is obtained through disparity calculation;

[0020] Height difference calculation: The height difference is calculated using the depth information obtained from stereo vision. The height difference is obtained by calculating the difference in depth between the elevator door and the horizontal ground based on the depth information in the left and right images. The formula is:

[0021] hr=S 梯 -S 层

[0022] In the formula, hr represents the height difference, S 梯 Indicates the distance between the binocular camera and the elevator floor, S 层 Indicates the distance between the binocular camera and the ground of the corresponding floor. If hr is a positive number, it means that the elevator door is lower than the depth of the ground of the corresponding floor. If hr is a negative number, it means that the elevator door is higher than the depth of the ground of the corresponding floor.

[0023] Further, the stereo matching algorithm includes any one of disparity mapping and block matching.

[0024] Furthermore, the preset standard threshold value represents the maximum value of the height difference that the slope adjustment mechanism can cope with, and the warning signal issued in S3 is expressed differently from the early warning signal issued in S1.

[0025] Furthermore, the estimated extension amount L of the slope adjustment mechanism is generated 长 The formula used is as follows:

[0026]

[0027] Wherein, G is a constant correction coefficient, and the value range of G is 0 to 1, and L0 represents the initial length of the slope adjustment mechanism.

[0028] Furthermore, the estimated extension amount L of the slope adjustment mechanism is generated 短 The formula used is as follows:

[0029]

[0030] Wherein, G is a constant correction coefficient, and the value range of G is 0 to 1, and L0 represents the initial length of the slope adjustment mechanism.

[0031] A computer vision-based elevator non-level door opening fault recognition system, the system includes a signal judgment module, a fault recognition module, a comparison and judgment module, and an early warning adjustment module;

[0032] Among them, the signal judgment module is equipped with a slope adjustment mechanism at the bottom of the elevator, and an infrared detection unit is installed at a position where the slope adjustment mechanism and the corresponding floor are flush with each other. After the elevator arrives at the corresponding floor, it is judged whether the infrared signal in the infrared detection unit is received. If the infrared signal can be received, no response action is taken; otherwise, an early warning signal is issued;

[0033] The fault identification module triggers the binocular camera unit upon receiving the warning signal, uses stereo vision technology to identify the fault information, and obtains the height difference between the elevator and the corresponding floor;

[0034] The comparison and judgment module compares the height difference between the elevator and the corresponding floor with the preset standard threshold. If the absolute value of the height difference exceeds the standard threshold, a warning signal is issued; otherwise, an emergency adjustment instruction is triggered;

[0035] The early warning adjustment module executes the emergency adjustment command. According to the established rule engine, when it is determined that the height difference between the elevator and the corresponding floor obtained in real time is a positive number, it sends an extension signal to the slope adjustment mechanism. According to the height difference between the elevator and the corresponding floor, a data calculation model is built to generate the estimated extension amount L of the slope adjustment mechanism. 长 ;

[0036] When it is determined that the height difference between the elevator and the corresponding floor obtained in real time is negative, a shortening signal is sent to the slope adjustment mechanism. According to the height difference between the elevator and the corresponding floor and the collected initial length of the slope adjustment mechanism, a data calculation model is built to generate an estimated shortening amount L of the slope adjustment mechanism. 短 .

[0037] (III) Beneficial effects

[0038] The present invention provides a method for identifying an elevator non-level door opening fault based on computer vision, which has the following beneficial effects:

[0039] 1. By adopting the infrared detection unit, infrared technology is used to effectively determine the elevator's non-level door opening fault, and combined with the binocular camera unit, stereo vision technology is used to identify the fault information to ensure the accuracy of the height difference between the elevator and the corresponding floor, so as to facilitate the subsequent corresponding instructions according to the situation. When the absolute value of the height difference exceeds the standard threshold, the elevator will be shut down for repair. Otherwise, it can ensure that the elevator can be used for emergency, which reflects the practicality and flexibility of the overall design scheme;

[0040] 2. By using a binocular camera unit and a stereo matching algorithm, the height difference generated when the door is opened at a non-level floor is calculated. A data calculation model is built based on the height difference and the original initial length of the slope adjustment mechanism, and the required estimated lengthening or shortening of the slope adjustment mechanism is generated, so that the longitudinal cylinder in the slope adjustment mechanism can be adjusted quickly and effectively according to the corresponding estimated amount, so that the elevator can be used in an emergency, avoiding the formation of a step surface due to the difference between the elevator and the ground of the corresponding floor, and ensuring the safety of passengers. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flowchart of the overall steps of the method for identifying the non-level door opening fault of the elevator in the present invention;

[0042] Figure 2 It is a schematic diagram of the modular structure of the elevator non-level door opening fault identification system of the present invention;

[0043] Figure 3 It is a schematic diagram of the overall structure of the slope adjustment mechanism in the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0045] Example 1: Please refer to Figure 1-Figure 3 This embodiment provides a method for identifying an elevator non-level door opening fault based on computer vision, and the method includes the following steps:

[0046] S1. Install a slope adjustment mechanism at the bottom of the elevator, and equip an infrared detection unit at a position where the slope adjustment mechanism and the corresponding floor are flush with each other. After the elevator arrives at the corresponding floor, determine whether the infrared signal in the infrared detection unit is received. If the infrared signal can be received, it means that the elevator is running normally and the system does not respond. If the infrared signal cannot be received, it means that the elevator is running abnormally and there is a fault of the elevator opening the door at a non-level floor, and an early warning signal is issued;

[0047] Wherein, the slope adjustment mechanism includes a longitudinal cylinder 101 and a transition plate 102;

[0048] The longitudinal cylinder 101 is installed in the elevator floor, and the longitudinal cylinder 101 is always located below the transition plate 102. The output end of the longitudinal cylinder 101 is hinged to the surface of the transition plate 102. One end of the transition plate 102 is connected to both sides of the inner wall of the elevator floor by setting a rotating shaft, and the other end faces the floor.

[0049] It should be noted that the function of the longitudinal cylinder 101 is to drive the transition plate 102 to rotate so that the transition plate 102 can cope with the state of the elevator door opening at a non-level floor, so that the step surface caused by the height difference between the elevator and the floor can be solved by the transition plate 102 in an inclined state; a number of brushes are also arranged on the end surface of the transition plate 102 facing the floor, which can block the gap between the transition plate 102 and the floor to a certain extent; a groove is provided on the surface of the elevator floor for the transition plate 102 in an unused state to be placed, refer to Figure 3 The state shown in the middle figure;

[0050] The infrared detection unit includes an infrared transmitter and an infrared receiver. The infrared transmitter is arranged on the surface of the corresponding floor, and the infrared receiver is embedded in the end surface of the transition plate 102 facing the floor. Whenever the elevator arrives at the corresponding floor, the infrared transmitter will send out an infrared signal. If the infrared receiver receives the infrared signal, it means that the elevator and the floor are flush with each other, showing Figure 3 If the infrared receiver fails to receive the infrared signal, it means that the elevator and the floor are not flush with each other, which may appear Figure 3 The state shown in the above or below figure is one or two manifestations of the non-level door opening state;

[0051] S2. Upon receiving the warning signal, trigger the binocular camera unit, use stereo vision technology to identify the fault information, and obtain the height difference between the elevator and the corresponding floor;

[0052] The triggered binocular camera unit is a binocular camera installed on the top of the elevator, and the shooting surface of the binocular camera covers the elevator door and the horizontal ground of the floor, and obtains images of the elevator door and the horizontal ground of the floor. The elevator door represents the left image, and the horizontal ground of the stairs represents the right image;

[0053] The process of obtaining the height difference between the elevator and the corresponding floor is as follows:

[0054] Stereo vision matching: stereo matching is performed on the images collected by the binocular camera unit, that is, the corresponding pixel points in the left and right images are matched to obtain the disparity information between them. The disparity information indicates the position difference of the object in the left and right images. The depth information of the corresponding object from the camera in the left and right images is obtained through disparity calculation;

[0055] Common stereo matching algorithms include disparity mapping and block matching;

[0056] Height difference calculation: Calculate the height difference using the depth information obtained from stereo vision;

[0057] The height difference is obtained by calculating the difference between the depth values ​​of the elevator door and the horizontal ground according to the depth information in the left and right images. The formula is:

[0058] hr=S 梯 -S 层

[0059] In the formula, hr represents the height difference, S 梯 Indicates the distance between the binocular camera and the elevator floor, S 层 Indicates the distance between the binocular camera and the ground of the corresponding floor. If hr is a positive number, it means that the elevator door is lower than the ground of the corresponding floor, as shown in the figure below. Figure 3 In the state shown in the figure below, if hr is a negative number, it means that the elevator door is higher than the depth of the corresponding floor, as shown in the figure below. Figure 3 The state shown in the figure above;

[0060] It should be noted that the installation position of the binocular camera needs to take into account the coverage of the viewing angle and the effect of stereo matching; generally speaking, the camera should be installed at an appropriate position inside the elevator to ensure that it can capture images of the elevator door and the horizontal ground of the floor and maintain an appropriate viewing angle;

[0061] For example: Assume that the binocular camera is installed on the upper part of the elevator, facing the elevator door and the horizontal ground. Through stereo matching technology, we can obtain the depth information of the elevator door and the horizontal ground, and calculate the difference in their depth values ​​to get the height difference; for example, the depth value of the elevator door is 1.5 meters, and the depth value of the horizontal ground is 0.8 meters, then the height difference is 0.7 meters.

[0062] If the infrared detection unit in S1 is not used, the horizontal line detection technology can be used in S2 to determine whether the elevator door and the horizontal ground of the floor are on the same horizontal line; in the matched stereo image, the horizontal line can be detected to determine whether the elevator door and the horizontal ground of the floor are on the same horizontal line; the horizontal line detection can be achieved by edge detection and straight line fitting. Common methods include Hough transform and RANSAC algorithm. The horizontal line detection technology is not used in this embodiment to reduce the storage capacity of the binocular camera and ensure that the binocular camera is only used to obtain the height difference between the elevator and the corresponding floor. To a certain extent, the accuracy of the height difference data can be guaranteed;

[0063] It should be noted that stereo matching technology refers to determining the position of an object in three-dimensional space by comparing the disparity information of corresponding pixels in binocular images; the following is a detailed introduction to stereo matching technology:

[0064] Stereo matching algorithm: The stereo matching algorithm aims to find the correspondence between similar pixels in the left and right images. Common algorithms include: window-based block matching, which divides the image into small blocks and finds the correspondence by comparing the similarity between the blocks. Common algorithms include mean difference and normalized cross correlation; local feature-based matching: using local feature descriptors in the image, such as SIFT and SURF, for matching; global optimization-based matching: using global optimization methods, such as dynamic programming and graph cuts, to obtain the best matching results;

[0065] Disparity map: After stereo matching, a disparity map can be obtained, in which each pixel represents the position difference of the corresponding object in the left and right images. The disparity map can intuitively display the depth information of the object;

[0066] Parameter adjustment and optimization: There are many parameters that need to be adjusted in the stereo matching algorithm, such as window size, matching cost function, etc. Adjusting these parameters can affect the accuracy and stability of the matching results;

[0067] Horizontal line detection technology refers to the technology of detecting horizontal lines in an image, which is used to determine whether objects are on the same horizontal line; the following is a detailed introduction to horizontal line detection technology:

[0068] Edge detection: First, perform edge detection on the image to find possible straight line candidates;

[0069] Line detection: Use Hough transform or other line detection algorithms to filter out possible lines from edge detection results;

[0070] Straight line fitting: Fit the detected straight line to obtain more accurate straight line parameters;

[0071] Horizontal line screening: Screen out the straight lines in the horizontal direction, i.e. horizontal lines, according to the slope of the straight line or the angle between the straight line and the horizontal direction;

[0072] Parameter adjustment and optimization: There are also some parameters in the horizontal line detection algorithm that need to be adjusted, such as the threshold of the edge detection algorithm and the accuracy of straight line fitting.

[0073] Specifically, by adopting an infrared detection unit, infrared technology is used to effectively determine the elevator's non-level door opening failure, and combined with a binocular camera unit, stereo vision technology is used to identify fault information to ensure the accuracy of the height difference between the elevator and the corresponding floor, so as to facilitate subsequent corresponding instructions based on the situation. When the absolute value of the height difference exceeds the standard threshold, the elevator will be shut down for repair. Otherwise, the elevator can be used for emergency purposes, which reflects the practicality and flexibility of the overall design scheme.

[0074] S3. Compare the height difference between the obtained elevator and the corresponding floor with the preset standard threshold. If the absolute value of the height difference exceeds the standard threshold, a warning signal is issued and an instruction to shut down for repair is executed; if the absolute value of the height difference does not exceed the standard threshold, an emergency adjustment instruction is triggered to ensure that the current elevator can be used normally.

[0075] The preset standard threshold represents the maximum value of the height difference that the slope adjustment mechanism can handle, and the standard threshold is set based on historical data or actual conditions;

[0076] The warning signal here is issued in a different manner from the above-mentioned early warning signal, and can be issued through the flashing of different indicator lights. For example, the warning signal here can be issued through the flashing of a red warning light, and the early warning signal can be issued through the flashing of a yellow warning light.

[0077] S4. Execute the emergency adjustment command. According to the established rule engine, when it is determined that the height difference between the elevator and the corresponding floor obtained in real time is a positive number, a lengthening signal is sent to the slope adjustment mechanism. When it is determined that the height difference between the elevator and the corresponding floor obtained in real time is a negative number, a shortening signal is sent to the slope adjustment mechanism.

[0078] If an extension signal is received, a data calculation model is built based on the height difference between the elevator and the corresponding floor to generate an estimated extension amount L of the slope adjustment mechanism. 长 If a shortening signal is received, a data calculation model is built based on the height difference between the elevator and the corresponding floor and the collected initial length of the slope adjustment mechanism to generate an estimated shortening amount L of the slope adjustment mechanism. 短 ; The slope adjustment mechanism is based on the estimated elongation L 长 Or shorten the estimated amount L 短 Perform adjustment operations.

[0079] Among them, the estimated extension amount L of the slope adjustment mechanism is generated 长 The formula used is as follows:

[0080]

[0081] Wherein, G is a constant correction coefficient, and its specific value can be adjusted and set by the user, or generated by analytical function fitting, and the value range of G is 0-1, L0 represents the initial length of the slope adjustment mechanism, that is, the initial elongation of the longitudinal cylinder 101 in the slope adjustment mechanism. For example, if the initial length L0 of the slope adjustment mechanism is 5, the height difference hr is also 10, and the value of G is 0.7, then the estimated elongation L of the slope adjustment mechanism is generated. 长It is 4.326, and the unit here is cm, so the estimated elongation of the slope adjustment mechanism is 4.326cm.

[0082] Generate the estimated shortening amount L of the slope adjustment mechanism 短 The formula used to generate the estimated elongation L of the slope adjustment mechanism 长 The formula is the same, because hr 2 The setting makes it possible to shorten the estimated amount L 短 Or the estimated elongation L 长 All are positive numbers;

[0083] It should be noted that the slope adjustment mechanism is based on the estimated elongation L 长 Or shorten the estimated amount L 短 After the adjustment operation, the binocular camera unit can also be used for verification. If an infrared signal is received, it means that the slope adjustment mechanism is adjusted accurately. If no infrared signal is received, it means that the slope adjustment mechanism is adjusted incorrectly, and it is necessary to rebuild the data calculation model and select a different constant correction coefficient G for adjustment until the infrared signal is received.

[0084] Specifically, by using a binocular camera unit and a stereo matching algorithm, the height difference generated when the door is opened on a non-level floor is calculated, and a data calculation model is built based on the height difference and the original initial length of the slope adjustment mechanism, and the required estimated lengthening or shortening of the slope adjustment mechanism is generated, so that the longitudinal cylinder 101 in the slope adjustment mechanism can be adjusted quickly and effectively according to the corresponding estimated amount, so that the elevator can be used in an emergency, avoiding the formation of a step surface due to the difference between the elevator and the ground of the corresponding floor, and ensuring the safety of passengers.

[0085] Example 2: Please refer to Figure 2 , based on Example 1, this embodiment also provides an elevator non-level door opening fault identification system based on computer vision, the system includes a signal judgment module, a fault identification module, a comparison and determination module and an early warning adjustment module;

[0086] Among them, the signal judgment module is equipped with a slope adjustment mechanism at the bottom of the elevator, and an infrared detection unit is installed at a position where the slope adjustment mechanism and the corresponding floor are flush with each other. After the elevator arrives at the corresponding floor, it is judged whether the infrared signal in the infrared detection unit is received. If the infrared signal can be received, no response action is taken; otherwise, an early warning signal is issued;

[0087] The fault identification module triggers the binocular camera unit upon receiving the warning signal, uses stereo vision technology to identify the fault information, and obtains the height difference between the elevator and the corresponding floor;

[0088] The comparison and judgment module compares the height difference between the elevator and the corresponding floor with the preset standard threshold. If the absolute value of the height difference exceeds the standard threshold, a warning signal is issued; otherwise, an emergency adjustment instruction is triggered;

[0089] The early warning adjustment module executes the emergency adjustment command. According to the established rule engine, when it is determined that the height difference between the elevator and the corresponding floor obtained in real time is a positive number, it sends an extension signal to the slope adjustment mechanism. According to the height difference between the elevator and the corresponding floor, a data calculation model is built to generate the estimated extension amount L of the slope adjustment mechanism. 长 ;

[0090] When it is determined that the height difference between the elevator and the corresponding floor obtained in real time is negative, a shortening signal is sent to the slope adjustment mechanism. According to the height difference between the elevator and the corresponding floor and the collected initial length of the slope adjustment mechanism, a data calculation model is built to generate an estimated shortening amount L of the slope adjustment mechanism. 短 .

[0091] In the application, the several formulas involved are all calculated by removing the dimensions and taking their numerical values. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The formula is set by technical personnel in this field according to actual conditions.

[0092] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0093] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0094] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A computer vision-based elevator non-level door opening fault identification method, characterized in that: The steps include: S1. Install a slope adjustment mechanism at the bottom of the elevator, and equip an infrared detection unit at a position where the slope adjustment mechanism and the corresponding floor are flush with each other. After the elevator arrives at the corresponding floor, determine whether the infrared signal in the infrared detection unit is received. If the infrared signal can be received, no response action is taken; otherwise, an early warning signal is issued; S2. Upon receiving the warning signal, trigger the binocular camera unit, use stereo vision technology to identify the fault information, and obtain the height difference between the elevator and the corresponding floor; S3, comparing the height difference between the obtained elevator and the corresponding floor with the preset standard threshold, if the absolute value of the height difference exceeds the standard threshold, a warning signal is issued; otherwise, an emergency adjustment instruction is triggered; S4. Execute the emergency adjustment command. According to the established rule engine, when it is determined that the height difference between the elevator and the corresponding floor obtained in real time is a positive number, an extension signal is sent to the slope adjustment mechanism. According to the height difference between the elevator and the corresponding floor, a data calculation model is established to generate an estimated extension amount L of the slope adjustment mechanism. 长 ; When it is determined that the height difference between the elevator and the corresponding floor obtained in real time is negative, a shortening signal is sent to the slope adjustment mechanism. According to the height difference between the elevator and the corresponding floor and the collected initial length of the slope adjustment mechanism, a data calculation model is built to generate an estimated shortening amount L of the slope adjustment mechanism. 短 The slope adjustment mechanism comprises a longitudinal cylinder (101) and a transition plate (102); the longitudinal cylinder (101) is installed in the elevator floor, and the longitudinal cylinder (101) is always located below the transition plate (102); the output end of the longitudinal cylinder (101) is hinged to the lower surface of the transition plate (102), and one end of the transition plate (102) is connected to both sides of the inner wall of the elevator floor by setting a rotating shaft, and the other end of the transition plate (102) faces the floor; the infrared detection unit comprises an infrared transmitter and an infrared receiver, the infrared transmitter is arranged on the surface of the corresponding floor, and the infrared receiver is embedded in the transition plate (102) In the end surface facing the floor, whenever the elevator arrives at the corresponding floor, the infrared generator sends out an infrared signal. If the infrared receiver receives the infrared signal, it means that the elevator and the floor are flush with each other. If the infrared receiver does not receive the infrared signal, it means that there is a fault that the elevator does not open the door at the same level. The triggered binocular camera unit is a binocular camera installed on the upper part of the elevator, and the shooting surface of the binocular camera covers the elevator door and the horizontal ground of the floor, and the images of the elevator door and the horizontal ground of the floor are obtained. The elevator door represents the left image, and the staircase horizontal ground represents the right image. The process of obtaining the height difference between the elevator and the corresponding floor is as follows: Stereo vision matching: stereo matching is performed on the images collected by the binocular camera unit, that is, the corresponding pixel points in the left and right images are matched to obtain the disparity information between them. The disparity information indicates the position difference of the object in the left and right images. The depth information of the corresponding object from the camera in the left and right images is obtained through disparity calculation; Height difference calculation: The height difference is calculated using the depth information obtained from stereo vision. The height difference is obtained by calculating the difference in depth between the elevator door and the horizontal ground based on the depth information in the left and right images. The formula is: hr=S 梯 -S 层 In the formula, hr represents the height difference, S 梯 Indicates the distance between the binocular camera and the elevator floor, S 层 Represents the distance between the binocular camera and the ground of the corresponding floor. If hr is a positive number, it means that the elevator door is lower than the depth of the ground of the corresponding floor. If hr is a negative number, it means that the elevator door is higher than the depth of the ground of the corresponding floor. The stereo matching algorithm includes any one of parallax mapping and block matching. The preset standard threshold represents the maximum value of the height difference that the slope adjustment mechanism can cope with. The warning signal issued in S3 is expressed differently from the warning signal issued in S1. Generate the estimated extension amount L of the slope adjustment mechanism 长 The formula is as follows: Where G is a constant correction coefficient, and the value range of G is 0 to 1. L0 represents the initial length of the slope adjustment mechanism. The estimated shortening amount L of the slope adjustment mechanism is generated. 短 The formula is as follows: Wherein, G is a constant correction coefficient, and the value range of G is 0 to 1, and L0 represents the initial length of the slope adjustment mechanism.

Images