A platform type elevator safety monitoring method, system, device and medium

Abstract

The application provides a platform type elevator safety monitoring method, system, device and medium, the method comprises the following steps: obtaining the initial image of the elevator platform; obtaining the real-time image in the running process of the elevator platform, identifying the target object according to the real-time image; comparing the real-time image containing the target object with the initial image to determine the position information of the target object in the elevator platform, and controlling the running speed of the elevator platform according to the position information; the method controls the elevator platform through real-time monitoring and image recognition, which is safer than triggering protection when foreign matter touches the platform edge, can brake in advance before the touch occurs, thereby avoiding the danger of platform collision or pinching people, and can be widely applied in the technical field of elevator control.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of elevator control technology, and in particular to a platform type elevator safety monitoring method, system, device and medium. BACKGROUND

[0002] Villa elevators have various structures. Currently, a popular glass shaft platform type villa elevator uses a frame structure of a glass shaft, and a car uses a non-closed platform structure. When a user rides the elevator, the user can conveniently observe the changes in the environment around the user. Such a structure is not only beautiful and fashionable, but also can improve the space utilization rate of the car. However, the platform and the glass shaft are in a state of relative motion during platform operation. If a user touches the glass wall at this time, the user is easily pulled by the glass wall and is in danger of colliding with the platform or flying.

[0003] However, in the related technical solution, the platform ladder anti-pinch technology is to install an elastic mechanical switch around the platform. When a foreign object touches the edge of the platform, the protection is triggered. However, the platform and the foreign object cannot be collided or the danger of pinching a person is not predicted in advance. SUMMARY

[0004] Therefore, in order to at least partially solve one of the above technical problems or defects, the purpose of the embodiments of the present application is to provide a platform type elevator safety monitoring method which is safer and can realize early warning of danger. In addition, the embodiments also provide a system, a device and a storage medium which can realize the method.

[0005] In one aspect, the technical solution of the present application provides a platform type elevator safety monitoring method, including the following steps:

[0006] An initial image of an elevator platform is acquired.

[0007] A real-time image during operation of the elevator platform is acquired, and target identification is performed according to the real-time image to determine a target object.

[0008] The real-time image containing the target object is compared with the initial image to determine position information of the target object in the elevator platform, and the running speed of the elevator platform is controlled according to the position information.

[0009] In one feasible embodiment of the present application, the area of the elevator platform includes a platform area, a boundary area and a safety area. The real-time image containing the target object is compared with the initial image to determine the position information of the target object in the elevator platform, and the running speed of the elevator platform is controlled according to the position information, including at least one of the following steps:

[0010] determining that the target object falls into the safety area, controlling the elevator platform to run at a first speed;

[0011] determining that the target object exceeds the safety area and does not exceed the boundary area, controlling the elevator platform to run at a reduced speed;

[0012] determining that the target object exceeds the boundary area, controlling the elevator platform to stop running.

[0013] In an embodiment of the present application, the initial image of the elevator platform is obtained by:

[0014] acquiring monitoring pictures of the elevator platform through at least one shooting angle;

[0015] merging a plurality of monitoring pictures according to the shooting angle and the angle of view range of the monitoring pictures to obtain the initial image.

[0016] In an embodiment of the present application, the initial image of the elevator platform is obtained by:

[0017] determining the safety area according to the platform area of the elevator platform and the gap between the elevator platform and the vertical plane;

[0018] determining the platform area according to the safety area and a first preset distance;

[0019] determining the boundary area as the area range between the safety area and the platform area.

[0020] In an embodiment of the present application, the real-time image during the running of the elevator platform is obtained, and target recognition is performed according to the real-time image to determine a target object, comprising:

[0021] performing gray scale processing on the real-time image to obtain a first gray scale value image;

[0022] performing filtering processing on the first gray scale value image, and performing edge detection on the filtered first gray scale value image to obtain edge information of the target object;

[0023] obtaining the target object according to the edge information.

[0024] In an embodiment of the present application, the real-time image containing the target object is compared with the initial image to determine the position information of the target object in the elevator platform, and the running speed of the elevator platform is controlled according to the position information, further comprising:

[0025] performing gray scale processing on the initial image to obtain a second gray scale value image;

[0026] The first gray value image containing the edge information is subjected to edge detection with the second gray value image to determine the position information of the edge information.

[0027] In an available embodiment of the present application, the filtering processing is performed on the first gray value image, and the edge information of the target object is obtained by performing edge detection on the filtered first gray value image.

[0028] The first gray value image is subjected to filtering and noise reduction processing to obtain an intermediate state image.

[0029] The gradient amplitude and gradient direction of the intermediate state image are determined by a Sobel operator.

[0030] The non-maximum suppression processing is performed according to the gradient amplitude and gradient direction to obtain a binary image, and the edge information is determined according to the binary image.

[0031] On the other hand, the present application also provides a platform type elevator safety monitoring system, which comprises:

[0032] An initial image acquisition unit is configured to acquire an initial image of an elevator platform.

[0033] A real-time image acquisition unit is configured to acquire a real-time image during operation of the elevator platform, and to perform target recognition to determine a target object according to the real-time image.

[0034] A monitoring control unit is configured to compare the real-time image containing the target object with the initial image to determine position information of the target object in the elevator platform, and to control the operation speed of the elevator platform according to the position information.

[0035] On the other hand, the present application also provides a platform type elevator safety monitoring device, which comprises:

[0036] At least one processor;

[0037] At least one memory configured to store at least one program;

[0038] When the at least one program is executed by the at least one processor, the at least one processor is caused to perform a platform type elevator safety monitoring method according to any one of the first aspect.

[0039] On the other hand, the present application also provides a storage medium having a processor executable program stored therein, and the processor executable program is configured to perform a platform type elevator safety monitoring method according to any one of the first aspect when executed by a processor.

[0040] The advantages and beneficial effects of the present application will be partially given in the following description, and others can be understood by the specific embodiments of the present application:

[0041] The technical scheme of the present application provides a platform type elevator safety monitoring method, system, device and medium. The method compares the initial monitoring image when the elevator is not running with the image obtained by real-time monitoring during operation, identifies the target object on the elevator platform during real-time operation, determines the position of the target object on the elevator platform, and then determines the possible safety hazards caused by the target object according to the position of the target object, so as to control the running state of the elevator. The method controls the elevator platform through real-time monitoring and image recognition, which is safer than triggering protection when the foreign matter touches the edge of the platform, and can brake in advance before the touch occurs, thereby avoiding the danger of platform collision or pinching people. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0043] Figure 1 The step flow chart of a platform type elevator safety monitoring method provided in the technical scheme of the present application;

[0044] Figure 2 The area division schematic diagram of the elevator platform in the initial image in the technical scheme of the present application;

[0045] Figure 3 The schematic diagram of image synthesis in the technical scheme of the present application;

[0046] Figure 4 The step flow chart of image area setting in the technical scheme of the present application;

[0047] Figure 5 The step flow chart of another platform type elevator safety monitoring method provided in the technical scheme of the present application. DETAILED DESCRIPTION

[0048] Embodiments of the present application are described below in detail, examples of which are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only, for the purpose of explanation, and are not to be understood as a limitation of the present application. For the step numbers in the following embodiments, they are only set for the convenience of explanation, and no limitation is made on the order between the steps, and the execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0049] First, some technical terms in the technical solutions of the present application are explained:

[0050] In related technical solutions, the existing platform ladder anti-pinch technology can only detect whether there is foreign matter blocking between the platform and the glass wall, and there is no method to prevent the platform from pinching people in advance, and only when the accident occurs can the device stop the elevator, resulting in user personal and property losses.

[0051] Therefore, in the first aspect, the technical solutions of the present application propose a platform elevator safety monitoring method, which can define the safety area and the boundary area of the platform through the intelligent monitoring device, when the object is in the safety area, the elevator runs at normal speed, when the object is in the boundary area, the elevator reduces the running speed, when the object exceeds the boundary area and goes out, the elevator immediately stops running, thereby avoiding the danger of platform collision or pinching people; as shown in Figure 1 The method comprises steps S100-S300:

[0052] S100, acquiring an initial image of the elevator platform;

[0053] Specifically, in the embodiments, the intelligent monitoring device can be installed on the top of the elevator platform, and the images around the platform can be acquired through multiple cameras, and the intelligent monitoring device can intercept and merge the images collected by the cameras into one image according to the area angle set by each camera. In the embodiments, the monitoring screen of the elevator platform at a certain moment can also be selected as the initial image in the embodiments by the self-defined selection method.

[0054] More specifically, as shown in Figure 2 In the embodiments, the platform area 201, the boundary area 202 and the safety area 203 of the elevator platform can be determined in the initial image. In the embodiments, the platform area can be set in the initial image by acquiring the user instruction, and the safety area can be set in the platform area, and the boundary area can be continuously set, and after the setting is completed, the save operation can be clicked, and the intelligent monitoring device starts running and protection according to the initial image, the boundary area and the safety area set by the user.

[0055] S200, acquiring a real-time image in the running process of the elevator platform, and identifying a target object according to the real-time image;

[0056] In specific embodiments, the target object can be identified by target recognition or related target detection methods according to real-time monitoring of the running process of the elevator platform.

[0057] S300, comparing the real-time image containing the target object with the initial image to determine position information of the target object in the elevator platform, and controlling the running speed of the elevator platform according to the position information;

[0058] In specific embodiments, after determining that an object enters the platform during the running process of the elevator platform, the monitoring device can identify the contour of the target object by comparing the current image with the initial image. Further, a signal or instruction for controlling the running state of the elevator is triggered according to the position of the target object in the elevator platform, and the running speed of the elevator platform is controlled and adjusted.

[0059] In some possible embodiments, based on the premise that the elevator platform is divided into a platform region, a boundary region and a safety region in the initial image, the step S300 of comparing the real-time image containing the target object with the initial image to determine the position information of the target object in the elevator platform, and controlling the running speed of the elevator platform according to the position information can include steps S310-S330:

[0060] S310, determining that the target object falls into the safety region, and controlling the elevator platform to run at a first speed;

[0061] S320, determining that the target object exceeds the safety region but does not exceed the boundary region, and controlling the elevator platform to run at a reduced speed;

[0062] S330, determining that the target object exceeds the boundary region, and controlling the elevator platform to stop running;

[0063] In specific embodiments, during the comparison between the initial image and the real-time image, when the object is in the safety region, the monitoring device sends a normal use signal to the elevator control system, and the elevator control system controls the elevator to run at a normal speed. When the object exceeds the safety region to the boundary region, the monitoring device sends a reduced speed running signal to the elevator control system, and the elevator control system controls the elevator to run at a reduced speed. When the object exceeds the boundary region, the monitoring device sends a stop running signal to the elevator control system, and the elevator control system controls the elevator to stop running.

[0064] In some feasible implementations, the step S100 of acquiring the initial image of the elevator platform in the embodiment method may include steps S110-S120:

[0065] S110. Acquire monitoring footage of the elevator platform from at least one shooting angle;

[0066] S120. The initial image is obtained by merging several monitoring images according to the shooting angle and the viewing angle range of the monitoring image.

[0067] For example, such as Figure 3 As shown, the intelligent monitoring device in this embodiment can be installed on the top of the elevator platform and can acquire images of the platform's surroundings through three cameras. The three cameras are respectively installed at the east, south, and west positions on the top of the platform. The intelligent monitoring device will crop and merge the images captured by the cameras into a single image at a 120° angle for each area.

[0068] In some feasible embodiments, the step S100 of acquiring the initial image of the elevator platform in the embodiment method may further include a process of setting the platform area, boundary area, and safety area of ​​the elevator platform. This setting process may include steps S130-S150:

[0069] S130. Determine the safety zone based on the platform area of ​​the elevator platform and the gap between the elevator platform and the vertical plane;

[0070] S140. Determine the platform area based on the safety zone and the first preset distance;

[0071] S150. The area between the security area and the platform area is defined as the boundary area.

[0072] Specifically, in this embodiment, the current image can be set as the initial image via software. After setting, the platform area, safety area, and boundary area are drawn on the image. After setting, click "Save and Run". For example, as shown... Figure 4 As shown, in one embodiment, the platform area in the initial image should include the entire elevator platform and the gap between the elevator platform and the glass wall. The safety area should be within the platform area, with the boundary of the safety area being 30–100 mm from the boundary of the platform area. The boundary area should be the unincluded zone between the platform area and the safety area, defined as the area between the boundary of the safety area and the boundary of the boundary area. The boundary of the boundary area should be ≥20 mm from the boundary of the safety area and ≥10 mm from the boundary of the platform area.

[0073] In some possible embodiments, the step S200 of acquiring real-time images in the running process of the elevator platform in the embodiment method, and determining the target object according to the real-time images, can include steps S210-S230.

[0074] S210, performing gray processing on the real-time images to obtain a first gray value image;

[0075] S220, performing filtering processing on the first gray value image, and performing edge detection on the filtered first gray value image to obtain edge information of the target object;

[0076] S230, obtaining the target object according to the edge information.

[0077] Specifically, in the embodiment, after the real-time images in the running process of the elevator platform are acquired, the real-time images are subjected to gray processing, so that the apparent characteristics (such as color distribution, overall brightness, size, etc.) of each image are as consistent as possible without changing the essential information carried by the images; in some necessary implementation environments, operations such as analog-digital conversion, filtering, blur elimination, noise reduction, and geometric distortion correction can be performed. After the radian processing, the gray image is subjected to filtering processing to simplify the image information, and the edge line is used to represent the information carried by the image. Then, the pixels in the gray image are subjected to gradient operation through an edge detection operator, and then based on the gradient graphs of the X and Y axes obtained after the gradient operation, an edge graph is integrated to determine the edge of the target object based on the information in the edge graph, so as to complete the identification of the target object.

[0078] In some optional embodiments, the step S300 of comparing the real-time images containing the target object with the initial images in the embodiment method, determining the position information of the target object in the elevator platform, and controlling the running speed of the elevator platform according to the position information can further include steps S301-S302.

[0079] S301, performing gray processing on the initial images to obtain a second gray value image;

[0080] S302, performing edge detection on the first gray value image containing the edge information and the second gray value image to determine the position information of the edge information;

[0081] Specifically, in the embodiment, the intelligent monitoring device first performs gray processing on the current image and the initial image to obtain the gray value images of the current image and the initial image, then filters the gray value of the current image according to the gray value of the initial image, so as to obtain the filtered image, and then performs filtering and edge detection processing on the image, so as to obtain the contour image of the object.

[0082] It should be noted that the high-definition camera used in the embodiment can obtain clearer images, and the image has more pixels, and the smart monitoring device can capture smaller objects such as fingers and pet leashes.

[0083] In some possible embodiments, the edge detection operator used in the identification process of the target object is a Canny operator; and the step S220 of filtering the first gray value image and performing edge detection on the filtered first gray value image to obtain the edge information of the target object in the embodiment can include steps S221-S223.

[0084] S221, filtering and denoising the first gray value image to obtain an intermediate state image;

[0085] S222, determining the gradient amplitude and gradient direction of the intermediate state image by using a Sobel operator;

[0086] S223, performing non-maximum suppression processing according to the gradient amplitude and the gradient direction to obtain a binary image, and determining the edge information according to the binary image;

[0087] In particular, in the embodiment, due to various reasons such as the acquisition device, environmental interference and the like, the collected image information contains a large amount of noise information, and the most common noise is salt and pepper noise and Gaussian noise. Therefore, the embodiment uses Gaussian filtering to remove noise. On the basis of the image after removing noise, the embodiment uses a first-order finite difference to calculate the gradient to obtain two matrices of partial derivatives of the image in x and y directions, and the embodiment can use a Sobel operator to calculate the amplitude and direction of the gradient. Then, the non-maximum value data is suppressed, which can also be understood as excluding the possibility that the non-maximum value data is an edge. The greater the element value in the image gradient amplitude matrix in the neighborhood, the greater the gradient value of the point in the image, and in combination with the gradient direction of the detection point, the approximate edge information can be located.

[0088] The specific implementation of the embodiment of the present application is described as follows: Figure 5 The specific implementation of the embodiment of the present application is described as follows:

[0089] In the embodiment, the smart monitoring device is installed on the top of the platform, and three cameras are used to obtain images around the platform. The three cameras are installed at the east, south and west of the top of the platform, and the smart monitoring device intercepts and merges the images collected by the cameras into one image according to each region of 120°. Then, the software sets the current image as the initial image, and after setting, draws the platform region, the safe region and the boundary region on the image, and after setting, clicks to save and run. The platform region should include the entire platform and the gap between the platform and the glass wall.

[0090] The safety area should be within the platform area, and the distance between the boundary of the safety area and the boundary of the platform area should be 30-100 mm. The boundary area should be in the uncontained zone between the platform area and the safety area, and the boundary area is the area between the boundary of the safety area and the boundary of the boundary area, and the distance between the boundary of the boundary area and the boundary of the safety area should be ≥20 mm, and the distance from the platform area boundary should be ≥10 mm. The intelligent monitoring device starts running and protection according to the initial image, platform area, boundary area and safety area set by the user.

[0091] When an object enters the elevator platform, the monitoring device can identify the outline of the object according to the comparison between the current image and the initial image. The intelligent monitoring device first performs grayscale processing on the current image and the initial image to obtain the grayscale value images of the current image and the initial image, then filters the grayscale value of the current image according to the grayscale value of the initial image, that is, the filtered image is obtained, and then the image is filtered and edge detection processing is performed, that is, the outline image of the object is obtained. Using a high-definition camera can obtain clearer images with more pixels, and through the intelligent monitoring device, smaller items such as fingers, pet leashes, etc. can be captured.

[0092] When the object is in the safety area, the monitoring device sends a normal use signal to the elevator control system, and the elevator control system controls the elevator to run at normal speed. When the object is in the boundary area beyond the safety area, the monitoring device sends a deceleration running signal to the elevator control system, and the elevator control system controls the elevator to run at a reduced speed. When the object exceeds the boundary area, the monitoring device sends a stop running signal to the elevator control system, and the elevator control system controls the elevator to stop running. The intelligent monitoring device avoids the danger of platform collision or pinching of the object by judging the position area of the object, and protects the personal and property safety of the user in advance.

[0093] On the other hand, the embodiment of the present application also provides a platform type elevator safety monitoring system, which comprises:

[0094] An initial image acquisition unit is configured to acquire an initial image of an elevator platform.

[0095] A real-time image acquisition unit is configured to acquire a real-time image during the running of the elevator platform, and to perform target recognition to determine a target object according to the real-time image.

[0096] A monitoring control unit is configured to compare the real-time image containing the target object with the initial image, to determine the position information of the target object in the elevator platform, and to control the running speed of the elevator platform according to the position information.

[0097] Specifically in the embodiment, the initial image acquisition unit and the real-time image acquisition unit jointly constitute the intelligent monitoring device, which is connected with the monitoring control unit through CAN communication, and the monitoring control unit controls the elevator operation and speed according to the signal of the intelligent monitoring device. In addition, the intelligent monitoring device can be connected with the intelligent monitoring device through WIFI, and the image information of the intelligent monitoring device is obtained by using software.

[0098] In another aspect, the technical scheme of the present application also provides a platform type elevator safety monitoring device; it comprises:

[0099] At least one processor; at least one memory for storing at least one program; when the at least one program is executed by the at least one processor, the at least one processor runs the platform type elevator safety monitoring method in the first aspect.

[0100] The embodiment of the present application also provides a storage medium which stores a corresponding execution program, and the program is executed by a processor to realize the platform type elevator safety monitoring method in the first aspect.

[0101] From the above specific implementation process, it can be concluded that the technical scheme provided by the present application has the following advantages or advantages compared with the prior art:

[0102] 1. The embodiment of the present application is beneficial to avoid platform collision or danger of pinching in advance, and protects the personal and property safety of the user.

[0103] 2. The embodiment of the present application detects objects by image recognition method, and can detect small articles such as fingers, pet leading ropes, etc., and has higher recognition accuracy and sensitivity.

[0104] 3. The system structure provided by the embodiment of the present application is simple to debug and easy to install and use.

[0105] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features can be integrated in a single physical device and / or software module, or one or more functions and / or features can be realized in separate physical devices or software modules. It can also be understood that detailed discussion about the actual implementation of each module is unnecessary for understanding the present application. Rather, given the properties, functions and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the routine skill of an engineer. Therefore, those skilled in the art can implement the present application as set forth in the claims using ordinary skill without undue experimentation. It can also be understood that the disclosed specific concepts are merely illustrative and are not intended to limit the scope of the present application, the scope of the present application being determined by the full scope of the appended claims and their equivalents.

[0106] The logic and / or steps represented in flow diagrams or otherwise described herein, for example, can be considered as a sequence of executable instructions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions, or a combination thereof.

[0107] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Also, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in an appropriate manner.

[0108] Although the embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions, and alterations can be made hereto without departing from the principles and spirit of the application, and the scope of the present application is defined by the claims and their equivalents.

[0109] The above is a specific description of the preferred embodiments of the present application, but the present application is not limited to the above-described embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present application, and these equivalent modifications or substitutions are included in the scope defined by the claims of the present application.

Claims

1. A platform type elevator safety monitoring method, characterized by, The method comprises the following steps: obtaining an initial image of an elevator platform, including: selecting a monitoring picture of the elevator platform at a certain time as the initial image by a self-defined selection manner; the area of the elevator platform includes a platform area, a boundary area and a safety area; setting the platform area in the initial image by obtaining a user instruction, and setting the safety area in the platform area, and continuing to set the boundary area; obtaining a real-time image during the operation of the elevator platform, and determining a target object according to the real-time image, including: performing gray processing on the real-time image to obtain a first gray value image; performing filtering processing on the first gray value image, and performing edge detection on the filtered first gray value image to obtain edge information of the target object, including: performing filtering and noise reduction processing on the first gray value image to obtain an intermediate state image; determining the gradient amplitude and gradient direction of the intermediate state image by a Sobel operator; performing non-maximum suppression processing according to the gradient amplitude and the gradient direction to obtain a binary image, and determining the edge information according to the binary image; determining the target object according to the edge information, including: performing gradient operation on pixels in the gray image by an edge detection operator, then integrating the X and Y axis gradient graphs obtained after the gradient operation to obtain an edge graph, and determining the edge of the target object based on the information in the edge graph to complete the identification of the target object; comparing the real-time image containing the target object with the initial image to determine the position information of the target object in the elevator platform, and controlling the running speed of the elevator platform according to the position information, including at least one of the following steps: determining that the target object falls into the safety area, and controlling the elevator platform to run at a first speed; determining that the target object exceeds the safety area but does not exceed the boundary area, and controlling the elevator platform to run at a reduced speed; determining that the target object exceeds the boundary area, and controlling the elevator platform to stop running; The method for obtaining an initial image of an elevator platform further comprises: determining the safety area according to the platform area of the elevator platform and the gap between the elevator platform and the vertical plane; determining the platform area according to the safety area and a first preset distance; determining the range of the area between the safety area and the platform area as the boundary area; The platform area includes the entire platform and the gap between the platform and the glass wall.

2. A platform elevator safety monitoring method according to claim 1, characterized in that, The method for obtaining an initial image of an elevator platform comprises: acquiring monitoring pictures of the elevator platform through at least one shooting angle; merging a plurality of monitoring pictures to obtain the initial image according to the shooting angle and the viewing angle range of the monitoring pictures.

3. The method of claim 1, wherein the method further comprises: The method for comparing the real-time image containing the target object with the initial image to determine the position information of the target object in the elevator platform, and controlling the running speed of the elevator platform according to the position information further comprises: performing gray processing on the initial image to obtain a second gray value image; The first gray value image containing the edge information is subjected to edge detection with the second gray value image to determine the position information of the edge information.

4. A platform elevator safety monitoring system for implementing the method according to any one of claims 1 to 3, characterized by The method comprises the following steps: An initial image acquisition unit is configured to acquire an initial image of an elevator platform, including: selecting a monitoring picture of the elevator platform at a certain time as the initial image by a self-defined selection manner; the area of the elevator platform includes a platform area, a boundary area, and a safety area; The platform area is set in the initial image by acquiring a user instruction, and the safety area is set in the platform area, and the boundary area is continuously set; A real-time image acquisition unit is configured to acquire a real-time image during the operation of the elevator platform, and to determine a target object by target recognition based on the real-time image, including: A first gray value image is obtained by performing gray processing on the real-time image; The first gray value image is subjected to filtering processing, and the filtered first gray value image is subjected to edge detection to obtain edge information of the target object, including: An intermediate state image is obtained by performing filtering and noise reduction processing on the first gray value image; The gradient amplitude and gradient direction of the intermediate state image are determined by a Sobel operator; A binary image is obtained by performing non-maximum suppression processing based on the gradient amplitude and gradient direction, and the edge information is determined based on the binary image; The target object is determined based on the edge information, including: An edge detection operator is used to perform gradient operation on pixels in a gray image, and then based on the X and Y axis gradient graphs obtained after the gradient operation, an edge graph is integrated to determine the edge of the target object, thereby completing the recognition of the target object; A monitoring control unit is configured to compare the real-time image containing the target object with the initial image to determine the position information of the target object in the elevator platform, and to control the running speed of the elevator platform based on the position information, including at least one of the following steps: If the target object falls entirely into the safety area, the elevator platform is controlled to run at a first speed; If the target object exceeds the safety area but does not exceed the boundary area, the elevator platform is controlled to run at a reduced speed; If the target object exceeds the boundary area, the elevator platform is controlled to stop running; The initial image of the elevator platform further comprises: The safety area is determined based on the platform area of the elevator platform and the gap between the elevator platform and the vertical plane; The platform area is determined based on the safety area and a first preset distance; The area range between the safety area and the platform area is determined as the boundary area; The platform area includes the entire platform and the gap between the platform and the glass wall.

5. A platform elevator safety monitoring device, characterized in that The method comprises the following steps: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor executes a platform elevator safety monitoring method according to any one of claims 1-3.

6. A storage medium having stored therein a program that is executable by a processor, characterized by The program executable by the processor, when executed by the processor, is used to run the platform type elevator safety monitoring method as claimed in any one of claims 1-3.

Images