Door opening degree detection method and device and storage medium

Abstract

The invention provides a door opening degree detection method and device and a storage medium, a depth sensor is arranged on a door of an elevator, and the top of the door of the elevator is divided into a plurality of intervals in the opening and closing direction; the method comprises the steps that when a depth sensor collects depth image data from a door of an elevator, depth values of pixel points in the depth image data are converted into height values; writing the pixel points into the interval according to the height value; identifying index points representing the side surface of the door of the elevator according to the pixel points in each section; two index points which are symmetrical about a door of the elevator and are flush with the height are screened out to serve as a candidate point set; performing speed verification on the candidate point group to obtain a target point group; and the opening degree of the door of the elevator is determined according to the interval mapped by the two index points in the target point set. According to the embodiment, the opening degree of the door of the elevator is continuously and stably detected according to factors such as symmetry, height and speed for the depth image data, the interference of a user entering and exiting the elevator is effectively reduced, and the accuracy of detecting the opening degree of the door of the elevator is improved.

Description

Technical Field

[0001] This invention belongs to the technical field of elevators, and in particular relates to a method, device and storage medium for detecting door opening degree. Background Technology

[0002] In residential buildings, shopping malls, office buildings and other buildings, elevators are one of the most commonly used vertical transportation tools. When the elevator stops at different floors, the elevator door is controlled to open and close, and the opening degree of the elevator door is detected so that users can safely enter and exit the elevator.

[0003] Currently, one method for detecting elevator door opening is to use a depth sensor to detect the edge of the elevator door frame and calculate the elevator door opening based on the edge of the elevator door frame.

[0004] However, as elevator doors open and close, users often enter and exit, which can obstruct the depth sensor signal, resulting in lower accuracy in detecting the elevator door's opening degree. This affects the elevator door's opening and closing logic and poses a safety risk. Summary of the Invention

[0005] In view of this, the present invention provides a method, device and storage medium for detecting door opening degree, so as to improve the accuracy of detecting elevator door opening degree.

[0006] A first aspect of the present invention provides a method for detecting door opening degree, wherein a depth sensor is installed on an elevator door, and the top of the elevator door is divided into multiple sections along the opening / closing direction; the method includes: When the depth sensor collects depth image data from the elevator door, the depth value of the pixel in the depth image data is converted into a height value; The pixel is written into the interval according to the height value; Based on the index point representing the side of the elevator door within the interval; Two index points that are symmetrical about the elevator door and at the same height are selected as candidate point groups; The candidate point group is subjected to velocity verification to obtain the target point group; The opening degree of the elevator door is determined based on the interval mapped by the two index points in the target point group.

[0007] A second aspect of the present invention provides a door opening detection device. A depth sensor is installed on the elevator door, and the top of the elevator door is divided into multiple sections along the opening / closing direction; the device includes: A depth image conversion module is used to convert the depth values ​​of pixels in the depth image data into height values ​​when the depth sensor collects depth image data from the elevator door. A pixel division module is used to write the pixel into the interval according to the height value; An index point recognition module is used to identify index points representing the sides of the elevator doors within the interval. The candidate point group filtering module is used to filter out two index points that are symmetrical about the elevator door and are at the same height as the candidate point group. The target point group verification module is used to perform velocity verification on the candidate point group to obtain the target point group. The door opening determination module is used to determine the door opening of the elevator based on the interval mapped by the two index points in the target point group.

[0008] A third aspect of the present invention provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the door opening detection method as described in the first aspect above.

[0009] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the door opening detection method as described in the first aspect above.

[0010] A fifth aspect of the present invention provides a computer program product that, when run on a computer, causes the computer to perform the door opening detection method as described in the first aspect above.

[0011] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: In this embodiment, a depth sensor is installed on the elevator door, and the top of the elevator door is divided into multiple sections along the opening / closing direction. When the depth sensor collects depth image data from the elevator door, the depth values ​​of the pixels in the depth image data are converted into height values. Pixels are written into sections based on their height values. Index points representing the sides of the elevator door are identified based on the pixels in each section. Two index points that are symmetrical about the elevator door and aligned with its height are selected as candidate point groups. The candidate point groups are then subjected to speed verification to obtain target point groups. The opening degree of the elevator door is determined based on the section mapped by the two index points in the target point group. This embodiment continuously and stably detects the opening degree of the elevator door based on factors such as symmetry, height, and speed of the depth image data, effectively reducing interference from users entering and exiting the elevator and improving the accuracy of detecting the opening degree of the elevator door. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of a door opening detection method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the door division section of an elevator provided by an embodiment of the present invention; Figure 3 This is a schematic diagram of the field of view of a depth sensor provided in an embodiment of the present invention; Figure 4 This is a side view of an elevator door provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of a door opening detection device provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0014] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the present invention. However, those skilled in the art will recognize that the present application may be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted to avoid unnecessary detail that could obscure the description of the present application.

[0015] The technical solution of the present invention will be illustrated below through specific embodiments.

[0016] Reference Figure 1 The diagram illustrates a door opening detection method provided by an embodiment of the present invention, which may specifically include the following steps: Step 101: When the depth sensor collects depth image data from the elevator door, convert the depth value of the pixel in the depth image data into a height value.

[0017] Different types of buildings, especially high-rise buildings, have different transportation needs for people, pets, and goods. Therefore, different types of elevators can be deployed in buildings according to different transportation needs, such as passenger elevators, freight elevators, sightseeing elevators, etc. This embodiment does not impose any restrictions on this.

[0018] The structure of elevators also varies among different types of elevators.

[0019] In one example, the components of a certain type of elevator include an elevator control system, car, traction machine, control cabinet, speed governor, door operator, car frame, car door, counterweight guide rail, car guide rail, guide rail support, traveling cable, counterweight device, compensating chain (cable), landing door, guide device for compensating chain (cable), buffer, etc.

[0020] In some types of elevators, the traction machine, control cabinet, speed governor, traveling cable, etc., can be omitted.

[0021] These devices can be divided into different sets according to their functions, thus forming various subsystems that support the operation of the elevator. The elevator control system is connected to the multiple systems of the elevator via wired means such as serial port or serial clock line (SCL). The elevator control system monitors each system and controls the operation of each subsystem, so that the car moves in the hoistway and reaches each floor of the building.

[0022] In one example, the elevator control system includes a door system, a frequency converter system, a call system, and a traction system. The door system controls the elevator doors. The car is equipped with a car door, and the elevator has hall doors on each floor. That is, the elevator doors include the car door and the hall doors on each floor. Both the car door and the hall door have two doors, which open to both sides and close to the middle simultaneously. The frequency converter system controls the frequency converter. The call system controls the logic of internal call (calling the elevator from inside the car) and external call (calling the elevator from the hall). The traction system controls the car to move vertically (vertically upward or vertically downward) in the hoistway.

[0023] Elevator managers or owners can choose whether to install edge computing nodes on the elevator based on factors such as the elevator's load status. If they choose not to install edge computing nodes, the elevator control system will maintain its original control logic and will not affect the normal operation of the elevator. If they choose to install edge computing nodes, they can select appropriate computing devices as side computing nodes for the elevator according to their needs. The edge computing nodes and the original elevator control system will be combined to form a new elevator control system and redefine the elevator's control logic.

[0024] Generally, edge computing nodes are computing devices with strong computing capabilities, such as computers, servers, or embedded devices. In addition, depending on the different intelligent services, edge computing nodes can be equipped with graphics processing units (GPUs) or embedded neural network processors (NPUs).

[0025] Edge computing nodes refer to new business platforms built at the network edge near elevators, providing storage, computing, and network resources. This allows some critical business applications to be offloaded to the edge of the access network, reducing bandwidth and latency losses caused by network transmission and multi-level forwarding. Located between the user and the cloud (server), edge computing nodes are closer to the user (data source) than traditional cloud computing. They are characterized by miniaturization, distribution, and closer proximity to the user. Massive amounts of data (such as audio data) no longer need to be uploaded to the cloud for processing; data processing can be achieved at the network edge, reducing request response time, reducing network bandwidth, and ensuring data security and privacy.

[0026] In addition, edge computing nodes can realize algorithm functions and model inference, communicate with the original elevator control system, and provide the original elevator control system with artificial intelligence (AI) and complex computing capabilities; edge computing can also communicate with the cloud to realize algorithm functions and model updates, and relay the original elevator control system's function calls, etc.

[0027] In this embodiment, a depth sensor, such as a TOF (Time of Flight) sensor, can be installed on the elevator door (e.g., the center of the beam above the car door). The depth sensor's field of view faces downwards, and the car door and hall door are visible within the depth sensor's field of view.

[0028] Under normal circumstances, the car door and the hall door open and close simultaneously. Moreover, the hall door has a larger visible area under the car door's line of sight. Therefore, the opening degree of the hall door can be detected separately.

[0029] Of course, in addition to detecting the opening of the hall door separately, the opening of the car door can also be detected separately, or the opening of the hall door and the car door can be detected together, etc. This embodiment does not limit this.

[0030] Once the depth sensor is installed, the location of the elevator door can be marked in the depth image data collected by the depth sensor to obtain the detection frame.

[0031] If the elevator is detected to be either open or closed, the depth sensor can be used to collect raw depth image data downwards. Pixels located within the detection frame are extracted from the raw depth image data to obtain partial depth image data collected facing the elevator door. At this point, using the floor or other planes on the current floor as a reference plane, the depth values ​​of the pixels in this partial depth image data are converted into height values, thereby converting this partial depth image data into point cloud data.

[0032] Step 102: Write the pixels into the range based on the height value.

[0033] like Figure 2As shown, in the downward field of view of the depth sensor, that is, looking down at the top of the elevator door 200, the top of the elevator door 200 is divided into multiple sections 201 along the opening and closing direction (that is, the direction of opening the elevator door and the direction of closing the elevator door).

[0034] In this section, each section 201 is supported by the center line 202 at the top of the elevator door 201, and the lengths of each section 201 may be equal or unequal.

[0035] For example, if the top of the elevator door is 70cm long in the opening and closing direction, it can be divided into 70 sections with 1cm intervals.

[0036] In this embodiment, if the X and Y coordinates of a pixel fall within the range of the interval, the height value of the pixel can be used to determine whether the pixel falls within the effective detection range on the Z axis. If the pixel falls within the effective detection range on the Z axis, the pixel is written into the interval to filter out some noise.

[0037] In specific implementations, such as Figure 3 As shown, the field of view of the depth sensor 301 is high in the middle and low on both sides, with a certain blind zone. The height range of each interval can be marked according to the field of view of the depth sensor, and the height range represents the effective detection range.

[0038] The height range includes the upper and lower limits of the elevator door height under the field of view of the depth sensor, with a preset distance (e.g., 400mm) between the upper and lower limits. In this case, the height range (effective detection range) represents the top area of ​​the elevator door, which can filter out the point cloud data (i.e., noise) generated when the user passes through the elevator door to enter or exit the elevator car.

[0039] Then, the height range associated with each interval can be queried. For the same interval, the height value corresponding to the pixel point whose X coordinate and Y coordinate fall within the range of the interval is compared with the height range corresponding to that interval.

[0040] If the height value is within the height range, it means that the pixel may belong to the elevator door, so the pixel is written into the range.

[0041] If the height value is outside the height range, it indicates that the pixel may be noise, and the pixel should be ignored.

[0042] Step 103: Identify the index point representing the side of the elevator door within the interval.

[0043] like Figure 4 As shown, each interval can be traversed, and the index point of the side 401 of the elevator door 400 in the opening and closing direction can be identified based on the distribution information of the pixels in each interval.

[0044] In one embodiment of the present invention, step 103 may include the following steps: Step 1031: Count the number of pixels in each interval to obtain the point cloud number sequence.

[0045] In this embodiment, the number of pixels in each interval can be counted, and the number of corresponding pixels can be sorted according to the order of the intervals to obtain the point cloud number sequence.

[0046] Step 1032: Identify peak points in the point cloud data sequence.

[0047] In this embodiment, the changing trend of the number of pixels in each interval of the point cloud sequence can be identified, thereby locating the peak point of local change in the point cloud sequence.

[0048] In the specific implementation, a sliding window can be added to the point cloud sequence. The window is configured with parameters such as width and step size. For example, if the elevator door is divided into intervals of 1cm, the width of the sliding window is 10cm and the step size is 1cm.

[0049] As the window slides in steps, the average number of pixels in each interval of the window can be calculated with each slide, which is used as a moving average. That is, the moving average is a sequence of average numbers in the window at each slide, and the standard deviation of the number of pixels in each interval of the window is also calculated.

[0050] Add a multiple of the standard deviation (e.g., 2 times) to the moving average to obtain the upper limit line, and identify the peak point in the upper limit line.

[0051] Since point cloud data contains some random fluctuations (such as vibration data from depth sensors, interference data from obstacles, etc.), the number of pixels within the interval is smoothed by using the window average value, which reduces noise interference. Furthermore, multiple values ​​of the standard deviation can filter out statistically significant outliers, thereby improving the objectivity and reliability of peak points.

[0052] Furthermore, the peak points can be compared with a preset peak threshold (such as 5) to filter out peak points smaller than the peak threshold and reduce noise interference.

[0053] Step 1033: Use the neighborhood of the peak point in the point cloud sequence to determine the index point representing the side of the elevator door.

[0054] Since point cloud data contains some random fluctuations, the index points representing the sides of elevator doors can be identified by referring to the neighborhood (one-dimensional interval) of the peak points in the point cloud data sequence, which reduces noise interference and improves the accuracy of the index points.

[0055] In the specific implementation, in the point cloud number sequence, the peak point is used as the reference to expand to the left to the first proportion (such as 95%) of the peak point and to the back to the second proportion (such as 95%) of the peak point to obtain the neighborhood of the peak point. The center point in the neighborhood of the peak point is determined to represent the side of the elevator door (that is, the side of the elevator door may be located in the interval mapped by the center point in the neighborhood of the peak point). The center point in the neighborhood of the peak point is recorded as the index point.

[0056] Step 104: Select two index points that are symmetrical about the elevator doors and have the same height as the elevator doors, and use them as candidate point groups.

[0057] In practical applications, the two doors of an elevator are symmetrical about the center line and are at roughly the same height (i.e., level). Therefore, the symmetry and the fact that they are level can be used to select two index points from all index points that are more likely to represent the side of the elevator door as candidate point groups.

[0058] In one embodiment of the present invention, step 104 may include the following steps: Step 1041: Select two index points located on either side of the center line of the elevator door as a matching point group.

[0059] In this embodiment, any index point located to the left of the center line can be matched with any index point located to the right of the center line to construct a matching point group, thereby reducing the amount of computation.

[0060] Step 1042: Calculate the first error value between two index points in the matching point group, representing the door symmetry with respect to the elevator.

[0061] In this embodiment, by traversing each matching point group, a first error value representing the symmetry of the elevator door centerline between two index points in the matching point group can be calculated.

[0062] For example, with the center line of the elevator door as 0, the intervals located on one side of the center line as positive values ​​and the intervals located on one side of the center line as negative values, the absolute value of the sum between two index points in the matching point group is taken to obtain the first error value about the symmetry of the elevator door.

[0063] Step 1043: If the first error value is less than or equal to the preset offset threshold, then calculate the second error value, which represents the height alignment between the neighborhoods of the two index points in the matching point group.

[0064] The first error value of the symmetry between two index points in the matching point group with respect to the elevator door is compared with a preset offset threshold.

[0065] If the first error value is greater than the preset offset threshold, it means that the two index points in the matching point group are not symmetrical about the elevator door, and these two index points are ignored.

[0066] If the first error value is less than or equal to the preset offset threshold, it means that the two index points in the matching point group are symmetrical about the elevator door. Then, the second error value, which represents the height alignment between the neighborhoods of the two index points in the matching point group, is calculated to reduce noise interference.

[0067] For example, for each interval, the maximum height value of the pixels within that interval can be calculated.

[0068] For these two index points, for each index point in the matching point group, calculate the average of the largest height values ​​among the pixels in the current index point and multiple adjacent intervals (such as the three intervals on the left and the three intervals on the right) to obtain a reference value. Take the absolute value of the sum between the reference values ​​corresponding to the two index points in the matching point group to obtain the second error value representing the height alignment.

[0069] Step 1044: For the matching point group, merge the first error value and the second error value into a total error value.

[0070] In this embodiment, for the same set of matching points, the first error value and the second error value can be merged into the total error value of the set of matching points using linear (such as weighted summation, addition, etc.) or nonlinear methods.

[0071] Step 1045: If the matching point groups map to the same interval, then the matching point group with the smallest total error value is determined as the candidate point group.

[0072] In this embodiment, if the intervals mapped by each index point in the matching point group are the same, the total error values ​​of each matching point group can be compared, and the matching point group with the smallest total error value can be determined as the candidate point group.

[0073] Step 105: Perform velocity verification on the candidate point group to obtain the target point group.

[0074] In practical applications, elevator doors are set with corresponding movement modes to control their opening and closing according to safety regulations. Therefore, their movement modes can be used as prior knowledge to track the speed of candidate point groups, thereby verifying the legality of the candidate point groups and obtaining the target point group.

[0075] In a specific implementation, the total offset value representing the movement of the elevator door position between the current frame candidate point group and the previous frame target point group can be calculated. The previous frame target point group contains the index points in the previous frame depth image data used to locate the opening of the elevator door.

[0076] For example, for two index points in the current frame candidate point group and the previous frame target point group that are located on the same side of the elevator door centerline, the distance between the intervals mapped by these two index points is calculated to obtain the single-sided offset value. The sum of the single-sided offset values ​​is calculated to obtain the total offset value representing the movement of the elevator door position.

[0077] The total offset value is compared with the preset speed threshold.

[0078] If the total offset value corresponding to all candidate point groups is greater than the preset speed threshold, it means that the speed of all candidate point groups is relatively fast. In this case, the result of the previous frame is maintained, that is, the candidate point groups of the current frame are excluded, and the target point groups of the previous frame are set as the target point groups of the current frame.

[0079] If the total offset value corresponding to at least one candidate point group is less than or equal to the preset speed threshold, it means that the speed of at least one candidate point group is reasonable. Then, the total offset values ​​corresponding to at least one candidate point group are compared, and the candidate point group with the smallest total offset value is determined as the target point group of the current frame.

[0080] Step 106: Determine the elevator door opening based on the interval mapped by the two index points in the target point group.

[0081] In this embodiment, two intervals mapped by two index points in the target point group can be identified, that is, the two intervals where the two index points in the target point group are located. The opening degree of the elevator door can be determined based on the position of these two intervals.

[0082] For example, if the top of the elevator door is divided into sections at 1cm intervals, and each section is numbered sequentially, then the subscript (i.e., the number) of these two sections is the opening (in cm) with the center line as the zero point.

[0083] In this embodiment, a depth sensor is installed on the elevator door, and the top of the elevator door is divided into multiple sections along the opening / closing direction. When the depth sensor collects depth image data from the elevator door, the depth values ​​of the pixels in the depth image data are converted into height values. Pixels are written into sections based on their height values. Index points representing the sides of the elevator door are identified based on the pixels in each section. Two index points that are symmetrical about the elevator door and aligned with its height are selected as candidate point groups. The candidate point groups are then subjected to speed verification to obtain target point groups. The opening degree of the elevator door is determined based on the section mapped by the two index points in the target point group. This embodiment continuously and stably detects the opening degree of the elevator door based on factors such as symmetry, height, and speed of the depth image data, effectively reducing interference from users entering and exiting the elevator and improving the accuracy of detecting the opening degree of the elevator door.

[0084] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0085] Reference Figure 5The diagram illustrates a door opening detection device according to an embodiment of the present invention. A depth sensor is installed on the elevator door, and the top of the elevator door is divided into multiple sections along the opening / closing direction. The device may specifically include the following modules: The depth image conversion module 501 is used to convert the depth value of the pixel in the depth image data into the height value when the depth sensor collects depth image data from the elevator door. Pixel division module 502 is used to write the pixel into the interval according to the height value; Index point recognition module 503 is used to identify index points representing the side of the elevator door based on the interval; The candidate point group filtering module 504 is used to filter out two index points that are symmetrical about the elevator door and are at the same height as the candidate point group. The target point group verification module 505 is used to perform velocity verification on the candidate point group to obtain the target point group; The door opening determination module 506 is used to determine the door opening of the elevator based on the interval mapped by the two index points in the target point group.

[0086] In one embodiment of the present invention, the pixel division module 502 includes: The height range query module is used to query the height range associated with each of the intervals; the height range includes the upper limit and lower limit of the elevator door height under the field of view of the depth sensor; the upper limit and lower limit are separated by a preset distance value; The write interval module is used to write the pixel into the interval if the height value is within the height range.

[0087] In one embodiment of the present invention, the index point recognition module 503 includes: The quantity statistics module is used to count the number of pixels in each interval to obtain a point cloud number sequence. The peak point identification module is used to identify peak points in the point cloud sequence; An index point determination module is used to determine index points representing the sides of the elevator doors using the neighborhood of the peak points in the point cloud sequence.

[0088] In one embodiment of the present invention, the peak point identification module includes: A window adding module is used to add windows to the point cloud number sequence; A window statistics module is used to calculate the average value of the quantity within the window as a moving average line during the sliding process of the window, and to calculate the standard deviation of the quantity within the window. The moving upper limit line determination module is used to add a multiple of the standard deviation to the moving average line to obtain the moving upper limit line. The upper limit line identification module is used to identify peak points in the upper limit line of movement.

[0089] In one embodiment of the present invention, the index point determination module includes: The peak neighborhood determination module is used to determine the neighborhood of the peak point by expanding to the left of the peak point by a first proportion and to the back of the peak point by a second proportion, based on the peak point in the point cloud number sequence. The center point determination module is used to determine the center point in the neighborhood of the peak point, which represents the side of the elevator door, as an index point.

[0090] In one embodiment of the present invention, the candidate point group screening module 504 includes: The matching point group filtering module is used to filter out two index points located on both sides of the center line of the elevator door as a matching point group; The first error value calculation module is used to calculate a first error value between two index points in the matching point group, representing the door symmetry with respect to the elevator. The second error value calculation module is used to calculate a second error value representing height alignment between the neighborhoods of two index points in the matching point group if the first error value is less than or equal to a preset offset threshold. The total error value calculation module is used to merge the first error value and the second error value into a total error value for the matching point group. The candidate point group determination module is used to determine the matching point group with the smallest total error value as the candidate point group if the matching point groups map the same interval.

[0091] In one embodiment of the present invention, the first error value calculation module is further configured to: The absolute value of the sum between two index points in the matching point group is taken to obtain the first error value of the door symmetry with respect to the elevator.

[0092] In one embodiment of the present invention, the second error value calculation module is further configured to: For each index point in the matching point group, the average value of the maximum height value among the index point and the pixels in the multiple intervals adjacent to the index point is calculated to obtain a reference value; The absolute value of the sum of the reference values ​​is taken to obtain a second error value representing the height alignment.

[0093] In one embodiment of the present invention, the target point group verification module 505 includes: The total offset calculation module is used to calculate the total offset value between the candidate point group in the current frame and the target point group in the previous frame, representing the movement of the elevator door position. The first target point group setting module is used to set the target point group of the previous frame as the target point group of the current frame if the total offset value of all the above is greater than a preset speed threshold. The second target point group setting module is used to determine the candidate point group with the smallest total offset value as the target point group of the current frame if the total offset value is less than or equal to a preset velocity threshold.

[0094] In one embodiment of the present invention, the total offset calculation module is further configured to: For two index points in the candidate point group of the current frame and the target point group of the previous frame that are located on the same side of the door center line of the elevator, calculate the distance between the intervals mapped by the two index points to obtain the single-sided offset value. The sum of the offset values ​​on each side is calculated to obtain the total offset value representing the movement of the elevator door position.

[0095] The present invention provides a door opening degree detection device, which can realize the steps in the aforementioned door opening degree detection method embodiments.

[0096] It should be noted that the module division in the various door opening detection devices provided in the above embodiments is illustrative and only represents one logical functional division. In actual implementation, other division methods may also be used. Furthermore, the functional modules in the various embodiments of this invention can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0097] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the technical solution of the embodiments of the present invention can be embodied in the form of a computer program product, which is stored in a computer storage medium and includes several instructions to cause an electronic device or processor to execute all or part of the steps of the methods in the various embodiments of the present invention. The aforementioned computer storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0098] Furthermore, the door opening detection device and the door opening detection method provided in the above embodiments belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0099] Reference Figure 6 The diagram illustrates an electronic device according to an embodiment of the present invention. Figure 6 As shown, the electronic device in this embodiment of the invention includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps in the above-described door opening detection method embodiment. Alternatively, when the processor executes the computer program, it implements the functions of each module in the above-described door opening detection device embodiment.

[0100] For example, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to complete this application. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which can be used to describe the execution process of the computer program in the electronic device.

[0101] The electronic device may be a desktop computer, a cloud server, or other computing device. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that... Figure 6 This is merely one example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than illustrated, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0102] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0103] The memory can be an internal storage unit of the electronic device, such as a hard drive or RAM. Alternatively, it can be an external storage device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory can include both internal and external storage units. The memory is used to store the computer program and other programs and data required by the electronic device. The memory can also be used to temporarily store data that has been output or will be output.

[0104] This invention also discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the door opening detection method as described in the foregoing embodiments.

[0105] This invention also discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the door opening detection method as described in the foregoing embodiments.

[0106] This invention also discloses a computer program product that, when run on a computer, causes the computer to execute the door opening detection method described in the foregoing embodiments.

[0107] The embodiments described above are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for detecting door opening degree, characterized in that, A depth sensor is installed on the elevator door, and the top of the elevator door is divided into multiple sections along the opening / closing direction; the method includes: When the depth sensor collects depth image data from the elevator door, the depth value of the pixel in the depth image data is converted into a height value; The pixel is written into the interval according to the height value; Based on the index point representing the side of the elevator door within the interval; Two index points that are symmetrical about the elevator door and at the same height are selected as candidate point groups; The candidate point group is subjected to velocity verification to obtain the target point group; The opening degree of the elevator door is determined based on the interval mapped by the two index points in the target point group.

2. The method according to claim 1, characterized in that, The step of writing the pixel into the interval based on the height value includes: Query the height range associated with each of the intervals; the height range includes the upper limit and lower limit of the elevator door height under the field of view of the depth sensor; the upper limit and lower limit of the height are separated by a preset distance value; If the height value is within the specified height range, then the pixel is written into the specified interval.

3. The method according to claim 1, characterized in that, The step of identifying the index point representing the side of the elevator door within the interval includes: The number of pixels in each interval is counted to obtain a point cloud sequence. Identify peak points in the point cloud sequence; The index point representing the side of the elevator door is determined using the neighborhood of the peak point in the point cloud sequence.

4. The method according to claim 3, characterized in that, The identification of peak points in the point cloud sequence includes: Add a window to the point cloud number sequence; During the sliding of the window, the average value of the quantity within the window is calculated as a moving average, and the standard deviation of the quantity within the window is calculated. By adding a multiple of the standard deviation to the moving average, the upper limit of the moving average is obtained; Identify the peak point in the upper limit line of the movement.

5. The method according to claim 3, characterized in that, The step of using the neighborhood of the peak point in the point cloud sequence to determine the index point representing the side of the elevator door includes: In the point cloud sequence, the neighborhood of the peak point is obtained by expanding to the left of the peak point by a first proportion and to the back of the peak point by a second proportion, based on the peak point. The center point in the neighborhood of the peak point is determined to represent the side of the elevator door, and is used as an index point.

6. The method according to any one of claims 1-5, characterized in that, The process of selecting two index points that are symmetrical about the elevator door and aligned with its height as candidate point groups includes: Select the two index points located on either side of the center line of the elevator door as a matching point group; Calculate a first error value between two index points in the matching point set, representing door symmetry with respect to the elevator; If the first error value is less than or equal to a preset offset threshold, then a second error value representing height alignment between the neighborhoods of two index points in the matching point group is calculated. For the set of matching points, the first error value and the second error value are merged into a total error value; If the matching point groups map to the same interval, then the matching point group with the smallest total error value is determined as the candidate point group.

7. The method according to claim 6, characterized in that, The calculation of the first error value representing the door symmetry of the elevator between two index points in the matching point set includes: The absolute value of the sum between two index points in the matching point group is taken to obtain the first error value of door symmetry about the elevator. The calculation of the second error value representing height alignment between the neighborhoods of two index points in the matching point group includes: For each index point in the matching point group, the average value of the maximum height value among the index point and the pixels in the multiple intervals adjacent to the index point is calculated to obtain a reference value; The absolute value of the sum of the reference values ​​is taken to obtain a second error value representing the height alignment.

8. The method according to any one of claims 1-5 and 7, characterized in that, The step of performing velocity verification on the candidate point group to obtain the target point group includes: Calculate the total offset value representing the door position movement of the elevator between the candidate point group in the current frame and the target point group in the previous frame; If the total offset value is greater than the preset velocity threshold, then the target point group of the previous frame is set as the target point group of the current frame; If the total offset value is less than or equal to a preset velocity threshold, then the candidate point group with the smallest total offset value is determined as the target point group of the current frame.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the door opening detection method as described in any one of claims 1-8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the door opening detection method as described in any one of claims 1-8.

Images