An elevator door control method and device, electronic equipment and storage medium

Abstract

The application discloses an elevator door control method and device, electronic equipment and storage medium, the elevator door control method comprises the following steps: collecting the image of the area in the elevator car through the sensor when the elevator door of the elevator is opened; target detection and tracking are performed on the image to obtain biological feature data and behavior characteristic data of the object in the car, and the category of the object is determined according to at least one of the biological feature data and the behavior characteristic data; the elevator door is controlled to be closed according to the category of the object, the biological feature data comprises at least one of height and projection area, and the behavior characteristic data comprises at least one of body position, body movement speed, limb movement speed and operation behavior data, so that the biological feature data and the behavior data of the objects of different categories when riding the elevator are used for identifying the objects of different categories, and the objects such as adults, children, passengers riding wheelchairs, dwarf patients and pets can be identified, so that the elevator door can be accurately controlled to be closed according to the objects of different categories.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of elevator control, and in particular to an elevator door control method and device, electronic equipment and a storage medium. BACKGROUND

[0002] With the development of elevator intelligence, the elevator door is usually automatically closed after a preset time period without intervention after the elevator door is opened, and the categories of passengers are not distinguished.

[0003] At present, the related technology discloses delaying closing the elevator door when the passenger is a child. The disclosed technology distinguishes whether the passenger is a child by detecting the height of the passenger, and does not consider adult passengers riding wheelchairs or adult passengers with low height (such as dwarfism patients or people with disabilities resulting in low height). That is, in the prior art, adults and children are distinguished according to height, which cannot finely and accurately identify passengers of multiple categories, resulting in inaccurate control of closing the elevator door. SUMMARY

[0004] The present application provides an elevator door control method, device, electronic equipment and storage medium to solve the problem of inaccurate passenger category identification in the prior art, which leads to inaccurate control of closing the elevator door.

[0005] In a first aspect, the present application provides an elevator door control method, comprising:

[0006] collecting an image of an area inside a car of an elevator through a sensor when an elevator door of the elevator is opened;

[0007] performing target detection and tracking on the image to obtain biological feature data and behavior feature data of an object inside the car, the biological feature data including at least one of a height of the object and a projection area on a bottom of the car, and the behavior feature data including at least one of a body position, a body movement speed, a limb movement speed and operation behavior data of the object;

[0008] determining a category of the object according to at least one of the biological feature data and the behavior feature data;

[0009] controlling the elevator door to close according to the category of the object.

[0010] In a second aspect, the present application provides an elevator door control device, comprising:

[0011] an image collection module configured to collect an image of an area inside a car of an elevator through a sensor when an elevator door of the elevator is opened;

[0012] a target detection and tracking module configured to perform target detection and tracking on the image to obtain biological feature data and behavior feature data of the object in the car, the biological feature data comprising at least one of a height of the object and a projection area of the object on the bottom of the car, and the behavior feature data comprising at least one of a body position, a body movement speed, a limb movement speed and operation behavior data of the object;

[0013] a category determination module configured to determine a category of the object according to at least one of the biological feature data and the behavior feature data;

[0014] an elevator door control module configured to control the elevator door to close according to the category of the object.

[0015] In a third aspect, the present application provides an electronic device, which comprises:

[0016] at least one processor; and

[0017] a memory in communication with the at least one processor; wherein

[0018] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the elevator door control method according to the first aspect of the present application.

[0019] In a fourth aspect, the present application provides a computer readable storage medium storing computer instructions for enabling a processor to perform the elevator door control method according to the first aspect of the present application when executed by the processor.

[0020] The embodiment of the present application collects an image of an area in a car of an elevator through a sensor when an elevator door of the elevator is opened, performs target detection and tracking on the image to obtain biological feature data and behavior feature data of an object in the car, determines a category of the object according to at least one of the biological feature data and the behavior feature data, and controls the elevator door to close according to the category of the object, wherein the biological feature data comprises at least one of a height of the object and a projection area of the object on the bottom of the car, and the behavior feature data comprises at least one of a body position, a body movement speed, a limb movement speed and operation behavior data of the object, thereby realizing recognition of different categories of objects according to biological feature data and behavior data of different categories of objects such as adults, children, passengers riding wheelchairs, patients with dwarfism and pets when the objects ride an elevator, solving the problem of low accuracy of recognition of different categories of objects according to height, and realizing accurate control of the elevator door to close according to different categories of objects through discrimination of behavior features including operation behavior data after entering the elevator.

[0021] It is to be understood that the details described in this section are not intended to identify key or critical elements of the embodiments of the application or to limit the scope of the application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. 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 any creative effort based on these drawings.

[0023] Figure 1 is a schematic diagram of installation of a sensor in an elevator of the present embodiment;

[0024] Figure 2 is a flow chart of an elevator door control method provided by the first embodiment of the present application;

[0025] Figure 3 is a flow chart of an elevator door control method provided by the second embodiment of the present application;

[0026] Figure 4 is a structural schematic diagram of an elevator door control device provided by the third embodiment of the present application;

[0027] Figure 5 is a structural schematic diagram of an electronic device provided by the fourth embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the person skilled in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort should be within the scope of protection of the present application.

[0029] Embodiment One

[0030] Figure 2 is a flow chart of an elevator door control method provided by the first embodiment of the present application. The present embodiment can be applied to control the closing of an elevator door according to different categories of objects riding the elevator. The method can be executed by an elevator door control device, which can be realized in the form of hardware and / or software, and can be configured in an electronic device, such as a controller of an elevator. As shown in the figure, the elevator door control method comprises: Figure 2

[0031] ​S201, collect an image of the area inside the car of the elevator through a sensor when the elevator door of the elevator is opened.

[0032] As shown in the figure, the embodiment is installed with a sensor 3 on the car of the elevator, which can be a common camera, such as a black and white camera, an RGB camera, etc., and can also be an active light sensor, such as a TOF (Time of Flight) depth sensor, a structured light sensor, etc., that is, a sensor that can obtain a depth image by emitting and receiving light, of course, the sensor can also be a radar, etc., and the embodiment does not limit the type of sensor. Figure 1 In one example, the sensor of the embodiment can be an active light sensor, and the sensor 3 can be installed on the car 1 so that the detection area of the sensor 3 covers the area inside the car 1 and the area of the waiting hall 2. Optionally, the sensor 3 can be installed on the lintel of the car door of the car 1, such as the middle position of the lintel of the car door, so that the detection area of the sensor 3 covers the area inside the car 1 and the area of the waiting hall 2.

[0033] In one example, the number of sensors 3 can be one, that is, the sensor 3 can be an active light sensor with a larger field of view angle, and further, when the number of sensors 3 is one, the angle of the sensor 3 is adjustable, that is, the angle between the light emitting axis of the sensor 3 and the vertical direction is variable, that is, the sensor 3 can adjust the angle or be fixed, or, so that the detection area of the sensor 3 can be enlarged or reduced.

[0034] As shown in the figure, in another example, the number of sensors 3 can be two, among the two sensors 3, the light emitting axis of one sensor 3 is directed towards the inside of the car 1 to collect an image of the area inside the car 1, and the light emitting axis of the other sensor 3 is directed towards the waiting hall 2 to collect an image of the area of the waiting hall 2. Optionally, the detection ranges of the two sensors 3 have an overlapping area to ensure that the images of all areas from the car 1 to the waiting hall 2 can be collected, while avoiding the overexposure problem caused by the simultaneous collection of images of all areas from the car 1 to the waiting hall 2 when the sensor is one active light sensor with the light emitting axis vertical to the direction. Exemplarily, the angles between the light emitting axes of the two sensors 3 and the vertical direction can be adjusted to adjust the detection areas of the two sensors 3. Of course, the angles between the light emitting axes of the two sensors 3 and the vertical direction can also be fixed.

[0035] Figure 1

[0036] ​​In practical applications, the sensor 3 can collect depth images at a preset frame rate and send the depth images to the controller of the elevator. The elevator will usually open the door when reaching a target floor, at which time the sensor 3 collects depth images of the area inside the car 1 and the area of the waiting hall 2.

[0037] S202, target detection and tracking are performed on the image to obtain biological feature data and behavior feature data of the object inside the car.

[0038] In this embodiment, the biological feature data includes at least one of the height of the object and the projection area at the bottom of the car, and the behavior feature data includes at least one of the body position, the body movement speed, the limb movement speed, and the operation behavior data of the object. The height refers to the distance between the highest point of the detected object and the bottom of the car, the projection area is the projection of the outer contour of the detected object in the direction perpendicular to the bottom of the car, the body position can be the position of the detected object inside the car, the body movement speed can be the average speed when the position of the detected object inside the car changes, the limb movement speed is the speed when the recognized object moves its limbs (such as the speed when a person's hand operates a key, or the speed when a person's hand makes other movements), and the operation behavior data can be the sequence of the object's operation on the control keys inside the car after entering the car.

[0039] This embodiment can pre-train a target detection and tracking model, which can recognize and track the object to obtain the height, projection area, body position, body movement speed, limb movement speed, and limb movement position of the object, and estimate the operation behavior data based on the limb movement position.

[0040] S203, determining the category of the object according to at least one of the biological feature data and the behavior feature data.

[0041] In this embodiment, the biological feature data and the behavior feature data of objects of different categories are different. For example, for an adult, the height is greater than or equal to a preset height threshold, and the difference between the projection area and a preset projection area is less than a preset value. For objects with a height less than the preset height threshold, they can be children, people riding wheelchairs, dwarf patients (or other disabled adults with a short height), animals (pets), etc. Therefore, the activity level of the object needs to be calculated according to the detected behavior data such as body position, body movement speed, and limb movement speed, and the operation behavior data of the object's operation sequence on the keys inside the car to determine whether the object is a child or a dwarf patient.

[0042] Of course, in another optional embodiment, the image sequence can also be directly input into a pre-trained target classification model to directly classify the object inside the car through the target classification model.

[0043] S204, controlling the closing of the elevator door according to the category of the object.

[0044] In one embodiment, when the object is an adult object and a dwarf patient, the closing of the elevator door is controlled according to a preset closing time, such as a default and normal closing time; when the object is a person riding a tool, the closing of the elevator door is delayed, such as a passenger riding a wheelchair or a toy car; when the object in the car is a child or a pet, the closing of the elevator door is controlled to keep open, that is, when a child or a pet is detected to ride the elevator alone, the closing of the elevator door is controlled to keep open, and a reminder message is broadcast through a broadcasting device in the car to remind the child or the pet to get out of the elevator, so as to avoid the child or the pet entering the elevator alone or staying in the elevator, which may cause a safety hazard.

[0045] The embodiment of the application collects the image of the area in the car of the elevator through the sensor when the elevator door of the elevator is opened, performs target detection and tracking on the image to obtain biological feature data and behavior feature data of the object in the car, determines the category of the object according to at least one of the biological feature data and the behavior feature data, and controls the closing of the elevator door according to the category of the object, wherein the biological feature data includes at least one of the height of the object and the projection area on the bottom of the car, and the behavior feature data includes at least one of the body position, the body movement speed, the limb movement speed and the operation behavior data of the object, so as to realize the recognition of different categories of objects according to the biological feature data and the behavior data of different categories of objects such as adults, children, passengers riding wheelchairs, dwarf patients and pets when they ride the elevator, solve the problem of low accuracy of recognizing different categories of objects according to height, and realize the accurate control of the closing of the elevator door according to different categories of objects through the discrimination of behavior features including operation behavior data after entering the elevator.

[0046] Embodiment two

[0047] Figure 3 A flowchart of an elevator door control method provided for the embodiment two of the application is shown in the figure, and the embodiment of the application is optimized on the basis of the above-mentioned embodiment one. Figure 3 The elevator door control method includes:

[0048] S301, when the elevator door of the elevator is opened, controlling the sensor facing the car to collect multiple frames of images of the area in the car of the elevator at a preset frame rate to obtain an image sequence.

[0049] In practical applications, the car of the elevator stops running when reaching the target floor hall in the uplink or downlink process, and controls the opening of the door to make the passengers in the car get out of the elevator, and the objects in the hall who have the demand of taking the elevator enter the car, wherein the objects can be people, pets and other objects that need to take the elevator.

[0050] When the door is opened, the sensor 3 can collect depth images at a preset frame rate and send the depth images to the controller of the elevator, as shown in Figure 1 When the number of sensors 3 is one, the sensor 3 can be controlled to face the area of the car 1 to collect multiple images when the door starts to open, and when the number of sensors 3 is two, the sensor pair facing the car 1 can be controlled to collect multiple images of the area of the car 1. It should be noted that the sensor 3 can collect images from the start of the door opening to the end of the door closing, and in addition, the frame rate of the sensor collecting images can be a fixed frame rate, or a dynamically adjustable frame rate.

[0051] After each frame of image is collected, the image can be preprocessed, such as denoising, binarization and other image processing to generate an image sequence.

[0052] S302, input the image sequence into the target detection and tracking model to obtain at least one of the height of the object in the car, the projection area on the bottom of the car as the biological feature data, and at least one of the body movement speed, the limb movement speed and the operation behavior data as the behavior feature data.

[0053] In this embodiment, the target detection and tracking model can be a neural network such as RNN, CNN, DNN, etc. When the target detection and tracking model is trained, the image after labeling the height, projection area, position, movement speed and operation behavior data of the object in the image can be used as training data, and the labeled image sequence is input into the target detection and tracking model to predict the height, projection area, position, movement speed and operation behavior data of each object in the image sequence. After the data, the loss rate is calculated by the predicted data and the labeled data, and the model parameters are adjusted by the loss rate until the loss rate is less than a preset value to obtain a trained target detection and tracking model. In this embodiment, the model structure is not limited, and the training method of the model is not limited.

[0054] Of course, after the object is identified, the height, projection area and position of the object can be calculated through the installation position of the sensor, the imaging principle, the internal and external parameters of the sensor, and the speed can be calculated through the position difference of the object in two frames of images and the frame rate. This embodiment does not limit the way of obtaining the biological feature data and behavior feature data of the object.

[0055] S303, judge whether the height of the object is greater than a preset height threshold.

[0056] The embodiment can obtain a height demarcation line between adults and minors according to big data analysis, set the demarcation line as a height threshold, determine whether the height of each object is greater than the height threshold, if yes, it is indicated that the object is an adult, and S304 is executed, and if not, the object can be a child, an adult suffering from dwarfism (or an adult with other disabilities leading to short height), a pet, a person riding a wheelchair or a toy car, etc., and S305 is executed.

[0057] S304, determining that the object is an adult object.

[0058] When the height of the object entering the car is greater than or equal to the height threshold, it is determined that the object is an adult object, and subsequently the elevator door can be controlled to be closed according to a control strategy for adults riding the elevator.

[0059] S305, calculating a difference between the projection area of the object and a preset area.

[0060] When the height of the object is less than the height threshold, in order to further identify the object as one of a child, an adult suffering from dwarfism or other disabilities leading to short height, a pet, a person riding a wheelchair or a toy car, etc., the projection area of the object can be used to further determine the category of the object. Specifically, a projection area of a normal person can be preset as a preset area, and a difference between the projection area of the identified object and the preset area can be calculated.

[0061] S306, determining whether the difference is greater than a preset threshold.

[0062] The smaller the difference is, the closer the projection area of the object is to the projection area of a normal person standing, and the larger the difference is, the greater the difference between the projection area of the object and the projection area of a normal person standing is. For example, when a person rides a wheelchair or sits in a toy car, the projection area is greater than the projection area of a normal person standing. When the difference is greater than or equal to the preset threshold, S307 is executed, and otherwise, S308 is executed.

[0063] S307, determining that the object is an object riding a tool.

[0064] Specifically, when the difference between the projection area of the object and the preset area is greater than the preset threshold, it is indicated that the object can be a passenger riding a wheelchair or a toy car, or a patient lying on a movable hospital bed or a stretcher in a hospital.

[0065] S308, determining the category of the object according to at least one of the body position, the body movement speed, the limb movement speed and the operation behavior data, the category including a dwarfism patient and a child.

[0066] If the height of the object is less than the height threshold, and the difference between the projected area of the object and the preset area is less than the preset threshold, the object can be an adult patient with dwarfism (or other disabled adult with short height) or a child. In order to further identify the adult patient with dwarfism or the child, the activity level of the object and the operation behavior data of the buttons in the car are combined to further identify the category to which the object belongs.

[0067] Alternatively, the height, body position, body movement speed, and limb movement speed can be used to calculate the activity level of the object, and it is determined whether the activity level is greater than a preset activity level threshold. If yes, when the operation sequence represented by the operation behavior data conforms to the preset call sequence, it is determined that the object is an adult patient with dwarfism. If no, when the operation sequence represented by the operation behavior data does not conform to the preset call sequence, it is determined that the object is a child.

[0068] The preset call sequence can be one of the following operation sequences:

[0069] Operation sequence one: first press the target floor button, then press the door closing button. That is, after entering the elevator, the adult patient with dwarfism, who is not a child, can usually first press the target floor button to select the target floor, and then press the door closing button if there is no one else entering the car and the door is open.

[0070] Operation sequence two: first press the door closing button, then press the target floor selection button. That is, after entering the elevator, the adult patient with dwarfism, who is not a child, can first press the door closing button to close the door, and then press the target floor selection button to select the target floor if there is no one else entering the car.

[0071] Operation sequence three: press one target floor selection button. That is, after entering the elevator, the adult patient with dwarfism, who is not a child, and has someone else entering the car, usually only presses one target floor selection button to select the target floor.

[0072] Operation sequence four: press one door closing button. That is, after entering the elevator, the adult patient with dwarfism, who is not a child, and has someone else entering the car, usually only presses one door closing button.

[0073] For those who do not conform to the preset call sequence, due to the curiosity and active characteristics of children, children may press more than two target floor selection buttons, or operate the door closing button multiple times, or repeatedly and alternately press the target floor selection button and the door closing button, etc.

[0074] In one embodiment, the height change range of the height of the object can be calculated, the position activity range of the object can be obtained, the weights of the height change range, the position activity range, the trunk moving speed and the limb moving speed can be obtained, the weighted sum can be calculated by using the height change range, the position activity range, the trunk moving speed, the limb moving speed and the corresponding weights, and the activity level of the object can be obtained.

[0075] The height change range can refer to the difference between the maximum height and the minimum height of the object in the process from the first time the object is recognized to the time when the position of the object is stable. If the object is an adult patient with dwarfism, the height change range is normal when walking. If the object is a child, the child is active, and the height change range is large when the child stands, squats or bends. The position activity range can refer to the area of the largest polygon formed by the connecting lines of the positions of the object in the car. In contrast, the position activity range of the adult patient with dwarfism is small, and the position activity range of the child is large. The trunk moving speed can be the moving speed of the body of the object. The trunk moving speed of the adult patient with dwarfism is large, and the trunk moving speed of the child is small. The limb moving speed can refer to the moving speed of the hands of the object. For example, the speed of the adult patient with dwarfism in stretching the hand to press the target floor button and the door closing button is fast, and the speed of the child is relatively slow.

[0076] In this embodiment, the weights of the height change range, the position activity range, the trunk moving speed and the limb moving speed can be set in advance. After the height change range, the position activity range, the trunk moving speed and the limb moving speed of the object are obtained, the weighted sum is calculated by using the corresponding weights as the activity level of the object. The activity level of the object represents the behavior activity level of the object in the process of riding the elevator, and can distinguish the adult patient with dwarfism and the child.

[0077] In another optional embodiment, for an object with a smaller height, the contour feature data of the object can be extracted by a model, the contour feature data of the object is matched with the data in the preset pet feature database, and when it is determined that the contour feature data has a matching item, it is determined that the object is an animal. That is, the contour feature of the animal is usually different from that of the human being, such as the dog and the cat usually have a long trunk, four limbs and a tail. When it is identified that the contour feature data of the object matches the data in the preset pet feature database, it is determined that the object is an animal.

[0078] S309, when the object is an adult object and an adult patient with dwarfism, the elevator door is closed according to the preset door closing time.

[0079] If the object is an adult or an adult dwarf patient object, since the behavior and action ability of adult is stronger, the elevator door can be closed according to the preset door closing time control, such as the elevator door is closed in 30 seconds countdown, the elevator door can be closed at the end of 30 seconds countdown.

[0080] S310, when the object exists, delay closing the elevator door.

[0081] When it is identified that the person who rides the wheelchair, the toy car or lies on the bed, stretcher and other tools rides the elevator, in order to have enough time for the person who rides the above tools to enter the car, the time of closing the elevator door can be extended, such as delaying 5 seconds, 10 seconds and so on before closing the elevator door.

[0082] S311, when the object in the car is a child or a pet, control the elevator door to keep open.

[0083] When it is detected that the object who rides the elevator is a child or a pet, such as the passengers in the car are all children and / or pets, it is indicated that the children, pets ride the elevator alone without adult accompanying, in order to ensure the safety of the object who has no behavior ability to ride the elevator, the elevator door will be controlled to keep open, and the broadcast in the car will broadcast the reminder voice information to remind the children or pets to get out of the elevator, or to remind the adult who accompanies the children or pets in the waiting hall to enter the elevator, or to lead the children, pets to get out of the elevator, so as to avoid the accident of the children or pets riding the elevator alone.

[0084] The embodiment obtains at least one of the height of the object and the projection area of the object on the bottom of the car as the biometric feature data and at least one of the body movement speed, the limb movement speed and the operation behavior data as the behavior feature data through the image sequence collected by the sensor, and determines the object as an adult object when the height is greater than or equal to a height threshold, and determines the object as an object riding the tool when the difference between the projection area of the object and a preset area is greater than or equal to a preset threshold, and calculates the activity of the object by using the height, the body position, the body movement speed and the limb movement speed when the difference between the projection area of the object and the preset area is less than the preset threshold, and determines that the object is an adult dwarf patient or a child in combination with the activity and the sequence of the object operating the buttons in the car, controls the elevator door to be normally closed according to the preset closing time of the door when the object is the adult object and the dwarf patient object, delays the closing of the elevator door when the object riding the tool exists, and controls the elevator door to be kept open when the object in the car is the child or the pet, so that the adult, the child and the dwarf patient are accurately identified according to the biometric feature data and the behavior feature data of the object, the pet can be identified by matching the contour feature data of the object with a preset pet database, the elevator door can be accurately controlled according to different categories of objects entering the car, the safety of the elevator is ensured for different categories of objects, the closing of the elevator door is accurately controlled according to different categories of objects, and the passenger experience of taking the elevator is improved.

[0085] Further, the activity of the object is calculated by using the height, the body position, the body movement speed and the limb movement speed, and it is determined that the object is an adult dwarf patient or a child in combination with the activity and the sequence of the object operating the buttons in the car, so that the problem that the adult dwarf patient is misjudged as a child and the door of the elevator cannot be automatically closed is solved, and the closing of the door of the elevator can be accurately controlled.

[0086] Further, the embodiment can identify the child and the pet, control the elevator door to be kept open when the child or the pet takes the elevator alone, and broadcast a prompt information, so that the child or the pet taking the elevator alone or the child or the pet staying in the car does not cause an accident, and the safety of the child and the pet taking the elevator is ensured.

[0087] Embodiment Three

[0088] Figure 4 A structural schematic diagram of an elevator door control device provided for the embodiment three of the application is shown in FIG. 3. Figure 4 As shown in the figure, the elevator door control device comprises:

[0089] An image acquisition module 401 is configured to acquire an image of an area in a car of an elevator by a sensor when a door of the elevator is opened.

[0090] The target detection and tracking module 402 is configured to perform target detection and tracking on the image to obtain biological feature data and behavior feature data of the object in the car, the biological feature data including at least one of a height of the object and a projection area of the object on the bottom of the car, and the behavior feature data including at least one of a body position, a body movement speed, a limb movement speed and operation behavior data of the object.

[0091] The category determination module 403 is configured to determine a category of the object according to at least one of the biological feature data and the behavior feature data.

[0092] The elevator door control module 404 is configured to control the elevator door to close according to the category of the object.

[0093] Optionally, the image acquisition module 401 includes:

[0094] The image acquisition unit is configured to control the sensor inside the car to acquire a plurality of frames of images of the area inside the car of the elevator at a preset frame rate when the elevator door of the elevator is opened, to obtain an image sequence.

[0095] Optionally, the target detection and tracking module 402 includes:

[0096] The model input unit is configured to input the image sequence into a target detection and tracking model to obtain at least one of a height of the object and a projection area of the object on the bottom of the car as the biological feature data, and to obtain at least one of a body movement speed, a limb movement speed and operation behavior data as the behavior feature data.

[0097] Optionally, the biological feature data includes the height of the object and the projection area of the object on the bottom of the car, and the behavior feature data includes a body position, a body movement speed, a limb movement speed and operation behavior data, and the category determination module 403 includes:

[0098] The height judgment submodule is configured to judge whether the height of the object is greater than a preset height threshold.

[0099] The adult object determination submodule is configured to determine that the object is an adult object.

[0100] The area difference calculation submodule is configured to calculate a difference between the projection area of the object and a preset area.

[0101] The difference judgment submodule is configured to judge whether the difference is greater than a preset threshold.

[0102] The riding tool object determination submodule is configured to determine that the object is a riding tool object.

[0103] The category determining sub-module is configured to determine the category of the object according to at least one of the body position, the body movement speed, the limb movement speed, and the operation behavior data.

[0104] The operation behavior data includes an operation sequence of the object on control buttons in the elevator car, and the category determining sub-module includes:

[0105] The activity degree calculation unit is configured to calculate the activity degree of the object by using the height, the body position, the body movement speed, and the limb movement speed.

[0106] The activity degree judging unit is configured to judge whether the activity degree is greater than a preset activity degree threshold.

[0107] The dwarf patient determining unit is configured to determine that the object is an adult dwarf patient object when the operation sequence represented by the operation behavior data conforms to a preset elevator calling operation sequence.

[0108] The child object determining unit is configured to determine that the object is a child when the operation sequence represented by the operation behavior data does not conform to the preset elevator calling operation sequence.

[0109] Optionally, the preset elevator calling operation sequence includes one of the following operation sequences:

[0110] Operation sequence one: pressing a target floor button first, and then pressing a door closing button;

[0111] Operation sequence two: pressing the door closing button first, and then pressing a target floor selection button;

[0112] Operation sequence three: pressing a next target floor selection button;

[0113] Operation sequence four: pressing a door closing button once.

[0114] Optionally, the activity degree calculation unit includes:

[0115] The height change amplitude calculation sub-unit is configured to calculate a height change amplitude of the object by using the height.

[0116] The position activity range calculation sub-unit is configured to calculate a position activity range of the object by using the body position.

[0117] The weight obtaining sub-unit is configured to obtain weights of the height change amplitude, the position activity range, the body movement speed, and the limb movement speed.

[0118] The activity degree calculation sub-unit is configured to calculate a weighted sum by using the height change amplitude, the position activity range, the body movement speed, the limb movement speed, and the corresponding weights, to obtain the activity degree of the object.

[0119] Optionally, the biometric data further comprises contour feature data of the object, and the category determining module 403 comprises:

[0120] a data matching unit, configured to match the contour feature data of the object with data in a preset pet feature database;

[0121] an animal object determining unit, configured to determine the object as an animal when it is determined that the contour feature data has a matching item.

[0122] Optionally, the elevator door control module 404 comprises:

[0123] a normal closing unit, configured to control the elevator door to close according to a preset closing time when the object is an adult object or an adult dwarfism patient object;

[0124] a delayed closing unit, configured to delay closing the elevator door when there is an object riding a tool;

[0125] a keeping open unit, configured to control the elevator door to keep open when the object in the car is a child or a pet.

[0126] The elevator door control device provided by the embodiment of the present application can execute the elevator door control method provided by the first embodiment and the second embodiment, and has the corresponding function modules and beneficial effects of the execution method.

[0127] Embodiment Four

[0128] Figure 5 A structural schematic diagram of an electronic device 50 that can be used to implement embodiments of the present application is shown. The electronic device 50 is intended to represent various forms of digital computers, such as laptops, desktops, tablets, servers, blades, mainframes, and so on. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0129] As Figure 5As shown, the electronic device 50 includes at least one processor 51, and a memory, such as a read-only memory (ROM) 52, a random access memory (RAM) 53, etc., connected to the at least one processor 51 in communication. The memory stores computer programs executable by the at least one processor 51, and the processor 51 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 52 or loaded from the storage unit 58 into the random access memory (RAM) 53. In the RAM 53, various programs and data required for the operation of the electronic device 50 can also be stored. The processor 51, the ROM 52, and the RAM 53 are connected to each other through a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0130] Various components in the electronic device 50 are connected to the I / O interface 55, including an input unit 56, such as a keyboard, a mouse, a sensor, etc., an output unit 57, such as various types of displays, a speaker, etc., a storage unit 58, such as a magnetic disk, an optical disk, etc., and a communication unit 59, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 59 allows the electronic device 50 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0131] The processor 51 can be various general and / or special-purpose processing components having processing and computing capabilities. Some examples of the processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 51 performs various methods and processes described above, such as the elevator door control method.

[0132] In some embodiments, the elevator door control method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 58. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 50 via the ROM 52 and / or the communication unit 59. When the computer program is loaded into the RAM 53 and executed by the processor 51, one or more steps of the elevator door control method described above can be performed. Alternatively, in other embodiments, the processor 51 can be configured to perform the elevator door control method by any other appropriate means, such as by means of firmware.

[0133] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0134] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package and partially on a remote machine or entirely on a remote machine or server.

[0135] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0136] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0137] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0138] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0139] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0140] The above detailed description does not limit the scope of the present disclosure. It is understood that various modifications, combinations, sub-combinations, and alternatives can be made to the detailed disclosure without departing from the spirit and principles of the present disclosure. Any modifications, equivalent substitutions, improvements, and the like that are made within the spirit and principles of the present disclosure are included in the scope of the present disclosure.

Claims

1. An elevator door control method, characterized by, The method comprises: collecting an image of an area in a car of an elevator by a sensor when an elevator door of the elevator is open; performing target detection tracking on the image to obtain biological feature data and behavior feature data of an object in the car, the biological feature data comprising at least one of a height of the object and a projection area of the object on a bottom of the car, and the behavior feature data comprising at least one of a body position, a body movement speed, a limb movement speed and operation behavior data of the object; determining a category of the object according to at least one of the biological feature data and the behavior feature data; controlling the elevator door to close according to the category of the object; the biological feature data comprises the height of the object and the projection area of the object on the bottom of the car, the behavior feature data comprises the body position, the body movement speed, the limb movement speed and the operation behavior data, and the determining the category of the object according to at least one of the biological feature data and the behavior feature data comprises: determining whether the height of the object is greater than a preset height threshold; if yes, determining that the object is an adult object; if no, calculating a difference between the projection area of the object and a preset area; determining whether the difference is greater than a preset threshold; if yes, determining that the object is an object riding a tool; if no, calculating an activity level of the object by using the height, the body position, the body movement speed and the limb movement speed; determining whether the activity level is greater than a preset activity level threshold; if yes, determining that the object is a patient with dwarfism when an operation sequence represented by the operation behavior data conforms to a preset call elevator operation sequence; if no, determining that the object is a child when the operation sequence represented by the operation behavior data does not conform to the preset call elevator operation sequence.

2. The method of claim 1, wherein, The collecting an image of an area in a car of an elevator by a sensor when an elevator door of the elevator is open comprises: controlling a sensor facing into the car to collect a plurality of images of an area in the car of the elevator at a preset frame rate when the elevator door of the elevator is open, to obtain an image sequence.

3. The method of claim 1, wherein, The performing target detection tracking on the image to obtain biological feature data and behavior feature data of an object in the car comprises: inputting the image sequence into a target detection tracking model to obtain at least one of a height of the object and a projection area of the object on the bottom of the car as the biological feature data, and to obtain at least one of a body movement speed, a limb movement speed and operation behavior data as the behavior feature data.

4. The method of claim 1, wherein, The preset call elevator operation sequence comprises one of the following operation sequences: operation sequence one: pressing a target floor button first, and then pressing a door closing button; operation sequence two: pressing the door closing button first, and then pressing a target floor selection button; operation sequence three: pressing a next target floor selection button; operation sequence four: pressing a next door closing button.

5. The method of claim 1, wherein, The calculating an activity level of the object by using the height, the body position, the body movement speed and the limb movement speed comprises: calculating a height change amplitude of the object by using the height. The body position is used to calculate a position activity range of the object; The height variation range, the position activity range, the body movement speed, the limb movement speed, and the corresponding weights are obtained; The height variation range, the position activity range, the body movement speed, the limb movement speed, and the corresponding weights are used to calculate a weighted sum, so as to obtain the activity level of the object.

6. The method of claim 1, wherein, The biological feature data further includes contour feature data of the object, and the category of the object is determined according to at least one of the biological feature data and the behavior feature data, including: The contour feature data of the object is matched with data in a preset pet feature database; When it is determined that the contour feature data has a matching item, the object is determined to be a pet.

7. The method according to any one of claims 1 to 6, wherein The elevator door is controlled to be closed according to the category of the object, including: When the object is an adult object and a dwarfism patient, the elevator door is controlled to be closed according to a preset door closing time; When there is an object riding a tool, the elevator door is delayed to be closed; When the object in the car is a child or a pet, the elevator door is controlled to be kept open.

8. An elevator door control device, characterized by Including: An image acquisition module is configured to acquire an image of an area in a car of an elevator through a sensor when an elevator door of the elevator is opened; A target detection and tracking module is configured to perform target detection and tracking on the image, so as to obtain biological feature data and behavior feature data of an object in the car, the biological feature data including at least one of a height of the object and a projection area of the object on a bottom of the car, and the behavior feature data including at least one of a body position of the object, a body movement speed of the object, a limb movement speed of the object, and operation behavior data of the object; A category determination module is configured to determine a category of the object according to at least one of the biological feature data and the behavior feature data; An elevator door control module is configured to control the elevator door to be closed according to the category of the object; The biological feature data includes the height of the object and the projection area of the object on the bottom of the car, the behavior feature data includes the body position, the body movement speed, the limb movement speed, and the operation behavior data, and the operation behavior data includes an operation sequence of the object on control buttons in the car, and the category determination module includes: A height judgment submodule is configured to judge whether the height of the object is greater than a preset height threshold; An adult object determination submodule is configured to determine that the object is an adult object; An area difference calculation submodule is configured to calculate a difference between the projection area of the object and a preset area; A difference judgment submodule is configured to judge whether the difference is greater than a preset threshold; A tool-riding object determination submodule is configured to determine that the object is a tool-riding object; A category determination submodule is configured to determine the category of the object according to at least one of the body position, the body movement speed, the limb movement speed, and the operation behavior data; The category determination submodule includes: An activity level calculation unit is configured to obtain a calculation using the height, the body position, the body movement speed, and the limb movement speed to calculate the activity level of the object. an activity level judging unit, configured to judge whether the activity level is greater than a preset activity level threshold; a dwarf patient determining unit, configured to determine that the object is an adult dwarf patient object when the operation sequence represented by the operation behavior data is consistent with a preset elevator calling operation sequence; a child object determining unit, configured to determine that the object is a child when the operation sequence represented by the operation behavior data is not consistent with the preset elevator calling operation sequence.

9. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the elevator door control method in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, and the computer instructions are used to enable the processor to implement the elevator door control method in any one of claims 1-7 when executed.

Images