Method and device for managing overpopulation of an elevator, image acquisition device and storage medium

Abstract

The application discloses an elevator overpopulation management method and device, image acquisition equipment and a storage medium. The method comprises the following steps: acquiring an image of an elevator; determining initial data of the elevator according to the image; filtering data in the initial data which is within the range of the cage door of the elevator through an out-of-cage filtering algorithm to obtain in-cage data; correcting the in-cage data through an abnormal filtering algorithm to obtain target data; and judging whether to send an alarm signal according to the target data. The processor is arranged in the image acquisition equipment, so that the hardware structure can be simplified and the recognition speed can be improved. Meanwhile, the out-of-cage filtering algorithm and the abnormal filtering algorithm can improve the accuracy of recognizing the number of people in the elevator and reduce the false detection rate and the missed detection rate.

Description

Technical Field

[0001] This application relates to the field of computer vision and target detection technology, specifically to a method, apparatus, image acquisition device, and storage medium for managing overcrowding in elevators. Background Technology

[0002] Because safety supervision departments have strict requirements on the number of people that construction hoists can carry, construction hoists need to be equipped with relevant systems for real-time monitoring to identify the number of people in the hoist cage and prevent overloading. However, the existing systems mainly consist of two components: a camera and a processor. These components exist independently, which places greater demands on the installation space and layout of the product, hindering convenient installation.

[0003] Furthermore, image recognition algorithms inherently have a certain rate of false negatives and false positives. Directly using image recognition results as the number of people in a crowd makes the algorithm's identification inaccurate. Additionally, when identifying people inside the cage, there is a problem of misclassifying people outside the cage as part of the cage's headcount. Therefore, the hardware used in current elevator overcrowding management technologies is relatively complex and lacks accuracy in identifying the number of people in the elevator, resulting in false negatives and false positives. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, image acquisition equipment, and storage medium for managing overcrowding in elevators, in order to solve the problem that the hardware equipment in the prior art is relatively complex and the identification of the number of people in the elevator is not accurate enough.

[0005] To achieve the above objectives, the first aspect of this application provides a method for managing overcrowding in an elevator, applied to an image acquisition device installed in the elevator, the method comprising:

[0006] Acquire an image of the elevator;

[0007] Determine the initial data of the elevator based on the image;

[0008] The initial data within the cage door area is filtered using an external cage filtering algorithm to obtain the data inside the cage.

[0009] The data within the cage is corrected using an anomaly filtering algorithm to obtain the target data;

[0010] Determine whether to send an alarm signal based on the target data.

[0011] In this embodiment of the application, the data within the elevator cage door area in the initial data is filtered using an external cage filtering algorithm to obtain the internal cage data, including:

[0012] Calibrate the cage door of the elevator to determine the cage door range of the elevator;

[0013] Determine whether each person in the initial data is located in the cage door range according to the pixel coordinates of the person;

[0014] Determine the number of persons not located in the cage door range as the cage-in data.

[0015] In the embodiments of the present application, determining whether each person in the initial data is located in the cage door range according to the pixel coordinates of the person includes:

[0016] Determine a preset number of pixel coordinates of each person respectively;

[0017] Determine whether the preset number of pixel coordinates of each person are all in the cage door range respectively;

[0018] For any person, in a case that at least one of the preset number of pixel coordinates of the person is not in the cage door range, determine the person as a person not located in the cage door range.

[0019] In the embodiments of the present application, correcting the cage-in data by an abnormal filtering algorithm to obtain the target data includes:

[0020] Obtain a preset number of cage-in data to obtain a plurality of cage-in data;

[0021] Remove the maximum value and the minimum value of the plurality of cage-in data to obtain remaining cage-in data;

[0022] Determine the target data according to the mean value of the remaining cage-in data.

[0023] In the embodiments of the present application, determining whether to send an alarm signal according to the target data includes:

[0024] Determine whether the target data is greater than a preset value;

[0025] In a case that the target data is greater than the preset value, send the alarm signal;

[0026] In a case that the target data is not greater than the preset value, do not send the alarm signal.

[0027] In the embodiments of the present application, the image acquisition device communicates with the controller of the elevator, and the initial data of the elevator is determined according to the image, which includes:

[0028] In a case that a start closing signal sent by the controller is received, determine the initial data of the elevator according to the image;

[0029] The method further includes:

[0030] In a case where the complete closing signal sent by the controller is acquired, the target data is sent to the controller of the elevator.

[0031] In the embodiments of the present application, the image acquisition device also communicates with the management terminal, and the method further comprises:

[0032] In a case where the alarm signal is determined to be sent, the alarm signal is sent to the management terminal, and the operation of the elevator is suspended; and / or

[0033] In a case where the alarm signal is determined to be sent, the alarm signal is sent to the controller, and the operation of the elevator is suspended.

[0034] The second aspect of the present application provides an image acquisition device, comprising:

[0035] an image acquisition module configured to acquire an image of the elevator;

[0036] a memory configured to store instructions; and

[0037] a processor configured to call the instructions from the memory and capable of realizing the method of elevator overpopulation management according to the above when the instructions are executed.

[0038] The third aspect of the present application provides an apparatus for elevator overpopulation management, comprising:

[0039] the image acquisition device described above;

[0040] a controller of the elevator in communication with the image acquisition device, configured to send a start closing signal and a complete closing signal to the image acquisition device, and receive the target data and the alarm signal sent by the image acquisition device;

[0041] a management terminal in communication with the image acquisition device, configured to receive the alarm signal sent by the image acquisition device.

[0042] The fourth aspect of the present application provides a machine readable storage medium having instructions stored thereon, the instructions being used to cause a machine to execute the method of elevator overpopulation management described above.

[0043] Through the above technical solution, the image of the elevator is acquired, and the initial data of the elevator is determined according to the image. The data in the initial data that is within the range of the cage door of the elevator is filtered through the out-of-cage filtering algorithm to obtain in-cage data, and the in-cage data is corrected through the abnormal filtering algorithm to obtain target data. Finally, whether to send an alarm signal is determined according to the target data. The present application can simplify the hardware structure, improve the recognition speed, improve the accuracy of recognizing the number of people in the elevator, and reduce the false detection rate and the missed detection rate by setting the processor in the image acquisition device.

[0044] Other features and advantages of the embodiments of the present application will be described in the following detailed description of the embodiments of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0045] The accompanying drawings, which are included to provide a further understanding of the embodiments of the present application and constitute a part of this application, illustrate embodiments of the present application and together with the detailed description below help explain the embodiments of the present application. In the drawings:

[0046] Figure 1 A flow chart of a method for elevator over-occupancy management is schematically shown according to an embodiment of the present application;

[0047] Figure 2 A schematic diagram of an elevator image recognition result is schematically shown according to an embodiment of the present application;

[0048] Figure 3 A structural block diagram of an image acquisition device is schematically shown according to an embodiment of the present application;

[0049] Figure 4 A structural diagram of a device for elevator over-occupancy management is schematically shown according to an embodiment of the present application.

[0050] REFERENCE NUMERALS

[0051] 201 cage door 202 personnel

[0052] 203 first pixel coordinate 204 second pixel coordinate

[0053] 205 third pixel coordinate 206 fourth pixel coordinate

[0054] 310 image acquisition module 320 memory

[0055] 330 processor 401 image acquisition device

[0056] 402 controller of the elevator 403 management terminal DETAILED DESCRIPTION

[0057] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. It should be understood that the specific embodiments described herein are merely used to explain and illustrate the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0058] It should be noted that if the application embodiments have directionality indications (such as up, down, left, right, front, back, etc.), the directionality indications are only used to explain the relative position relationship, movement condition, etc. between components in a certain posture (as shown in the drawings), and if the certain posture changes, the directionality indications also change accordingly.

[0059] In addition, if the application embodiments have descriptions of "first", "second", etc., the "first", "second", etc. descriptions are only for description purposes and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or cannot be realized, it should be considered that the combination of technical solutions does not exist and is not within the protection scope required by the application.

[0060] Figure 1 The flowchart of the method for elevator over-occupancy management according to the embodiments of the application is schematically shown. As shown in the figure, the embodiments of the application provide a method for elevator over-occupancy management, which is applied to an image acquisition device arranged in an elevator. The method can include the following steps. Figure 1

[0061] Step 101, acquiring an image of the elevator;

[0062] Step 102, determining initial data of the elevator according to the image;

[0063] Step 103, filtering the data in the initial data within the range of the cage door of the elevator by an out-of-cage filtering algorithm to obtain in-cage data;

[0064] Step 104, correcting the in-cage data by an abnormality filtering algorithm to obtain target data;

[0065] Step 105, judging whether to send an alarm signal according to the target data.

[0066] In the following, the method for elevator over-occupancy management provided by the embodiments of the application will be described mainly taking the processor as an execution subject.

[0067] ​In the embodiment of the present application, the processor can obtain target data according to the image of the elevator, so as to determine whether an alarm signal needs to be sent. The image acquisition device is provided with an image acquisition module, a memory and a processor. For example, the image acquisition device can be a camera integrated with an AI chip, and the AI chip can complete the configured control algorithm. The processor has a trained elevator passenger number calculation algorithm model written in, so that in the case of obtaining an image, the image acquisition device will automatically run the elevator passenger number calculation algorithm model in the processor to count the number of people in the elevator cage and send the data to the controller of the elevator.

[0068] The processor can obtain the image of the elevator through the image acquisition module in the image acquisition device. In the case of obtaining the image of the elevator, the processor can determine the initial data of the elevator based on the elevator passenger number calculation algorithm based on convolutional neural network. The elevator passenger number calculation algorithm based on convolutional neural network can detect personnel in the elevator. The algorithm includes but is not limited to YOLO algorithm, region convolutional neural network (R-CNN) and SSD algorithm. According to the obtained image of the elevator, the processor can determine the initial data of the elevator through the elevator passenger number calculation algorithm. The initial data includes the number of personnel in the elevator and the pixel coordinates of each personnel.

[0069] Since the position of the image acquisition device is fixed, the cage door range in the image obtained by the image acquisition device is also fixed. The cage door range in the image can be determined by calibrating the cage door of the elevator. The cage door range refers to the range of the cage door of the elevator displayed in the image. In the case that the pixel coordinates of the personnel within the preset number are within the cage door range, the processor can determine that the personnel is outside the elevator and exclude the personnel from the cage data, i.e. filter the data within the initial data within the cage door range of the elevator. By filtering the initial data through the cage-out filtering algorithm, the processor can obtain the cage-in data. The cage-in data includes the number of personnel located in the elevator. In this way, the false detection rate can be reduced.

[0070] Further, the processor can correct the cage-in data through an abnormality filtering algorithm to obtain target data, i.e. collect a preset number of cage-in data, remove the maximum value and the minimum value of the plurality of cage-in data, and take the average value of the remaining cage-in data as the target data. The processor can determine whether to send an alarm signal according to the target data. By correcting the cage-in data through the abnormality filtering algorithm, the accuracy of identifying the number of people in the elevator can be improved.

[0071] The above technical solution acquires images of the elevator and determines initial data based on these images. An external filtering algorithm filters data within the elevator cage door area from the initial data to obtain internal data. An anomaly filtering algorithm then corrects the internal data to obtain the target data. Finally, the target data is used to determine whether to send an alarm signal. This application, by integrating the processor into the image acquisition device, simplifies the hardware structure, increases recognition speed, and improves the accuracy of identifying the number of people in the elevator, while reducing false positive and false negative rates.

[0072] In this embodiment of the application, step 103, filtering the data within the elevator cage door range of the initial data using an external cage filtering algorithm to obtain the internal cage data, may include:

[0073] The cage doors of the elevator are calibrated to determine the range of cage doors for the elevator;

[0074] Determine whether each person is within the cage door area based on the pixel coordinates of the personnel in the initial data;

[0075] The number of people not located within the cage door area is defined as the cage interior data.

[0076] Specifically, since people outside the elevator may appear within the field of view of the image acquisition device, the processor can use an outside-cage filtering algorithm to filter the number of people outside the elevator to obtain the inside-cage data. The position of the image acquisition device is fixed; therefore, the cage door range in the image acquired by the image acquisition device is also fixed. The cage door range in the image can be determined by calibrating the elevator's cage door. Based on the pixel coordinates of the people in the initial data, it is determined whether each person is within the cage door range. If the pixel coordinates of a preset number of people are all within the cage door range, the processor can determine that the person is outside the elevator and exclude them from the inside-cage data, i.e., filter the data in the initial data that are within the elevator's cage door range. People not within the cage door range are those inside the elevator. The processor can determine the number of people not within the cage door range as the inside-cage data.

[0077] Figure 2 A schematic diagram illustrating an image recognition result of an elevator according to an embodiment of this application is shown. Figure 2As shown, the elevator can include a cage door 201. The cage door 201 range in the image can be determined by calibrating the cage door 201 of the elevator. According to the pixel coordinates of the person 202 in the initial data, it is determined whether each person is located in the cage door range. In the case that the preset number of pixel coordinates of the person 202 are all within the cage door 201 range, the processor can determine that the person 202 is outside the elevator, and the person 202 is not counted in the cage data, that is, the data in the initial data within the cage door 201 range is filtered. Finally, the processor can determine the number of persons 202 not located in the cage door 201 range as the cage data, so as to improve the accuracy of identification and reduce the false detection rate.

[0078] In the embodiment of the present application, determining whether each person is located in the cage door range according to the pixel coordinates of the person in the initial data can include:

[0079] determining a preset number of pixel coordinates of each person respectively;

[0080] determining whether the preset number of pixel coordinates of each person are all within the cage door range respectively;

[0081] For any person, in the case that at least one of the preset number of pixel coordinates of the person is not within the cage door range, the person is determined as a person not located in the cage door range.

[0082] Specifically, the processor can determine the person not located in the cage door range according to the preset number of pixel coordinates of each person. In the embodiment of the present application, the preset number is 4. That is, the processor can determine the first pixel coordinate, the second pixel coordinate, the third pixel coordinate and the fourth pixel coordinate of each person based on the elevator person number calculation algorithm. In the case that the four pixel coordinates of each person are determined based on the elevator person number calculation algorithm, the processor can determine whether each person is located in the elevator through the four pixel coordinates of each person respectively. If at least one of the four pixel coordinates of each person is not within the cage door range, it is determined that the person is located in the elevator. If the four pixel coordinates of each person are all within the cage door range, it is determined that the person is located outside the elevator.

[0083] As Figure 2As shown, the processor can determine the person 202 not located in the range of the cage door 201 according to the preset number of pixel coordinates of each person 202. The person 202 not located in the range of the cage door 201 refers to the person 202 in the elevator. In the embodiment of the present application, the preset number is 4. That is, the processor can determine the first pixel coordinate 203, the second pixel coordinate 204, the third pixel coordinate 205 and the fourth pixel coordinate 206 of each person 202 based on the elevator passenger number calculation algorithm. In the case of determining the four pixel coordinates of each person 202 based on the elevator passenger number calculation algorithm, the processor can determine whether each person 202 is located in the elevator through the four pixel coordinates of each person 202. If at least one of the four pixel coordinates of each person 202 is not in the range of the cage door 201, it is determined that the person 202 is located in the elevator. If the four pixel coordinates of each person 202 are all in the range of the cage door 201, it is determined that the person 202 is located outside the elevator. Through the cage-out filtering algorithm, the processor can filter the person 202 outside the elevator in the field of view of the image acquisition device, improve the accuracy of identifying the number of persons 202 in the elevator, and reduce the false detection rate and the missed detection rate.

[0084] In the embodiment of the present application, step 104, modifying the cage-in data through the abnormal filtering algorithm to obtain the target data can include:

[0085] Obtaining a preset number of cage-in data to obtain a plurality of cage-in data;

[0086] Removing the maximum value and the minimum value of the plurality of cage-in data to obtain remaining cage-in data;

[0087] Determining the target data according to the mean value of the remaining cage-in data.

[0088] Specifically, the processor can correct the cage-in data by the exception filtering algorithm to obtain the target data. First, the processor needs to obtain initial data of a preset number of times, and filter the data in the initial data within the range of the cage door of the elevator by the cage-out filtering algorithm to obtain cage-in data of a preset number of times. The processor can create a queue of a preset capacity in advance, and list the obtained cage-in data in the queue in chronological order until the preset capacity is reached. The preset capacity matches the preset number of times. In an example, the processor can create a queue of a capacity of 10 in advance, and then obtain cage-in data of a preset number of times, and list the cage-in data in the queue in chronological order of the time when the cage-in data is obtained. It should be noted that the cage-in data obtained later is arranged first. In this way, it can be ensured that the plurality of cage-in data obtained finally is the latest cage-in data obtained by the processor. In the case of obtaining a plurality of cage-in data, the processor can remove the maximum value and the minimum value in the plurality of cage-in data to obtain remaining cage-in data, and determine the mean value of the remaining cage-in data as the target data. In the case that the mean value of the remaining cage-in data contains a decimal, the processor can round up to determine the target data. In an example, the remaining cage-in data is 5, 6, 6, 6, and 6, and then the mean value of the remaining cage-in data is 5.8, at this time, the processor rounds up to determine the target data as 6. By correcting the cage-in data by the exception filtering algorithm, the accuracy of identifying the number of people in the elevator can be improved, and the false detection rate and the missed detection rate can be reduced.

[0089] In the embodiment of the present application, step 105, determining whether to send an alarm signal according to the target data can include:

[0090] determining whether the target data is greater than a preset value;

[0091] in the case that the target data is greater than the preset value, sending an alarm signal;

[0092] in the case that the target data is not greater than the preset value, not sending an alarm signal.

[0093] Specifically, the processor can determine whether to send an alarm signal according to the target data. According to the actual situation, a preset value can be set in advance. The preset value is used to determine whether the elevator is overloaded. The processor can determine whether the target data is greater than the preset value. In the case that the target data is greater than the preset value, an alarm signal is sent. In the case that the target data is not greater than the preset value, no alarm signal is sent. In an example, the preset value is 12, in the case that the target data is greater than 12, an alarm signal is sent; in the case that the target data is not greater than 12, no alarm signal is sent. In this way, the demand for elevator overstaff management can be met.

[0094] In the embodiment of the present application, the image acquisition device communicates with the controller of the elevator, and step 102, determining the initial data of the elevator according to the image can include:

[0095] In a case where the start closing signal sent by the controller is received, initial data of the elevator is determined according to the image;

[0096] The method can further include:

[0097] In a case where the complete closing signal sent by the controller is acquired, the target data is sent to the controller of the elevator.

[0098] Specifically, the processor can communicate with the controller of the elevator. The controller of the elevator sends a start closing signal to the processor when the cage door of the elevator starts to close. In a case where the start closing signal sent by the controller is received, the processor can determine initial data of the elevator according to the image. The controller of the elevator sends a complete closing signal to the processor when the cage door of the elevator is completely closed. In a case where the complete closing signal sent by the controller is acquired, the processor can send the target data to the controller of the elevator. In this way, the efficiency of collecting data can be improved, and it is ensured that the elevator can be managed in time in the case of overloading.

[0099] In the embodiments of the present application, the image acquisition device also communicates with the management terminal, and the method can further include:

[0100] In a case where it is determined to send an alarm signal, the alarm signal is sent to the management terminal, and the operation of the elevator is suspended; and / or

[0101] In a case where it is determined to send an alarm signal, the alarm signal is sent to the controller, and the operation of the elevator is suspended.

[0102] Specifically, the processor can send an alarm signal to the management terminal and / or to the controller of the elevator. According to the target data, in a case where the processor determines that the alarm signal needs to be sent, the processor can send the alarm signal to the management terminal, and suspend the ascending, descending of the elevator, and / or send the alarm signal to the controller, and suspend the ascending, descending of the elevator. In a case where the alarm signal is received by the management terminal and / or the controller of the elevator, the management terminal and / or the controller of the elevator perform overloading alarm. The overloading alarm mode includes but is not limited to sound alarm, voice alarm and vibration alarm. By sending the alarm signal to the management terminal and / or the controller of the elevator, the way to manage the elevator can be increased, and the possibility that the elevator cannot be controlled due to the failure of the management terminal or the controller of the elevator can be reduced.

[0103] Figure 3 The structure block diagram of the image acquisition device according to the embodiments of the present application is schematically shown. As shown in FIG. 3, the embodiments of the present application provide an image acquisition device, which can include:

[0104] The image acquisition module 310 is configured to acquire an image of the elevator;

[0105] The memory 320 is configured to store instructions; and

[0106] The processor 330 is configured to call the instructions from the memory 320 and implement the above-mentioned method for elevator overpopulation management when the instructions are executed.

[0107] Specifically, in the embodiment of the present application, the processor 330 can be configured to:

[0108] acquire an image of the elevator;

[0109] determine initial data of the elevator according to the image;

[0110] filter data within the cage door range in the initial data by an out-of-cage filtering algorithm to obtain in-cage data;

[0111] correct the in-cage data by an anomaly filtering algorithm to obtain target data;

[0112] determine whether to send an alarm signal according to the target data.

[0113] Further, the processor 330 can also be configured to:

[0114] calibrate the cage door of the elevator to determine the cage door range of the elevator;

[0115] determine whether each person is located within the cage door range according to the pixel coordinates of the person in the initial data;

[0116] determine the number of persons not located within the cage door range as the in-cage data.

[0117] Further, the processor 330 can also be configured to:

[0118] determine a preset number of pixel coordinates of each person;

[0119] determine whether the preset number of pixel coordinates of each person are all within the cage door range;

[0120] for any person, in a case where at least one of the preset number of pixel coordinates of the person is not within the cage door range, determine the person as a person not located within the cage door range.

[0121] Further, the processor 330 can also be configured to:

[0122] acquire in-cage data of a preset number of times to obtain a plurality of in-cage data;

[0123] remove the maximum value and the minimum value of the plurality of in-cage data to obtain remaining in-cage data;

[0124] determining the target data according to the mean value of the remaining cage data.

[0125] Further, the processor 330 can be further configured to:

[0126] determining whether the target data is greater than a preset value;

[0127] in a case where it is determined that the target data is greater than the preset value, sending an alarm signal;

[0128] in a case where it is determined that the target data is not greater than the preset value, not sending the alarm signal.

[0129] Further, the processor 330 can be further configured to:

[0130] in a case where a start closing signal sent by the controller is received, determining initial data of the elevator according to the image;

[0131] The method further includes:

[0132] in a case where a complete closing signal sent by the controller is acquired, sending the target data to the controller of the elevator.

[0133] Further, the processor 330 can be further configured to:

[0134] in a case where it is determined to send the alarm signal, sending the alarm signal to a management terminal and suspending operation of the elevator; and / or

[0135] in a case where it is determined to send the alarm signal, sending the alarm signal to the controller and suspending operation of the elevator.

[0136] Through the above technical solution, the image of the elevator is acquired, and the initial data of the elevator is determined according to the image. The cage data is obtained by filtering the data in the initial data within the range of the cage door of the elevator through the cage-out filtering algorithm, and the target data is obtained by correcting the cage data through the abnormal filtering algorithm. Finally, whether to send an alarm signal is determined according to the target data. The processor is arranged in the image acquisition device in the present application, which can simplify the hardware structure, improve the recognition speed, improve the accuracy of recognizing the number of people in the elevator, and reduce the false detection rate and the missed detection rate.

[0137] Figure 4 A structural diagram of an elevator overpopulation management device according to an embodiment of the present application is schematically shown. As shown in Figure 4 The present application further provides an elevator overpopulation management device, which can include:

[0138] the image acquisition device 401 described above;

[0139] The controller 402 of the elevator, in communication with the image acquisition device 401, is configured to send a start closing signal and a complete closing signal to the image acquisition device 401, and receive target data and an alarm signal sent by the image acquisition device 401;

[0140] The management terminal 403, in communication with the image acquisition device 401, is configured to receive the alarm signal sent by the image acquisition device 401.

[0141] Specifically, the image acquisition device 401 comprises an image acquisition module, a memory and a processor. The image acquisition module is configured to acquire images of the elevator. The controller 402 of the elevator, in communication with the image acquisition device 401, is configured to send a start closing signal and a complete closing signal to the image acquisition device 401, and receive target data and an alarm signal sent by the image acquisition device 401. The management terminal 403, in communication with the image acquisition device 401, is configured to receive the alarm signal sent by the image acquisition device 401. Upon receiving the alarm signal sent by the image acquisition device 401, the controller 402 of the elevator and the management terminal 403 can both temporarily stop the operation of the elevator and perform an overpopulation alarm.

[0142] The embodiment of the present application also provides a machine readable storage medium, which stores instructions for causing a machine to execute the method for overpopulation management of an elevator.

[0143] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer-usable program code.

[0144] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks

[0145] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0146] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that are executed on the computer or other programmable apparatus provide steps for implementing the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0147] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0148] The memory can include non-persistent memory and / or volatile memory, such as a random access memory (RAM) including a cache area for the temporary storage of data. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), flash memory, or a combination of non-volatile memories in different forms. The memory is an example of computer readable storage media.

[0149] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media, such as modulated data signals and carrier waves.

[0150] It should also be noted that the terms "comprising", "comprises" or other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0151] The above embodiments are only used to illustrate the present application, but not to limit it. Instead of the above, various modifications and changes can be made to the application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall fall into the scope of the claims of the application.

Claims

1. A method for managing overcrowding in elevators, characterized in that, Applied to an image acquisition device, wherein the image acquisition device is installed in an elevator, the method includes: Acquire an image of the elevator; The initial data of the elevator is determined based on the image, wherein the initial data includes the number of people inside the elevator, the number of people outside the elevator, and a preset number of pixel coordinates for each person; The initial data within the range of the elevator cage door is filtered by an external filtering algorithm to obtain the internal data, which includes the number of people inside the elevator. The data within the cage is corrected using an anomaly filtering algorithm to obtain the target data; Determine whether to send an alarm signal based on the target data.

2. The method according to claim 1, characterized in that, The step of filtering the initial data within the range of the elevator cage door using an external filtering algorithm to obtain the internal data includes: The cage door of the elevator is calibrated to determine the range of the cage door of the elevator; Based on the pixel coordinates of the personnel in the initial data, determine whether each person is within the range of the cage door; The number of people not located within the cage door area is defined as the cage interior data.

3. The method according to claim 2, characterized in that, The step of determining whether each person is within the cage door area based on the pixel coordinates of the persons in the initial data includes: Determine a preset number of pixel coordinates for each person; Determine whether the preset number of pixel coordinates for each person are all within the cage door range; For any person, if at least one of the preset number of pixel coordinates of the any person is not within the range of the cage door, the any person is determined to be a person not located within the range of the cage door.

4. The method according to claim 1, characterized in that, The step of correcting the data within the cage using an anomaly filtering algorithm to obtain the target data includes: Acquire the cage data a preset number of times to obtain multiple cage data sets; Remove the maximum and minimum values ​​of the multiple cage data to obtain the remaining cage data; The target data is determined based on the mean of the remaining data in the cage.

5. The method according to claim 1, characterized in that, The step of determining whether to send an alarm signal based on the target data includes: Determine whether the target data is greater than a preset value; If the target data is determined to be greater than the preset value, the alarm signal is sent. If the target data is determined to be no greater than the preset value, the alarm signal will not be sent.

6. The method according to claim 1, characterized in that, The image acquisition device communicates with the elevator's controller, and determining the elevator's initial data based on the image includes: Upon receiving a start-stop signal from the controller, the initial data of the elevator is determined based on the image; The method further includes: Upon receiving a complete shutdown signal from the controller, the target data is sent to the elevator controller.

7. The method according to claim 6, characterized in that, The image acquisition device also communicates with a management terminal, and the method further includes: If an alarm signal is detected, the alarm signal is sent to the management terminal, and the operation of the elevator is suspended; and / or If an alarm signal is detected, the alarm signal is sent to the controller, and the operation of the elevator is suspended.

8. An image acquisition device, characterized in that, include: The image acquisition module is configured to acquire images of the elevator. The memory is configured to store instructions; as well as A processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the method for managing elevator overcrowding according to any one of claims 1 to 7.

9. A device for managing overcrowding in elevators, characterized in that, include: The image acquisition device according to claim 8; The elevator controller communicates with the image acquisition device and is configured to send start-off signals and complete-off signals to the image acquisition device, and to receive target data and alarm signals sent by the image acquisition device. The management terminal communicates with the image acquisition device and is configured to receive alarm signals sent by the image acquisition device.

10. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to perform the method of elevator overcrowding management according to any one of claims 1 to 7.

Images