Person number recognition method, device, system, storage medium and electronic device

Abstract

The application discloses a kind of crowd identification method, device, system, storage medium and electronic equipment, and elevator safety monitoring technical field, a kind of crowd identification method, comprising: obtaining first cage personnel distribution map, the first cage personnel distribution map is obtained using visual recognition technology;Obtain cage weight information, and obtain second cage personnel distribution map based on the cage weight information;The first cage personnel distribution map and second cage personnel distribution map are mutually checked, and the crowd identification result is obtained.Through the feedback weight value of cage bottom, i.e.second cage personnel distribution map and the personnel distribution map, i.e.first cage personnel distribution map, which is fed back by the person number recognition camera, is mutually checked to determine the number of people in the cage, which can correct the misjudgment of the camera, thereby improving the crowd identification result.

Description

Technical Field

[0001] This application relates to the field of elevator safety monitoring technology, specifically to a people identification method, a people identification device, a people identification system, a machine-readable storage medium, and an electronic device. Background Technology

[0002] Elevators are a primary tool for transporting personnel. Currently, an increasing number of elevators operate fully automatically. To prevent overcrowding and ensure passenger safety, elevators require increasingly stringent measures for detecting the number of people inside the cage. Therefore, a safe and reliable personnel detection method is essential for the safe operation of elevators.

[0003] Most existing elevators use cameras to identify the number of people inside the cage through visual recognition technology. However, the accuracy of this identification method is greatly affected by the lighting inside the cage and the distribution of people. The accuracy is not high, and the identification results can only be used as a reference and cannot be used as an accurate basis for control.

[0004] Therefore, existing methods for recognizing people in elevators suffer from low accuracy. Summary of the Invention

[0005] The purpose of this application is to provide a people recognition method, a people recognition device, a people recognition system, a machine-readable storage medium, and an electronic device to solve the problem of low accuracy in people recognition in the prior art.

[0006] To achieve the above objectives, the first aspect of this application provides a method for recognizing people, comprising:

[0007] A distribution map of the people inside the first cage is obtained using visual recognition technology.

[0008] Obtain the weight information inside the cage, and obtain the personnel distribution map inside the second cage based on the weight information inside the cage;

[0009] The distribution maps of people in the first cage and the distribution maps of people in the second cage are cross-checked to obtain the number of people identification results.

[0010] In this embodiment of the application, the step of cross-checking the distribution map of the people in the first cage and the distribution map of the people in the second cage to obtain the number of people identification results includes:

[0011] Determine whether the personnel distribution map in the first cage and the personnel distribution map in the second cage are the same;

[0012] If the distribution map of people in the first cage and the distribution map of people in the second cage are the same, the number of people is identified based on the distribution map of people in the first cage or the distribution map of people in the second cage.

[0013] If the distribution map of people in the first cage is different from that in the second cage, the distribution map of people in the first cage or the distribution map of people in the second cage is corrected to obtain the number of people identification results.

[0014] In this embodiment of the application, the step of correcting the personnel distribution map in the first cage or the personnel distribution map in the second cage to obtain the personnel identification result includes:

[0015] If it is determined that the number of people in the first cage distribution map is less than the number of people in the second cage distribution map, a first difference region is obtained based on the first cage distribution map and the second cage distribution map.

[0016] Visual recognition technology is used to perform human body recognition on the first difference region to obtain the first difference recognition result;

[0017] Based on the first difference identification result, the number of people in the personnel distribution map of the first cage is corrected to obtain the number of people identification result.

[0018] In this embodiment of the application, the step of correcting the personnel distribution map in the first cage or the personnel distribution map in the second cage to obtain the personnel identification result includes:

[0019] If it is determined that the number of people in the first cage distribution map is greater than the number of people in the second cage distribution map, a second difference region is obtained based on the first cage distribution map and the second cage distribution map.

[0020] Determine the weight information of the second difference region;

[0021] Based on the distribution map of people in the first cage, determine the personnel information of the second difference area and obtain the number of people in the difference area;

[0022] Based on the weight information and the number of people in the second difference area, determine whether the distribution map of people in the first cage is incorrect;

[0023] If the distribution map of people in the first cage is confirmed to be incorrect, the number of people in the distribution map of people in the first cage or the number of people in the distribution map of people in the second cage is corrected to obtain the number of people identification results.

[0024] In this embodiment of the application, determining whether the personnel distribution map in the first cage is erroneous based on the weight information and the number of different personnel in the second difference region includes:

[0025] The theoretical weight is obtained by multiplying the preset weight value by the number of people with the difference.

[0026] Based on the theoretical weight and the weight information of the second difference region, determine whether the personnel distribution map in the first cage is incorrect.

[0027] In this embodiment of the application, the weight information inside the cage includes the weight information of multiple small pieces;

[0028] The process of obtaining the personnel distribution map in the second cage based on the weight information inside the cage includes:

[0029] Based on the weight information of the multiple small blocks, the shape of the contact surface under the force of the cage bottom plate is simulated to obtain the personnel distribution map inside the second cage.

[0030] A second aspect of this application provides a people recognition system for an elevator, comprising: a people recognition camera, a controller, and a weight detection device; the weight detection device is located on the back of the elevator cage bottom plate, and the people recognition camera is located inside the elevator cage;

[0031] The people recognition camera is used to acquire a distribution map of people in the first cage and send the distribution map of people in the first cage to the controller;

[0032] The weight detection device is used to acquire the weight information inside the cage and send the weight information inside the cage to the controller;

[0033] The controller is used to obtain a second distribution map of people in the cage based on the weight information in the cage, and to cross-check the first distribution map of people in the cage and the second distribution map of people in the cage to obtain the number of people identification results.

[0034] A third aspect of this application provides a people recognition device, comprising:

[0035] The first acquisition module is used to acquire a distribution map of people inside the first cage, which is obtained using visual recognition technology.

[0036] The second acquisition module is used to acquire the weight information inside the cage and obtain a distribution map of the people inside the second cage based on the weight information inside the cage.

[0037] The cross-verification module is used to cross-verify the personnel distribution map in the first cage and the personnel distribution map in the second cage to obtain the personnel identification result.

[0038] A fourth aspect of this application provides an electronic device, the electronic device comprising:

[0039] At least one processor;

[0040] A memory connected to the at least one processor;

[0041] The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the above-described people recognition method by executing the instructions stored in the memory.

[0042] A fifth aspect of this application provides a machine-readable storage medium storing instructions that, when executed by a processor, configure the processor to perform the aforementioned people recognition method.

[0043] The above technical solution involves obtaining a first distribution map of people inside the cage using visual recognition technology; then acquiring weight information inside the cage and obtaining a second distribution map of people inside the cage based on this weight information; and cross-calibrating the first and second distribution maps to obtain the number of people. By cross-calibrating the weight (force) value fed back from the cage bottom (i.e., the second distribution map of people inside the cage) with the distribution map fed back from the people recognition camera (i.e., the first distribution map of people inside the cage), the number of people inside the cage can be determined, which can correct for camera misjudgments and thus improve the number of people recognition results.

[0044] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0045] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0046] Figure 1 The illustration shows a flowchart of a people recognition method according to an embodiment of this application;

[0047] Figure 2 A schematic diagram of a foot according to an embodiment of this application is shown;

[0048] Figure 3 A flowchart illustrating the process of recognizing passengers in an elevator according to an embodiment of this application is shown schematically.

[0049] Figure 4 A schematic diagram of a hoist cage according to an embodiment of this application is shown.

[0050] Figure 5 A schematic diagram of the back surface components of the cage bottom plate according to an embodiment of this application is shown.

[0051] Figure 6 A partial view of the back of the cage bottom plate according to an embodiment of this application is schematically shown;

[0052] Figure 7The schematic diagram illustrates a structural schematic of a people recognition device according to an embodiment of this application;

[0053] Figure 8 The diagram illustrates the internal structure of a computer device according to an embodiment of this application.

[0054] Explanation of reference numerals in the attached figures

[0055] 1-People recognition camera; 2-Controller; 3-Cage bottom plate; 4-Weight detection device; 5-Power supply and signal line; 410-First acquisition module; 420-Second acquisition module; 430-Mutual calibration module; A01-Processor; A02-Network interface; A03-Internal memory; A04-Display screen; A05-Input device; A06-Non-volatile storage medium; B01-Operating system; B02-Computer program. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0057] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0058] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0059] Please refer to Figure 1 and Figure 4 , Figure 1 This illustration schematically shows a flowchart of a people recognition method according to an embodiment of this application. Figure 4 A schematic diagram of a hoist cage according to an embodiment of this application is shown. Figure 1 As shown in the figure, this application provides a method for people recognition, which may include the following steps:

[0060] Step 210: Obtain the distribution map of the people in the first cage, which is obtained using visual recognition technology;

[0061] In this embodiment, the personnel distribution map inside the first cage can be obtained by real-time monitoring of the cage by a camera inside the hoist cage that identifies the number of people, and transmitting the identified number and distribution of people to the controller 2. Specifically, the number of people inside the cage and the personnel distribution map are identified by visual recognition technology using a camera inside the cage. Specific methods can include head feature recognition, head and shoulder feature recognition, etc.

[0062] Step 220: Obtain the weight information inside the cage, and obtain the personnel distribution map inside the second cage based on the weight information inside the cage;

[0063] In this embodiment, the cage bottom plate 3 of the elevator cage is the load-bearing plate at the bottom of the elevator cage. A weight detection device 4 can be installed on the cage bottom plate 3. When the cage bottom plate 3 is compressed, the weight detection device 4 deforms, and outputs different voltage or current values ​​according to the magnitude of the deformation, thereby reflecting the real-time weight value and obtaining the weight information inside the cage. In some embodiments, the cage bottom plate 3 can be divided into several small pieces, with a weight detection device 4 installed on the back of each piece. When the cage bottom plate 3 is compressed, the weight detection device 4 deforms, and outputs different voltage or current values ​​according to the magnitude of the deformation, thereby reflecting the real-time weight value and obtaining the weight information inside the cage. The method of dividing the cage bottom plate 3 into several small pieces, with a weight detection device 4 installed on the back of each piece, provides more accurate weight information inside the cage. By using the weight feedback from the small squares, the foot contours are obtained, leading to a distribution map of the people inside the cage and ultimately determining the number of people inside.

[0064] In some embodiments, the weight information inside the cage includes weight information of multiple small blocks; obtaining the second personnel distribution map inside the cage based on the weight information inside the cage includes: simulating the contact surface shape of the cage bottom plate 3 under stress based on the multiple small block weight information to obtain the second personnel distribution map inside the cage.

[0065] In this embodiment, when personnel or goods move onto the cage bottom plate 3, the various small blocks of the cage bottom plate 3 will deform under stress. At this time, the weight detection device 4 can measure the weight of the personnel or goods on that small block and transmit the test weight value to the controller 2 in real time. Based on the weight value transmitted by each small block, the controller 2 can simulate the contact surface shape between the cage bottom plate 3 and the personnel or goods, and thus simulate the weight distribution map inside the entire cage to obtain the personnel distribution map inside the second cage. Figure 2 As shown, Figure 2 A schematic diagram of the foot assembly according to an embodiment of this application is shown. The weight distribution shape within the cage can be simulated based on the weight information of each small component, thus obtaining a personnel distribution diagram within the second cage.

[0066] Step 230: Cross-check the personnel distribution map in the first cage and the personnel distribution map in the second cage to obtain the personnel identification result.

[0067] In this embodiment, after obtaining the personnel distribution maps of the first and second cages, the corresponding personnel identification results can be obtained from the first and second cage personnel distribution maps respectively. Since the personnel distribution map of the first cage is obtained by the camera from above the cage, and the personnel distribution map of the second cage is obtained based on weight information, the first and second personnel distribution maps can be cross-calibrated to obtain more accurate personnel identification results.

[0068] In some embodiments, the cross-calibration of the personnel distribution map in the first cage and the personnel distribution map in the second cage to obtain the personnel identification result includes the following steps:

[0069] First, determine whether the personnel distribution map in the first cage and the personnel distribution map in the second cage are the same;

[0070] In this embodiment, the distribution map of the people in the first cage and the distribution map of the people in the second cage can be placed in the same coordinate system to determine whether the shapes of the two distribution maps of the people in the cage are consistent, so as to determine whether the distribution map of the people in the first cage and the distribution map of the people in the second cage are the same.

[0071] Then, if it is determined that the distribution map of people in the first cage is the same as the distribution map of people in the second cage, the number of people is identified based on the distribution map of people in the first cage or the distribution map of people in the second cage.

[0072] Then, if it is determined that the distribution map of people in the first cage is different from that in the second cage, the distribution map of people in the first cage or the distribution map of people in the second cage is corrected to obtain the number of people identification results.

[0073] In this embodiment, if the personnel distribution map in the first cage and the personnel distribution map in the second cage are the same, it means that the personnel situation identified by the camera is the same as the personnel situation obtained by weight identification, indicating that the cross-calibration is successful. In this case, the number of people in the first cage or the second cage personnel distribution map is directly output to obtain the personnel identification result. If the personnel distribution map in the first cage and the second cage are different, it means that the cross-calibration has failed, and redundant personnel need to be removed. That is, the personnel distribution map in the first cage or the second cage personnel distribution map needs to be corrected to obtain the personnel identification result.

[0074] In practice, controller 2 can perform a verification based on the personnel distribution maps of the first and second cages transmitted by the people recognition camera 1. This process eliminates interference from non-human weights. For example, if there are other heavy objects in the cage, there will be weight feedback, but the image from the people recognition camera will clearly not be a human body. There are also cases where people are obstructing each other, and the camera does not capture complete personnel information, but according to the weight distribution map, there are two people's weights at the obstruction point, which match the contact surface of human feet, thus indicating that someone is present. Through this cross-verification of the personnel distribution maps of the first and second cages, an accurate number of people in the cages is obtained. Finally, the calculated number of people in the cages is used to control the start and stop of the elevator. When there are too many people, the elevator operation is prohibited, and excess personnel are reminded to leave the elevator.

[0075] When the personnel distribution maps in the first and second cages differ, one possibility is that the number of people at the bottom of the cage exceeds the number of people captured by the camera. In other words, the number of people in the second cage distribution map is greater than the number in the first cage distribution map. This could be due to tools, vehicles, or other objects entering the cage, causing the weight recognition to misidentify them as people. In this case, the camera can be used to re-identify the relevant area, and the personnel recognition result can be corrected after confirming that the objects are not human. In some embodiments, correcting the personnel distribution map in the first or second cage to obtain the personnel recognition result includes the following steps:

[0076] First, if it is determined that the number of people in the first cage distribution map is less than the number of people in the second cage distribution map, a first difference region is obtained based on the first cage distribution map and the second cage distribution map.

[0077] In this embodiment, by comparing the personnel distribution map in the first cage with the personnel distribution map in the second cage, a first difference area can be obtained. The first difference area refers to the area where there is a difference in personnel identification.

[0078] Then, visual recognition technology is used to perform human body recognition on the first difference region to obtain the first difference recognition result;

[0079] Finally, based on the first difference identification result, the number of people in the distribution map of the people in the first cage is corrected to obtain the number of people identification result.

[0080] In this embodiment, a camera is used to perform human body recognition on the first difference area to determine whether the first difference area is a person. If all of them are people, the number of people in the personnel distribution map in the first cage is corrected according to the number of people identified, and the number of people is obtained. If none of them are people, the number of people identified in that part is removed, and the number of people is obtained. If some of them are people, the number of people in the personnel distribution map in the first cage is corrected according to the number of people identified, and the part that is not a person is removed, and the number of people is obtained.

[0081] By performing visual recognition on the first difference area again, the number of people in the distribution map of the people in the first cage can be corrected, and the number of people can be identified. This can avoid misidentification of non-person items, thereby improving the accuracy of the number of people identification.

[0082] When the personnel distribution maps in the first and second cages differ, a second possibility exists: the camera may recognize more people than the weight, meaning the number of people in the second cage distribution map is less than the number in the first cage distribution map. This could be due to the camera misidentifying a helmet or other round object. In some embodiments, correcting the first or second cage distribution map to obtain the personnel recognition result includes:

[0083] First, if it is determined that the number of people in the first cage distribution map is greater than the number of people in the second cage distribution map, a second difference region is obtained based on the first cage distribution map and the second cage distribution map.

[0084] In this embodiment, by comparing the personnel distribution map in the first cage and the personnel distribution map in the second cage, a second difference area can be obtained. The aforementioned second difference area refers to the area where there are differences in personnel identification.

[0085] Then, the weight information of the second difference region is determined;

[0086] In this embodiment, after determining the second difference region, the weight information of the second difference region can be obtained based on the weight information of the small piece corresponding to the second difference region.

[0087] Then, based on the personnel distribution map in the first cage, the personnel information in the second difference area is determined, and the number of difference personnel is obtained;

[0088] In this embodiment, based on the second difference region, the corresponding personnel information can be determined from the personnel distribution map in the first cage to obtain the number of different personnel.

[0089] Then, based on the weight information and the number of people in the second difference area, it is determined whether the distribution map of people in the first cage is incorrect;

[0090] The process of the above judgment includes:

[0091] The first step is to calculate the product of the preset weight value and the number of people with the difference to obtain the theoretical weight;

[0092] The second step is to determine whether the distribution map of the people in the first cage is incorrect, based on the theoretical weight and the weight information of the second difference area.

[0093] Finally, if it is confirmed that the distribution map of people in the first cage is incorrect, the number of people in the distribution map of the first cage or the number of people in the distribution map of the second cage is corrected to obtain the number of people identification results.

[0094] In this embodiment, after calculating the theoretical weight, the system compares the theoretical weight with the weight information of the second difference region. If the weight significantly deviates from the number of people multiplied by their weight, meaning the weight information of the second difference region does not meet the theoretical weight, the system considers this a camera misjudgment. Therefore, the system corrects the number of people in either the first or second cage's personnel distribution map. This correction can involve removing the number of people with discrepancies from the number of people with discrepancies in the first cage's personnel distribution map. If the condition is met, it indicates the camera's recognition is correct, and the number of people with discrepancies can be added to the number of people with discrepancies in the second cage's personnel distribution map.

[0095] By verifying the second difference region based on its weight information, if the weight information in the second difference region is found to be significantly different from the number of people multiplied by their weight, the system considers it a camera misjudgment and corrects the result. This can prevent the camera from misidentifying safety helmets or other round objects, thereby improving the accuracy of people recognition.

[0096] In the above implementation process, a first personnel distribution map inside the cage is obtained using visual recognition technology. Then, weight information inside the cage is acquired, and a second personnel distribution map inside the cage is obtained based on this weight information. The first and second personnel distribution maps are cross-calibrated to obtain the personnel identification result. By cross-calibrating the weight (force) value fed back from the cage bottom (i.e., the second personnel distribution map) with the personnel distribution map fed back from the personnel recognition camera 1 (i.e., the first personnel distribution map), the number of people inside the cage can be determined. This can correct for camera misjudgments, thereby improving the personnel identification result. Furthermore, the personnel identification result can be used to continuously improve the cage weight and camera personnel distribution analysis technology to obtain more accurate first and second personnel distribution maps, further improving the identification accuracy and fully meeting the elevator control requirements.

[0097] It should be noted that the aforementioned personnel recognition function can be turned on or off in the construction hoist control system to cope with different operating conditions.

[0098] Figure 1 This is a flowchart illustrating a people recognition method in one embodiment. It should be understood that, although... Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0099] This embodiment provides a people recognition system for an elevator, including: a people recognition camera 1, a controller 2, and a weight detection device 4; the weight detection device 4 is located on the back of the elevator's cage bottom plate 3, and the people recognition camera 1 is located inside the elevator's cage; the people recognition camera 1 is used to acquire a first distribution map of people inside the cage and send the first distribution map to the controller 2; the weight detection device 4 is used to acquire weight information inside the cage and send the weight information to the controller 2; the controller 2 is used to obtain a second distribution map of people inside the cage based on the weight information inside the cage, and to cross-check the first and second distribution maps to obtain a people recognition result.

[0100] In this embodiment, please refer to Figures 4-6The hoist cage is equipped with a people recognition camera 1, i.e., a cage-inside people recognition camera 1. A weight detection device 4 is installed on the back of the cage bottom plate 3. The weight detection device 4 can be a strain gauge. The cage bottom plate 3 is divided into several small pieces, and a strain gauge is installed on the back of each piece. Each strain gauge is connected to the controller 2 via a power supply and signal line 5. When the cage bottom plate 3 is compressed, the strain gauge will deform, and different voltage or current values ​​will be output according to the magnitude of the deformation, thereby reflecting the real-time weight value. The aforementioned weight detection device 4 can also communicate with the controller 2 wirelessly.

[0101] Please refer to Figure 3 , Figure 3 The flowchart illustrating the elevator passenger identification process according to an embodiment of this application is shown. The weight values ​​of each block of the cage bottom plate 3 are fed back to the controller 2 for calculation via weight feedback. The controller 2 simulates a weight distribution map inside the cage and compares it with a personnel distribution map inside the cage fed back by the camera. If the two distribution maps are successfully cross-checked, the number of passengers is output; if the two distribution maps are not successfully cross-checked, the excess passengers are removed before the number of passengers is output.

[0102] It should be noted that the controller 2 mentioned above can be the controller in the elevator control system. If the people recognition camera 1 has the function of calculation and comparison, the controller 2 mentioned above can also be the people recognition camera 1. The weight detection device 4 sends the data to the people recognition camera 1 and completes all the people calculation work in the camera. The controller in the elevator control system only receives the people to control the elevator action.

[0103] In the above implementation process, a people recognition camera 1, a controller 2, and a weight detection device 4 are installed in the elevator. The weight detection device 4 is located on the back of the cage bottom plate 3 of the elevator, and the people recognition camera 1 is located inside the cage of the elevator. The people recognition camera 1 is used to acquire a first distribution map of people inside the cage and send the first distribution map to the controller 2. The weight detection device 4 is used to acquire weight information inside the cage and send the weight information inside the cage to the controller 2. The controller 2 is used to obtain a second distribution map of people inside the cage based on the weight information inside the cage, and cross-check the first and second distribution maps to obtain the people recognition result. This can correct for camera misjudgments and improve the people recognition result. Furthermore, the analysis technology of cage weight and camera personnel distribution can be continuously improved by obtaining the people recognition result to obtain more accurate first and second distribution maps of people inside the cage, further improving the recognition accuracy and fully meeting the control requirements of the elevator. Neither the weight detection device 4 nor the people recognition camera directly contacts people or transported goods, reducing the possibility of damage and interference.

[0104] Based on the same inventive concept, this embodiment provides a people recognition device, please refer to... Figure 7 , Figure 7 The schematic diagram illustrates a structure of a people recognition device according to an embodiment of this application. The people recognition device includes a first acquisition module 410, a second acquisition module 420, and a cross-verification module 430, wherein:

[0105] The first acquisition module 410 is used to acquire a distribution map of people inside the first cage, which is obtained using visual recognition technology.

[0106] The second acquisition module 420 is used to acquire the weight information inside the cage and obtain a distribution map of the people inside the second cage based on the weight information inside the cage.

[0107] The cross-verification module 430 is used to cross-verify the personnel distribution map in the first cage and the personnel distribution map in the second cage to obtain the personnel identification result.

[0108] The people recognition device includes a processor and a memory. The first acquisition module 410, the second acquisition module 420, and the start control module 430 are all stored in the memory as program units. The processor executes the program modules stored in the memory to implement the corresponding functions.

[0109] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and kernel parameters can be adjusted to avoid boot lag issues.

[0110] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0111] This invention provides a processor for running a program, wherein the program executes the people recognition method during runtime.

[0112] This application provides a machine-readable storage medium storing a program that, when executed by a processor, implements the aforementioned people recognition method.

[0113] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8As shown in the figure, the computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05, and a memory (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A06. The network interface A02 is used for communication with external terminals via a network connection. When the computer program is executed by the processor A01, it implements a people recognition method. The display screen A04 can be a liquid crystal display (LCD) or an e-ink display. The input device A05 can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0114] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0115] In one embodiment, the people recognition device provided in this application can be implemented as a computer program, and the computer program can be implemented in such a way as... Figure 8 The device runs on the computer shown. The computer's memory can store the various program modules that make up the people recognition device, for example, Figure 7 The first acquisition module 410, the second acquisition module 420, and the cross-verification module 430 are shown. The computer program comprised of these modules causes the processor to execute the steps of the people recognition methods in the various embodiments of this application described in this specification.

[0116] Figure 8 The computer device shown can be used as follows Figure 7 The first acquisition module 410 in the shown people recognition device executes step 210. The computer device can execute step 220 via the second acquisition module 420. The computer device can execute step 230 via the cross-verification module 430.

[0117] This application provides an electronic device comprising: at least one processor; and a memory connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements the aforementioned people recognition method by executing the instructions stored in the memory. When the processor executes the instructions, it performs the following steps:

[0118] A distribution map of the people inside the first cage is obtained using visual recognition technology.

[0119] Obtain the weight information inside the cage, and obtain the personnel distribution map inside the second cage based on the weight information inside the cage;

[0120] The distribution maps of people in the first cage and the distribution maps of people in the second cage are cross-checked to obtain the number of people identification results.

[0121] In one embodiment, the step of cross-checking the distribution maps of the people in the first cage and the distribution maps of the people in the second cage to obtain the number of people identification results includes:

[0122] Determine whether the personnel distribution map in the first cage and the personnel distribution map in the second cage are the same;

[0123] If the distribution map of people in the first cage and the distribution map of people in the second cage are the same, the number of people is identified based on the distribution map of people in the first cage or the distribution map of people in the second cage.

[0124] If the distribution map of people in the first cage is different from that in the second cage, the distribution map of people in the first cage or the distribution map of people in the second cage is corrected to obtain the number of people identification results.

[0125] In one embodiment, the step of correcting the personnel distribution map in the first cage or the personnel distribution map in the second cage to obtain the personnel identification result includes:

[0126] If it is determined that the number of people in the first cage distribution map is less than the number of people in the second cage distribution map, a first difference region is obtained based on the first cage distribution map and the second cage distribution map.

[0127] Visual recognition technology is used to perform human body recognition on the first difference region to obtain the first difference recognition result;

[0128] Based on the first difference identification result, the number of people in the personnel distribution map of the first cage is corrected to obtain the number of people identification result.

[0129] In one embodiment, the step of correcting the personnel distribution map in the first cage or the personnel distribution map in the second cage to obtain the personnel identification result includes:

[0130] If it is determined that the number of people in the first cage distribution map is greater than the number of people in the second cage distribution map, a second difference region is obtained based on the first cage distribution map and the second cage distribution map.

[0131] Determine the weight information of the second difference region;

[0132] Based on the distribution map of people in the first cage, determine the personnel information of the second difference area and obtain the number of people in the difference area;

[0133] Based on the weight information and the number of people in the second difference area, determine whether the distribution map of people in the first cage is incorrect;

[0134] If the distribution map of people in the first cage is confirmed to be incorrect, the number of people in the distribution map of people in the first cage or the number of people in the distribution map of people in the second cage is corrected to obtain the number of people identification results.

[0135] In one embodiment, determining whether the personnel distribution map in the first cage is incorrect based on the weight information and the number of people in the second difference region includes:

[0136] The theoretical weight is obtained by multiplying the preset weight value by the number of people with the difference.

[0137] Based on the theoretical weight and the weight information of the second difference region, determine whether the personnel distribution map in the first cage is incorrect.

[0138] In one embodiment, the weight information inside the cage includes the weight information of multiple small pieces;

[0139] The process of obtaining the personnel distribution map in the second cage based on the weight information inside the cage includes:

[0140] Based on the weight information of the multiple small blocks, the shape of the contact surface under the force of the cage bottom plate is simulated to obtain the personnel distribution map inside the second cage.

[0141] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0142] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0143] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0144] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0145] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0146] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0147] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0148] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0149] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for recognizing people, characterized in that, include: A distribution map of the people inside the first cage is obtained using visual recognition technology. Obtain the weight information inside the cage, and obtain the personnel distribution map inside the second cage based on the weight information inside the cage; The distribution maps of people in the first cage and the distribution maps of people in the second cage are cross-checked to obtain the number of people identification results. The weight information inside the cage includes the weight information of multiple small blocks; the cage bottom plate is divided into several small blocks. When personnel or goods move onto the cage bottom plate, each small block of the cage bottom plate deforms under the force, and the weight of the personnel or goods on that small block is measured to obtain the weight information of the small block. The step of obtaining the second personnel distribution map based on the weight information inside the cage includes: simulating the contact surface shape of the cage bottom plate under stress based on the weight information of the multiple small blocks to obtain the second personnel distribution map.

2. The method according to claim 1, characterized in that, The process of cross-checking the distribution maps of people in the first cage and the second cage to obtain the number of people identification results includes: Determine whether the personnel distribution map in the first cage and the personnel distribution map in the second cage are the same; If the distribution map of people in the first cage and the distribution map of people in the second cage are the same, the number of people is identified based on the distribution map of people in the first cage or the distribution map of people in the second cage. If the distribution map of people in the first cage is different from that in the second cage, the distribution map of people in the first cage or the distribution map of people in the second cage is corrected to obtain the number of people identification results.

3. The method according to claim 2, characterized in that, The step of correcting the personnel distribution map in the first cage or the personnel distribution map in the second cage to obtain the personnel identification result includes: If it is determined that the number of people in the first cage distribution map is less than the number of people in the second cage distribution map, a first difference region is obtained based on the first cage distribution map and the second cage distribution map. Visual recognition technology is used to perform human body recognition on the first difference region to obtain the first difference recognition result; Based on the first difference identification result, the number of people in the personnel distribution map of the first cage is corrected to obtain the number of people identification result.

4. The method according to claim 2, characterized in that, The step of correcting the personnel distribution map in the first cage or the personnel distribution map in the second cage to obtain the personnel identification result includes: If it is determined that the number of people in the first cage distribution map is greater than the number of people in the second cage distribution map, a second difference region is obtained based on the first cage distribution map and the second cage distribution map. Determine the weight information of the second difference region; Based on the distribution map of people in the first cage, determine the personnel information of the second difference area and obtain the number of people in the difference area; Based on the weight information and the number of people in the second difference area, determine whether the distribution map of people in the first cage is incorrect; If the distribution map of people in the first cage is confirmed to be incorrect, the number of people in the distribution map of people in the first cage or the number of people in the distribution map of people in the second cage is corrected to obtain the number of people identification results.

5. The method according to claim 4, characterized in that, The step of determining whether the personnel distribution map in the first cage is incorrect based on the weight information and the number of people in the second difference region includes: The theoretical weight is obtained by multiplying the preset weight value by the number of people with the difference. Based on the theoretical weight and the weight information of the second difference region, determine whether the personnel distribution map in the first cage is incorrect.

6. A people recognition system, characterized in that, For use in a lift, including: a people recognition camera, a controller, and a weight detection device; the weight detection device is located on the back of the bottom plate of the lift cage, and the people recognition camera is located inside the lift cage; The people recognition camera is used to acquire a distribution map of people in the first cage and send the distribution map of people in the first cage to the controller; The weight detection device is used to acquire the weight information inside the cage and send the weight information inside the cage to the controller; wherein, the weight information inside the cage includes the weight information of multiple small blocks; the cage bottom plate is divided into several small blocks, and when a person or goods move to the cage bottom plate, each small block of the cage bottom plate deforms under the force, and the weight of the person or goods on the small block is measured to obtain the weight information of the small block. The controller is used to obtain a second personnel distribution map in the cage based on the weight information in the cage, and to cross-check the first personnel distribution map in the cage and the second personnel distribution map in the cage to obtain the personnel identification result; obtaining the second personnel distribution map in the cage based on the weight information in the cage includes: simulating the contact surface shape of the cage bottom plate under force based on the weight information of the multiple small blocks to obtain the second personnel distribution map in the cage.

7. A people recognition device, characterized in that, include: The first acquisition module is used to acquire a distribution map of people inside the first cage, which is obtained using visual recognition technology. The second acquisition module is used to acquire the weight information inside the cage and obtain a second personnel distribution map inside the cage based on the weight information inside the cage; wherein, the weight information inside the cage includes the weight information of multiple small blocks; the cage bottom plate is divided into several small blocks, and when personnel or goods move onto the cage bottom plate, each small block of the cage bottom plate deforms under the force, and the weight of the personnel or goods on the small block is measured to obtain the weight information of the small block; obtaining the second personnel distribution map inside the cage based on the weight information inside the cage includes: simulating the contact surface shape of the cage bottom plate under the force based on the multiple small block weight information to obtain the second personnel distribution map inside the cage. The cross-verification module is used to cross-verify the personnel distribution map in the first cage and the personnel distribution map in the second cage to obtain the personnel identification result.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; A memory connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the people recognition method according to any one of claims 1 to 5 by executing the instructions stored in the memory.

9. A machine-readable storage medium storing instructions thereon, characterized in that, When executed by a processor, this instruction causes the processor to be configured to perform the people recognition method according to any one of claims 1 to 5.

Images