An elevator occupancy detection method, device, equipment and storage medium

Abstract

The application discloses a kind of detection method, device, equipment and storage medium of lift occupancy, the method includes: to the elevator is divided into idle state and operating state alternately, wherein, elevator includes car;In current idle state, original image data is collected inside car;According to original image data, exclude the interference left in last operating state, to update background image data;In current operating state, target image data is collected inside car;Difference operation is executed to background image data and target image data, and the lift object that enters car in current operating state is obtained;According to lift object and background image data, the occupancy of car is counted.This embodiment provides pure background, counts the occupancy of car, widely applicable scene, can effectively improve the accuracy of the occupancy of car, to improve the scheduling efficiency of car.

Description

Technical Field

[0001] This invention relates to the technical field of elevators, and more particularly to a method, apparatus, equipment, and storage medium for detecting elevator occupancy rate. Background Technology

[0002] Elevators are installed in buildings such as office buildings, residences, and hospitals. Elevators have a wide range of uses. If there are large objects such as delivery vehicles, goods, hospital beds, and wheelchairs inside the car, the car cannot accommodate more people. However, the weight is not enough to trigger the full load signal. When dispatching the car, it will still stop at the floor with the external call signal. Opening and closing the door will cause a waste of time.

[0003] Therefore, during elevator operation, a target detection algorithm is used to detect people or objects entering the car, thereby calculating the occupancy rate of the car. When the occupancy rate is high, a full load signal is triggered, ignoring floors with external call signals and directly reaching the floor indicated by the internal call signal.

[0004] However, object detection algorithms detect common categories of objects. In elevator cars, there are many different objects, such as updates to the interior, advertisements, property notices, carpets, etc., or objects carried by users. These situations often exceed the detection range of object detection algorithms, causing the detection results to frequently be abnormal. This results in low accuracy of calculating elevator car occupancy and affects the scheduling efficiency of the elevator cars. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and storage medium for detecting elevator occupancy rate, in order to solve the problem of how to improve the accuracy of statistical analysis of elevator car occupancy rate.

[0006] According to one aspect of the present invention, a method for detecting elevator occupancy rate is provided, comprising:

[0007] The elevator is divided into alternating idle and running states, wherein the elevator includes a car;

[0008] In the current idle state, raw image data is acquired inside the car;

[0009] Based on the original image data, interference left over from the previous operating state is eliminated in order to update the background image data;

[0010] In the current operating state, target image data is acquired inside the car;

[0011] Perform a difference operation on the background image data and the target image data to obtain the elevator passenger who enters the car in the current operating state;

[0012] The occupancy rate of the elevator car is calculated based on the data of the passengers and the background image.

[0013] According to another aspect of the present invention, an elevator occupancy detection device is provided, comprising:

[0014] A state division module is used to divide the elevator into alternating idle and running states, wherein the elevator includes a car;

[0015] The raw image data acquisition module is used to acquire raw image data inside the car during the current idle state.

[0016] The background image data update module is used to eliminate interference left over from the previous operating state based on the original image data in order to update the background image data;

[0017] The target image data acquisition module is used to acquire target image data inside the car during the current operating state.

[0018] The elevator passenger detection module is used to perform a difference operation on the background image data and the target image data to obtain the elevator passenger objects that enter the car in the current operating state.

[0019] The occupancy statistics module is used to calculate the occupancy rate of the elevator car based on the elevator passenger and the background image data.

[0020] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0021] At least one processor; and

[0022] A memory communicatively connected to the at least one processor; wherein,

[0023] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the elevator occupancy detection method according to any embodiment of the present invention.

[0024] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program configured to cause a processor to execute and implement the elevator occupancy detection method according to any embodiment of the present invention.

[0025] In this embodiment, the elevator is divided into alternating idle and running states, where the elevator includes a car. In the current idle state, raw image data is acquired inside the car. Based on the raw image data, interference from the previous running state is eliminated to update the background image data. In the current running state, target image data is acquired inside the car. A difference operation is performed on the background image data and the target image data to obtain the passengers entering the car in the current running state. The occupancy rate of the car is calculated based on the passengers and the background image data. This embodiment dynamically updates the background image data in the idle state, eliminating interference from the previous running state and providing a cleaner background as much as possible, providing a more fundamental basis for detecting passengers. In the running state, the differences between the image data are used to identify passengers, thereby calculating the car occupancy rate. This eliminates the dependence on predetermined categories, has a wide range of applicable scenarios, and can effectively improve the accuracy of calculating car occupancy, thereby improving the car scheduling efficiency.

[0026] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a flowchart of a method for detecting elevator occupancy rate according to Embodiment 1 of the present invention;

[0029] Figure 2 This is an example diagram of dividing the base plate area according to Embodiment 1 of the present invention;

[0030] Figure 3 This is a schematic diagram of the structure of a device for detecting elevator occupancy rate according to Embodiment 2 of the present invention;

[0031] Figure 4 This is a schematic diagram of the structure of an electronic device provided according to Embodiment 3 of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate so that the embodiments of the invention described herein can cover implementations in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] Example 1

[0035] Figure 1 This is a flowchart of a method for detecting elevator occupancy rate according to Embodiment 1 of the present invention. This embodiment is applicable to detecting people and objects entering the elevator car using a clean background under conditions of eliminating interference, thereby calculating the occupancy rate of the elevator car. This method can be executed by an elevator occupancy rate detection device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0036] Step 101: Divide the elevator into alternating idle and running states.

[0037] Different types of buildings, especially high-rise buildings, have different transportation needs for people and goods. Therefore, different types of elevators can be deployed in buildings according to different transportation needs, such as passenger elevators, freight elevators, sightseeing elevators, etc. This embodiment does not impose any restrictions on this.

[0038] The structure of elevators also varies among different types of elevators.

[0039] In one example, the components of a certain type of elevator include traction machine, control cabinet, speed governor, door operator, car frame, car, car door, counterweight guide rail, car guide rail, guide rail support, traveling cable, counterweight device, compensating chain (cable), landing door, guide device for compensating chain (cable), buffer, etc.

[0040] In some types of elevators, the traction machine, control cabinet, speed governor, traveling cable, etc., can be omitted.

[0041] These components can be divided into different sets according to their functions, thus forming various subsystems that support the operation of the elevator. The elevator controller is connected to multiple systems of the elevator via wired means such as serial port or serial clock line (SCL). The controller monitors each system and controls the operation of each subsystem.

[0042] In one example, the system includes a door system, a frequency conversion system, a call system, and a traction system. The door system is used to control the elevator doors, which include the car door and the doors of the waiting halls on each floor. The frequency conversion system is used to control the frequency converter. The call system is used to control the logic of internal call (calling the elevator from inside the car) and external call (calling the elevator from the waiting hall). The traction system is used to control the car's movement in the hoistway.

[0043] When the elevator is in normal operation, the elevator's state can be divided into multiple alternating idle states and multiple running states on the timeline.

[0044] The idle state can refer to a situation where the elevator has not received a call signal (including external and internal calls) and has not performed the call task. In this case, the elevator's sensors (such as cameras, radar, infrared sensors, etc.) have not detected any person or object entering the car.

[0045] Normally, the idle state begins when the task of calling the elevator is completed and ends when the elevator call signal is received.

[0046] The operating status can refer to the elevator receiving a call signal (including external and internal calls) and executing the call task. At this time, the elevator's sensors (such as cameras, radar, infrared sensors, etc.) will usually detect people or objects inside the car.

[0047] Normally, the operation begins when a call signal is received and ends when the call is completed (all personnel have left the elevator car).

[0048] The term "mutual alternation" means that when the idle state ends, the running state begins, and when the running state ends, the idle state begins, and so on in a cycle.

[0049] Step 102: In the current idle state, collect raw image data inside the car.

[0050] Each time the elevator enters an idle state, the camera installed inside the car can be used to collect image data of the environment inside the car, and then wait for the background image data to be updated.

[0051] When the elevator enters its current idle state, the camera installed inside the car continues to collect image data of the environment inside the car, which is recorded as raw image data.

[0052] Furthermore, the car can be equipped with lighting devices, such as displays, LED (Light Emitting Diode Light) lights, etc., which can be used to query lighting parameters (such as on or off, brightness, etc.) set for the idle state. The lighting parameters are information for controlling the lighting equipment.

[0053] The lighting equipment in the car is controlled according to the lighting parameters to simulate a uniform lighting environment in the car. Raw image data is collected in the lighting environment and can be updated as background image data. This reduces the impact of lighting on the updated background image data and improves the quality of the updated background image data.

[0054] Step 103: Eliminate interference left over from the previous running state based on the original image data to update the background image data.

[0055] When the elevator is in the previous operating state (i.e., the operating state before the current idle state), the interior of the car (such as advertisements, property notices, carpets, etc.) may change, and users may leave objects they are carrying (such as cleaning tools, etc.) in the car. These interior decorations and left objects will interfere with the updating of background image data, and therefore can be called interference objects.

[0056] Some interfering objects can be used as background and are not included in the occupancy statistics. Therefore, based on the original image data, we can eliminate as many interfering objects left over from the previous running state as possible to create cleaner background image data.

[0057] In the actual implementation, it is possible to query whether background image data exists in the previous idle state.

[0058] If no background image data exists in the previous idle state, the original image data will be set as the background image data.

[0059] If background image data existed in the previous idle state, then check in the previous background image data (i.e., the background image data of the previous idle state) to see if there are any interference objects left over from the previous running state.

[0060] If there are no interfering objects in the previous background image data, considering that the current idle state and the previous running state are adjacent in time, the car usually will not change much in a short period of time. Therefore, the difference between the original image data and the previous background image data can be calculated by using differential algorithms to detect whether there are any interfering objects left over from the previous running state in the original image data.

[0061] Generally, if the difference between the original image data and the previous background image data meets the preset conditions (such as the area being greater than or equal to a preset threshold), the difference can be considered as interference left over from the previous running state in the original image data; if the difference between the original image data and the previous background image data does not meet the preset conditions (such as the area being less than a preset threshold), the difference can be considered as interference left over from the previous running state in the original image data.

[0062] If there are interfering objects in the original image data, then the original image data is set as the new background image data, and the interfering objects are marked in the new background image data.

[0063] If there are no interfering objects in the original image data, then the original image data is set as the new background image data.

[0064] If there are interfering objects in the previous background image data, the difference between the original image data and the previous background image data is calculated to detect whether there are any interfering objects left over from the previous running state in the original image data.

[0065] If there are interfering objects in the original image data, then the original image data is set as the new background image data, and the interfering objects present in the original image data are marked in the new background image data.

[0066] If there are no interfering objects in the original image data, then the interfering objects present in the previous background image data are regarded as the background, the interfering objects are excluded from the previous background image data, and the original image data is set as the new background image data.

[0067] Furthermore, the floor area and side wall area of ​​the car can be divided in the background image data. The actual three-dimensional structure of the car is shown, while the floor area and side wall area of ​​the car, which are fitted in the background image data, are two-dimensional structures projected onto the two-dimensional image data.

[0068] Since the camera's installation location, FOV (Field of View), focal length, and other factors are fixed, the structure of the car in the background image data is fixed. Therefore, the car's floor area and side wall area are also fixed. Thus, the car's floor area and side wall area can be divided offline, and when updating the background image data, the car's floor area and side wall area can be loaded into the background image data.

[0069] Each interfering object is compared with the base plate area and the side wall area respectively.

[0070] If all interfering objects are located in the side wall area, then the interfering object is regarded as background (such as advertisements, property notices, etc.) and excluded from the background image data.

[0071] If the interfering object is partially or entirely located in the base plate area, then in the area where the interfering object is located, common target objects in elevators (such as human bodies, pets, common objects (such as bicycles, chairs, etc.)) are used as the targets for detection and tracking. Tracking algorithms such as Deep-sort and FairMOT are used to detect and track the target objects in subsequent target image data to obtain the coordinates of the target objects.

[0072] If the coordinates can form a moving trajectory, then the interfering object is considered as interior decoration such as carpet or advertisement, belonging to the background of the car. Therefore, the interfering object can be excluded from the background image data.

[0073] Step 104: In the current operating state, collect target image data inside the car.

[0074] Each time the elevator enters operation, the camera installed inside the car can be used to collect image data of the environment inside the car, thereby achieving safety monitoring.

[0075] When the elevator enters its current operating state, it continuously calls the camera installed inside the car to collect image data of the environment inside the car, which is recorded as target image data.

[0076] Step 105: Perform a difference operation on the background image data and the target image data to obtain the elevator passenger object that enters the car in the current running state.

[0077] The current idle state and the current running state are adjacent in time. The elevator car usually does not change much in a short period of time. Therefore, a difference operation can be performed on the background image data and the target image data. The difference between the two is the elevator passenger that enters the car in the current running state. Here, the elevator passenger refers to the object that takes the elevator, including people, pets, objects, etc.

[0078] In the specific implementation, for the same position, the pixels of the background image data are subtracted from the pixels of the target image data to obtain the original difference image data.

[0079] The target difference image data is obtained by taking the absolute value of each pixel in the original difference image data (i.e., the difference between the pixels in the background image data and the pixels in the target image data).

[0080] Using linear functions, logarithmic functions, power-law functions, etc., can transform target difference image data into grayscale image data.

[0081] Perform filtering operations on grayscale image data to remove isolated noise points in the grayscale image data.

[0082] If the filtering operation is completed, then the grayscale image data is binarized using methods such as fixed threshold method, average method, bimodal method, and maximum inter-class variance method to obtain binary image data.

[0083] Perform an erosion operation on the binary image data. If the erosion operation is completed, perform a dilation operation on the binary image data to obtain the elevator passenger object that has entered the car in the current operating state.

[0084] The erosion operation can eliminate noise and some boundary values, making the target (the elevator object entering the car in the current running state) shrink as a whole. The expansion operation can increase the feature value of the target (the elevator object entering the car in the current running state), making the target (the elevator object entering the car in the current running state) enlarge as a whole. Using the two together can better segment the independent elevator objects entering the car in the current running state.

[0085] Step 106: Calculate the occupancy rate of the elevator car based on the data of the passengers and the background image.

[0086] When the elevator is in operation, if it is detected that the car is not empty and there is an identifiable passenger inside the car, then wait for the car door to close. When the car door is closed, compare the passenger (pixel) with the background image data in two-dimensional or three-dimensional space to evaluate the proportion of the passenger in the car in the actual state, which is taken as the occupancy rate.

[0087] In one embodiment of the present invention, step 106 may include the following steps:

[0088] Step 1061: Query the floor area of ​​the car in the background image data.

[0089] In reality, the proportion of the elevator car occupied by the passenger can be simplified to the projection of the passenger onto the floor of the car. Therefore, in the background image data, the floor area of ​​the car can be queried, and the occupancy rate of the car can be calculated.

[0090] Furthermore, most of the cameras inside the elevator car are installed in a corner of the ceiling, and the image data they collect is subject to a certain degree of distortion. That is, the image of the passenger is distorted to a certain extent. Generally, as the distance between the passenger and the camera increases, the degree of image distortion first increases and then decreases.

[0091] For example, such as Figure 2 As shown, the floor area of ​​the elevator car (A, B, C, D) is divided into 9 sub-areas, numbered 1-9. If the camera is installed above point A, the image distortion is smaller when the passenger is in sub-areas 1, 3, 6, 7, 8, or 9, resulting in a smaller error in the image area of ​​the passenger in the floor area. However, the image distortion is larger when the passenger is in sub-areas 2, 4, or 5, resulting in a larger error in the image area of ​​the passenger in the floor area. In particular, the passenger in sub-area 5 may occupy not only sub-area 5 but also parts of sub-areas 6, 8, and 9 during imaging.

[0092] Therefore, the floor area of ​​the car can be divided into multiple regular or irregular sub-regions based on factors such as the installation location of the camera and the size (length and width) of the car. Each sub-region is assigned a weight representing the degree of image distortion. The weight is negatively correlated with the degree of image distortion; that is, the greater the degree of image distortion, the smaller the weight, and vice versa.

[0093] Since the elevator monitoring process uses target detection algorithms in real time, the detection boxes output by the target detection algorithms for elevator passengers can be queried. Based on factors such as the sub-region where the bottom of the detection box is located and the degree of overlap between the detection box and each sub-region, the sub-region where the elevator passenger is located in the actual situation can be queried as the first target region.

[0094] The elevator object is multiplied by the weight corresponding to the first target area to obtain a new elevator object, thereby correcting the elevator object.

[0095] If there are unremoved interference objects in the background image data, the detection boxes output by the target detection algorithm for the interference objects can be queried. Based on factors such as the sub-region where the bottom of the detection box is located and the degree of overlap between the detection box and each sub-region, the sub-region where the interference objects are located in the actual situation can be queried as the second target region.

[0096] The interference object is multiplied by the weight corresponding to the second target region to form a new interference object, thereby correcting the interference object.

[0097] This embodiment corrects for elevator passengers and interference by adjusting the degree of imaging distortion of the camera, thereby improving the realism of the image and further enhancing the accuracy of the elevator car occupancy rate.

[0098] Step 1062: If there are no interfering objects in the background image data, calculate the ratio between the projection of the passenger object on the floor area and the floor area, and use it as the occupancy rate of the elevator car.

[0099] If there are no interfering objects in the background image data, the projection of the passenger on the floor area in the vertical direction in the real three-dimensional space can be evaluated, and the ratio between the projection of the passenger on the floor area and the floor area can be calculated as the occupancy rate of the elevator car.

[0100] Step 1063: If there are interfering objects in the background image data, then overlay the interfering objects onto the elevator object to obtain the target object.

[0101] Step 1064: Calculate the ratio between the projection of the target object onto the floor area and the floor area itself, and use this ratio as the occupancy rate of the car.

[0102] If there are interfering objects in the background image data, the interfering objects can be included in the statistics and superimposed on the elevator ride object to obtain the target object. That is, the target object is the combination of the elevator ride object and the interfering objects.

[0103] The evaluation assesses the projection of the target object onto the floor area in the vertical direction within a real three-dimensional space, and calculates the ratio between the projection of the target object onto the floor area and the floor area itself, which is used as the occupancy rate of the car.

[0104] In this embodiment, the elevator is divided into alternating idle and running states, where the elevator includes a car. In the current idle state, raw image data is acquired inside the car. Based on the raw image data, interference from the previous running state is eliminated to update the background image data. In the current running state, target image data is acquired inside the car. A difference operation is performed on the background image data and the target image data to obtain the passengers entering the car in the current running state. The occupancy rate of the car is calculated based on the passengers and the background image data. This embodiment dynamically updates the background image data in the idle state, eliminating interference from the previous running state and providing a cleaner background as much as possible, providing a more fundamental basis for detecting passengers. In the running state, the differences between the image data are used to identify passengers, thereby calculating the car occupancy rate. This eliminates the dependence on predetermined categories, has a wide range of applicable scenarios, and can effectively improve the accuracy of calculating car occupancy, thereby improving the car scheduling efficiency.

[0105] Example 2

[0106] Figure 3 This is a schematic diagram of a device for detecting elevator occupancy rate according to Embodiment 2 of the present invention. Figure 3 As shown, the device includes:

[0107] The state division module 301 is used to divide the elevator into alternating idle and running states, wherein the elevator includes a car;

[0108] The raw image data acquisition module 302 is used to acquire raw image data inside the car during the current idle state.

[0109] Background image data update module 303 is used to eliminate interference left over from the previous operating state based on the original image data in order to update the background image data;

[0110] The target image data acquisition module 304 is used to acquire target image data inside the car during the current operating state.

[0111] The elevator object detection module 305 is used to perform a difference operation on the background image data and the target image data to obtain the elevator object that enters the car in the current operating state.

[0112] The occupancy statistics module 306 is used to calculate the occupancy rate of the elevator car based on the elevator passenger and the background image data.

[0113] In one embodiment of the present invention, the raw image data acquisition module 302 includes:

[0114] The lighting parameter query module is used to query the lighting parameters set for the idle state;

[0115] The lighting equipment control module is used to control the operation of the lighting equipment in the car according to the lighting parameters, so as to simulate a uniform lighting environment in the car;

[0116] The illumination acquisition module is used to acquire raw image data in the illumination environment.

[0117] In one embodiment of the present invention, the background image data update module 303 includes:

[0118] The first background setting module is used to set the original image data as background image data if there is no background image data in the aforementioned idle state.

[0119] The interference query module is used to query the background image data in the previous idle state if background image data exists in the previous idle state, and to query the interference left over from the previous running state.

[0120] The first interference detection module is used to calculate the difference between the original image data and the previous background image data if there is no interference in the previous background image data, so as to detect whether there is interference left over from the previous running state in the original image data.

[0121] The second background setting module is used to set the original image data as new background image data and mark the interference in the new background image data if there are interfering objects in the original image data.

[0122] The third background setting module is used to set the original image data as new background image data if there are no interfering objects in the original image data.

[0123] The second interference detection module is used to calculate the difference between the original image data and the previous background image data if there are interferences in the previous background image data, so as to detect whether there are interferences left over from the previous running state in the original image data.

[0124] The fourth background setting module is used to set the original image data as new background image data and mark the interference in the new background image data if there are interfering objects in the original image data.

[0125] The fifth background setting module is used to exclude the interference from the previous background image data if there is no interference in the original image data, and set the original image data as new background image data.

[0126] In one embodiment of the present invention, the background image data update module 303 further includes:

[0127] The car partitioning module is used to partition the floor area and side wall area of ​​the car from the background image data;

[0128] The first interference removal module is used to remove the interference from the background image data if all the interferences are located in the side wall area.

[0129] An interference tracking module is used to detect the coordinates of a target object in the area where the interference object is located if the interference object is partially or entirely located in the base plate area.

[0130] The second interference removal module is used to remove interference from the background image data if the coordinates form a moving trajectory.

[0131] In one embodiment of the present invention, the elevator passenger detection module 305 includes:

[0132] The original difference image data generation module is used to subtract the pixel points of the background image data from the pixel points of the target image data to obtain the original difference image data;

[0133] The target difference image data generation module is used to take the absolute value of each pixel in the original difference image data to obtain the target difference image data;

[0134] A grayscale image data conversion module is used to convert the target difference image data into grayscale image data;

[0135] A filtering operation execution module is used to perform filtering operations on the grayscale image data;

[0136] The binarization operation execution module is used to perform a binarization operation on the grayscale image data to obtain binary image data if the filtering operation is completed.

[0137] The erosion operation execution module is used to perform erosion operations on the binary image data;

[0138] The expansion operation execution module is used to perform an expansion operation on the binary image data if the erosion operation is completed, to obtain the elevator passenger object that enters the car in the current operating state.

[0139] In one embodiment of the present invention, the occupancy rate statistics module 306 includes:

[0140] The floor area query module is used to query the floor area of ​​the car in the background image data;

[0141] The first ratio calculation module is used to calculate the ratio between the projection of the elevator passenger on the floor area and the floor area if there are no interfering objects in the background image data, and use this ratio as the occupancy rate of the elevator car.

[0142] The target object generation module is used to superimpose the interference objects onto the elevator object if there are interference objects in the background image data to obtain the target object;

[0143] The second ratio calculation module is used to calculate the ratio between the projection of the target object onto the floor area and the floor area itself, as the occupancy rate of the car.

[0144] In one embodiment of the present invention, the occupancy rate statistics module 306 further includes:

[0145] The base plate region division module is used to divide the base plate region into multiple sub-regions, and each sub-region is configured with a weight representing the degree of imaging distortion.

[0146] The first target area query module is used to query the sub-area where the elevator passenger is located, and use it as the first target area;

[0147] The elevator object correction module is used to multiply the elevator object with the weight corresponding to the first target area to correct the elevator object;

[0148] The second target region query module is used to query the sub-region where the interference is located if there is interference in the background image data, and use it as the second target region.

[0149] An interference correction module is used to multiply the interference with the weight corresponding to the second target region to correct the interference.

[0150] The elevator occupancy detection device provided in this embodiment of the invention can execute the elevator occupancy detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the elevator occupancy detection method.

[0151] Example 3

[0152] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0153] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0154] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0155] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for detecting elevator occupancy.

[0156] In some embodiments, the method for detecting elevator occupancy can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for detecting elevator occupancy described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the method for detecting elevator occupancy by any other suitable means (e.g., by means of firmware).

[0157] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0158] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0159] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0160] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0161] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0162] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0163] Example 4

[0164] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the elevator occupancy detection method provided in any embodiment of this invention.

[0165] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0166] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0167] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting elevator occupancy rate, characterized in that, include: The elevator is divided into alternating idle and running states, wherein the elevator includes a car; In the current idle state, raw image data is acquired inside the car; Based on the original image data, interference left over from the previous operating state is eliminated in order to update the background image data; In the current operating state, target image data is acquired inside the car; Perform a difference operation on the background image data and the target image data to obtain the elevator passenger who enters the car in the current operating state; The occupancy rate of the elevator car is calculated based on the data of the passengers and the background image.

2. The method according to claim 1, characterized in that, The process of acquiring raw image data inside the car includes: Query the lighting parameters set for the idle state; The lighting equipment in the car is controlled according to the lighting parameters to simulate a uniform lighting environment in the car. Raw image data was acquired in the aforementioned lighting environment.

3. The method according to claim 1, characterized in that, The step of eliminating interference left over from the previous operating state based on the original image data to update the background image data includes: If the idle state described above does not contain background image data, then the original image data is set as the background image data; If background image data exists in the aforementioned idle state, then query the aforementioned background image data for interference left over from the aforementioned operating state; If there are no interfering objects in the background image data described above, then the difference between the original image data and the background image data described above is calculated to detect whether there are any interfering objects left over from the previous running state in the original image data. If there are interfering objects in the original image data, then the original image data is set as new background image data, and the interfering objects are marked in the new background image data; If there are no interfering objects in the original image data, then the original image data is set as the new background image data; If there are interfering objects in the background image data described above, the difference between the original image data and the background image data described above is calculated to detect whether there are any interfering objects left over from the previous running state in the original image data. If there are interfering objects in the original image data, then the original image data is set as new background image data, and the interfering objects are marked in the new background image data; If there are no interfering objects in the original image data, then the interfering objects are excluded from the previous background image data, and the original image data is set as the new background image data.

4. The method according to claim 3, characterized in that, The step of eliminating interference left over from the previous operating state based on the original image data to update the background image data further includes: The floor area and side wall area of ​​the car are divided in the background image data; If all the interfering objects are located in the sidewall region, then the interfering objects are excluded from the background image data; If the interfering object is partially or entirely located in the base plate area, the coordinates of the target object are detected in the area where the interfering object is located. If the coordinates form a moving trajectory, then the interference is excluded from the background image data.

5. The method according to claim 1, characterized in that, The step of performing a difference operation on the background image data and the target image data to obtain the elevator passenger entering the car in the current operating state includes: Subtract the pixels of the background image data from the pixels of the target image data to obtain the original difference image data; The absolute value of each pixel in the original differential image data is taken to obtain the target differential image data; The target differential image data is converted into grayscale image data; Perform a filtering operation on the grayscale image data; If the filtering operation is completed, then the grayscale image data is binarized to obtain binary image data; Perform an erosion operation on the binary image data; If the erosion operation is completed, a dilation operation is performed on the binary image data to obtain the elevator passenger object that enters the car in the current operating state.

6. The method according to any one of claims 1-5, characterized in that, The step of calculating the occupancy rate of the elevator car based on the passenger data and the background image data includes: Query the floor area of ​​the car in the background image data; If there are no interfering objects in the background image data, the ratio between the projection of the passenger on the floor area and the floor area is calculated and used as the occupancy rate of the elevator car. If there are interfering objects in the background image data, the interfering objects are superimposed on the elevator object to obtain the target object; The ratio between the projection of the target object onto the floor area and the floor area itself is calculated and used as the occupancy rate of the car.

7. The method according to claim 6, characterized in that, The method of calculating the occupancy rate of the elevator car based on the passenger and background image data also includes: The base plate area is divided into multiple sub-regions, and each sub-region is assigned a weight representing the degree of imaging distortion. The sub-region where the elevator passenger is located is selected as the first target region. The elevator-riding object is multiplied by the weight corresponding to the first target area to correct the elevator-riding object; If there are interfering objects in the background image data, the sub-region where the interfering object is located is queried and used as the second target region; The interference is multiplied by the weight corresponding to the second target region to correct the interference.

8. A device for detecting elevator occupancy rate, characterized in that, include: A state division module is used to divide the elevator into alternating idle and running states, wherein the elevator includes a car; The raw image data acquisition module is used to acquire raw image data inside the car during the current idle state. The background image data update module is used to eliminate interference left over from the previous operating state based on the original image data in order to update the background image data; The target image data acquisition module is used to acquire target image data inside the car during the current operating state. The elevator passenger detection module is used to perform a difference operation on the background image data and the target image data to obtain the elevator passenger objects that enter the car in the current operating state. The occupancy statistics module is used to calculate the occupancy rate of the elevator car based on the elevator passenger and the background image data.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the elevator occupancy detection method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method for detecting elevator occupancy rate as described in any one of claims 1-7.

Images