Elevator system and elevator control method

Abstract

The invention provides an elevator system and an elevator control method, which can reduce the load of image analysis of a camera arranged on an elevator. An elevator system is provided with: an object detection processing unit (23) that detects the presence or absence of a person or an object in a car by analyzing an image captured by a camera (12) provided in the car; a person detection processing unit (22) that detects the attributes of persons in the car by analyzing the image captured by the camera (12); an image analysis scheme switching unit (21) that selectively performs detection by the object detection processing unit (23) and detection by the person detection processing unit (22); and an image analysis result determination unit (24) that determines an image analysis result of either the detection by the object detection processing unit (23) or the detection by the person detection processing unit (22). On the basis of the result determined by the image analysis result determination unit (24), operation control of the elevator or notification to another system connected to the elevator system is performed.

Description

Technical Field

[0001] The invention relates to an elevator system and an elevator control method. Background Art

[0002] In recent years, elevators have installed cameras in the car and at the landing to detect elevator users based on images captured by the cameras. By having cameras, elevators can, for example, detect elevator congestion, detect the absence of passengers, detect passenger abnormalities, and confirm the conditions in the car when abnormalities occur based on the captured images.

[0003] In addition, the elevator analyzes the images captured by the camera and detects the age, gender, etc. of the elevator user, thereby collecting detailed information about the elevator's usage. Furthermore, the elevator can use the camera as a safety measure to restrict elevator users by performing facial authentication based on the images captured by the camera.

[0004] Patent document 1 describes the following technology: a camera is installed on the upper part of the elevator door, and the user who intends to take the elevator is judged by image analysis using an image analysis algorithm for detecting the user who intends to take the elevator. In addition, Patent document 1 describes the image analysis algorithm installed in the image analysis engine that analyzes the image of the camera on the upper part of the elevator door by switching the image analysis algorithm by detecting the door opening direction.

[0005] In addition, the image analysis device that analyzes the camera image can perform advanced detection such as identifying an individual through facial recognition, but in order to perform advanced detection such as facial recognition, it is necessary to always detect the face in the camera image and analyze the detected face with high accuracy. In the case where an image analysis device that performs advanced analysis processing is built into the elevator car or the control device, the elevator system needs a corresponding advanced device, which complicates the structure of the elevator system. In addition, if the elevator system always performs advanced image analysis processing, the burden of power consumption becomes large, so the power consumption of the elevator system increases.

[0006] In addition, Patent Document 1 describes an image analysis algorithm and a technology for switching the algorithm, wherein the image analysis algorithm, when detecting an elevator user from a camera image, determines whether the user is a user who intends to take the elevator based on the direction in which the door is opened, thereby identifying a user who intends to take the elevator.

[0007] The technology of switching image analysis algorithm described in Patent Document 1 is an algorithm for performing image analysis on a user (person), and any algorithm requires relatively advanced image analysis. Therefore, in the switching process described in Patent Document 1, the burden reduction of the elevator control device is limited, and it is expected to further reduce the burden of the device and reduce power consumption.

[0008] Patent Document 1: Japanese Patent Application Publication No. 2020-152528 Summary of the invention

[0009] In view of the above-mentioned problems, an object of the present invention is to provide an elevator system and an elevator control method capable of reducing the burden of analyzing camera images.

[0010] In order to solve the above-mentioned problems, for example, a structure described in the scope of patent protection is adopted.

[0011] The present application includes multiple means for solving the above-mentioned problems. If one example is given, as an elevator system, processing corresponding to an image captured by a camera installed in a car is performed, and the elevator system includes: an object detection processing unit, which detects whether there is a person or an object in the car by analyzing the image captured by the camera; a person detection processing unit, which detects the attributes of the person in the car by analyzing the image captured by the camera; an image analysis mode switching unit, which selectively performs detection in the object detection processing unit and detection in the person detection processing unit; and an image analysis result determination unit, which determines the image analysis result of any one of the detection in the object detection processing unit and the detection in the person detection processing unit, and based on the result determined by the image analysis result determination unit, performs elevator operation control or notifies other systems connected to the elevator system.

[0012] According to the present invention, by selectively performing the object detection processing unit and the human detection processing unit, it is possible to perform appropriate detection while reducing the burden of image analysis.

[0013] The following description of the embodiments will make other problems, structures, and effects clear. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A schematic configuration of the entire elevator system according to an embodiment of the present invention is shown.

[0015] Figure 2 This is a block diagram showing a configuration example of an elevator system according to an embodiment of the present invention.

[0016] Figure 3 This is a block diagram showing a hardware configuration example of a control system according to an embodiment of the present invention.

[0017] Figure 4 This is a flowchart showing a processing example (Example 1) of the elevator system according to one embodiment of the present invention.

[0018] Figure 5 This is a flowchart showing a processing example (Example 2) of the elevator system according to one embodiment of the present invention.

[0019] Figure 6 This is a flowchart showing a processing example (Example 3) of the elevator system according to one embodiment of the present invention.

[0020] Figure 7 This is a flowchart showing a processing example (Example 4) of the elevator system according to one embodiment of the present invention.

[0021] Figure 8 This is a flowchart showing a processing example (Example 5) of the elevator system according to one embodiment of the present invention. DETAILED DESCRIPTION

[0022] Hereinafter, an elevator system according to an embodiment example (hereinafter referred to as “this example”) of the present invention will be described with reference to the drawings.

[0023] [Overview of the entire elevator system]

[0024] First, refer to Figure 1 The schematic configuration of the elevator system of this example will be described.

[0025] The elevator system of this example includes a car 10 that travels (rises and falls) under the control of an elevator control device 100 .

[0026] The car 10 is driven by a hoisting machine (not shown) by the elevator control device 100. Figure 1 In the figure, a mechanism for moving the car 10, such as a hoist, is omitted.

[0027] The car 10 includes a door 11 that opens and closes when the car 10 arrives at a landing on each floor.

[0028] In addition, a camera 12 and a lighting device 13 are provided in the car 10. The camera 12 is provided on the ceiling of the car 10 or the like, and captures the conditions in the car 10 in a moving image or a still image. The camera 12 is provided on the ceiling or the wall on the inner side of the car 10 away from the door 11, and can capture not only the interior of the car 10 but also the door 11. Therefore, in the image captured by the camera 12, the substantially entire interior of the car 10 is captured from the ceiling side, and the conditions of the passengers who enter the car 10 through the door 11 (passenger's face, etc.) are also captured.

[0029] The image captured by the camera 12 is analyzed by an image analyzing device 20 installed in the car 10. The image analyzing device 20 is installed, for example, in the upper part of the car 10 (on the upper side of the ceiling). However, the fact that the car 10 is equipped with the image analyzing device 20 is an example, and the image analyzing device 20 may be installed in the elevator machine room, the pit, etc. together with the elevator control device 100. Alternatively, the image analyzing device 20 may be integrated with the camera 12.

[0030] The lighting device 13 is turned on during the passenger transport service performed by the elevator to illuminate the interior of the car 10. On the contrary, the lighting of the lighting device 13 is stopped during the period when the passenger transport service is stopped (suspended).

[0031] The analysis result of the image analysis device 20 is transmitted together with the captured image to the elevator control device 100. The elevator control device 100 determines the utilization status of the car 10 based on the image analysis result of the image analysis device 20, and controls the operation of the elevator based on the determination result.

[0032] The image analysis device 20 also transmits the analysis result together with the captured image to the monitoring system 200. A plurality of external systems (a first external system 210, a second external system 220, and a third external system 230) are connected to the monitoring system 200, and the image analysis result is used in each external system.

[0033] [Structure of elevator control device, image analysis device, etc.]

[0034] Figure 2 The structure of each part of the elevator system of this example is shown. Figure 2 1 , regarding the elevator control device 100 , only the configuration related to the processing of the image captured by the camera 12 is shown, and other configurations included in the elevator control device 100 are omitted.

[0035] The elevator control device 100 includes a door open state acquisition unit 111 , an operation state acquisition unit 112 , a door open state determination unit 113 , an operation state determination unit 114 , an elevator state management unit 115 , and an elevator control processing unit 116 .

[0036] The door open state acquisition unit 111 acquires data on the door open state of the door 11 from a switch or a sensor (not shown) provided on the door 11 of the car 10 .

[0037] The operation state acquisition unit 112 acquires data on the operation state (running, stopped, etc.) from the operation state detection unit 101 of the car 10 .

[0038] The door open state determination unit 113 determines the door open state of the door 11 based on the data acquired by the door open state acquisition unit 111 .

[0039] The operating state determination unit 114 determines the operating state of the car 10 based on the data acquired by the operating state acquisition unit 112 .

[0040] The elevator state management unit 115 manages the operation of the elevator based on the door open state determined by the door open state determination unit 113 and the operating state determined by the operating state determination unit 114. In addition, the elevator state management unit 115 generates an image analysis mode switching instruction based on the door open state and the operating state, and sends the generated image analysis mode switching instruction to the image analysis device 20, or sends the door open state and the operating state to the image analysis device 20 at a regular cycle or when the state changes.

[0041] The elevator control processing unit 116 sends an operation control command to the operation control unit 102 of the car 10. The operation control unit 102 controls the operation of the car 10. In addition to the driving command of the car 10, the operation control command also includes a command to open and close the door 11. The command to open and close the door 11 is also transmitted to the door open state acquisition unit 111. In addition, when the elevator control processing unit 116 generates an operation control command for the operation control unit 102, it reflects the image analysis result sent from the image analysis device 20. For example, according to the number of passengers in the car 10 obtained by the image analysis device 20, when the door 11 of the stop floor is in the door open state, the time for which the door open state is continued is changed. For example, when the number of passengers is large, the door open time at the stop floor through the stop floor registration operation is made longer than usual. Regarding the processing of changing the time for which the door open state is continued, the time for which the door open state is continued may be further changed according to the age group of the passengers, the determination of the wheelchair user, etc. For example, when it is determined that a person such as an elderly person, a child, or a person carrying goods is riding the elevator and needs a longer door open time than usual to get on or off the elevator, the door open time at the stop floor is made longer than usual.

[0042] The image analyzing device 20 provided in the car 10 acquires the captured image outputted from the image management unit 12a of the camera 12, and performs analysis of the acquired image.

[0043] The image analysis device 20 includes an image analysis mode switching unit 21 , a human detection processing unit 22 , an object detection processing unit 23 , an image analysis result determination unit 24 , and an image analysis result transmission unit 25 .

[0044] The image analysis mode switching unit 21 performs image analysis mode switching processing based on the door state and the operation state which are signals from the elevator control device 100. The switching processing here is a switching processing between the human detection processing in the human detection processing unit 22 and the object detection processing in the object detection processing unit 23 which will be described below. The human detection processing in the human detection processing unit 22 and the object detection processing in the object detection processing unit 23 are configured so that only one of them is selectively performed.

[0045] The human detection processing unit 22 performs a process of detecting the attributes of a person from the image captured by the camera 12 through image analysis processing. The process of detecting the attributes of a person, for example, detects the approximate age and gender of the person. In addition, when the face can be detected from the image captured by the camera 12, the human detection processing unit 22 performs a process of identifying the person through a facial recognition process. In addition, the human detection processing unit 22 also detects wheelchair users, stroller users, users of assistive tools such as crutches, etc. through image analysis.

[0046] Regarding the person detection process performed by the image analysis process, the person detection process can be performed by generating an attribute analysis model by learning the image data of the user, or by comparing with the stored data of a pre-prepared database. The person detection process is a process for detecting the detailed conditions of the attributes of the person, and requires a relatively large amount of calculation processing. In addition, the image data used to generate the model may not be the actual image data but a produced CG image.

[0047] The object detection processing unit 23 performs processing such as detecting the presence or absence of an object in the image captured by the camera 12 through image analysis processing. The object here also includes a person. Therefore, the object detection processing unit 23 detects objects existing in the car 10 and determines whether they are passengers. In other words, it detects whether there are passengers in the car 10, the number of passengers in the car 10, etc. In addition, the object detection processing unit 23 also detects large cargo other than people.

[0048] The object detection process performed by the image analysis process in the object detection processing unit 23 detects the presence or absence of an object of a certain size such as a person from the captured image, and can be executed by a computational process that is lighter than that of the person detection process.

[0049] The object detection processing unit 23 includes a disturbance detection unit 23a for detecting a situation where a passenger moves significantly (a disturbance state) based on the detection of the passenger, and a stay detection unit 23b for detecting a state where the detected passenger stays in the car 10 for a long time.

[0050] The image analysis result determination unit 24 acquires the image analysis result from the human detection processing unit 22 and the image analysis result from the image analysis result transmission unit 25 , and performs an image analysis result determination process for determining the analysis result.

[0051] The image analysis result transmitting unit 25 transmits the determination result of the image analysis result determining unit 24 to the elevator control device 100 and the monitoring system 200 .

[0052] The monitoring system 200 includes a data management unit 201 and a data distribution unit 202 .

[0053] The data management unit 201 acquires the determination result obtained by the image analysis device 20 together with the captured image.

[0054] The data distribution unit 202 distributes the acquired determination results to the external systems 210 , 220 , and 230 .

[0055] For example, the first external system 210 is a crowd detection system for a building with an elevator. Then, the data distribution unit 202 provides the first external system 210 with data on the number of elevator users (number of people boarding and getting off the elevator on each floor) and data on the age group of the users in the image analysis result. Thus, the first external system 210 as a crowd detection system can detect the details of the crowd using the elevator.

[0056] In addition, the second external system 220 is a security system of a building where an elevator is installed. Then, the data distribution unit 202 provides detailed data such as the face recognition result in the image analysis result to the second external system 220. As a result, the second external system 220 as a security system can identify the elevator user and perform safety processing such as allowing the car 10 to stop at the safety release floor.

[0057] In addition, the third external system 230 is a service system that causes the display device in the car 10 to display advertisements. Then, the data distribution unit 202 provides data such as the age group of elevator users in the image analysis result to the third external system 230. As a result, the third external system 230 as a service system for displaying advertisements can distinguish the age group and gender of elevator users, and cause the advertisements displayed on the display device in the car 10 to match the age group and gender of passengers in the car 10.

[0058] [Hardware structure of elevator control device]

[0059] The elevator control device 100, the image analysis device 20, and the monitoring system 200 can each be constituted by a computer.

[0060] Figure 3 A hardware configuration example when the elevator control device 100 is constituted by a computer is shown.

[0061] The computer as the elevator control device 100 is composed of a CPU (Central Processing Unit) 191 , a memory 192 , a storage device 193 , an image input / output unit 194 , a data input / output unit 195 , and an interface (I / F) 196 .

[0062] The CPU 191 executes a program stored in the memory 192 or the storage device 193. The memory 192 is composed of, for example, a RAM (Random Access Memory), stores computer programs and calculation result data, and provides the CPU 191 with a work area required for each process.

[0063] In this embodiment, the CPU 191 executes a program, and a door open state acquisition unit 111, an operation state acquisition unit 112, a door open state determination unit 113, an operation state determination unit 114, an elevator state management unit 115 and an elevator control processing unit 116 are formed in a working area in the memory 192.

[0064] The image input / output unit 194 inputs the image captured by the camera 12 from the image analysis device 20 , and outputs the image to the monitoring system 200 or the like.

[0065] The data input / output unit 195 receives the image analysis result from the image analysis device 20, various data from the operation state detection unit 101 and the door 11, etc. The data input / output unit 195 also outputs a switching instruction to the image analysis mode switching unit 21, the elevator state, an instruction to the operation control unit 102, etc.

[0066] The interface 196 performs communication processing with other devices via the connected network.

[0067] The image analysis device 20 and the monitoring system 200 can also be used to Figure 3 The elevator control device 100 shown in the figure also has a hardware structure composed of a computer.

[0068] In addition, the elevator control device 100, the image analysis device 20, and the monitoring system 200 are constituted by a computer, which is an example. For example, a part or all of the processing may be constituted by hardware such as an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). In addition, for image processing, a processor for image processing called a GPU (Graphics Processing Unit) may be used.

[0069] [Analysis Processing in Image Analysis Device (Example 1: Switching Processing Based on Elevator Control Instructions)]

[0070] Next, in the elevator system of this example, an example of switching processing of the image analysis method in the image analysis device 20 is described. Regarding the switching processing of the image analysis method in the image analysis device 20, it is considered that the switching is performed due to various reasons. First, as Example 1, referring to Figure 4 An example of switching processing based on elevator control instructions is described with reference to the flowchart of FIG.

[0071] Figure 4 This is a flowchart showing an example of processing when switching is performed based on an elevator control signal transmitted from the elevator state management unit 115 of the elevator control device 100 to the image analysis mode switching unit 21.

[0072] First, the image analysis mode switching unit 21 monitors the elevator control signal sent from the elevator control device 100 (step S11). Then, the image analysis mode switching unit 21 determines whether human detection is in a valid state by monitoring the elevator control signal (step S12). The state in which human detection is valid refers to, for example, the state in which the camera 12 and the image analysis device 20 are operating normally, or the state in which a car call is made and it is determined that a passenger is using the car.

[0073] If it is determined in step S12 that human detection is effective (YES in step S12 ), the image analysis mode switching unit 21 selects the image analysis process as the human detection mode (step S13 ), and causes the human detection processing unit 22 to execute detection processing based on image analysis.

[0074] In addition, in step S12, when it is determined that human detection is not in a valid state (No in step S12), the image analysis mode switching unit 21 determines whether object detection is in a valid state (step S14). For example, the determination of whether object detection is in a valid state is performed based on the control validity signal determined by the elevator and whether it is the elevator service time period. Alternatively, although the elevator is used, if the detection state of a person or an object does not change for a certain period of time, it is determined that object detection is invalid. Here, it is also possible to simply make a determination based on the setting information of the image analysis device 20.

[0075] If it is determined in step S14 that object detection is enabled (YES in step S14 ), the image analysis mode switching unit 21 selects the image analysis process as the object detection mode (step S15 ) and causes the object detection processing unit 23 to execute detection processing based on image analysis.

[0076] When it is determined in step S14 that the object detection is ineffective (No in step S14 ), the image analysis mode switching unit 21 returns to the monitoring in step S11 .

[0077] Then, when the image analysis is performed in the human detection processing unit 22 in step S13 and when the image analysis is performed in the object detection processing unit 23 in step S15, the image analysis result determination unit 24 obtains the analysis result and performs management processing of the analysis result (step S16).

[0078] Furthermore, in the management process of step S16, when the detection state of a person or an object changes, the image analysis result transmitting unit 25 transmits the current analysis result to the elevator control device 100 and the monitoring system 200 (step S17).

[0079] like Figure 4 As shown in the flowchart of , the image analysis method in the image analysis device 20 is switched based on the control signal (control command) from the elevator control device 100, so that the image analysis device 20 does not need to always detect the attributes of a person through the person detection processing unit 22. For example, the image analysis device 20 only needs to perform image analysis that places a heavy burden on the person detection processing unit 22 when the passenger transportation service is in progress. On the contrary, when there are few movements of a person, the image analysis device 20 only needs to perform image analysis processing that places a light burden on the object detection processing unit 23. Therefore, the image analysis device 20 can reduce the processing burden of image analysis, reduce the burden on the device, and reduce the power consumption required for image analysis.

[0080] [Analysis Processing in Image Analysis Device (Example 2: Switching Processing Based on Door Open State)]

[0081] Next, refer to Figure 5 Another example (Example 2) of the image analysis method switching process in the image analysis device 20 in the elevator system of this example will be described.

[0082] Figure 5 The example shown is a flowchart showing a case where a switching process of the image analysis method is performed based on the door open state and the running state of the door 11 of the car 10 .

[0083] First, the image analysis mode switching unit 21 monitors the door opening state and the operation state based on the signal sent from the elevator control device 100 (step S21). Then, the image analysis mode switching unit 21 determines whether the door 11 of the current car 10 is in the door opening state by monitoring the elevator control signal (step S22). The door opening state here may include, for example, the state in which the door 11 is fully opened, the state in which the door 11 is in the opening action, and the state in which the door 11 is in the closing action.

[0084] In the determination of step S22, when the door is in the open state ("Yes" in step S22), the image analysis mode switching unit 21 determines whether the elevator car 10 has stopped at any floor (step S23).

[0085] In step S23, when the vehicle stops at any floor (Yes in step S23), the image analysis mode switching unit 21 selects the image analysis processing as the human detection mode (step S24), and causes the human detection processing unit 22 to perform the detection processing based on the image analysis. In addition, in step S23, when the vehicle does not stop at any floor (No in step S23), the monitoring returns to step S21.

[0086] If it is determined in step S22 that the door is not open (No in step S22), the image analysis mode switching unit 21 determines whether it is within a predetermined time from the start of the elevator car 10 running (step S25). The predetermined time here is set to a relatively short time of several seconds to about 10 seconds, for example.

[0087] In step S25, within a predetermined time from when the elevator car 10 starts traveling (yes in step S25), the image analysis mode switching unit 21 selects the image analysis processing as the object detection mode (step S26), and causes the object detection processing unit 23 to perform detection processing based on image analysis.

[0088] In step S25, if it is not within the predetermined time from the start of the travel of the elevator car 10 (No in step S25), the image analysis device 20 does not perform the image analysis process and returns to the monitoring of step S21.

[0089] Then, when human image analysis is performed in the human detection processing unit 22 in step S24, or object image analysis is performed in the object detection processing unit 23 in step S26, and the detection status of the person or object changes, the image analysis result sending unit 25 sends the current analysis result to the elevator control device 100 and the monitoring system 200 (step S27).

[0090] like Figure 5 As shown in the flowchart of , the image analysis method in the image analysis device 20 is switched based on the door open state signal and the operation state signal from the elevator control device 100, so that the image analysis device 20 performs the attribute detection of the person by the person detection processing unit 22 when the door is open and the possibility of passenger movement is high. In addition, in other states, the image analysis device 20 performs the image analysis processing with light load by the object detection processing unit 23.

[0091] Therefore, the image analysis device 20 can reduce the processing burden of image analysis based on the door open state, and can reduce the power consumption required for image analysis. In addition, when a certain period of time has passed since the start of operation in the door closed state, the image analysis device 20 considers that there is no movement of passengers and stops the image analysis of the object detection processing unit 23, thereby further reducing the burden of the image analysis device 20. In addition, by not operating the two image analysis algorithms at the same time, it can be implemented within the limited CPU, GPU, and memory resources such as embedded software.

[0092] [Analysis Processing in Image Analysis Device (Example 3: Another Example of Switching Processing Based on Door Open State)]

[0093] Next, refer to Figure 6 Another example (Example 3) of the image analysis method switching process in the image analysis device 20 in the elevator system of this example will be described.

[0094] Figure 6 The example shown (Example 3) is similar to Figure 5 The example shown is the same as that shown in FIG. 1 , and is a flowchart showing a case where the image analysis method is switched based on the door opening state and the driving state of the door 11 of the car 10. Figure 6 In the example (Example 3) shown, both the detection by the disturbance detection unit 23a and the detection by the stay detection unit 23b included in the object detection processing unit 23 are shown.

[0095] exist Figure 6 In, with Figure 5 The same processing in the flowchart is marked with the same step number, and repeated description is omitted.

[0096] exist Figure 6 In the example of FIG. 2, in step S25, it is determined whether it is within the predetermined time (first predetermined time). If it is not within the first predetermined time, the image analysis mode switching unit 21 further determines whether it is within the second predetermined time from the start of travel (step S28). The second predetermined time here is, for example, a time of about 1 minute to several minutes, which is a time when the possibility of the elevator's continued travel is high.

[0097] Then, when it is determined in step S28 that the vehicle is within the second predetermined time from the start of travel (YES in step S28), the image analysis mode switching unit 21 detects whether the passenger (object) is tampering by the tampering detection unit 23a of the object detection processing unit 23 (step S29).

[0098] When it is determined in step S28 that the time is not within the second predetermined time from the start of travel (No in step S28), the image analysis mode switching unit 21 detects the presence of a passenger (object) staying via the staying detection unit 23b of the object detection processing unit 23 (step S30).

[0099] Then, in step S27, in addition to the case where the image analysis is performed in the person detection processing unit 22 in step S24 and the case where the image analysis is performed in the object detection processing unit 23 in step S26, the analysis result is transmitted in the case where the disturbance detection is performed in step S29 and the retention detection is performed in step S30. That is, in the case where the disturbance detection is performed in step S29 and the retention detection is performed in step S30, the image analysis result transmission unit 25 also transmits the current analysis result to the elevator control device 100 and the monitoring system 200.

[0100] If the Figure 6 As shown in the flowchart, when the elevator is considered to be running, the turmoil detection unit 23a detects the turmoil as a large movement of the passenger, and can take measures such as stopping the car 10. In addition, the retention detection unit 23b detects that the passenger is still retained even if a relatively long time has passed since the start of the trip, and can also take measures when the passenger is retained.

[0101] [Analysis Processing in Image Analysis Device (Example 4: Another Example of Switching Processing Based on Door Open State)]

[0102] Next, refer to Figure 7 Another example (Example 4) of the image analysis method switching process in the image analysis device 20 in the elevator system of this example will be described.

[0103] Figure 7 The example shown is a flowchart showing still another example of a case where the image analysis method switching process is performed based on the door opening state of the door 11 of the car 10 .

[0104] First, the image analysis mode switching unit 21 monitors the door open state and the operation state based on the signal sent from the elevator control device 100, and determines whether the door 11 of the car 10 is currently in the door open state (step S31).

[0105] When the door is in the open state in the judgment of step S31 ("Yes" in step S31), the image analysis mode switching unit 21 determines whether the elevator car 10 has reached any floor through a floor call (button operation in the floor, etc.) and is in the door open state (step S32) based on the signal from the elevator control device 100.

[0106] In step S32, when it is determined that the elevator has arrived by a landing call (Yes in step S32), the image analysis mode switching unit 21 selects the image analysis processing as the human detection mode (step S33), and causes the human detection processing unit 22 to perform detection processing based on image analysis. Here, since there is a high possibility that a new passenger will appear when arriving by a landing call, human detection is performed when getting on the elevator.

[0107] In addition, when it is determined in step S32 that the vehicle has not arrived in the state of a hall call (No in step S32), the process returns to the determination in step S31.

[0108] If the door is not open in step S31 (No in step S31), the image analysis mode switching unit 21 determines whether a destination call is currently registered in the car 10 (step S34). Registration of a destination call means that a destination button of a certain floor is pressed in the car 10 to register the destination.

[0109] When it is determined in step S32 that a destination floor call is registered (yes in step S34), the image analysis mode switching unit 21 selects the image analysis processing as the object detection mode (step S35), and causes the object detection processing unit 23 to perform detection processing based on image analysis. Here, when only a destination floor call arrives, the possibility of a new passenger being generated is low and the possibility of a passenger being present is high, so object detection is performed.

[0110] If the destination floor call is not registered in step S34 (No in step S34), the image analyzing device 20 does not perform analysis, and the process returns to monitoring in step S31.

[0111] Then, when image analysis is performed in the human detection processing unit 22 in step S33 or image analysis is performed in the object detection processing unit 23 in step S35 and the detection status of the human or object changes, the image analysis result sending unit 25 sends the current analysis result to the elevator control device 100 and the monitoring system 200 (step S36).

[0112] like Figure 7 As shown in the flowchart of , the image analysis method in the image analysis device 20 is switched based on the door open state signal from the elevator control device 100, the arrival of the landing call, and whether the destination floor registration has been performed, thereby the image analysis device 20 can appropriately switch the image analysis processing. Specifically, when arriving based on the landing call, the possibility of a passenger boarding the car 10 is high, so the human detection processing unit 22 can appropriately detect the boarding passenger by performing the attribute detection of the passenger. On the other hand, in the door closed state (not the door open state) where the destination floor call is registered, the possibility of there being a passenger in the car 10 is high, so the human detection processing unit 22 can appropriately detect the number of passengers, etc.

[0113] [Analysis Processing in Image Analysis Device (Example 5: Another Example of Switching Processing Based on Door Open State)]

[0114] Next, refer to Figure 8 Another example (Example 5) of the image analysis method switching process in the image analysis device 20 in the elevator system of this example will be described.

[0115] Figure 8 The example shown (Example 5) is similar to Figure 5 The example shown is the same, and is a flowchart showing a case where a process of switching the image analysis method is performed based on the door opening state of the door 11 of the car 10.

[0116] In this Figure 6 In the example (Example 3) shown, the object detection processing unit 23 performs both detection in the disturbance detection unit 23a and detection in the stay detection unit 23b.

[0117] Figure 8 The example shown is a flowchart showing a case where a process of switching the image analysis method is performed based on the door opening state of the door 11 of the car 10 .

[0118] First, the image analysis mode switching unit 21 monitors the door opening state and the operation state based on the signal sent from the elevator control device 100 (step S41). Then, the image analysis mode switching unit 21 determines whether the door 11 of the car 10 is currently in the door opening state by monitoring the elevator control signal (step S42).

[0119] When the door is in the open state in step S42 ("Yes" in step S42), the image analysis mode switching unit 21 determines whether the elevator car 10 is stopped at any floor (step S43).

[0120] In step S43, when the vehicle stops at any floor (Yes in step S43), the image analysis mode switching unit 21 selects the image analysis processing as the human detection mode (step S44), and causes the human detection processing unit 22 to perform the detection processing based on the image analysis. In step S43, when the vehicle does not stop at any floor (No in step S43), the monitoring returns to step S41.

[0121] If it is determined in step S42 that the door is not open (No in step S42), the image analysis mode switching unit 21 determines whether it is within a first predetermined time from the start of the elevator car 10 (step S45). The predetermined time here is set to a relatively short time of, for example, several seconds to about 10 seconds.

[0122] In step S45, within a predetermined time from when the elevator car 10 starts traveling (yes in step S45), the image analysis mode switching unit 21 selects the image analysis processing as the object detection mode (step S46), and causes the object detection processing unit 23 to perform detection processing based on image analysis.

[0123] In addition, in step S45, when it is not within the predetermined time from the start of the travel of the elevator car 10 (No in step S45), the image analysis mode switching unit 21 further determines whether the elevator car 10 has stopped (step S47). Here, when it is not stopped (No in step S47), the image analysis mode switching unit 21 returns to the monitoring of step S41.

[0124] In addition, when it is determined in step S47 that the elevator has stopped (Yes in step S47), the image analysis mode switching unit 21 determines whether the lighting device (not shown) in the car 10 is turned on (step S48). Here, when the lighting device 13 in the car 10 is turned on (Yes in step S48), the image analysis mode switching unit 21 detects whether the passenger (object) is moving around by the turmoil detection unit 23a of the object detection processing unit 23 (step S49).

[0125] When the lighting device 13 in the car 10 is not turned on (No in step S48), the image analysis mode switching unit 21 detects the presence or absence of a passenger (object) staying by the staying detecting unit 23b of the object detection processing unit 23 (step S50).

[0126] Then, except for the case where image analysis is performed in the human detection processing unit 22 in step S44 and the case where image analysis is performed in the object detection processing unit 23 in step S46, the image analysis result sending unit 25 sends the analysis results when disturbance detection is performed in step S49 and retention detection is performed in step S50 (step S51).

[0127] like Figure 8 As shown in the flowchart, when the elevator has stopped and the lighting device in the car has been lit, there is a high possibility that there is a user in the car, so a disturbance detection process is performed. When the elevator is not lit, it is unnatural to have a user in the car, so a retention detection process is performed. In this way, disturbance detection and retention detection can be appropriately performed according to the various states of the car 10.

[0128] [Modifications]

[0129] In addition, the embodiment examples described so far are described in detail in order to explain the present invention in an easily understandable manner, and are not necessarily limited to the embodiment examples having all the described configurations.

[0130] For example, in Figure 1 as well as Figure 2 In the configuration described in , the image analyzing device 20 is provided in the car 10. On the other hand, the elevator control device 100 may include the image analyzing device 20 therein.

[0131] In the above-mentioned embodiment, the image analysis processing is switched by the image analysis mode switching unit 21 in the image analysis device 20 receiving a signal from the elevator control device 100. Figures 4 to 8 In the processing described in each example, it is determined which image analysis method is better, and the image analysis method switching unit 21 executes the switching processing according to an instruction based on the determination.

[0132] In addition, the human detection method can also analyze only the image during the period from the start of door opening to the completion of door closing when the door sensor is shielded from light, thereby further reducing the processing load.

[0133] In addition, the object detection method can also set the image analysis object to the upper body and above. Even if there are a large number of passengers in the car, the overlap of people in the camera in the car will be reduced, thereby further improving the detection accuracy.

[0134] The model for detecting people taking the elevator can be the front image of the person, and the model for detecting people getting off the elevator can be the back image of the person. Model learning can be performed in advance to improve the detection accuracy of the camera in the elevator.

[0135] Taking into account the large amount of light entering from the floor when the door is open, the automatic calibration operation can automatically move to each floor to open the door, and automatically set the human / object detection threshold according to the amount of light when the door is opened on each floor. In the case of floor stations facing the outside such as apartments, since the amount of light varies according to the season and time, calibration operations can be performed regularly during unused time periods, thereby achieving improved accuracy corresponding to the environment.

[0136] The processing load may be further reduced by performing image analysis only on images when the door is completely closed and driving starts.

[0137] When image analysis is performed while the door is closed, the number of people can be counted only when the amount of movement (amount of change) of a person is less than a predetermined value, thereby improving the detection accuracy.

[0138] The detection accuracy can be improved by generating in advance a learning model of a person's back image corresponding to the installation position of the camera in the car.

[0139] In addition, Figure 1In the configuration of , one camera 12 is provided in the car 10, but a plurality of cameras may be provided and the analysis of the images captured by each camera may be switched.

[0140] In addition, Figure 2 In the structural diagram shown, only those control lines and information lines that are considered necessary for explanation are shown, and not all control lines and information lines may be shown in the product. In fact, it can be considered that almost all structures are connected to each other.

[0141] In addition, the program for executing the processing in the image analysis device 20 and the elevator control device 100 may be prepared in a storage device in a computer or may be placed in an external memory, an IC card, an SD card, an optical disk or other recording medium and transferred.

[0142] Description of Reference Numerals

[0143] 10…car, 11…door, 12…camera, 12a…image management unit, 13…illumination device, 20…image analysis device, 21…image analysis mode switching unit, 22…person detection processing unit, 23…object detection processing unit, 23a…disorder detection unit, 23b…stay detection unit, 24…image analysis result determination unit, 25…image analysis result transmission unit, 100…elevator control device, 101…operation status detection unit, 102…operation control unit, 111…door open status acquisition unit Unit, 112…operation status acquisition unit, 113…door open status determination unit, 114…operation status determination unit, 115…elevator status management unit, 116…elevator control processing unit, 191…CPU, 192…memory, 193…storage device, 194…image input and output unit, 195…data input and output unit, 196…interface, 200…monitoring system, 201…data management unit, 210…first external system, 220…second external system, 230…third external system.

Claims

1. An elevator system that performs processing corresponding to an image captured by a camera installed in a car, characterized in that: The elevator system comprises: an object detection processing unit for detecting whether there is a person or an object in the car based on an analysis of the image captured by the camera; a human detection processing unit for detecting attributes of a person in the car based on analysis of the image captured by the camera; an image analysis mode switching unit that selectively performs detection in the object detection processing unit and detection in the human detection processing unit; as well as an image analysis result determination unit configured to determine an image analysis result of either detection by the object detection processing unit or detection by the person detection processing unit, Based on the result determined by the image analysis result determination unit, operation control of the elevator or notification to other systems connected to the elevator system is performed.

2. The elevator system according to claim 1, characterized in that The image analysis mode switching unit switches detection in the object detection processing unit and detection in the human detection processing unit based on a determination in the operation state determination unit of the elevator control device.

3. The elevator system according to claim 1, characterized in that When the door open state determination unit of the elevator control device determines that the door of the car is in the open state, the image analysis mode switching unit causes the human detection processing unit to perform human detection, When the door open state determination unit determines that the door of the car is in the closed state, the image analysis method switching unit causes the object detection processing unit to execute object detection.

4. The elevator system according to claim 3, characterized in that The door open state determination unit determines that the door of the car is in the open state based on the open state of the door of the car due to a car call at a landing.

5. The elevator system according to claim 4, characterized in that The door open state determination unit determines that the door of the car is in the closed state when a destination floor is registered in the car.

6. The elevator system according to claim 1, characterized in that The elevator system includes an operation control unit that performs operation control of the car based on the result determined by the image analysis result determination unit. The door opening time of the car at the stop floor is changed based on the result determined by the image analysis result determination unit.

7. The elevator system according to claim 1, characterized in that The result determined by the image analysis result determination unit is sent to a crowd flow detection system that determines the use status of the elevator or the use status of the building where the elevator is installed.

8. The elevator system according to claim 1, characterized in that The result determined by the image analysis result determination unit is transmitted to a security system of a building where an elevator is installed.

9. The elevator system according to claim 1, characterized in that The object detection processing unit includes both or either a disturbance detection unit for detecting a movement of an object inside the car exceeding a predetermined value and a retention detection unit for detecting a retention of an object inside the car exceeding a predetermined time.

10. An elevator control method, performing processing corresponding to an image captured by a camera installed in a car, characterized in that: The elevator control method comprises: Object detection processing, detecting whether there are people or objects in the car based on the analysis of the image captured by the camera; Human detection processing, detecting the attributes of the human in the car based on the analysis of the image captured by the camera; an image analysis mode switching process for selectively performing detection in the object detection process and detection in the person detection process; An image analysis result determination process for determining an image analysis result of any one of the detection in the object detection process and the detection in the person detection process; as well as The image analysis result transmission process performs operation control of the elevator or notification to other systems connected to the elevator system based on the result determined by the image analysis result determination unit.

Images