JP2021127251A - User detection system of elevator - Google Patents

Abstract

To provide a user detection system of an elevator which can accurately detect a user in the vicinity of an elevator from an image captured by a camera.SOLUTION: A user detection system of an elevator comprises: imaging means which is installed in the vicinity of a door of a car and captures an image including the inside of the car and a hall; setting means which sets a plurality of detection areas for detecting a person or object on the captured image and sets different detection sensitivities for each of the plurality of set detection areas; detection means which executes detection processing for detecting a person or object for each set detection area; and control means which reflects the result of the detection processing on the door opening/closing control of the door of the car.SELECTED DRAWING: Figure 1

Description

An embodiment of the present invention relates to an elevator user detection system.

In recent years, various technologies have been devised to prevent people and objects from being caught in the elevator car door. For example, a technique has been devised in which a camera is used to detect a user in the vicinity of an elevator and control the opening / closing of the door of the elevator.

In such a technique, it is necessary to accurately detect a user in the vicinity of an elevator from an image taken by a camera, and improvement of the detection accuracy is desired.

Japanese Patent No. 6092433

An object to be solved by the embodiment of the present invention is to provide an elevator user detection system capable of accurately detecting a user in the vicinity of an elevator from an image taken by a camera.

According to one embodiment, the elevator user detection system is installed near the door of the car, and is a shooting means for taking an image including the inside of the car and the landing, and the taken image is made into a block of a certain size. A detection means that executes a detection process for detecting a person or an object by paying attention to a change in the brightness value of each block, and a plurality of detection areas are set on the captured image, and the setting is performed. A setting means for setting a threshold value of the brightness difference for detecting the person or an object for each of the plurality of detection areas, and a control means for reflecting the result of the detection process in the door opening / closing control of the car door. And.

FIG. 1 is a diagram showing a configuration of an elevator user detection system according to an embodiment. FIG. 2 is a diagram showing a state in which the captured images in the same embodiment are divided into blocks. FIG. 3 is a flowchart showing the flow of the detection process in the same embodiment. FIG. 4 is a diagram showing a configuration of a portion around an entrance / exit in the car according to the same embodiment. FIG. 5 is a diagram for explaining the setting of the detection area in the same embodiment. FIG. 6 is a flowchart showing a main processing flow of the elevator user detection system in the same embodiment. FIG. 7 is a flowchart showing the flow of the first corresponding processing in the same embodiment. FIG. 8 is a flowchart showing the flow of the second corresponding processing in the same embodiment. FIG. 9 is a diagram showing an example of a data structure of set value information in the same embodiment. FIG. 10 is a diagram for explaining the advantages of the elevator user detection system in the same embodiment.

Hereinafter, embodiments will be described with reference to the drawings.
The disclosure is merely an example, and the invention is not limited by the contents described in the following embodiments. Modifications that can be easily conceived by those skilled in the art are naturally included in the scope of disclosure. In order to clarify the explanation, in the drawings, the size, shape, etc. of each part may be changed with respect to the actual embodiment and shown schematically. In a plurality of drawings, the corresponding elements may be designated by the same reference numerals and detailed description thereof may be omitted.

FIG. 1 is a diagram showing a configuration of an elevator user detection system according to an embodiment. Although the description will be given using one car as an example, the same configuration is used for a plurality of cars.

A camera 12 is installed above the doorway of the car 11. Specifically, the camera 12 is installed in the curtain plate 11a covering the upper part of the entrance / exit of the car 11 with the lens portion directed directly downward or in the direction of the landing 15. The camera 12 is a small surveillance camera such as an in-vehicle camera, has a wide-angle lens, and takes a wide range of images including the inside of the car 11 and the landing 15 with a viewing angle of 180 degrees or more. The camera 12 can continuously capture images of several frames (for example, 30 frames / second) per second.

At the landing 15 on each floor, a landing door 14 is installed at the arrival port of the car 11 so as to be openable and closable. The landing door 14 engages with the car door 13 when the car 11 arrives to open and close. The power source (door motor) is on the car 11 side, and the landing door 14 only opens and closes following the car door 13. In the following description, it is assumed that the landing door 14 is also open when the car door 13 is open, and the landing door 14 is also closed when the car door 13 is closed.

Each image (video) continuously captured by the camera 12 is analyzed and processed in real time by the image processing device 20. Although the image processing device 20 is taken out from the car 11 for convenience in FIG. 1, the image processing device 20 is actually housed in the curtain plate 11a together with the camera 12.

The image processing device 20 includes a storage unit 21 and a detection unit 22. The storage unit 21 has a buffer area for sequentially storing images taken by the camera 12 and temporarily storing data necessary for processing of the detection unit 22. The storage unit 21 may store an image that has undergone processing such as distortion correction, enlargement / reduction, and partial cropping as preprocessing for the captured image.

The detection unit 22 detects a user in the car 11 or in the landing 15 by using the captured image of the camera 12. When the detection unit 22 is functionally divided, it is composed of a detection area setting unit 22a and a detection processing unit 22b.

The detection area setting unit 22a sets at least two or more detection areas for detecting a user (a person using an elevator) or an object on the captured image of the camera 12. The "thing" referred to here includes, for example, a user's clothes and luggage, and a moving body such as a wheelchair. Further, devices related to elevator equipment such as operation buttons, lamps, and display devices in the car are also included. Since the details of the detection area will be described later, the detailed description thereof will be omitted here.

The detection processing unit 22b executes a detection process for detecting a person or an object (movement) for each detection area set by the detection area setting unit 22a. Specifically, as shown in FIG. 2, the detection processing unit 22b divides the image captured by the camera 12 into blocks of a certain size, pays attention to the change in the brightness value of each block, and pays attention to the change in the brightness value of each block. Motion) is detected. One block shown in FIG. 2 includes a plurality of pixels constituting a captured image.

Here, the detection process executed by the detection processing unit 22b will be described with reference to the flowchart of FIG.

When the detection processing unit 22b reads out the captured images stored in the storage unit 21 one by one and divides the captured captured images into blocks of a certain size, the average brightness value for each block (that is, a plurality of pixels included in the block). (Average of the brightness values of) is calculated (step S1). At that time, the detection processing unit 22b shall store, as an initial value, the average luminance value for each block calculated when the first image is read in the buffer area in the storage unit 21 (step S2). ).

When the second and subsequent images are obtained, the detection processing unit 22b sets the average luminance value for each block of the current image and the average luminance value for each block of the previous image held in the buffer area described above. Are compared (step S3). As a result, when there is a block having a brightness difference equal to or larger than a preset threshold value, the detection processing unit 22b regards the block as a moving block, and causes a person or an object (movement) in the block portion. It is determined that it has been detected (step S4).

When the detection of a person or an object targeting the current image is completed, the detection processing unit 22b writes the average luminance value for each block of the current image to the above-mentioned buffer area for comparison with the next image ( Step S5), the series of detection processes is completed.

In this way, the detection processing unit 22b pays attention to the average luminance value for each block in the image captured by the camera 12, and the average luminance value changes by a preset threshold value or more in two consecutive images. If there is a block, it is detected that there is a person or an object in the block.

A part or all the functions of the image processing device 20 may be mounted on the elevator control device 30 described later.

The elevator control device 30 controls the operation of various devices (destination floor buttons, lights, etc.) installed in the car 11. Further, the elevator control device 30 includes an operation control unit 31, a door opening / closing control unit 32, and a notification unit 33. The operation control unit 31 controls the operation of the car 11. The notification unit 33 calls attention to the user in the car 11 based on the detection result in the detection processing unit 22b.

The door opening / closing control unit 32 controls the opening / closing of the car door 13 when the car 11 arrives at the landing 15. Specifically, the door opening / closing control unit 32 opens the car door 13 when the car 11 arrives at the landing 15, and closes the door after a predetermined time has elapsed.

Here, for example, when a person or an object is detected by the detection processing unit 22b before the start of the door opening operation of the car door 13 or during the door opening operation, the door opening / closing control unit 32 causes a door accident (pulled into the door pocket). Door opening / closing control is performed to avoid accidents). Specifically, the door opening / closing control unit 32 temporarily stops the door opening operation of the car door 13, moves it in the opposite direction (door closing direction), slows down the door opening speed of the car door 13, and the like. Door opening and closing control is performed. Further, for example, when a person or an object is detected by the detection processing unit 22b before the door closing operation of the car door 13 is started (during full opening) or during the door closing operation, the door opening / closing control unit 32 causes a door accident (to the door). Door opening / closing control is performed to avoid accidents caused by being pinched. Specifically, the door opening / closing control unit 32 temporarily stops the door closing operation of the car door 13, moves it in the opposite direction (door opening direction), slows down the door closing speed of the car door 13, and the like. Door opening and closing control is performed.

FIG. 4 is a diagram showing a configuration of a portion around the entrance / exit in the car 11.
A car door 13 is provided at the entrance and exit of the car 11 so as to be openable and closable. In the example of FIG. 4, a double door double door type car door 13 is shown, and the two door panels 13a and 13b constituting the car door 13 open and close in opposite directions along the frontage direction (horizontal direction). .. The "frontage" is the same as the entrance / exit of the car 11.

Front pillars 41a and 41b are provided on both sides of the doorway of the car 11, and surround the doorway of the car 11 together with the curtain plate 11a. The "front pillar" is also referred to as an entrance / exit pillar or an entrance / exit frame, and a door pocket for storing the car door 13 is generally provided on the back side. In the example of FIG. 4, when the car door 13 is opened, one door panel 13a is housed in a door bag 42a provided on the back side of the front pillar 41a, and the other door panel 13b is a door bag provided on the back side of the front pillar 41b. It is stored in 42b.

A display 43, an operation panel 45 on which a destination floor button 44 and the like are arranged, and a speaker 46 are installed on one or both of the front pillars 41a and 41b. FIG. 4 shows a case where the speaker 46 is installed on the front pillar 41a, and the display 43 and the operation panel 45 are installed on the front pillar 41b.

Here, a camera 12 having a wide-angle lens is installed in the central portion of the curtain plate 11a above the entrance / exit of the car 11.

FIG. 5 is a diagram showing an example of a captured image of the camera 12. In FIG. 5, with the car doors 13 (door panels 13a and 13b) and the landing doors 14 (door panels 14a and 14b) fully open, the inside of the car 11 has a viewing angle of 180 degrees or more from the upper part of the doorway of the car 11. It shows the case where the landing 15 is photographed. The upper side of FIG. 5 shows the landing 15, and the lower side shows the inside of the car 11. Hereinafter, the opening / closing direction of the car door 13 will be referred to as the X direction, the direction perpendicular to the opening / closing direction of the car door 13 will be referred to as the Y direction, and the height direction of the car 11 will be referred to as the Z direction.

At the landing 15, three-sided frames 17a and 17b are provided on both sides of the arrival port of the car 11, and a band-shaped landing sill 18 having a predetermined width is provided on the floor surface 16 between the three-sided frames 17a and 17b. It is arranged along the opening / closing direction of 14. Further, a strip-shaped car sill 47 having a predetermined width is arranged on the entrance / exit side of the floor surface 19 of the car 11 along the opening / closing direction of the car door 13.

Here, detection areas E1 to E4 for detecting a person or an object are set in the car 11 and the landing 15 shown in the captured image.

The detection area E1 is an area for detecting (preventing) the user's pulling into the door (door pocket) in advance during the door opening operation, and is the inner side surfaces 41a-1, 41b-1 of the front pillars 41a and 41b. And the floor surface 19 of the car 11 near the front pillars 41a and 41b. In the following, the detection area E1 will be referred to as a retracted detection area E1.

Specifically, as shown in FIG. 5, the retracted detection areas E1-1 and E1-2 have predetermined widths D1 and D2 in the width direction of the inner side surfaces 41a-1 and 41b-1 of the front pillars 41a and 41b. Is set in a strip shape. The widths D1 and D2 described above are set to be the same as or slightly smaller than the width (width in the lateral direction) of the inner side surfaces 41a-1 and 41b-1, for example. The widths D1 and D2 described above may be the same or different. Further, the pull-in detection areas E1-1 and E1-2 are set from the floor surface 19 to the positions of heights h1 and h2. The heights h1 and h2 are arbitrary values, and the heights h1 and h2 may be the same or different.

The retracted detection areas E1-1 and E1-2 are areas for detecting the user's hand or arm touching the inner side surfaces 41a-1 and 41b-1 of the front pillars 41a and 41b, for example.

Further, as shown in FIG. 5, the retracted detection area E1-3 has a predetermined width D3 on the floor surface 19 of the car 11 and is set in a band shape. The width D3 described above may be the same as or different from the widths D1 and D2 described above. Further, the pull-in detection area E1-3 is set to have a predetermined width W1 in the X direction orthogonal to the width D3 described above. The width W1 described above is set to be the same as or slightly smaller than the width of the entrance / exit of the car door 13.

The retracted detection area E1-3 is an area for detecting, for example, a user's hand or arm touching the car door 13, a user close to the car door 13, and the like.

The detection area E2 is an area for detecting a user or an object on the landing sill 18 and the car sill 47, and is set in the landing sill 18 and the car sill 47. In the following, the detection area E2 will be referred to as the on-sill detection area E2.

Specifically, as shown in FIG. 5, the on-sill detection area E2 has a predetermined width W2 in the X direction and a predetermined distance L1 in the Y direction on the landing sill 18 and the car sill 47. Is set. The width W2 described above is set to be the same as or slightly smaller than the width of the entrance / exit of the car door 13. Further, the above-mentioned distance L1 is set to be the same as or slightly smaller than the sum of the distance in the Y direction of the landing sill 18 and the distance in the Y direction of the car sill 47.

The detection area E2 on the sill is an area for detecting, for example, a lead wire connecting pets, an object extending from the inside of the car 11 to the landing 15, and the like.

The detection area E3 is an area for detecting a person or an object in a place close to the car 11 at the landing 15, and is set near the entrance / exit of the car 11 at the landing 15. Hereinafter, the detection area E3 will be referred to as a proximity detection area E3.

Specifically, as shown in FIG. 5, the proximity detection area E3 is set with a predetermined distance L2 in the direction (Y direction) of the landing 15 from the entrance / exit of the car 11. The shape of the proximity detection area E3 may be a rectangle having a width equal to or greater than the width of the entrance / exit of the car door 13 in the X direction, or a trapezoid obtained by removing the blind spots of the three-sided frames 17a and 17b from the rectangle. Is also good. FIG. 5 shows a case where the proximity detection area E3 has a trapezoidal shape.

The detection area E4 is an area for detecting a user or an object approaching the car 11 from the landing 15, and is set in the landing 15. In the following, the detection area E4 will be referred to as a boarding intention estimation area E4.

Specifically, as shown in FIG. 5, the boarding intention estimation area E4 is set on the floor surface of the landing 15 farther from the car door 13 than the position where the proximity detection area E3 is set. The shape of the boarding intention estimation area E4 may be a rectangle having a width equal to or greater than the width of the doorway of the car door 13 in the X direction, or a trapezoid obtained by removing the blind spots of the three-sided frames 17a and 17b from the rectangle. You may. FIG. 5 shows a case where the shape of the boarding intention estimation area E4 is trapezoidal. Here, it is assumed that the boarding intention estimation area E4 is set separately from the proximity detection area E3, but the boarding intention estimation area E4 may be set including the proximity detection area E3. In this case, the boarding intention estimation area E4 is set with a predetermined distance L3 (L3> L2) in the direction (Y direction) of the landing 15 from the entrance / exit of the car 11.

The boarding intention estimation area E4 is an area that detects a person or an object in the area and detects whether or not the detected person or the object is approaching the car 11 from the landing 15.

The size and shape of each of the above-mentioned detection areas E1 to E4 may be fixed to the above-mentioned size and shape, or may be dynamically changed according to the door opening / closing operation of the car door 13.
In the claims, the retracted detection area E1 is referred to as the first detection area, the on-sill detection area E2 is referred to as the fourth detection area, and the proximity detection area E3 is referred to as the second detection area. The boarding intention estimation area E4 is referred to as a third detection area.

Next, the main operations of this system will be described.
FIG. 6 is a flowchart showing the overall processing flow in this system.

First, as an initial setting, the detection area setting process is executed by the detection area setting unit 22a of the detection unit 22 provided in the image processing device 20 (step S11). This detection area setting process is executed, for example, when the camera 12 is installed or when the installation position of the camera 12 is adjusted.

According to the detection area setting process, a plurality of detection areas E1 to E4 shown in FIG. 5 are set on the image captured by the camera 12. As described above, the retracted detection areas E1-1 and E1-2 are set on the inner side surfaces 41a-1 and 41b-1 of the front pillars 41a and 41b and the floor surface 19 of the car 11. Further, the detection area E2 on the sill is set on the landing sill 18 and the car sill 47, and the proximity detection area E3 is set near (the floor surface) the entrance / exit of the car 11 at the landing 15, and the boarding intention estimation area E4. Is set at the landing 15 (floor surface).

When setting each of the detection areas E1 to E4, the floor surface 19 of the car 11, the front pillars 41a, 41b, the car sill 47, the landing 15 (floor surface), the landing sill 18, etc. The imaged area is calculated based on the design value of each component of the car 11 and the eigenvalue of the camera 12. The design values of each component of the car 11 and the eigenvalues of the camera 12 include, for example, the following items.

・ Width of the frontage (width of the entrance and exit of the basket)
・ Door height
・ Pillar width
・ Door type (double door / right or left single door)
・ Floor and wall area
・ Camera relative position to frontage (3D)
・ Camera angle (3 axes)
・ Camera angle of view (focal length)
The detection area setting unit 22a calculates an area on the captured image in which the area to be set for each of the detection areas E1 to E4 is likely to appear based on the above-mentioned various values, and for the calculated area. Each detection area E1 to E4 is set.

Subsequently, the operation of the car 11 during operation will be described.
The camera 12 starts shooting the shooting target including the inside of the car 11 and the landing 15 at a predetermined frame rate. Shooting by the camera 12 is continuously performed. The image processing device 20 acquires the images taken by the camera 12 in time series (step S12), and executes the detection process shown in FIG. 3 in real time while sequentially storing these images in the storage unit 21.

When the car 11 arrives at the landing 15 on an arbitrary floor (Yes in step S13), the detection processing unit 22b of the image processing device 20 targets the retracted detection area E1 before the car door 13 is opened. The detected detection process is executed (step S14). Specifically, the detection processing unit 22b executes a series of detection processes shown in FIG. 3 for the blocks in the retracted detection area E1 among a large number of blocks included in the acquired captured image. do.

The result of the detection process in step S14 described above is output from the image processing device 20 to the elevator control device 30 (step S15). When the elevator control device 30 receives the result of the detection process in step S14 described above, the elevator control device 30 executes a response process (hereinafter, referred to as a first response process) according to the result of the detection process targeting the retracted detection area E1. (Step S16).

Here, the flow of the first correspondence process will be described with reference to the flowchart of FIG. 7.
When no person or object (movement) is detected in the retracted detection area E1 (No in step S16-1), the door opening / closing control unit 32 of the elevator control device 30 opens the car door 13 as usual. Control is performed (step S16-2), and the first correspondence process is terminated.

On the other hand, when a person or an object (movement) is detected in the retracted detection area E1 (step S16-1Yes), the notification unit 33 of the elevator control device 30 makes a voice announcement through the speaker 46 in the car 11. This is performed to alert the user in the car 11 to move away from the car door 13 (step S16-3). After that, the door opening / closing control unit 32 of the elevator control device 30 controls to open the car door 13 at a door opening speed slower than usual (step S16-4), and ends the first response process.

The process of step S16-4 described above may be executed after a predetermined time has elapsed after the process of step S16-3 described above is executed. According to this, since it is possible to secure the time for the user to leave the car door 13, it is possible to more reliably suppress the accident of being pulled into the car door 13.

Here, even if a person or an object is detected in the retracted detection area E1, the elevator control device 30 opens the car door 13 at a slower speed than usual after calling the user's attention. However, the present invention is not limited to this, and the elevator control device 30 may not open the car door 13 as long as a person or an object is detected in the retracted detection area E1. However, while such door opening / closing control has an advantage that the safety of the user can be greatly improved, it may reduce the operating efficiency. Therefore, for example, the pull-in detection area E1 After a lapse of a predetermined time after the person or the object is detected in the car door 13, the car door 13 may be opened even if the person or the object is detected in the retracted detection area E1.

Further, here, the description has been made on the assumption that the detection process targeting the retracted detection area E1 is executed before the car door 13 is opened, but even during the door opening operation of the car door 13. Similarly, the detection process targeting the pull-in detection area E1 may be executed. When a person or an object is detected in the detection area E1 during the door opening operation, the door opening / closing control unit 32 of the elevator control device 30 temporarily suspends the door opening operation of the car door 13, or the car door 13 Is controlled in the opposite direction (door closing direction).

Returning to the description of FIG. 6 again. When the car door 13 is opened as a result of the first response processing, the detection processing unit 22b executes the detection processing targeting each of the detection areas E1 to E4 (step S17). Specifically, the detection processing unit 22b targets each block in each detection area E1 to E4 among a large number of blocks included in the acquired captured image, and a series of detection processes shown in FIG. To execute.

The result of the detection process in step S17 described above is output from the image processing device 20 to the elevator control device 30 (step S18). When the elevator control device 30 receives the result of the detection process in step S17 described above, the elevator control device 30 performs a response process (hereinafter, referred to as a second response process) according to the result of the detection process targeting each of the detection areas E1 to E4. It is executed (step S19), and a series of operations in this system is terminated.

Here, the flow of the second correspondence process will be described with reference to the flowchart of FIG.
When no person or object (movement) is detected in each of the detection areas E1 to E4 (No in step S19-1), the door opening / closing control unit 32 of the elevator control device 30 closes the car door 13 as usual. The closing control is performed (step S19-2), and the second corresponding process is terminated. When all the car doors 13 are closed by the door opening / closing control unit 32, the car 11 departs for the next destination floor.

On the other hand, when a person or an object (movement) is detected in any of the detection areas E1 to E4 (Yes in step S19-1), the elevator control device 30 detects the person or the object (movement). The process corresponding to the detected detection area is executed (step S19-3).

For example, when a person or an object is detected in the retracted detection area E1 or the on-sill detection area E2, the door open / close control unit 32 of the elevator control device 30 maintains the door open state (fully open state) of the car door 13. , The notification unit 33 alerts the user in the car 11 to stay away from the vicinity of the doorway. Further, when a person or an object is detected in the proximity detection area E3, the door opening / closing control unit 32 of the elevator control device 30 maintains the door open state of the car door 13. Further, when a person or an object is detected in the boarding intention estimation area E4 and it is further detected that the detected person or the object is approaching the car 11, the elevator control is performed. The door open / close control unit 32 of the device 30 maintains the door open state of the car door 13. On the other hand, when a person or an object is detected in the boarding intention estimation area E4 and it is further detected that the detected person or the object is not approaching the car 11, the elevator control is performed. The device 30 executes the process of step S19-2 described above.

When a person or an object is detected in a plurality of detection areas, the elevator control device 30 executes a process corresponding to each detection area in which the person or the object is detected.

Although the description has been made here assuming that the detection process for each of the detection areas E1 to E4 is executed when the car door 13 is fully opened, the same applies during the door closing operation of the car door 13. , Detection processing targeting each detection area E1 to E4 may be executed. When a person or an object is detected in each of the detection areas E1 to E4 during the door closing operation, the door opening / closing control unit 32 of the elevator control device 30 basically interrupts the door closing operation of the car door 13. Controls such as reopening that moves the car door 13 in the opposite direction (door opening direction).

As described above, according to this system, it is possible to detect a person or an object (movement) in each of the detection areas E1 to E4 and realize door opening / closing control according to the detection result. ..

On the other hand, in the series of detection processes shown in FIG. 3 described above, the threshold value of the luminance difference used for detecting a person or an object (movement) is the same in each of the detection areas E1 to E4. , The following problems may occur. The above-mentioned threshold value of the brightness difference shall be set by a maintenance person based on the proximity detection area E3 for which one wants to reliably detect a person or an object (movement) (or is set in advance at the time of shipment). It is assumed that there is). Further, since the above-mentioned threshold value of the brightness difference is a value set for detecting a person or an object, the sensitivity for detecting a person or an object, or simply referred to as a detection sensitivity will be described below. In some cases.

For example, in the retracted detection area E1, there is a possibility that a shadow of a person or an object due to the lighting in the car 11 may be formed. In particular, since the pull-in detection area E1 is set near the operation panel 45 called the inner side surfaces 41a-1 and 41b-1 of the front columns 41a and 41b as described above, the user who operates the operation panel 45 There is a high possibility that shadows will be reflected. At this time, when the sensitivity for detecting a person or an object (movement) is uniformly set to a value capable of reliably detecting the person or an object in the proximity detection area E3 as described above (that is,). , When the detection sensitivity is set high), even a slight change in the brightness value is detected as a person or an object, so the above-mentioned movement of the shadow of the user may be erroneously detected as a person or an object. be.

According to this false detection, the elevator control device 30 performs erroneous door opening / closing control, and the door opening speed of the car door 13 becomes slow (or the car door 13 does not open forever). There is a possibility that the open state of the door 13 is maintained and the car door 13 is not closed (or the car door 13 is reopened many times). This is not a favorable situation for the user.

Therefore, the elevator user detection system according to the present embodiment is characterized in that different detection sensitivities are set for each of the detection areas E1 to E4. In the following, the detection sensitivity set in the proximity detection area E3 according to the operation of the maintenance staff will be referred to as a reference sensitivity or a reference threshold value.

In the process of step S11 shown in FIG. 6, the detection area setting unit 22a sets each detection area E1 to E4 on the captured image, and detects a person or an object (movement) according to the operation of the maintenance staff. Accepts the input of sensitivity to do. The detection area setting unit 22a sets the detection sensitivity at which the input is received to the sensitivity for detecting a person or an object in the proximity detection area E3, that is, the reference sensitivity.

Further, the detection area setting unit 22a sets the above-mentioned reference sensitivity as the detection sensitivity in the detection area E2 on the sill. This is because it is necessary to reliably detect a person or an object from the viewpoint that the detection area E2 on the sill is pinched by the door and suppresses an accident.

Further, the detection area setting unit 22a sets a detection sensitivity lower than the above-mentioned reference sensitivity as the detection sensitivity in the boarding intention estimation area E4 set at a place farther from the car door 13 than the proximity detection area E3 (that is,). , Set a luminance difference threshold that is greater than the luminance difference threshold that corresponds to the reference sensitivity). According to this, a detection process is performed such that a person or an object (movement) is reliably detected in a place near the car door 13, but a person or an object is not detected more than necessary in a place far from the car door 13. It is possible to achieve it.

Further, the detection area setting unit 22a sets a detection sensitivity lower than the above-mentioned reference sensitivity as the detection sensitivity in the retracted detection area E1 set near the operation panel 45 (that is, the brightness difference corresponding to the reference sensitivity). Set a threshold for luminance difference greater than the threshold for). According to this, a person or an object (movement) is reliably detected in a place near the car door 13 on the landing 15 side, but the user is in a place where the shadow of the user who operates the operation panel 45 is easily reflected. It is possible to realize a detection process that does not detect a person or an object by changing the brightness difference of the degree of shadow movement. Although the detection sensitivity set in the pull-in detection area E1 and the detection sensitivity set in the boarding intention estimation area E4 are both lower than the above-mentioned reference sensitivity, they are common. These detection sensitivities may be the same or different.

As shown in FIG. 9, it is assumed that the storage unit 21 stores in advance set value information in which the detection sensitivity and the threshold value of the luminance difference are associated with each other. For example, according to the set value information I1 shown in FIG. 9, it is shown that the threshold value of the luminance difference corresponding to the “detection sensitivity (medium)” is “A”. Similarly, according to the set value information I2, it is shown that the threshold value of the luminance difference corresponding to the “detection sensitivity (low)” is “B (> A)”. Further, according to the set value information I3, it is shown that the threshold value of the luminance difference corresponding to the “detection sensitivity (high)” is “C (<A)”.

The detection area setting unit 22a reads the threshold value of the brightness difference corresponding to the detection sensitivity that received the input according to the operation of the maintenance staff from the storage unit 21, and reads the read threshold value of the brightness difference from the proximity detection area E3. Set to. The threshold value of the luminance difference set in the proximity detection area E3 in this way corresponds to the above-mentioned reference sensitivity.

Therefore, for example, when the detection sensitivity that receives the input according to the operation of the maintenance staff is "detection sensitivity (medium)", the detection area setting unit 22a has a threshold of brightness difference corresponding to "detection sensitivity (medium)". The value "A" is read from the storage unit 21 and set in the proximity detection area E3. In this case, since the "detection sensitivity (medium)" becomes the reference sensitivity, for example, the detection sensitivity of the on-sill detection area E2 also becomes the "detection sensitivity (medium)", and the pull-in detection area E1 and the boarding intention estimation area E4 The detection sensitivity is "detection sensitivity (low)".

Further, for example, when the detection sensitivity that receives the input according to the operation of the maintenance staff is "detection sensitivity (high)", the detection area setting unit 22a sets the threshold value of the brightness difference corresponding to the "detection sensitivity (high)". “C” is read from the storage unit 21 and set in the proximity detection area E3. In this case, since the "detection sensitivity (high)" becomes the reference sensitivity, for example, the detection sensitivity of the on-sill detection area E2 also becomes the "detection sensitivity (high)", and the pull-in detection area E1 and the boarding intention estimation area E4 The detection sensitivity is either "detection sensitivity (medium)" or "detection sensitivity (low)", which is lower than "detection sensitivity (high)".

Although only three set value information I1 to I3 are shown in FIG. 9 for convenience of explanation, the number of set value information stored in the storage unit 21 is not limited to this, and more set value information can be obtained. It may be stored.

FIG. 10 is a diagram for explaining the advantages when different detection sensitivities are set for each of the detection areas E1 to E4. FIG. 10 focuses on one block out of a large number of blocks included in the captured image, and shows a time-series change in the difference in the average luminance value of the one block in two consecutive images. FIG. 10A shows a case where one block in the proximity detection area E3 is focused on, and FIG. 10B shows a case where one block in the retracted detection area E1 is focused on.

FIG. 10A shows a case where “A” is set as the threshold value of the brightness difference corresponding to the detection sensitivity in the proximity detection area E3, and the difference in the average brightness values at the times t1 to t2. Indicates a case where the threshold value “A” has been exceeded. In this case, the detection processing unit 22b detects that there is a person or an object in the proximity detection area E3 at times t1 to t2.

The alternate long and short dash line in FIG. 10 (b) shows the time-series change of the difference in the average luminance value due to the movement of the shadow of the user, and the solid line in FIG. 10 (b) is due to the movement of the user's hand or arm. It shows the time-series change of the difference between the average luminance values.

Similar to the proximity detection area E3 shown in FIG. 10A, when “A” is set as the threshold value of the luminance difference in the pull-in detection area E1, it is shown by the alternate long and short dash line in FIG. 10B. As described above, even if the difference in the average luminance value due to the movement of the shadow of the user exceeds the threshold value “A” at the time t3 to t6, the detection processing unit 22b may perform the detection processing unit 22b at the time t3 to t6. , If there is a person or an object in the pull-in detection area E1, it will be erroneously detected.

However, when "B (> A)" is set as the threshold value of the luminance difference in the pull-in detection area E1, as shown by the alternate long and short dash line in FIG. 10 (b), the movement of the shadow of the user Since the resulting difference in average luminance value never exceeds the threshold value "B", the detection processing unit 22b erroneously detects the movement of the shadow of the user as a person or an object (movement). Can be suppressed. On the other hand, as shown by the solid line in FIG. 10B, in the detection processing unit 22b, the difference in the average luminance value due to the movement of the user's hand or arm during the time t4 to t5 is the threshold value ". Since it exceeds "B", it is possible to detect that there is a person or an object in the pull-in detection area E1. That is, the detection processing unit 22b can detect only the movement of the user's hand or arm as a person or an object (movement).

As described above, the elevator user detection system according to the present embodiment is installed near the door 13 of the car 11, and is photographed by the camera 12 that captures an image including the inside of the car 11 and the landing 15. A plurality of detection areas E1 to E4 for detecting a person or an object are set on the image, and a detection area setting unit 22a for setting different detection sensitivities for each of the set plurality of detection areas E1 to E4 is set. A detection processing unit 22b that executes a detection process for detecting a person or an object in each of the detection areas E1 to E4, and an elevator control device 30 that reflects the result of the detection process in the door opening / closing control of the door 13 of the car 11. And have. According to this, since it is possible to set the detection sensitivity suitable for each of the detection areas E1 to E4, it is possible to improve the detection accuracy of the user.

Hereinafter, a modified example will be described.
(First modification)
The first modification is described above in that not only different detection sensitivities are set for each detection area E1 to E4, but also different detection sensitivities are set depending on the location even within the same detection area. It is different from the embodiment.

For example, the boarding intention estimation area E4 is divided into two, a side near the doorway of the car 11 and a side far from the doorway of the car 11, and the detection sensitivity of the side near the doorway of the car 11 is set to the side far from the doorway of the car 11. It may be higher than the detection sensitivity. That is, a detection sensitivity lower than that of the proximity detection area E3 is set on the side of the boarding intention estimation area E4 far from the entrance / exit of the car 11, and the entrance / exit of the car 11 in the boarding intention estimation area E4 is set. On the near side, a detection sensitivity lower than that of the proximity detection area E3 and higher than that on the side far from the entrance / exit of the car 11 is set.

This is because even in the boarding intention estimation area E4, the closer to the doorway of the car 11, the higher the need to detect a person or an object (movement), and the farther from the doorway of the car 11, the more necessary it is. It is due to being low.

Further, in the pull-in detection area E1, the detection sensitivity of the pull-in detection area E1-3 may be higher than the detection sensitivity of the pull-in detection areas E1-1 and E1-2. That is, the retracted detection areas E1-1 and E1-2 are set to have a lower detection sensitivity than the proximity detection area E3, and the retracted detection area E1-3 is lower than the proximity detection area E3 and is retracted. A detection sensitivity higher than that of the detection areas E1-1 and E1-2 is set.

This is because the inner side surfaces 41a-1 and 41b-1 of the front columns 41a and 41b in which the retracted detection areas E1-1 and E1-2 are set are generally made of easily reflective members such as metal and are used. While it is expected that the shadow of a person is likely to be reflected, the floor surface 19 of the car 11 in which the pull-in detection area E1-3 is set is unlikely to be composed of easily reflective members, and the user's shadow is likely to be reflected. This is because it is expected that shadows will not be reflected easily.

According to the first modification described above, even within the same detection area, it is possible to set different detection sensitivities depending on the location, and it is possible to further improve the detection accuracy of the user. ..

(Second modification)
The second modification is different from the above-described embodiment in that not only different detection sensitivities are set for each of the detection areas E1 to E4, but also different detection sensitivities are set according to the type of the car 11. doing.

For example, if the car 11 is a wheelchair-compatible machine, there is a high possibility that it will be used by a wheelchair user, and even in the boarding intention estimation area E4 away from the doorway of the car 11, a person or an object has a certain degree of detection sensitivity. Is preferably detected. Therefore, when the type of the car 11 is a wheelchair machine, the detection sensitivity of the boarding intention estimation area E4 may be higher than that of a general machine other than the wheelchair machine.

According to this, when the type of the car 11 is a wheelchair car, the boarding intention estimation area E4 is set to the boarding intention estimation area E4 of the general machine, while different detection sensitivities are set for each detection area E1 to E4. It is possible to set a higher detection sensitivity.

Further, here, a case where a different detection sensitivity is set according to the type of the car 11 has been described, but the present invention is not limited to this, and for example, it is assumed that a different detection sensitivity is set according to the type of the call. Is also good. In this case, it is necessary to set the detection sensitivity for the detection area every time the call is registered.

For example, when a call is registered via a wheelchair control panel operated by a wheelchair user, the vehicle gets on the vehicle while setting different detection sensitivities for each of the detection areas E1 to E4, as in the case of the wheelchair unit described above. The detection sensitivity of the intention estimation area E4 may be set higher than the detection sensitivity set in the boarding intention estimation area E4 when a general call is registered.

According to the second modification described above, it is possible to set a different detection sensitivity according to the type of the car 11 or the type of the call, and further improve the detection accuracy of the user under a certain condition. Is possible.

(Third modification example)
The third modification is different from the above-described embodiment in that not only different detection sensitivities are set for each detection area E1 to E4, but also the detection sensitivity of the detection area determined to be over-detected is changed in the middle. doing. In other words, it differs from the above-described embodiment in that the detection sensitivities set in each of the detection areas E1 to E4 are changed in real time.

For example, it is assumed that reopening is performed many times even though different detection sensitivities are set for each of the detection areas E1 to E4. In this case, the detection processing unit 22b counts in which detection area a person or an object has been detected and reopened, and when the number of reopenings exceeds a predetermined number of times, the reopening is performed. It is possible to determine the detection area as an over-detection area. In this case, the detection area setting unit 22a may be reopened further by changing the detection sensitivity of the detection area determined to be the over-detection area to a detection sensitivity lower than the current detection sensitivity. It is possible to suppress.

In the above, the number of times the reopening was performed was counted, but the number of times a person or object was detected was simply counted, and when the number of counts exceeded a predetermined number, it was determined to be an over-detection area. The detection sensitivity of the detection area may be changed to a detection sensitivity lower than the current detection sensitivity.

According to the third modification described above, it is possible to detect an over-detection area and change the detection sensitivity of the over-detection area, thereby suppressing a decrease in elevator operating efficiency due to over-detection of the user. Is possible.

In the present embodiment, the detection sensitivity has been described on the assumption that the detection sensitivity is set according to the operation of the maintenance staff at the site, but the description is not limited to this, and the detection sensitivity is not limited to this, for example, with an external device such as a remote monitoring center away from the site. It may be set by the communication of. In this case, the image processing device 20 is provided with a communication unit in order to realize communication with the external device.

Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are also included in the scope of the invention described in the claims and the equivalent scope thereof.

11 ... Car, 11a ... Curtain board, 12 ... Camera, 13 ... Car door, 14 ... Landing door, 15 ... Landing, 20 ... Image processing device, 21 ... Storage unit, 22 ... Detection unit, 22a ... Detection area setting unit , 22b ... Detection processing unit, 30 ... Elevator control device, 31 ... Operation control unit, 32 ... Door opening / closing control unit, 33 ... Notification unit.

Claims (9)

A shooting method that is installed near the car door and takes images including the inside of the car and the landing.
A detection means that divides the captured image into blocks of a certain size, pays attention to a change in the brightness value of each block, and executes a detection process for detecting a person or an object.
A setting means for setting a plurality of detection areas on the captured image and setting a threshold value of a brightness difference for detecting the person or an object for each of the set plurality of detection areas.
A control means for reflecting the result of the detection process in the door opening / closing control of the car door,
Elevator user detection system equipped with. The setting means is
A first detection area is set near the door on the car side, and a second detection area is set near the door on the landing side.
In the first detection area, a threshold value of a luminance difference larger than that of the second detection area is set.
The elevator user detection system according to claim 1. The first detection area is set on the front pillars installed on both sides of the entrance / exit of the car and the floor surface of the car.
The setting means is
In the first detection area set on the front pillar, a threshold value of a brightness difference larger than that of the first detection area set on the floor surface of the car is set.
The elevator user detection system according to claim 2. The first detection area is set to prevent the car from being pulled into the door.
The second detection area is set to prevent the car from being pinched by the door.
The elevator user detection system according to claim 2 or 3. The setting means is
A second detection area is set near the door on the landing side, and a third detection area is set on the floor of the landing, which is farther from the car than the second detection area.
In the third detection area, a threshold value of a luminance difference larger than that of the second detection area is set.
The elevator user detection system according to claim 1. The setting means is
A threshold value for a brightness difference smaller than that of the third detection area near the entrance / exit of the car is set on the side of the third detection area closer to the entrance / exit of the car.
The elevator user detection system according to claim 5. The setting means is
When the car is a wheelchair-compatible car, the threshold value of the brightness difference in the third detection area is set to a smaller value than that of a car that is not wheelchair-compatible.
The elevator user detection system according to claim 5 or 6. The setting means is
Set the 4th detection area on the landing sill and the car sill,
In the fourth detection area, a threshold value having the same brightness difference as that of the second detection area is set.
The elevator user detection system according to any one of claims 2 to 7. The setting means is
If the number of times the person or object is detected by the detection process exceeds a predetermined number of times from the start of opening the door of the car to the end of closing the door, the person or object is detected by the detection process. Change the threshold value of the brightness difference in the detection area to a value larger than the current value.
The elevator user detection system according to any one of claims 1 to 8.

Images