CN115108425B - Elevator user detection system - Google Patents

Abstract

The present invention relates to an elevator user detection system that prevents false detection of a shadow in an elevator car and accurately detects a user located near a door. The elevator user detection system according to one embodiment includes: a detection area setting unit that sets, on a captured image obtained from a camera provided in an elevator car, a 1 st detection area for pull-in detection near a door in the elevator car and a 2 nd detection area for elevator-taking detection from the door toward a hall; a detection processing unit that detects a user present in the 1 st detection area or the 2 nd detection area based on the captured image; and an adjustment unit that changes a target luminance value for the captured image when the door is fully closed and when the door is fully opened, and adjusts the target luminance value so that the target luminance value is lower than that when the door is fully opened and the interior of the car is captured darkly.

Description

Elevator user detection system

The present application is based on Japanese patent application 2021-044772 (filing date: 2021.3.18) and enjoys priority based on the application. This application is incorporated by reference into this application in its entirety.

Technical Field

Embodiments of the present invention relate to a user detection system for an elevator.

Background

When the car of the elevator opens, a finger or the like of a user located in the car may be pulled into the door camera. In addition, when a user located in a hall enters the car, the end of the door that is closing may sometimes be bumped. In order to prevent such an accident, there are the following systems: the user in the hall or the user in the car is detected by using 1 camera provided in the car, and reflected in the control of opening and closing the door.

In the system, the pull-in detection for the door camera is performed by detecting a change in brightness of an image in a detection area provided near a door in the car. That is, when the door is opened, if a change in the brightness of the image is detected in the detection area, it is determined that the user is located near the door, for example, the door opening operation is slowed down, a sound is sounded, or the like, and a pull-in accident is prevented.

However, due to the relationship of illumination light in the car, a shadow of the user enters the detection area, and a large change in brightness occurs with movement of the shadow, and the shadow may be erroneously detected as the user. In this case, although the user is away from the door, the door opening operation is slowed down, and a beep or the like gives an uncomfortable feeling to the user.

Disclosure of Invention

The invention provides a user detection system of an elevator, which can prevent false detection of a shadow in an elevator car and accurately detect a user near a door.

The elevator user detection system according to one embodiment includes: a detection area setting unit that sets, on a captured image obtained from a camera provided in an elevator car, a 1 st detection area for pull-in detection near a door in the elevator car and a 2 nd detection area for elevator-taking detection from the door toward a hall; a detection processing unit that detects a user present in the 1 st detection area or the 2 nd detection area based on the captured image; and an adjustment unit that changes a target luminance value for the captured image between a fully closed time and a fully open time of the door, and adjusts the target luminance value so that the target luminance value is lower than that at the fully closed time and the interior of the car is captured darkly.

According to the user detection system of the elevator with the above configuration, false detection of the shadow in the car can be prevented, and a user located near the door can be accurately detected.

Drawings

Fig. 1 is a diagram showing a configuration of a user detection system of an elevator according to an embodiment.

Fig. 2 is a view showing a configuration of an entrance peripheral portion in the car according to the embodiment.

Fig. 3 is a view showing an example of an image captured by the camera according to this embodiment.

Fig. 4 is a diagram schematically showing the configuration of the boarding detection region in this embodiment.

Fig. 5 is a diagram for explaining false detection of a shadow generated in the pull-in detection area in this embodiment.

Fig. 6 is a flowchart for explaining the processing operation of the user detection system in this embodiment.

Fig. 7 is a diagram for explaining a coordinate system in real space in this embodiment.

Fig. 8 is a diagram showing a state in which photographed images are divided in block units in this embodiment.

Fig. 9 is a diagram showing a relationship between a target brightness value for a captured image and opening and closing operations of a car door in this embodiment.

Fig. 10 is a view showing an example of a captured image at the time of full closing of the car door in this embodiment.

Fig. 11 is a view showing an example of a captured image when the car door is fully opened and closed in this embodiment.

Fig. 12 is a diagram for explaining an example of selecting the central 1/4 portion of the captured image as the adjustment portion of the luminance value as a modification.

Fig. 13 is a diagram for explaining an example of selecting the upper 1/2 portion of the captured image as the adjustment portion of the luminance value as a modification.

Fig. 14 is a diagram showing a configuration of a doorway peripheral portion in a car using a side-opening type car door as a modification.

Fig. 15 is a diagram for explaining the opening and closing operation of the side-opening type car door.

Detailed Description

Hereinafter, embodiments will be described with reference to the drawings.

The disclosure is merely an example, and the invention is not limited to the following embodiments. Variations that would be readily apparent to one of skill in the art are certainly included within the scope of this disclosure. In order to make the description more clear, the dimensions, shapes, and the like of the respective portions may be schematically shown in the drawings, which are changed with respect to the actual embodiments. In the drawings, the same reference numerals are given to corresponding elements, and detailed description thereof may be omitted.

Fig. 1 is a diagram showing a configuration of a user detection system of an elevator according to an embodiment. In this case, a single car is described as an example, but the same configuration applies to a plurality of cars.

A camera 12 is provided above the entrance of the car 11. Specifically, the camera 12 is provided in a door lintel plate 11a covering the upper part of the doorway of the car 11 so that the lens part is inclined at a predetermined angle to the right downward, to the hall 15 side, or to the inside of the car 11.

The camera 12 is a small-sized monitoring camera such as an in-vehicle camera, has a wide-angle lens or a fisheye lens, and can continuously capture images of a plurality of frames (for example, 30 frames/second) per second. The camera 12 is activated when the car 11 reaches the hall 15 of each floor, for example, and captures images so as to include the vicinity of the car door 13 and the hall 15. The camera 12 may be always in operation when the car 11 is running.

The imaging range at this time is adjusted to L1+L2 (L1 > L2). L1 is an imaging range on the hall side, and has a predetermined distance from the car door 13 toward the hall 15. L2 is an imaging range on the car side, and has a predetermined distance from the car door 13 toward the car rear surface. The ranges L1 and L2 are ranges in the depth direction, and the ranges in the width direction (direction orthogonal to the depth direction) are at least larger than the lateral width of the car 11.

In each floor hall 15, a hall door 14 is provided so as to be openable and closable at an arrival opening of the car 11. The hall doors 14 engage with the car doors 13 to perform opening and closing operations when the car 11 arrives. The power source (door motor) is located on the car 11 side, and the hoistway door 14 is opened and closed only following the car door 13. In the following description, it is assumed that the hoistway door 14 is also opened when the car door 13 is opened, and the hoistway door 14 is also closed when the car door 13 is closed.

Each image (video) continuously captured by the camera 12 is analyzed in real time by the image processing device 20. In fig. 1, the image processing device 20 is taken out from the car 11 for convenience, but in practice, the image processing device 20 is housed in the door lintel plate 11a together with the camera 12.

The image processing apparatus 20 includes a storage unit 21 and a detection unit 22. The storage unit 21 is configured by a storage device such as a RAM, for example. The storage section 21 has a buffer area for sequentially storing images captured by the camera 12 and temporarily storing data necessary for processing by the detection section 22. The storage unit 21 may store an image in which processing such as distortion correction, enlargement and reduction, and partial cropping is performed as preprocessing of the captured image.

The detection unit 22 is constituted by, for example, a microprocessor, and detects a user located near the car door 13 using the captured image of the camera 12. The detection unit 22 is functionally divided into a detection region setting unit 22a, a detection processing unit 22b, and an adjustment unit 22 c. In addition, these may be realized by software, or may be realized by hardware such as an Integrated Circuit (IC), or may be realized by using a combination of software and hardware.

The detection area setting unit 22a sets at least one detection area for detecting a user on the captured image acquired from the camera 12. In the present embodiment, a detection area E1 for detecting a user in the hall 15 and detection areas E2 and E3 for detecting a user in the car 11 are set. The detection area E1 is set from the entrance (car door 13) of the car 11 toward the hall 15 as a boarding detection area. The detection area E2 is set as a pull-in detection area on the entrance posts 41a, 41b in the car 11. The detection area E3 is used as a pull-in detection area similarly to the detection area E2, and is set on the floor 19 (see fig. 3) on the entrance side in the car 11.

The detection processing unit 22b detects a user or an object existing in the hall 15 based on a change in brightness of an image in the detection area E1 during the door closing operation of the car door 13. The detection processing unit 22b detects the door dark boxes 42a and 42b or a user or object approaching the car door 13 based on the change in brightness of the images in the detection areas E2 and E3 during the door opening operation of the car door 13. The "object" includes a moving body such as clothing or luggage of a user, and a wheelchair. In the following description, where reference is made to "detecting a user", an "object" is also included.

The adjustment unit 22c adjusts the target brightness value of the captured image when the car door 13 is fully closed and when the car door 13 is fully opened so that the target brightness value is lower than when the car door 13 is fully closed and the captured image in the car 11 is darker. Specifically, the camera 12 is provided with an exposure adjustment function, and exposure adjustment is automatically performed based on the target brightness value set by the adjustment unit 22 c. Here, the adjustment unit 22c adjusts the image capturing in the car 11 to be darker when the car door 13 is fully closed, by reducing the target luminance value than when it is fully opened. The adjustment unit 22c adjusts the imaging hall 15 to be bright by increasing the target brightness value when fully opened. In addition, the elevator control device 30 may be provided with a part or all of the functions of the image processing device 20.

The elevator control device 30 is constituted by a computer provided with a CPU, ROM, RAM or the like. The elevator control device 30 performs operation control of the car 11. The elevator control device 30 further includes a door opening/closing control unit 31 and a warning unit 32.

The door opening/closing control unit 31 controls the opening/closing of the doors 13 of the car when the car 11 reaches the hall 15. Specifically, the door opening/closing control unit 31 opens the car door 13 when the car 11 reaches the hall 15, and closes the door after a predetermined time elapses. However, when the detection processing unit 22b detects a user in the detection area E1 during the door closing operation of the car door 13, the door opening/closing control unit 31 prohibits the door closing operation of the car door 13, and reopens the car door 13 in the fully open direction and maintains the door open state.

When the detection processor 22b detects a user in the detection area E2 or E3 during the door opening operation of the car door 13, the door opening/closing controller 31 performs door opening/closing control for avoiding a door accident (a pull-in accident into the door camera). Specifically, the door opening/closing control unit 31 temporarily stops the door opening operation of the car door 13, moves in the opposite direction (door closing direction), or slows down the door opening speed of the car door 13.

Fig. 2 is a view showing a configuration of the surrounding portion of the doorway in the car 11.

A car door 13 is provided to open and close an entrance of the car 11. In the example of fig. 2, a car door 13 is shown which is split, and two door panels 13a, 13b constituting the car door 13 are opened and closed in opposite directions along the surface width direction (horizontal direction). The "face width" is the same as the entrance of the car 11.

Inlet posts 41a, 41b are provided on both sides of the entrance of the car 11, and surround the entrance of the car 11 together with the door lintel plate 11 a. The "entrance column" is also called a front column, and a door camera for accommodating the car door 13 is generally provided on the rear side. In the example of fig. 2, when the car door 13 has been opened, one door panel 13a is accommodated in a door box 42a provided on the back side of the entrance column 41a, and the other door panel 13b is accommodated in a door box 42b provided on the back side of the entrance column 41 b. One or both of the inlet posts 41a and 41b are provided with a display 43, an operation panel 45 provided with a destination layer button 44, and a speaker 46. In the example of fig. 2, a speaker 46 is provided to the inlet column 41a, and a display 43 and an operation panel 45 are provided to the inlet column 41 b.

The camera 12 is provided in a lintel plate 11a arranged in the horizontal direction at the upper part of the doorway of the car 11. In order to detect a user in the hall 15 immediately before the door is closed, the camera 12 is mounted in correspondence with the door closing position of the car door 13. Specifically, if the car door 13 is a split type, the camera 12 is mounted in the center portion of the lintel plate 11 a. A lighting device 48 using, for example, LEDs is provided on a ceiling surface in the car 11.

Fig. 3 is a diagram showing an example of a captured image of the camera 12. The hall 15 is located at the upper side, and the car 11 is located at the lower side. In the figure, 16 denotes the floor of the hall 15, and 19 denotes the floor of the car 11. E1, E2, E3 represent detection regions.

The car door 13 has two door panels 13a, 13b that move in opposite directions relative to each other on the car threshold 47. As is the case with the hall door 14, there are two door panels 14a, 14b that move in opposite directions relative to each other over the hall sill 18. The door panels 14a, 14b of the hoistway door 14 move in the door opening and closing direction together with the door panels 13a, 13b of the car door 13.

The camera 12 is provided at an upper portion of an entrance of the car 11. Therefore, as shown in fig. 1, when the car 11 has opened in the hall 15, a predetermined range (L1) on the hall side and a predetermined range (L2) in the car are photographed. A detection area E1 for detecting a user of the car 11 is set in a predetermined area (L1) on the hall side.

In real space, the detection area E1 has a distance L3 from the center of the entrance (face width) toward the hall (L3 is equal to or smaller than the imaging range L1 on the hall side). The width W1 of the detection region E1 at the time of full opening is set to be equal to or larger than the width W0 of the entrance (face width). As shown by oblique lines in fig. 3, the detection area E1 includes the thresholds 18 and 47 and is set so as to exclude dead corners of the door pocket 17a and 17 b. The size of the detection area E1 in the lateral direction (X-axis direction) may be changed in accordance with the opening/closing operation of the car door 13. The size of the detection area E1 in the longitudinal direction (Y-axis direction) may be changed in accordance with the opening/closing operation of the car door 13.

As shown in fig. 4, the detection area E1 serving as the boarding detection area is constituted by a boarding intention estimation area E1a, a proximity detection area E1b, and an on-threshold detection area E1 c. The boarding intention estimation region E1a is a region for estimating whether or not the user has boarding intention and is directed toward the boarding car 11. The approach detection area E1b is an area for detecting that the user is approaching the entrance of the car 11. The detection area E1c on the threshold is an area for detecting the user passing over the thresholds 18, 47. The detection processing of these areas E1a, E1b, E1c is not directly related to the present invention, and therefore, a detailed description thereof is omitted here.

Here, in the present system, the detection areas E2 and E3 are provided in addition to the detection area E1 for elevator detection. The detection areas E2, E3 serve as pull-in detection areas. The detection area E2 is set along the inner side surfaces 41a-1, 41b-1 of the entrance posts 41a, 41b of the car 11 with a predetermined width. The detection area E2 may be set according to the lateral width of the inner side surfaces 41a-1 and 41 b-1. The detection area E3 is set along the car threshold 47 of the floor 19 of the car 11 with a predetermined width.

In the door opening operation of the car door 13, when a user is detected in the detection area E2 or E3, corresponding processing such as temporarily stopping the door opening operation of the car door 13, moving in the opposite direction (door closing direction), or slowing down the door opening speed of the car door 13 is performed. In addition, a warning such as "please leave the door" is issued by sound broadcasting.

(problem of pull-in detection)

The pull-in detection is premised on that the brightness change of the image in the detection areas E2, E3 as the pull-in detection area is accurately expressed according to the intrusion of the user. However, the detection areas E2 and E3 are set in the car 11, and are strongly affected by the illumination environment in the car. That is, as shown in fig. 5, even when the user P1 gets on the elevator at a position away from the car door 13, the shadow S1 of the user P1 enters the detection area E2 or E3 due to the relationship of the illumination light of the illumination device 48. If the shadow S1 enters the detection area E2 or E3, a large brightness change occurs in the image along with the movement of the shadow S1, and the shadow S1 may be erroneously detected as the user P1. In the present embodiment, an object is to prevent false detection of shadows due to the lighting environment in the car 11, and to improve the accuracy of pull-in detection.

Next, the operation of the present system will be described.

Fig. 6 is a flowchart for explaining the processing operation of the present system. The flowchart includes a "pull-in detection process" performed during a door opening operation and a "boarding detection process" performed during a door closing operation.

First, as an initial setting, a detection area setting process is performed by a detection area setting unit 22a of a detection unit 22 provided in the image processing apparatus 20 (step S100). This detection area setting process is executed as follows, for example, when the camera 12 is set or when the setting position of the camera 12 is adjusted.

That is, the detection area setting unit 22a sets the detection area E1 having the distance L3 from the entrance to the hall 15 in the state where the car door 13 is fully opened. As shown in fig. 3, the detection area E1 includes the thresholds 18 and 47 and is set so as to exclude dead corners of the door pocket 17a and 17 b. In this case, in a state where the car door 13 is fully opened, the detection area E1 has a lateral dimension (X-axis direction) W1 and a distance equal to or greater than a lateral width W0 of the doorway (the surface width). The detection area setting unit 22a sets a detection area E2 having a predetermined width along the inner side surfaces 41a-1, 41b-1 of the entrance posts 41a, 41b of the car 11, and sets a detection area E3 having a predetermined width along the car threshold 47 of the floor surface 19 of the car 11.

Here, the car door 13 is in a fully closed state while the car 11 is moving to each floor. At this time, the exposure adjustment of the camera 12 is performed so as to take a dark image of the inside of the car 11 (step S101). When the car 11 reaches the hall 15 at an arbitrary floor (yes in step S102), the elevator control device 30 starts the door opening operation of the car door 13 (step S103). With this door opening operation, the camera 12 captures a predetermined range (L1) on the hall side and a predetermined range (L2) in the car at a predetermined frame rate (for example, 30 frames/second). As will be described later, the target luminance value for the captured image at this time is set to be dark (see range 1a of fig. 9).

The imaging by the camera 12 may be continuously performed from a state in which the car 11 has been closed. The image processing device 20 acquires images captured by the camera 12 in time series, and executes the following pull-in detection process in real time (step S105) while sequentially storing the images in the storage unit 21 (step S104). In addition, as preprocessing of the captured image, distortion correction, enlargement and reduction, clipping of a part of the image, and the like may be performed.

As shown in fig. 7, the camera 12 captures an image with an X-axis in a direction horizontal to the car door 13 provided at the entrance/exit of the car 11, a Y-axis in a direction from the center of the car door 13 to the hall 15 (a direction perpendicular to the car door 13), and a Z-axis in a height direction of the car 11. Among the images captured by the camera 12, images to be detected are compared in units of blocks. If the door opening operation is in progress, the images set in the detection areas E2 and E3 (pull-in detection areas) in the car 11 are targets of detection.

Fig. 8 shows an example in which a captured image is divided into a matrix by a predetermined block unit. An image obtained by dividing an original image into a grid of Wblock on one side is called a "block". In the example of fig. 7, the blocks have the same longitudinal and lateral lengths, but may have different longitudinal and lateral lengths. The blocks may be uniformly sized over the entire region of the image, or may be unevenly sized such as by shortening the length in the longitudinal direction (Y-axis direction) as the blocks get closer to the upper part of the image.

The detection processing unit 22b sequentially reads out the images stored in the storage unit 21 in time series order, and calculates the average luminance value of the images for each block. At this time, the average luminance value of each block calculated when the first image is input is held as an initial value in a 1 st buffer area, not shown, in the storage unit 21.

When the 2 nd and subsequent images are obtained, the detection processing section 22b compares the average luminance value of each block of the current image with the average luminance value of each block of the previous image held in the 1 st buffer. As a result, when a block having a luminance difference equal to or greater than the predetermined threshold value exists in the current image, the detection processing unit 22b determines that the block is a moving block. When determining the presence or absence of motion with respect to the current image, the detection processing section 22b holds the average luminance value of each block of the image in the 1 st buffer for comparison with the next image.

In the same manner as described above, the detection processing unit 22b repeatedly determines whether or not motion is present while comparing the luminance values of the respective images in units of blocks in time series. As a result, if there is a moving block in the image, the detection processing section 22b determines that there is a user or an object. For example, if a moving block is detected in the image in the detection area E2, the detection processing unit 22b determines that a user or an object is present near the car door 13 in the car 11.

When the presence of the user or the object is detected in the door opening operation (yes in step S106), a user detection signal is output from the image processing device 20 to the elevator control device 30. When receiving the user detection signal, the door opening/closing control unit 31 of the elevator control device 30 temporarily stops the door opening operation of the car door 13, and resumes the door opening operation from the stopped position after several seconds (step S107).

When the user detection signal is received, the door opening speed of the car door 13 may be made slower than usual, or the door opening operation may be restarted after the car door 13 is slightly moved in the opposite direction (door closing direction). Further, by activating the warning unit 32 of the elevator control apparatus 30, the user may be alerted to get away from the car door 13 by a sound broadcast through the speaker 46 in the car 11, or a warning sound may be generated. The process is repeated during the detection of the presence of a user or object within the detection area E2 or E3. Thus, for example, when the user is located near the car door 13, the pull-in door camera 42a or 42b can be prevented from being otherwise.

When the car door 13 is fully opened (yes in step S108), the exposure adjustment of the camera 12 is performed so as to image the inside of the car 11 and the hall 15 brightly (step S109). The full opening of the car door 13 may be detected by a signal of a full opening switch, not shown, provided in the driving mechanism of the car door 13, or may be detected based on the time required for the car door 13 to move from the full-closed position to the full-open position.

When a predetermined time has elapsed while the car door 13 is fully opened, a door closing operation is started (step S110). As will be described later, the target luminance value for the captured image at this time is set to be bright (see the 2 nd range b of fig. 9). The image processing device 20 acquires images captured by the camera 12 in time series, and executes the following boarding detection process in real time (step S112) while sequentially storing the images in the storage unit 21 (step S111).

The boarding detection process sets an image in a detection area E1 set from the entrance (car door 13) of the boarding car 11 toward the hall 15 as a detection target. The detection processing unit 22b compares the images in the detection area E1 acquired in time series during the door closing operation in units of blocks, and checks whether there is a moving block. As a result, if there is a moving block, the detection processing unit 22b determines that there is a person or object in the detection area E1.

By this means, when the presence of a user or an object is detected in the detection area E1 during the door closing operation (yes in step S113), a user detection signal is output from the image processing device 20 to the elevator control device 30. The door opening/closing control unit 31 of the elevator control device 30, upon receiving the user detection signal, prohibits the door closing operation of the car door 13 and maintains the door opening state (step S114).

When the presence of the user or the object is not detected in the detection area E1 (no in step S1113), the elevator control device 30 continues the door closing operation of the car door 13, and after the door closing operation is completed, the car 11 is moved to the destination floor. When the car door 13 is fully closed (yes in step S115), the exposure of the camera 12 is adjusted by the adjustment unit 22c so that the inside of the car 11 is captured as dark (step S116). The full closing of the car door 13 may be detected by a signal of a full closing switch, not shown, provided in a driving mechanism of the car door 13, or may be detected based on a time required for the car door 13 to move from the full open position to the full closed position.

Fig. 9 is a diagram showing a relationship between a target brightness value for a captured image and opening and closing operations of the car door 13. The luminance value is expressed by a gray scale of 0 to 255, and the lowest value of "0" is black and the highest value of "255" is white.

The pull-in detection process is premised on that the brightness change of the image in the detection areas E2, E3 as the pull-in detection area is accurately expressed in response to the intrusion of the user. In general, in order to improve the resolution of black, the target luminance value is set high and photographed bright. However, as described with reference to fig. 5, the shadow S1 of the user P1 is generated in the detection area E2 or the detection area E3 due to the relationship of the illumination light in the car 11. At this time, if the inside of the car 11 is brightly photographed, the black color of the shadow S1 is emphasized on the photographed image, so that a large change in the brightness of the shadow S1 occurs in the detection area E2 or the detection area E3, and erroneous detection is likely to occur.

Therefore, in the present embodiment, the target luminance value is set to be lower in the 1 st range a when the vehicle is fully closed than when the vehicle is fully open. In a period (t 1-t2 in the drawing) from full closing to full opening of the car door 13, the target luminance value is set to the 1 st range a. Therefore, the camera 12 photographs the inside of the car 11 as dark. If the inside of the imaging car 11 is imaged dark, as shown in fig. 10, a change in brightness due to the movement of the shadow S1 can be suppressed in the imaged image, and erroneous detection in the detection area E2 or E3 can be prevented.

On the other hand, the boarding detection process is premised on that the brightness change of the image in the detection area E1, which is the boarding detection area, is accurately expressed in response to the intrusion of the user. In this case, if the state of lowering the target luminance value is maintained in order to improve the accuracy of the pull-in detection, as shown in fig. 11, for example, in the case where the user P2 wears a black garment, the contrast between the user P2 and the ground 16 becomes small on the photographed image, and the movement of the user P2 cannot be accurately detected in the detection area E1.

Therefore, when the car door 13 is fully opened (t 2 in the figure), the target luminance value is set to be within the 2 nd range b, which is higher than that when it is fully closed. The upper diagram of fig. 9 shows the transition of the luminance value of the captured image obtained as a result of exposure adjustment performed on the camera 12 side by setting the target luminance value. Therefore, when the target luminance value is set to the 2 nd range b at the time of full door opening (t 2 in the figure), the exposure adjustment on the camera 12 side adjusts the luminance value of the captured image to be slightly slower than this time, and the captured image enters the 2 nd range b (t 3 in the figure). If the response characteristics of the camera 12 are good, the brightness value of the captured image may fall within the 2 nd range b substantially simultaneously with the time of full door opening. The 1 st and 2 nd ranges a and b are set to have a predetermined gradation width according to the experimental results in consideration of the illumination environment, camera performance, and the like, but specific numerical disclosure is omitted here.

When a predetermined time has elapsed after the car door 13 is fully opened, the door closing operation of the car door 13 is started. In the period (t 4-t5 in the figure) before the car door 13 is fully closed, the target luminance value is set to the 2 nd range b. Thus, the photographing hall 15 is photographed brightly by the camera 12. If the photographed hall 15 is photographed brightly, even if the user P2 of the hall 15 wears a black garment, the user P2 and the floor 16 can be distinguished on the photographed image, and thus the movement of the user P2 can be accurately detected in the detection area E1 and reflected in the door opening/closing control.

When the car door 13 is fully closed (t 5 in the figure), the target luminance value is switched to the 1 st range a. In this case, exposure adjustment is performed on the camera 12 side, so that the brightness value of the captured image is slightly slower than the time of full door closing and enters the 1 st range a (t 6 in the figure). If the response characteristics of the camera 12 are good, the brightness value of the captured image may fall within the 2 nd range b substantially simultaneously with the time when the door is fully closed.

As described above, according to the present embodiment, the target luminance value is changed between the fully closed time and the fully open time of the car door 13, and the target luminance value is lowered to be darker than the fully open time in the fully closed time, whereby false detection of shadows can be prevented, and a user in the vicinity of the door can be accurately detected, and a pull-in accident can be prevented. Further, when the target brightness value is increased at the time of full open than at the time of full close, the user located in the hall can be accurately detected and reflected in the door opening/closing control.

(modification)

(1) Adjustment part of brightness value

In general, exposure adjustment is performed so that the average luminance value of the entire captured image falls within the range of the target luminance value. However, the camera 12 has a function of enabling selection of a portion corresponding to the target luminance value on the captured image. In the case of using such a camera 12, exposure adjustment can be performed so that the average luminance value of a part of the captured image, not the average luminance value of the entire captured image, falls within the range of the target luminance value.

Specifically, the adjustment unit 22c selects a portion to be adjusted for the luminance value on the captured image, and controls the exposure adjustment function of the camera 12 so that the luminance value of the portion falls within the range of the target luminance value. In the present embodiment, the entrance of the car 11 is shown in the center of the captured image, and detection areas E2 and E3 for pull-in detection are set therein. Therefore, as shown in fig. 12, for example, if the central 1/4 portion of the image of n×m pixels is selected as the adjustment target, the pull-in detection can be performed with high accuracy by associating the luminance values of the portions including the detection regions E2 and E3 with the target luminance values.

Alternatively, the floor 19 portion in the car 11 may be selected as the adjustment target, and exposure adjustment may be performed so that the luminance value of the portion falls within the range of the target luminance value. Accordingly, since the exposure adjustment is performed only for the luminance value of the floor surface 19 in the car 11, the influence of the shadow appearing on the floor surface 19 can be reduced, and the accuracy of pull-in detection can be further improved.

In the present embodiment, the ground 16 of the hall 15 is reflected in the upper 1/2 portion of the captured image, and a detection area E1 for elevator riding detection is set therein. Therefore, as shown in fig. 13, if the upper 1/2 portion of the image of n×m pixels is selected, the exposure adjustment is performed so that the luminance value of the portion falls within the range of the target luminance value, and the accuracy of the boarding detection can be further improved.

(2) Adjustment of shutter speed and gain

In the above embodiment, the case where the camera 12 has an exposure adjustment function and exposure adjustment is automatically performed based on the target brightness value set from the outside has been described, but when the camera 12 not having such an exposure adjustment function is used, the shutter speed and gain of the camera 12 may be directly adjusted.

In this case, when the shutter speed is adjusted in a direction to increase the shutter speed, the time for which the imaging element included in the camera 12 is exposed to light through the lens becomes short, and thus a dark image can be obtained. When the shutter speed is adjusted in a direction to decrease the shutter speed, the time for which the imaging element included in the camera 12 is exposed to light through the lens becomes longer, and thus a bright image can be obtained. The "gain" is a coefficient for increasing or decreasing the output value of the camera 12. If the value of the gain is reduced, the output value of the camera 12 is also reduced, thereby obtaining a dark image. If the gain value is increased, the output value of the camera 12 is also increased, thereby obtaining a bright image.

Both the shutter speed and the gain may be adjusted, or either may be adjusted. However, when the gain is increased, noise contained in the image is also amplified, and therefore, the shutter speed is preferably adjusted in consideration of image quality.

Specifically, when the car door 13 is fully opened, a control signal is output from the adjustment unit 22c to the camera 12, and the adjustment is performed in a direction to increase the shutter speed of the camera 12 or in a direction to decrease the value of the gain so that the brightness value of the captured image falls within the 1 st range a shown in fig. 9. Thus, a dark image is obtained, and thus pull-in detection can be performed while preventing false detection of shadows in the detection region E2 or E3. When the car door 13 is fully closed, a control signal is output from the adjustment unit 22c to the camera 12, and the adjustment is performed in a direction to reduce the shutter speed of the camera 12 or in a direction to increase the gain so that the brightness value of the captured image falls within the 2 nd range b shown in fig. 9. This makes it possible to obtain a bright image, and thus it is possible to accurately detect the riding of the user in the detection area E1 and reflect the detection result in the door opening/closing control.

The shutter speed or gain may be directly adjusted for the camera 12 having the exposure adjustment function based on the setting of the target luminance value. Thus, the imaging can be performed by switching the target luminance value between the full-on state and the full-off state, regardless of the exposure adjustment function of the camera 12.

(3) Side-opening type

In the above embodiment, the car door of the side-by-side type has been described as an example, but the same applies to the side-by-side type.

Fig. 14 is a view showing a structure of a doorway peripheral portion in an elevator car using two car doors with side-opening doors. In this example, two car doors 13 whose doors are laterally opened are provided so as to be openable and closable in the entrance/exit of the car 11. As shown in fig. 15, the car door 13 has two door panels 13a, 13b that are opened and closed in the same direction along the surface width direction.

When the car door 13 is a side-open type, a door camera 42a is provided on one side of the doorway. In the example of fig. 14, a door box 42a is provided on the left side of the doorway, and when the door is opened, the two door panels 13a and 13b are housed in the door box 42a in a state of being overlapped with each other in the door box 42a. A detection area E2 for pull-in detection is set on the inner side surface of the entrance column 41a that contacts the door box 42a.

In this case, in the door closing operation of the car door 13, it is necessary to detect a user who is going to the car 11 from the hall 15 until immediately before the door is closed, and therefore the camera 12 is mounted at the door closing position in the upper portion of the car 11. In the example of fig. 14, a camera 12 is provided on the inlet post 41b side (right side) in the lintel plate 11 a.

In the case of the side-open car door 13, as in the above-described embodiment, the target luminance value is lowered at the time of full closing to be darker than that at the time of full opening, so that false detection of shadows can be prevented, and a user located near the door can be accurately detected, thereby preventing a pull-in accident. Further, when the target brightness value is increased at the time of full open than at the time of full close, the user in the hall can be accurately detected and reflected in the door opening/closing control.

According to at least one embodiment described above, it is possible to provide a user detection system for an elevator, which can prevent false detection of a shadow in a car and accurately detect a user located near a door.

In addition, although several embodiments of the present invention have been described, these embodiments are presented as examples and are not meant to limit the scope of the invention. These novel embodiments can be implemented in various other modes, and various omissions, substitutions, and changes can be made without departing from the spirit of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the scope equivalent thereto.

Claims (9)

1. A user detection system for an elevator, which is provided with a camera which is arranged in an elevator car and shoots a prescribed range including a door of the elevator car and a hall, and is characterized in that the user detection system for the elevator comprises:

a detection area setting unit that sets, on a captured image obtained from the camera, a 1 st detection area for pull-in detection in the vicinity of the door in the car and a 2 nd detection area for elevator taking detection from the door toward the hall;

a detection processing unit that detects a user present in the 1 st detection area or the 2 nd detection area based on the captured image; and

an adjustment unit that changes a target luminance value for the captured image at a time of full closing and a time of full opening of the door, and adjusts the target luminance value to be darker than the time of full opening so as to prevent false detection of a shadow of a user generated in the 1 st detection area due to illumination light in the car at the time of full closing,

the adjusting part reduces the target brightness value in the period before the full opening of the door in the door opening operation of the door,

the adjustment unit adjusts the hall to take a photograph brightly when the door is fully opened so that the target brightness value is increased as compared with the case of fully closing in order to accurately detect a user wearing black clothing in the 2 nd detection area of the hall.

2. The elevator user detection system of claim 1, wherein,

the adjustment unit increases the target luminance value during a period before the door is fully closed in a door closing operation of the door, compared with a period when the door is fully closed.

3. The elevator user detection system of claim 1, wherein,

the adjustment unit adjusts the brightness value of a part of the captured image so as to fall within a range set as the target brightness value.

4. The elevator user detection system of claim 3, wherein,

a part of the captured image includes a part corresponding to the 1 st detection area.

5. The elevator user detection system of claim 3, wherein,

a part of the captured image includes a part corresponding to the 2 nd detection area.

6. The elevator user detection system of claim 3, wherein,

a portion of the captured image includes a portion corresponding to a floor of the passenger car.

7. The elevator user detection system of claim 1, wherein,

the adjustment unit adjusts the shutter speed or gain of the camera to change the target brightness value for the captured image when the door is fully closed and when the door is fully opened, and reduces the target brightness value when the door is fully closed as compared with when the door is fully opened, thereby making the interior of the car dark.

8. The elevator user detection system of claim 1, wherein,

the door opening/closing control unit is further provided, and the door opening/closing control unit controls the opening/closing operation of the door based on the detection result of the detection processing unit.

9. The elevator user detection system of claim 1, wherein,

the camera is provided at an upper portion in the car in correspondence with a door closing position of the door.