JP6849760B2 - Elevator user detection system - Google Patents

Description

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

Normally, when the elevator car arrives at the landing and opens the door, the door closes and departs after a predetermined time has passed. At that time, since the elevator user does not know when the car will close, he / she may be caught in the door in the middle of closing the car when he / she gets on the car from the landing. This also applies when the user gets off the car. In order to prevent such a door accident, there is a system that photographs the vicinity of the car door with a camera, detects the user from the captured image, and reflects it in the door opening / closing control.

Japanese Patent No. 6092433 Japanese Unexamined Patent Publication No. 2019-108182

However, in the above-mentioned system, for example, it is premised that the structure (sil, floor surface, etc.) near the door is in an environment in which a predetermined color is reflected, and it may not be possible to respond to changes in lighting conditions in the actual environment.

An object to be solved by the present invention is to provide an elevator user detection system capable of correctly detecting a user or an object existing near a door even if the lighting conditions change.

The elevator user detection system according to the embodiment includes an image pickup means, a detection area setting means, a boundary detection means, a motion detection means, and a determination means.

The imaging means captures a predetermined range including the door from the car to the landing. The detection area setting means sets a detection area on a sill provided in the movement path of the door on the image taken by the photographing means. The boundary detecting means detects the boundary between the sill and the elevator structure on the image in the detection area set by the detection area setting means. The motion detecting means detects a change in brightness of an image due to the movement of a user or an object on the sill in the detection area. The determination means determines whether or not a user or an object exists in the vicinity of the door based on the detection result of the boundary detection means and the detection result of the motion detection means.
In the above configuration, the determination means detects when a break in the straight line representing the boundary of the sill is detected and a change in the brightness of the image due to the movement of the user or an object is detected in the vicinity of the break. It is characterized in that it is determined that a user or an object exists in the vicinity of the door.

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 configuration of a portion around an entrance / exit in the car according to the same embodiment. FIG. 3 is a diagram showing an example of a photographed image of the camera in the same embodiment. FIG. 4 is a flowchart showing the overall processing flow of the user detection system according to the same embodiment. FIG. 5 is a flowchart showing a user detection process executed in step S15 of FIG. FIG. 6 is a diagram for explaining a coordinate system in real space in the same embodiment. FIG. 7 is a diagram for explaining an area setting method in the same embodiment. FIG. 8 is a diagram for explaining another area setting method in the same embodiment. FIG. 9 is a diagram showing an example of a binarized image in the same embodiment. FIG. 10 is a diagram showing a state in which the captured images in the same embodiment are divided into blocks. FIG. 11 is a diagram showing a specific example for explaining boundary detection and motion detection in the same embodiment. FIG. 12 is a diagram showing a state in which the image of the sill in the detection area in the same embodiment is partially hidden. FIG. 13 is a diagram for explaining boundary detection and motion detection when the detection area in the same embodiment is divided into a matrix. FIG. 14 is a diagram for explaining boundary detection and motion detection when the detection area is divided into strips as another 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 represented schematically. In a plurality of drawings, the corresponding elements may be given the same reference numbers and detailed description 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 here by taking 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 tilted directly downward, or on the landing 15 side or the inside of the car 11 by a predetermined angle. ..

The camera 12 is a small surveillance camera such as an in-vehicle camera, has a wide-angle lens or a fisheye lens, and can continuously capture images of several frames (for example, 30 frames / second) per second. The camera 12 is activated when the car 11 arrives at the landing 15 on each floor, and photographs a predetermined range L including the vicinity of the car door 13.

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 or an object near the door of the car 11 by using 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. When the detection unit 22 is functionally divided, it is composed of a detection area setting unit 23 and a detection processing unit 24.

The detection area setting unit 23 sets the detection area E1 for the car sill 47 and the landing sill 18 provided at the entrance / exit of the car 11 on the captured image of the camera 12 (see FIG. 3). The car sill 47 is a member for guiding the opening / closing operation of the car door 13, and is provided on the movement path of the car door 13. The landing sill 18 is a member for guiding the opening / closing operation of the landing door 14, and is provided on the movement path of the landing door 14.

The detection processing unit 24 detects the presence or absence of a user or an object based on the image in the detection area E1 set by the detection area setting unit 23. The "thing" referred to here includes, for example, a user's clothes and luggage, and a moving body such as a wheelchair.

The detection processing unit 24 includes a boundary detection unit 24a, a motion detection unit 24b, and a determination unit 24c. In the following description, when the term "sill" is used, it is assumed that both the car sill 47 and the landing sill 18 are included. Further, when the term "door" is used, both the car door 13 and the landing door 14 are included.

The boundary detection unit 24a detects the boundary between the sill and the elevator structure on the image in the detection area E1. The elevator structure includes a floor surface 19 of the car 11 and a floor surface 16 of the landing 15 (see FIG. 3), and a gap 48 (see FIG. 12) between the car sill 47 and the landing sill 18.

The motion detection unit 24b detects a change in the brightness of the image due to the movement of the user or an object on the sill in the detection area E1. The determination unit 24c determines whether or not a user or an object exists in the vicinity of the door based on the detection result of the boundary detection unit 24a and the detection result of the motion detection unit 24b. The car control device 30 may have some or all of the functions of the image processing device 20.

The car control device 30 controls the operation of various devices (destination floor buttons, lights, etc.) installed in the car 11. The car control device 30 includes a door opening / closing control unit 31 and a notification unit 32.

The door opening / closing control unit 31 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 31 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, when a user or an object is detected while the car door 13 is open, the door open / close control unit 31 maintains the door open state of the car door 13. If a user or an object is detected during the door closing operation of the car door 13, the door opening / closing control unit 31 interrupts the door closing operation of the car door 13 and reopens the car door 13. The door closing speed of 13 is made slower than usual. The notification unit 32 calls attention to the user based on the detection result of the detection processing unit 24.

FIG. 2 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. 2, 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. When the car door 13 is opened, one door panel 13a is housed in a door pocket 42a provided on the back side of the front pillar 41a, and the other door panel 13b is housed in the door pocket 42b provided on the back side of the front pillar 41b. ..

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. In the example of FIG. 2, the speaker 46 is installed on the front pillar 41a, the display 43 and the operation panel 45 are installed on the front pillar 41b.

Here, the camera 12 is installed at the center of the curtain plate 11a above the doorway of the car 11. The camera 12 is installed from the lower part of the curtain plate 11a downward so that when the car door 13 is opened together with the landing door 14, the photograph including the vicinity of the entrance / exit of the car 11 can be taken (see FIG. 3). The door.

FIG. 3 is a diagram showing an example of a captured image of the camera 12. It shows a case where the car door 13 (door panels 13a and 13b) and the landing door 14 (door panels 14a and 14b) are fully opened and the image is taken downward from the upper part of the doorway of the car 11. In FIG. 3, the upper side shows the landing 15 and the lower side shows the inside of the car 11.

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, a rectangular detection area E1 is set so as to surround both the car sill 47 and the landing sill 18 on the captured image. The detection area E1 is used as an area for detecting a user or an object existing near the door of the car 11.

Next, the operation of this system will be described in detail.
FIG. 4 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 23 of the detection unit 22 provided in the image processing device 20 (step S11). This detection area setting process is executed as follows, for example, when the camera 12 is installed or when the installation position of the camera 12 is adjusted.

That is, the detection area setting unit 23 sets the detection area E1 in the area where the car sill 47 and the landing sill 18 are reflected on the image captured by the camera 12. The area in which the car sill 47 and the landing sill 18 are projected on the captured image is calculated based on the design value of each component of the car 11 and the value peculiar to the camera 12.

-Width of the frontage (doorway) of the car 11 (width in the X direction)
-Vertical width of the basket sill 47 and the landing sill 18 (width in the Y direction)
-Height of the car door 13 and the landing door 14-Relative position of the camera 12 with respect to the car sill 47 and the landing sill 18-Angle of the three axes of the camera 12-The angle of view and the focal length of the camera 12 The detection area setting unit 23 is these. The area where the car sill 47 and the landing sill 18 are reflected on the captured image is calculated based on the value of. That is, the detection area setting unit 23 assumes that a band-shaped car sill 47 having a predetermined width is arranged along the opening / closing direction of the car door 13 on the entrance / exit side of the floor surface 19 of the car 11. The three-dimensional coordinates of the car sill 47 are calculated based on the relative positions, angles, angles of view, and the like of 12.

As shown in FIG. 6, the three-dimensional coordinates are such that the direction horizontal to the car door 13 is the X-axis and the direction from the center of the car door 13 to the landing 15 (the direction perpendicular to the car door 13) is the Y-axis. , The coordinates when the height direction of the car 11 is the Z axis.

The detection area setting unit 23 projects the three-dimensional coordinates of the car sill 47 onto the two-dimensional coordinates on the captured image to obtain the x and y coordinate values for specifying the position of the car sill 47. In this case, as shown in FIG. 7, among the four points PA1 to PA4 constituting the rectangular car sill 47, the x and y coordinate values of at least the points PA1 and PA2 in contact with the floor surface 19 of the car 11 are set. You may ask for it.

The same applies to the landing sill 18. That is, the detection area setting unit 23 assumes that a band-shaped landing sill 18 having a predetermined width is arranged along the opening / closing direction of the landing door 14 on the entrance / exit side of the floor surface 16 of the landing 15, and the camera 12 The three-dimensional coordinates of the landing sill 18 are calculated based on the relative position, angle, angle of view, and the like. The detection area setting unit 23 projects the three-dimensional coordinates of the landing sill 18 onto the two-dimensional coordinates on the captured image to obtain the x and y coordinate values for specifying the position of the landing sill 18. In this case, as shown in FIG. 7, among the four points PB1 to PB4 constituting the rectangular landing sill 18, the x and y coordinate values of the points PB3 and PB4 in contact with the floor surface 16 of the landing 15 are obtained. That's fine.

In this way, when the x and y coordinate values of the points constituting the car sill 47 and the landing sill 18 are obtained, the detection area setting unit 23 determines the car sill 47 based on the x and y coordinate values of these points. And the detection area E1 surrounding the landing sill 18 is set. Specifically, the detection area setting unit 23 uses the x and y coordinate values of the points PA1 and PA on the floor surface 19 side of the car sill 47 and the x and y coordinate values of the points PB3 and PB4 on the floor surface 16 side of the landing sill 18. Based on the above, a rectangular detection area E1 having points PA1, PA2, PB3, and PB4 as vertices is set.

It is preferable to set at least the width in the Y direction to be slightly wider than the width in the X direction and the width in the Y direction of the detection area E1 in consideration of the error of the coordinate values caused by the deviation of the camera angle. ..

Further, although one detection area E1 surrounding the car sill 47 and the landing sill 18 is set here, as shown in FIG. 8, the detection area E2 surrounding the car sill 47 and the detection area E3 surrounding the landing sill 18 are set. It may be set separately for and.

The setting process of the detection area E1 is executed with the car door 13 opened. By setting the detection area E1 for the car sill 47 and the landing sill 18, it is possible to detect when the user is near the door when the door is open or closed before being caught by the door. Will be.

The operation of the car 11 during operation will be described below.
As shown in FIG. 4, when the car 11 arrives at the landing 15 on an arbitrary floor (Yes in step S12), the car control device 30 opens the car door 13 (step S13).

At this time, the periphery of the car door 13 is photographed at a predetermined frame rate (for example, 30 frames / second) by the camera 12 installed at the upper part of the doorway of the car 11. The image processing device 20 acquires images taken by the camera 12 in chronological order, and while sequentially storing these images in the storage unit 21 (step S14), executes the following user detection processing in real time. (Step S15). As preprocessing for the captured image, distortion correction, enlargement / reduction, and partial cropping of the image may be performed.

The user detection process is executed by the detection processing unit 24 of the detection unit 22 provided in the image processing device 20. The detection processing unit 24 extracts images in the detection area E1 from a plurality of captured images obtained by the camera 12 in time series, and detects the presence or absence of a user or an object based on these images.

Here, the user detection process in the present embodiment performs two detection processes, (a) boundary detection and (b) motion detection, and a user or an object exists near the door based on the results of these detection processes. It is characterized in determining whether or not it is.

(A) Boundary detection
FIG. 5 shows the details of the user detection process executed in step S15.

The detection processing unit 24 performs boundary detection through the boundary detection unit 24a. The boundary detection unit 24a detects the boundary between the car sill 47 and the floor surface 19 of the car 11 and the boundary between the landing sill 18 and the floor surface 16 of the landing 15 on the image in the detection area E1 shown in FIG. (Step S21).

Specifically, the boundary detection unit 24a performs binarization processing on the image in the detection area E1 with "0 (without edge)" and "1 (with edge)), and from the binarized image, the basket sill 47 The edge and the edge of the landing sill 18 are extracted. An example of a binarized image is shown in FIG. 9. The white part in the figure corresponds to an edge. In the example of FIG. 9, the entire captured image is binarized. However, at least the image in the detection area E1 may be binarized.

As a method of extracting an edge, for example, the brightness value of a predetermined pixel is compared with the brightness value of a pixel adjacent to the pixel, and when the difference between the two is equal to or more than a preset threshold value, the portion of the pixel is obtained. Is extracted as an edge. Alternatively, the brightness value of a predetermined pixel may be compared with the brightness value of a pixel separated from the pixel by a predetermined pixel. Further, the average luminance value of the pixel group composed of a plurality of pixels is compared with the average luminance value of the pixel group and the adjacent pixel group, and when the difference between them is equal to or more than a preset threshold value, the pixel group The part of may be extracted as an edge.

Further, the edge may be extracted by using a well-known image processing technique such as a Laplacian filter or a Canny method.

As shown in FIG. 3, the edge of the car sill 47 has both sides in the longitudinal direction and short sides in the lateral direction. One of both sides in the longitudinal direction is detected as a boundary between the car sill 47 and the floor surface 19 of the car 11. Similarly, the edge of the landing sill 18 has both sides in the longitudinal direction and short sides in the lateral direction. One of both sides in the longitudinal direction is detected as a boundary between the landing sill 18 and the floor surface 16 of the landing 15.

Here, the car sill 47 and the landing sill 18 are considered as one sill in the detection area E1, but as shown in FIG. 8, when the detection area E1 is divided into the detection areas E2 and E3, the detection area is divided into the detection areas E2 and E3. Boundaries may be detected for each of the car sill 47 in E2 and the landing sill 18 in the detection area E3.

(B) Motion detection
The detection processing unit 24 detects the motion of (b) above through the motion detection unit 24b. As shown in FIG. 10, the motion detection unit 24b divides the image in the detection area E1 into a matrix in predetermined block units, and detects a motion block among these blocks.

Specifically, the motion detection unit 24b reads out each image held in the storage unit 21 one by one in chronological order, and calculates the average luminance value of these images for each block. At that time, it is assumed that the average luminance value for each block calculated when the first image is input as the initial value is held in the first buffer area (not shown) in the storage unit 21.

When the second and subsequent images are obtained, the motion detection unit 24b 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 first buffer area. Compare with. As a result, when there is a block having a brightness difference equal to or larger than a preset value in the current image, the motion detection unit 24b determines the block as a block with motion. When determining the presence or absence of motion with respect to the current image, the motion detection unit 24b holds the average luminance value for each block of the image in the first buffer area for comparison with the next image. After that, in the same manner, the motion detection unit 24b repeats determining the presence or absence of motion while comparing the brightness values of each image in block units in chronological order.

In the flowchart shown in FIG. 5, motion detection is performed after boundary detection (step S21 → S22), but motion detection may be performed first, and then boundary detection may be performed (step S22). → S21). Further, both the boundary detection and the motion detection may be performed in parallel.

The above-mentioned boundary detection and motion detection will be described in detail with reference to specific examples.
Now, as shown in FIG. 11, for example, it is assumed that the user passes over the sill and gets into the car 11 while the door is open. As the user passes by, as shown in FIG. 12, the images of the sill (basket sill 47 and landing sill 18) in the detection area E1 are partially hidden.

When the straight line representing the boundary between the car sill 47 and the floor surface 19 of the car 11 is D1, and the straight line representing the boundary between the landing sill 18 and the floor surface 16 of the landing 15 is D2, at least one of the straight lines D1 and D2 is Since it is partially missing, it can be determined that the user exists on the sill. There is a gap 48 between the car sill 47 and the landing sill 18, and the determination may include the straight lines D3 and D4 representing the boundary on the gap 48 side. In this case, if at least one of the straight lines D3 and D4 is partially missing, it can be determined that the user exists on the sill.

However, boundary detection is susceptible to lighting. Due to lighting, when the sill is photographed brightly or darkly, the straight line representing the boundary (edge) of the sill may not be clearly extracted. In particular, when the sill and the floor surface have the same color system, the straight line representing the boundary of the sill is interrupted on the image, and the interrupted portion may be erroneously detected as a user.

As shown in FIG. 13, motion detection is performed in block units in which the image in the detection area E1 is divided into a matrix in the horizontal direction and the vertical direction. Ba in the figure shows one block divided in a matrix. The presence or absence of movement is repeatedly determined while comparing the brightness values of each image in chronological order in block units. In this case, when the user passes over the sill, the block corresponding to the user's toes is detected as moving. As a result, it can be determined that the user is on the sill, that is, near the door.

However, motion detection is susceptible to shadows. Shadows of people and doors are likely to occur near the door of the car 11 due to the influence of lighting equipment and sunlight. In particular, the color of the sill is often silver, and the shadows of people and doors tend to appear dark. Therefore, if the shadow is on the sill, it may be erroneously detected as a user when the shadow moves.

In this way, it is necessary to consider the lighting conditions in the actual environment for both boundary detection and motion detection. Therefore, in the present embodiment, when the boundary detection and the motion detection satisfy a predetermined condition, the detection result at that time is treated as valid. Specifically, it is a condition that the boundary detection detects a break in the straight line indicating the boundary of the sill, and the motion detection detects the movement in the vicinity of the broken portion. In addition, "movement is detected" means that, in detail, a change in brightness accompanying the movement of a user or an object is detected.

As shown in FIG. 5, when the above conditions are satisfied (Yes in step S23), the determination unit 24c determines that a user or an object exists near the door (step S24). Specifically, in FIG. 13, when the detection area E1 is viewed in block units divided in a matrix, there is a block in which at least one of the straight lines D1 and D2 representing the boundary of the sill is partially missing, and the block moves in the block. If is detected, it is determined to be a user or a thing. In the example of FIG. 13, in the block represented by Ba1, Ba2, Ba3, the break (hidden of the boundary of the sill) and the movement (change in brightness) of the straight lines D1 and D2 representing the boundary of the sill are detected.

If no break in the straight line indicating the boundary of the sill is detected, or if no movement is detected on the sill (No in step S23), the determination unit 24c determines that there is no user or object near the door. judge.

In this way, on the condition that the straight line representing the boundary of the sill is interrupted in the boundary detection, and the movement is detected in the vicinity of the interrupted part in the motion detection, the user or object near the door Can be detected correctly. Therefore, for example, even if the sill and the floor surface have the same color system and the straight line representing the boundary of the sill is not clearly extracted due to lighting and the image is interrupted, the movement must be detected. For example, since it is determined that the user or the object does not exist, the user or the object near the door can be correctly detected without erroneous detection.

On the other hand, with regard to motion detection, even if a shadow is reflected on the sill due to lighting, if the shadow portion and the interrupted portion of the straight line representing the boundary of the sill do not match, it is not determined as a user or an object. Therefore, even if the lighting conditions change and shadows are generated at each location on the sill, the user or an object can be correctly detected without erroneous detection.

In step 21, for example, the reflected light from the sill is strong due to lighting, and the boundary of the sill may not be detected at all on the captured image. In such a case, the presence or absence of a user or an object may be determined only by the result of motion detection. That is, in step 23, when the straight line indicating the boundary is not detected, the determination unit 24c determines that the user or the object is a user or an object based on the result of motion detection. In this case, if the movement on the sill is detected by the motion detection, the determination unit 24c determines that a user or an object is present near the door.

Returning to FIG. 4, when the presence of a user or an object is detected in the detection area E1 (that is, on the sill) by the user detection process described above (Yes in step S16), the image processing device 20 to the car control device 30 A user detection signal is output to. Upon receiving this user detection signal, the door open / close control unit 31 of the car control device 30 extends the door opening time of the car door 13 more than usual to maintain the door open state (step S17).

Further, the notification unit 32 of the car control device 30 may make a voice announcement through the speaker 46 in the car 11 to alert the user to move away from the door (step S18). The notification method is not limited to voice announcement, for example, a message such as "Be careful not to get caught in the door" may be displayed, or voice announcement and message display may be used together. .. Further, a warning sound may be sounded.

The above process is repeated while the presence of a user or an object is detected in the detection area E1. As a result, when the user is near the door when the door is opened, it is possible to prevent the user from being caught in the door. If the presence of a user or an object is not detected in the detection area E1 (No in step S16), the car control device 30 starts closing the car door 13 after a predetermined time, and after the door is closed, the car 11 Departs toward the destination floor (step S19).

Although the description has been made assuming that the door is open, the same applies when the door is closed, and the user detection process shown in FIG. 5 is executed. As a result, for example, when the presence of a user or an object is detected in the detection area E1 (that is, on the sill) during door closing, the door opening / closing control unit 31 interrupts the door closing operation and reopens the car door 13. The door can be opened or the car door 13 can be closed at a slower speed than usual to prevent the user from being caught in the door. Further, although the explanation has been given by taking a double door type car door as an example, the same applies to the single door type.

As described above, according to the present embodiment, the illumination conditions are changed by performing boundary detection and motion detection of the sill on the captured image and determining that the user or the object is a user or an object when these detection results satisfy predetermined conditions. Even so, it is possible to correctly detect a user or an object existing near the door and reflect it in the door opening / closing control. This makes it possible to prevent the user or an object from being caught in the door when the door is opened or closed.

(Other embodiments)
In the above embodiment, the detection area E1 is divided into blocks in a matrix to perform boundary detection and motion detection, but the detection area E1 may be divided into another unit.

FIG. 14 shows an example in which the detection area E1 is divided into strips in a direction (Y direction) orthogonal to the door opening / closing direction (X direction). Bb in the figure shows one block divided into strips. The size of the block Bb in the Y direction is substantially the same as the size of the detection area E1 in the Y direction. The size of the block Bb in the X direction may be, for example, the same size as the block Ba shown in FIG. 13, or may be a different size. The reason why the block Ba has a long strip shape in the Y direction is that the block Ba advances in the Y direction with respect to the sill regardless of whether the user gets on or off the car 11.

In such a configuration, when the detection area E1 is viewed in the Y direction in block units, there is a block in which at least one of the straight lines D1 and D2 representing the boundary of the sill is partially missing, and movement is detected in that block. For example, it is determined to be a user or a thing. In the example of FIG. 14, in the strip-shaped block represented by Bb1, Bb2, Bb3, the breakage (hidden of the boundary of the sill) and the movement of the straight lines D1 and D2 representing the boundary of the sill are detected.

Here, when a photograph is taken near the door, a partial omission (noise) may occur in the photographed image. P1, P2, and P3 in the figure indicate missing parts of the image. If there is such an image omission, the boundary detection and the motion detection may not be correctly performed in the omission portion of the image in the fine block units divided in the matrix shown in FIG. On the other hand, as shown in FIG. 14, if the detection area E1 is divided into strips in block units, the range of one block Bb expands in the Y direction. Boundary detection and motion detection can be performed with. That is, for example, even if there is an image omission in the portion indicated by P1, boundary detection and motion detection can be performed in another portion in the strip-shaped block Bb1 including the omission portion.

In this way, by dividing the detection area E1 into strips and performing boundary detection and motion detection, it is possible to prevent omission of detection of boundaries and motion due to image omission during shooting, and to prevent users or objects on the sill. Can be detected correctly.

According to at least one embodiment described above, it is possible to provide an elevator user detection system capable of correctly detecting a user or an object existing near a door even if the lighting conditions change.

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, 16 ... Landing floor, 17a, 17b ... Three-sided frame, 18 ... Landing sill, 19 ... Riding Car floor, 20 ... Image processing device, 21 ... Storage unit, 22 ... Detection unit, 23 ... Detection area setting unit, 24a ... Boundary detection unit, 24b ... Motion detection unit, 24c ... Judgment unit, 30 ... Car control device , 31 ... Door open / close control unit, 32 ... Notification unit, 41a, 41b ... Front pillar, 42a, 42b ... Door pocket, 43 ... Display, 44 ... Destination floor button, 45 ... Operation panel, 46 ... Speaker, 47 ... Basket sill , E1, E2, E3 ... Detection area.

Claims (9)

An imaging means that captures a predetermined range including the door from the car to the landing,
A detection area setting means for setting a detection area on a sill provided in the movement path of the door on an image taken by the imaging means, and a detection area setting means.
Boundary detection means for detecting the boundary between the sill and the elevator structure on the image in the detection area set by the detection area setting means, and
A motion detecting means for detecting a change in the brightness of an image due to the movement of a user or an object on the sill in the detection area, and a motion detecting means.
A determination means for determining whether or not a user or an object exists in the vicinity of the door is provided based on the detection result of the boundary detection means and the detection result of the motion detection means.
The above-mentioned determination means
When a break in the straight line representing the boundary of the sill is detected, and a change in brightness of the image due to the movement of the user or an object is detected in the vicinity of the break, the user or the object is near the door. An elevator user detection system characterized by determining that it exists. The above-mentioned determination means
The claim is characterized in that when a straight line representing the boundary of the sill is not detected, it is determined whether or not a user or an object exists in the vicinity of the door based on the detection result of the motion detecting means. 1 Elevator user detection system described. The above-mentioned determination means
The user of the elevator according to claim 2 , wherein if a change in the brightness of the image due to the movement of the user or the object is detected on the sill, it is determined that the user or the object exists in the vicinity of the door. Detection system. Boundary detection by the boundary detecting means and motion detection by the motion detecting means
The user detection system for an elevator according to claim 1, wherein the detection area is divided into units in a matrix. Boundary detection by the boundary detecting means and motion detection by the motion detecting means
The user detection system for an elevator according to claim 1, wherein the detection area is divided into strips in a direction orthogonal to the opening / closing direction of the door. The boundary detection means is
The elevator user detection system according to claim 1, wherein the sill and the floor surface and the boundary of the car are detected on the image, and the boundary between the sill and the floor surface of the landing is detected. The user detection system for an elevator according to claim 1, further comprising a door opening / closing control means for controlling the opening / closing operation of the door based on the determination result of the determination means. The door opening / closing control means
The user detection system for an elevator according to claim 7 , wherein when a user or an object is detected while the door is open, the door is maintained in the open state. The door opening / closing control means
If a user or an object is detected during the door closing operation, the door closing operation may be interrupted and reopened, or the door closing speed may be slower than usual. The elevator user detection system according to claim 7.

Images