WO2020240783A1

WO2020240783A1 - Passenger detecting device for elevator, and elevator system

Info

Publication number: WO2020240783A1
Application number: PCT/JP2019/021575
Authority: WO
Inventors: 博行村上; 誠一熊谷; 清高渡邊; 晴之岩間; 関　真規人; 淳二堀
Original assignee: 三菱電機ビルテクノサービス株式会社; 三菱電機株式会社
Priority date: 2019-05-30
Filing date: 2019-05-30
Publication date: 2020-12-03
Also published as: JPWO2020240783A1; CN113874309A; JP6645642B1; CN113874309B

Abstract

Provided are a passenger detecting device and an elevator system with which it is possible to suppress the false detection of a passenger even when the environment inside a car changes. An input unit (12) in this passenger detecting device (4) or elevator system (1) receives the inputs of a first image and a second image. The first image is captured by a first camera (11a) provided in a car (2). The second image is captured from a different direction from the first camera (11a) by a second camera (11b) provided in the car (2). The first image and the second image include the floor surface (5) of the car (2). A transforming unit (13) performs homographic transformation on the first image and the second image so that the range of the floor surface (5) of the car (2) in the first image and the range of the floor surface (5) of the car (2) in the second image overlap. A determining unit (16) determines the presence or absence of a passenger inside the car (2) on the basis of the difference between the overlapping ranges of the floor surface (5) of the car (2) in the first image and the second image after the homographic transformation.

Description

Elevator passenger detector and elevator system

The present invention relates to an elevator passenger detection device and an elevator system.

Patent Document 1 discloses an example of an elevator. The elevator safety device is equipped with a camera that photographs the inside of the elevator car. The safety device detects passengers inside the car based on the image taken by the camera.

Japanese Patent Application Laid-Open No. 2008-100782

However, in the elevator described in Patent Document 1, passengers inside the car are detected by background subtraction of images taken by the camera. Therefore, if the environment inside the car changes over time, passengers may be erroneously detected.

The present invention has been made to solve such a problem. An object of the present invention is to provide a passenger detection device and an elevator system capable of suppressing false detection of passengers even when the environment inside the car changes.

The passenger detection device for an elevator according to the present invention captures a first image including the floor surface of the car taken by a first camera provided in the car of the elevator and a second camera provided in the car from a direction different from that of the first camera. The input unit that accepts the input of the second image including the floor surface of the car, the range of the floor surface of the car included in the first image, and the range of the floor surface of the car included in the second image overlap each other. Passengers inside the car based on the difference between the conversion unit that performs homography conversion on the image and the second image and the range of the floor surface of the car that overlaps the first image and the second image after the homography conversion by the conversion unit. It is provided with a determination unit for determining the presence or absence of.

The elevator system according to the present invention travels inside a hoistway provided over a plurality of floors to transport passengers getting on and off the inside through a car door that opens and closes, and passengers inside the car to be input. A control panel that controls the operation of the car based on the presence / absence judgment result, a first image including the floor surface of the car taken by the first camera provided in the car, and a first camera in the second camera provided in the car. The input unit that accepts the input of the second image including the floor surface of the car taken from different directions, the floor surface range of the car included in the first image, and the floor surface range of the car included in the second image overlap each other. The car is based on the difference in the range of the floor surface of the car that overlaps the first image and the second image after the homography conversion by the conversion unit and the conversion unit that performs homography conversion on the first image and the second image. It is provided with a determination unit for determining the presence or absence of passengers inside the vehicle, and an output unit for outputting the determination result by the determination unit to the control panel.

According to the present invention, the input unit accepts inputs of the first image and the second image. The first image is taken by the first camera provided in the elevator car. The first image includes the floor of the car. The second image is taken by the second camera provided in the car from a direction different from that of the first camera. The second image includes the floor of the car. The conversion unit performs homography conversion on the first image and the second image so that the range of the car floor surface included in the first image and the range of the car floor surface included in the second image overlap each other. The determination unit determines the presence or absence of passengers inside the car based on the difference in the range of the floor surface of the car that overlaps the first image and the second image after the homography conversion by the conversion unit. As a result, even when the environment inside the car changes, false detection of passengers is suppressed.

It is a block diagram of the elevator system which concerns on Embodiment 1. FIG. It is a figure which shows the example of setting of the floor surface parameter in the passenger detection apparatus which concerns on Embodiment 1. FIG. It is a figure which shows the example of setting of the distortion parameter in the passenger detection apparatus which concerns on Embodiment 1. FIG. It is a figure which shows the example of the passenger detection in the passenger detection device which concerns on Embodiment 1. FIG. It is a flowchart which shows the example of the operation of the passenger detection apparatus which concerns on Embodiment 1. FIG. It is a figure which shows the hardware configuration of the main part of the passenger detection apparatus which concerns on Embodiment 1. FIG. It is a figure which shows the example of the passenger detection in the passenger detection device which concerns on Embodiment 2. FIG. It is a figure which shows the example of the passenger detection in the passenger detection device which concerns on Embodiment 3.

The embodiment for carrying out the present invention will be described with reference to the attached drawings. In each figure, the same or corresponding parts are designated by the same reference numerals, and duplicate description will be appropriately simplified or omitted.

Embodiment 1.
FIG. 1 is a configuration diagram of an elevator system according to the first embodiment.

The elevator system 1 includes a car 2, a control panel 3, and a passenger detection device 4. The elevator system 1 is provided, for example, in a building having a plurality of floors. In the building, a hoistway (not shown) is provided. The hoistway is provided over multiple floors. A landing (not shown) is provided on each of the multiple floors. The landing is connected to the hoistway by the landing entrance. The landing entrance is an opening that connects the landing and the hoistway. At each of the plurality of landings, a landing door is provided at the landing entrance / exit.

Car 2 is a device that transports passengers between multiple floors by traveling vertically inside the hoistway. The car 2 travels inside the hoistway by, for example, a hoist (not shown). The basket 2 has a floor surface 5, a wall surface 6, and a ceiling 7. The space inside the car 2 is surrounded by a floor surface 5, a wall surface 6, and a ceiling 7. The space inside the car 2 has, for example, a rectangular parallelepiped shape. The floor surface 5 of the car 2 is a horizontal flat surface. The wall surface 6 of the car 2 is, for example, a vertical flat surface. The ceiling 7 of the car 2 is a plane facing the floor surface 5 above the floor surface 5 of the car 2. The car 2 includes a car door 8, a lighting device 9, an air conditioner 10, a first camera 11a, and a second camera 11b.

The car door 8 is a device that opens and closes so that passengers can get on and off the inside of the car 2 from the landing when the car 2 is stopped on the floor where the landing is provided. The car door 8 is provided on the wall surface 6 of the car 2. When the car door 8 is opened and closed, the landing door is interlocked to open and close.

The lighting device 9 is a device that illuminates the space inside the car 2. The lighting device 9 is provided on the ceiling 7 of the car 2, for example. The lighting device 9 is equipped with a function of adjusting the amount of light.

The air conditioner 10 is a device that adjusts the air in the space inside the car 2 by, for example, ventilation, temperature control, or humidity control. The air conditioner 10 is provided, for example, in the upper part of the car 2.

The first camera 11a is a device that captures the first image. The first image is an image including the floor surface 5 of the car 2. The first camera 11a is provided, for example, on the ceiling 7 of the car 2. Alternatively, the first camera 11a may be provided on the upper portion of the wall surface 6 of the car 2. In this example, the first camera 11a is provided on the left back side of the ceiling 7 of the car 2. The first camera 11a may be, for example, a wide-angle camera.

The second camera 11b is a device that captures a second image. The second image is an image including the floor surface 5 of the car 2. The second camera 11b is provided, for example, on the ceiling 7 of the car 2. Alternatively, the second camera 11b may be provided on the upper portion of the wall surface 6 of the car 2. The second camera 11b is directed toward the floor surface 5 of the car 2 from a direction different from that of the first camera 11a. In this example, the second camera 11b is provided on the right back side of the ceiling 7 of the car 2. The second camera 11b may be, for example, a wide-angle camera.

In FIG. 1, the thick solid line indicates the range of the floor surface 5 of the car 2. The floor surface 5 of the car 2 is a flat surface in a closed area. The floor surface 5 of the car 2 is a horizontal flat surface. In this example, the floor surface 5 of the car 2 is a rectangular flat surface. In this example, the floor surface 5 of the car 2 is entirely included in both the first image and the second image.

In FIG. 1, the thick broken line indicates the closed range of the second plane. The second plane is a plane that does not overlap the floor surface 5. The second plane is, for example, a plane perpendicular to the floor surface 5. In this example, the second plane is a rectangular area of a portion of the surface of the car door 8. The second plane may cover the entire surface of the car door 8. The second plane may be a part of the wall surface 6 of the car 2. In this example, the second plane is entirely included in both the first and second images.

The control panel 3 is a device that controls the operation of the car 2. The operation of the car 2 includes, for example, traveling on a hoistway, opening and closing a car door 8, emitting light from a lighting device 9, and operating an air conditioner 10. The control panel 3 is provided, for example, at the upper part or the lower part of the hoistway.

The passenger detection device 4 is a device that detects the presence or absence of passengers inside the car 2. The passenger detection device 4 includes an input unit 12, a conversion unit 13, a parameter setting unit 14, a parameter storage unit 15, a determination unit 16, and an output unit 17.

The input unit 12 is a part that receives inputs of the first image and the second image. The input unit 12 is connected to the first camera 11a and the second camera 11b so that the input of the first image and the second image can be accepted.

The conversion unit 13 is a part that converts the first image and the second image. The conversion by the conversion unit 13 includes a homography transformation in which the range of the floor surface 5 of the car 2 included in the first image and the range of the floor surface 5 of the car 2 included in the second image overlap each other. Further, the conversion by the conversion unit 13 includes lens distortion correction. The conversion unit 13 is connected to the input unit 12 so that the first image and the second image can be acquired.

The parameter setting unit 14 is a part for setting conversion parameters by the conversion unit 13. The parameter setting by the parameter setting unit 14 is performed based on, for example, the first image and the second image. At this time, the parameter setting unit 14 is connected to the input unit 12 so that the first image and the second image can be acquired. Alternatively, the parameter setting by the parameter setting unit 14 may be performed based on the input from the external input device 18. The input device 18 is an information terminal such as a personal computer. The input device 18 is operated by, for example, a maintenance person or an administrator of the elevator system 1.

The parameter setting unit 14 includes a floor surface parameter setting unit 19 and a distortion parameter setting unit 20. The floor surface parameter setting unit 19 is a portion for setting floor surface parameters. The floor surface parameter is a parameter that defines the range of the floor surface 5 of the car 2 included in the first image and the second image. The floor surface parameters are, for example, the coordinates of the four corners of the floor surface 5 in the first image and the second image. The distortion parameter setting unit 20 is a portion for setting distortion parameters. The distortion parameter is a parameter used for lens distortion correction such as distortion center and distortion coefficient. The parameters set by the parameter setting unit 14 include floor surface parameters and distortion parameters.

The parameter storage unit 15 is a unit that stores the parameters set by the parameter setting unit 14. The parameter storage unit 15 is connected to the parameter setting unit 14 so that the set parameters can be acquired. The parameter storage unit 15 is connected to the conversion unit 13 so that the stored parameters can be output.

The determination unit 16 determines the presence or absence of passengers inside the car 2 based on the difference in the range of the floor surface 5 of the car 2 that overlaps the first image and the second image after the homography conversion by the conversion unit 13. It is a part. The determination unit 16 is connected to the conversion unit 13 so that the first image and the second image after the homography conversion can be acquired.

The output unit 17 is a part that outputs the determination result by the determination unit 16 to an external device of the passenger detection device 4. The output unit 17 is connected to, for example, a control panel 3 so that the determination result can be output.

Subsequently, an example of parameter setting by the parameter setting unit 14 will be described with reference to FIGS. 2 and 3.
FIG. 2 is a diagram showing an example of setting floor surface parameters in the passenger detection device according to the first embodiment.
FIG. 3 is a diagram showing an example of setting distortion parameters in the passenger detection device according to the first embodiment.

The setting of the floor surface parameter for the first image will be described with reference to FIG. In FIG. 2, an example of the first image is shown.

Floor parameters are set, for example, at the time of initial setting or at the time of maintenance and inspection. When setting the floor surface parameters, the maintenance personnel place the markers 21 at the four corners of the floor surface 5 of the car 2. The marker 21 is, for example, a sheet on which a predetermined pattern is represented.

The first camera 11a captures the first image. The input unit 12 receives the input of the first image from the first camera 11a.

The parameter setting unit 14 acquires the first image from the input unit 12. The floor surface parameter setting unit 19 recognizes the marker 21 in the first image acquired by the parameter setting unit 14. In FIG. 2, the broken line frame indicates the position of the marker 21 recognized by the floor parameter setting unit 19. The floor surface parameter setting unit 19 recognizes the positions of the four corners of the floor surface 5 of the car 2 according to the positions of the recognized markers 21. The floor surface parameter setting unit 19 sets the range of the floor surface 5 in the first image as the floor surface parameter according to the recognized positions of the four corners of the floor surface 5.

The floor surface parameter setting unit 19 sets the floor surface parameters for the second image in the same manner as the floor surface parameters for the first image.

The parameter storage unit 15 acquires the floor surface parameters set by the floor surface parameter setting unit 19. The parameter storage unit 15 stores the acquired floor surface parameters.

The maintenance staff collects the placed marker 21.

FIG. 3 describes the setting of the distortion parameter for the first image. In FIG. 3, an example of the first image is shown. In this example, FIG. 3 is a first image taken by the first camera 11a, which is a wide-angle camera.

The distortion parameter is set, for example, at the time of initial setting. Alternatively, the distortion parameter may be set, for example, when the determination unit 16 determines that there are no passengers inside the car 2.

Panel A shows an example of the first image taken by the first camera 11a. The image taken of the inside of the car 2 includes features derived from the structure of the car 2. A feature derived from the structure of the car 2 is a linear edge 22 in real space, such as the boundary between the floor surface 5 and the wall surface 6 or the boundary between adjacent wall surfaces 6. On the other hand, the first image taken by the first camera 11a is distorted due to lens distortion. Therefore, the linear edge 22 in the real space becomes the curved edge 22 in the first image.

The parameter setting unit 14 acquires the first image from the input unit 12. The distortion parameter setting unit 20 extracts the edge 22 in the first image acquired by the parameter setting unit 14.

In panel B, the broken line indicates the edge 22 extracted from the first image. The distortion parameter setting unit 20 extracts the edge 22 which is curved due to the lens distortion by approximating it with, for example, a polygonal line.

The strain parameter setting unit 20 sets the strain parameter by a numerical optimization method or the like so that the curved edge 22 approximated by the polygonal line approaches the linear edge 22.

Panel C shows an example of the first image in which the lens distortion is corrected according to the set distortion parameters. The linear edge 22 in the real space becomes the linear edge 22 in the first image after the lens distortion correction.

The distortion parameter setting unit 20 sets the distortion parameter for the second image in the same manner as for setting the distortion parameter for the first image.

The parameter storage unit 15 acquires the distortion parameter set by the distortion parameter setting unit 20. The parameter storage unit 15 stores the acquired distortion parameter.

Subsequently, the function of the elevator system 1 will be described with reference to FIG.
FIG. 4 is a diagram showing an example of passenger detection in the passenger detection device according to the first embodiment.

The first camera 11a and the second camera 11b capture the first image and the second image inside the car 2. At this time, a passenger is on the inside of the car 2.

The input unit 12 accepts the input of the first image and the second image. The conversion unit 13 acquires the input first image and the second image. The conversion unit 13 acquires the parameters stored in the parameter storage unit 15. The conversion unit 13 converts the lens distortion correction for each of the first image and the second image based on the distortion parameters acquired from the parameter storage unit 15.

The conversion unit 13 homogenizes the first image and the second image that have undergone lens distortion correction conversion so that the ranges of the floor surface 5 of the car 2 overlap each other based on the floor surface parameters acquired from the parameter storage unit 15. Perform graphic conversion. In this example, the conversion unit 13 performs homography conversion so that the range of the floor surface 5 of the car 2 in the first image and the second image is a rectangular range having the same shape and dimensions. By the homography transformation, the first image and the second image projected on the floor surface 5 of the car 2 from the directions of the first camera 11a and the second camera 11b are obtained. At this time, in the first image and the second image, a portion of the floor surface 5 of the car 2 is cut out.

The first camera 11a and the second camera 11b are photographing the floor surface 5 of the car 2 from different directions. Therefore, when there are passengers on the floor surface 5 of the car 2, the first image and the second image after the homography conversion are different images from each other. On the other hand, since the floor surface 5 of the car 2 is a flat surface, the first image and the second image after the homography conversion become images similar to each other when there are no passengers on the floor surface 5 of the car 2. ..

The determination unit 16 acquires the first image and the second image after the homography conversion. The determination unit 16 calculates the degree of dissimilarity between the first image and the second image. The determination unit 16 calculates the dissimilarity as follows, for example.

The determination unit 16 generates a difference image between the acquired first image and the second image. The difference image is generated, for example, by taking the difference in the luminance value for each pixel between the first image and the second image. The determination unit 16 calculates the dissimilarity based on, for example, the absolute value or the average value, the median value, or the maximum value of the square values of the brightness values of the difference images. The determination unit 16 may calculate the dissimilarity by another method.

The determination unit 16 determines that there are passengers inside the car 2 when the calculated dissimilarity is larger than a preset threshold value. On the other hand, the determination unit 16 determines that there are no passengers inside the car 2 when the calculated dissimilarity is equal to or less than a preset threshold value.

The output unit 17 acquires the determination result of the presence or absence of passengers inside the car 2 from the determination unit 16. The output unit 17 outputs the acquired determination result to the control panel 3.

The control panel 3 controls the operation of the car 2 based on the input determination result.

For example, when the input determination result indicates that there are no passengers inside the car 2, the control panel 3 increases the traveling speed of the car 2. Alternatively, at this time, the control panel 3 may increase the upper limit of the traveling speed of the car 2.

For example, when the input determination result indicates that there are no passengers inside the car 2, the control panel 3 stops the operation of the air conditioner 10. Alternatively, at this time, the control panel 3 may weaken the operation of the air conditioner 10. On the other hand, the control panel 3 starts the operation of the air conditioner 10 when the input determination result indicates that there are passengers inside the car 2.

For example, when the landing call is not registered in the car 2 on the floor where the car 2 is stopped by opening the car door 8, the input determination result indicates that there are no passengers inside the car 2. In addition, the control panel 3 shortens the time during which the car door 8 is open.

In addition, there is an elevator system 1 that shifts to a diagnostic operation for diagnosing an abnormality of equipment when the seismograph detects an earthquake. In such an elevator system 1, when the input determination result indicates that there are passengers inside the car 2, the control panel 3 limits the transition to the diagnostic operation. That is, even if an earthquake occurs while a passenger is in the car 2, the control panel 3 does not perform the diagnostic operation until it is determined that the passenger is not in the car 2.

Subsequently, an example of the operation of the passenger detection device 4 will be described with reference to FIG.
FIG. 5 is a flowchart showing an example of the operation of the passenger detection device according to the first embodiment.

In step S1, the input unit 12 acquires the first image from the first camera 11a. Further, the input unit 12 acquires a second image from the second camera 11b. After that, the operation of the passenger detection device 4 proceeds to step S2.

In step S2, the conversion unit 13 converts the lens distortion correction for the first image and the second image acquired by the input unit 12. After that, the operation of the passenger detection device 4 proceeds to step S3.

In step S3, the conversion unit 13 performs homography conversion on the first image and the second image to which the lens distortion has been corrected. After that, the operation of the passenger detection device 4 proceeds to step S4.

In step S4, the determination unit 16 calculates the degree of dissimilarity between the first image and the second image that have undergone homography conversion. After that, the operation of the passenger detection device 4 proceeds to step S5.

In step S5, the determination unit 16 determines whether the calculated dissimilarity is greater than a preset threshold value. When the determination result is Yes, the operation of the passenger detection device 4 proceeds to step S6. When the determination result is No, the operation of the passenger detection device 4 proceeds to step S7.

In step S6, the determination unit 16 determines that there are passengers inside the car 2. After that, the operation of the passenger detection device 4 ends.

In step S7, the determination unit 16 determines that there are no passengers inside the car 2. After that, the operation of the passenger detection device 4 ends.

As described above, the passenger detection device 4 according to the first embodiment includes an input unit 12, a conversion unit 13, and a determination unit 16. The input unit 12 accepts inputs of the first image and the second image. The first image includes the floor surface 5 of the elevator car 2. The first image is taken by the first camera 11a. The first camera 11a is provided in the car 2. The second image includes the floor surface 5 of the car 2. The second image is taken by the second camera 11b from a direction different from that of the first camera 11a. The second camera 11b is provided in the car 2. The conversion unit 13 homographs the first image and the second image so that the range of the floor surface 5 of the car 2 included in the first image and the range of the floor surface 5 of the car 2 included in the second image overlap each other. Perform the conversion. The determination unit 16 determines the presence or absence of passengers inside the car 2 based on the difference in the range of the floor surface 5 of the car 2 that overlaps the first image and the second image after the homography conversion by the conversion unit 13. ..

Further, the elevator system 1 according to the first embodiment includes a car 2, a control panel 3, an input unit 12, a conversion unit 13, a determination unit 16, and an output unit 17. The car 2 transports passengers by traveling inside the hoistway. The hoistway is provided over multiple floors. Passengers get on and off the inside of the car 2 through the car door 8 that opens and closes. The control panel 3 controls the operation of the car 2 based on the input determination result of the presence or absence of passengers inside the car 2. The input unit 12 accepts inputs of the first image and the second image. The first image includes the floor surface 5 of the car 2. The first image is taken by the first camera 11a. The first camera 11a is provided in the car 2. The second image includes the floor surface 5 of the car 2. The second image is taken by the second camera 11b from a direction different from that of the first camera 11a. The second camera 11b is provided in the car 2. The conversion unit 13 homographs the first image and the second image so that the range of the floor surface 5 of the car 2 included in the first image and the range of the floor surface 5 of the car 2 included in the second image overlap each other. Perform the conversion. The determination unit 16 determines the presence or absence of passengers inside the car 2 based on the difference in the range of the floor surface 5 of the car 2 that overlaps the first image and the second image after the homography conversion by the conversion unit 13. .. The output unit 17 outputs the determination result by the determination unit 16 to the control panel 3.

By the homography transformation, the first image and the second image projected on the floor surface 5 of the car 2 from the directions of the first camera 11a and the second camera 11b can be obtained. At this time, the difference between the first image and the second image changes depending on the presence or absence of passengers on the floor surface 5 of the car 2. The passengers in the car 2 are on the floor surface 5, which is a closed area. Therefore, the presence or absence of passengers inside the car 2 can be determined based on the difference between the first image and the second image after the homography transformation. At this time, the determination unit 16 does not need a background image. As a result, even when the internal environment of the car 2 changes, erroneous detection of passengers is suppressed. Here, changes in the environment inside the car 2 include, for example, changes in the amount of light of the lighting device 9, and changes in the external brightness due to time or weather when the car 2 has a window. Further, the change in the internal environment of the car 2 includes the change in the interior such as the wall surface 6 or the floor surface 5 of the car 2. Changes in interiors include changes in notices such as posters, or changes in dynamic display such as signage.

Further, the conversion unit 13 corrects the lens distortion for each of the first image and the second image before the homography conversion.

When photographing the inside of the car 2, a wide-angle camera may be used so that the entire car 2 can be photographed. Even in this case, it is possible to suppress a decrease in the accuracy of detecting the presence or absence of passengers by the determination unit 16.

Further, the passenger detection device 4 includes a distortion parameter setting unit 20. The parameter setting unit 14 sets the distortion parameter based on the first image and the second image received by the input unit 12. The conversion unit 13 corrects the lens distortion based on the distortion parameter set by the distortion parameter setting unit 20.
Further, the passenger detection device 4 includes a floor surface parameter setting unit 19. The floor surface parameter setting unit 19 sets the floor surface parameters based on the first image and the second image received by the input unit 12. The floor surface parameter is a parameter that defines the range of the floor surface 5 of the car 2 included in the first image and the second image. The conversion unit 13 performs homography conversion based on the floor surface parameters set by the floor surface parameter setting unit 19.

The distortion parameter setting unit 20 and the floor surface parameter setting unit 19 set the distortion parameter and the floor surface parameter based on the captured image. For this reason, for example, maintenance personnel do not have to directly adjust strain parameters or floor parameters. The passenger detection device 4 can be easily applied to the elevator system 1.

Further, when the floor surface parameter setting unit 19 recognizes the marker 21 in the first image and the second image, the floor surface parameter setting unit 19 sets the floor surface parameter based on the position of the marker 21.

This allows the floor parameters to be easily calibrated by the placement of the markers 21. Therefore, the accuracy of the determination by the determination unit 16 can be easily maintained.

Further, the control panel 3 increases the traveling speed of the car 2 when the input determination result indicates that there are no passengers inside the car 2.
Further, in the control panel 3, when the landing call is not registered in the car 2 on the floor where the car 2 is stopped by opening the car door 8, the passenger can input the determination result inside the car 2. When indicating that the car door 8 is not open, the time during which the car door 8 is open is shortened.

When there are no passengers inside the car 2, the control panel 3 can be operated to improve the operation efficiency of the car 2. As a result, the utilization efficiency of the elevator system 1 is increased.

Further, the control panel 3 limits the transition to the diagnostic operation when the input determination result indicates that there are passengers inside the car 2.

As a result, even if an earthquake occurs while the passenger is in the car 2, the shift to the diagnostic driving prevents the passenger from being trapped in the car 2.

Further, the car 2 is provided with an air conditioner 10 for adjusting the air in the internal space. The control panel 3 stops the operation of the air conditioner 10 when the input determination result indicates that there are no passengers inside the car 2.

When there are no passengers inside the car 2, the control panel 3 refrains from unnecessary operation of the air conditioner 10. This increases the energy efficiency of the elevator system 1.

When the determination unit 16 detects the movement of a passenger in at least one of the first image and the second image, it may determine that the passenger is inside the car 2 before the homography conversion. Passenger movements are detected, for example, by the frame difference method.

It is presumed that what moves inside the car 2 is a passenger or an object brought in by the passenger. Therefore, it is possible to detect that a passenger is on board by detecting the movement inside the car 2. At this time, the passenger detection device 4 can detect the presence or absence of passengers without performing image processing such as homography conversion. The passenger detection device 4 can reduce the calculation load due to image processing in passenger detection. Even when the passengers are stopped inside the car 2, the determination unit 16 can determine the presence or absence of passengers based on the difference between the images after the homography conversion.

Further, the determination unit 16 determines the position of the floor surface 5 of the car 2 in the first image or the second image based on the deviation of the features derived from the structure of the car 2 extracted from the first image and the second image. The deviation may be detected.

The determination unit 16 detects the deviation as follows, for example. As a feature derived from the structure of the car 2, the determination unit 16 extracts a linear edge 22 from the first image and the second image in a real space such as a boundary between the floor surface 5 and the wall surface 6. The determination unit 16 stores the position of the extracted edge 22 in the image. When the position of the edge 22 is extracted again, the determination unit 16 determines whether there is a difference between the position of the extracted edge 22 and the position of the stored edge 22. When determining that there is a difference, the determination unit 16 detects a deviation in the position of the floor surface 5 of the car 2. The determination unit 16 may correct the position of the floor surface 5 of the car 2 based on the detected deviation. The determination unit 16 may notify the administrator or the like when detecting the deviation. This prevents erroneous detection of passengers due to misalignment of the positions or postures of the first camera 11a and the second camera 11b.

Further, the car 2 is provided with a lighting device 9 in which the amount of light that illuminates the internal space can be adjusted. The control panel 3 may adjust the amount of light of the lighting device 9 when the input determination result indicates that there are passengers inside the car 2. At this time, the conversion unit 13 performs homography conversion on the first image and the second image taken after adjusting the light intensity of the lighting device 9 so that the ranges of the floor surface 5 of the car 2 overlap each other. The determination unit 16 again determines the presence or absence of passengers inside the car 2 based on the difference in the range of the floor surface 5 of the car 2 that overlaps the first image and the second image after the homography conversion by the conversion unit 13. To do.

Passenger detection by the passenger detection device 4 is performed based on the images taken by the first camera 11a and the second camera 11b. For this reason, blackout of the image due to insufficient lighting inside the car 2 and whiteout of the image due to excessive lighting inside the car 2 may occur. At this time, the determination unit 16 may erroneously detect that there are passengers even though the passengers are not actually on board. In such a case, the control panel 3 adjusts the amount of light of the lighting device 9. After that, the passenger detection device 4 performs passenger detection again. As a result, erroneous detection of passengers due to lighting conditions is suppressed. The passenger detection device 4 can more reliably detect that a passenger is not on board. Therefore, the operation efficiency and energy efficiency of the elevator system 1 are more effectively enhanced.

Further, the marker 21 may be any one that can determine the range of the floor surface 5. The marker 21 may be, for example, a sheet that represents a linear pattern and is arranged along four sides of a rectangular floor surface 5. Alternatively, the marker 21 may have a pattern represented on the floor surface 5 of the car 2.

Further, the floor surface 5 may be a closed flat surface on which passengers inside the car 2 ride. The floor surface 5 may be a plane having a curved boundary such as an arc.

Further, when the lens distortion of the first image and the second image output from the first camera 11a and the second camera 11b is small, the conversion unit 13 does not have to perform the lens distortion correction. For example, the first camera 11a and the second camera 11b themselves may be equipped with a lens distortion correction function.

Further, the building provided with the elevator system 1 may have a machine room of the elevator system 1. At this time, for example, the hoisting machine and the control panel 3 may be provided in the machine room.

Further, the passenger detection device 4 may be arranged, for example, in the upper part of the car 2, the control device, the hoistway, the machine room, or the like. Some or all of the functions of the passenger detection device 4 may be realized by individual hardware. Some or all of the functions of the passenger detection device 4 are realized by, for example, the first camera 11a, the second camera 11b, or other equipment provided in the car 2, the control panel 3, or other equipment of the elevator system 1. May be good.

Subsequently, an example of the hardware configuration of the passenger detection device 4 will be described with reference to FIG.
FIG. 6 is a diagram showing a hardware configuration of a main part of the passenger detection device according to the first embodiment.

Each function of the passenger detection device 4 can be realized by a processing circuit. The processing circuit includes at least one processor 4b and at least one memory 4c. The processing circuit may include at least one dedicated hardware 4a with or as a substitute for the processor 4b and the memory 4c.

When the processing circuit includes the processor 4b and the memory 4c, each function of the passenger detection device 4 is realized by software, firmware, or a combination of software and firmware. At least one of the software and firmware is written as a program. The program is stored in the memory 4c. The processor 4b realizes each function of the passenger detection device 4 by reading and executing the program stored in the memory 4c.

The processor 4b is also referred to as a CPU (Central Processing Unit), a processing device, an arithmetic unit, a microprocessor, a microcomputer, and a DSP. The memory 4c is composed of, for example, a non-volatile or volatile semiconductor memory such as RAM, ROM, flash memory, EPROM, EEPROM, a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, a DVD, or the like.

When the processing circuit is provided with dedicated hardware 4a, the processing circuit is realized by, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.

Each function of the passenger detection device 4 can be realized by a processing circuit. Alternatively, each function of the passenger detection device 4 can be collectively realized by a processing circuit. For each function of the passenger detection device 4, a part may be realized by the dedicated hardware 4a, and the other part may be realized by software or firmware. In this way, the processing circuit realizes each function of the passenger detection device 4 by hardware 4a, software, firmware, or a combination thereof.

Embodiment 2.
In the second embodiment, the differences from the examples disclosed in the first embodiment will be described in detail. As for the features not described in the second embodiment, any of the features of the examples disclosed in the first embodiment may be adopted.

FIG. 7 is a diagram showing an example of passenger detection in the passenger detection device according to the second embodiment.

FIG. 7 shows examples of the first image and the second image. In the first image and the second image of FIG. 7, the thick solid line indicates the range of the floor surface 5. In the first and second images of FIG. 7, the dashed line indicates the closed area of the second plane. In this example, the second plane is part of the surface of the car door 8.

The conversion unit 13 generates a first image and a second image projected on the floor surface 5 of the car 2 from the directions of the first camera 11a and the second camera 11b by homography conversion or the like. The determination unit 16 generates a difference image of the floor surface 5 with respect to the first image and the second image projected on the floor surface 5 of the car 2.

In this example, the passenger is standing in front of the car door 8 and boarding. The front of the car door 8 is near the boundary of the floor surface 5. Therefore, in the difference image of the floor surface 5, the difference due to the user being on board is small.

Here, the conversion unit 13 performs the first image and the second image projected onto the second plane from the directions of the first camera 11a and the second camera 11b by homography conversion or the like by the same processing as the processing on the floor surface 5. To generate. The determination unit 16 generates a difference image of the second plane with respect to the first image and the second image projected on the second plane.

The determination unit 16 determines that the dissimilarity calculated from the difference image of the floor surface 5 is larger than the preset threshold value, or the dissimilarity calculated from the difference image of the second plane is greater than the preset threshold value. If it is large, it is determined that there are passengers inside the car 2.

As described above, in the passenger detection device 4 according to the second embodiment, the conversion unit 13 closes the closed range of the second plane included in the first image and the second plane included in the second image. Homography conversion is performed on the first image and the second image so that the ranges overlap each other. The second plane is a plane that does not overlap with the floor surface 5. The determination unit 16 determines the presence or absence of passengers inside the car 2 based on the difference in the range of the second plane on which the first image and the second image overlap each other after the homography conversion by the conversion unit 13.

Further, in the elevator system 1 according to the second embodiment, the conversion unit 13 causes the closed range of the second plane included in the first image and the closed range of the second plane included in the second image to overlap each other. , Perform homography conversion on the first image and the second image. The second plane is a plane that does not overlap with the floor surface 5. The determination unit 16 determines the presence or absence of passengers inside the car 2 based on the difference in the range of the second plane on which the first image and the second image overlap each other after the homography conversion by the conversion unit 13.

The determination unit 16 detects the presence or absence of passengers in the difference image of the floor surface 5 based on the total difference of the floor surface 5. On the other hand, when the passenger stands near the boundary of the floor surface 5, the dissimilarity calculated from the difference image of the floor surface 5 may be small. At this time, there is a possibility that the passengers on board are not detected. In this case, the determination unit 16 detects the presence or absence of passengers based on the dissimilarity calculated from the difference image of the second plane that does not overlap the floor surface 5. Therefore, even when the passengers are standing near the boundary of the floor surface 5, the omission of detection of the passengers in the car 2 is suppressed.

The second plane may be a plane parallel to the floor surface 5 of the car 2. The second plane may be a plane having a height different from that of the floor surface 5 of the car 2. The second plane may face in a direction different from that of the floor surface 5. The second plane may be a plane perpendicular to the floor surface 5. A plurality of second planes may be set in the passenger detection device 4.

Further, the conversion unit 13 performs homography conversion with at least a part of the surface of the wall surface 6 of the car 2 or the car door 8 of the car 2 as the second plane. The determination unit 16 determines the presence or absence of passengers inside the car 2 based on the difference in the range of the second plane.

At this time, the second plane is above the boundary of the floor surface 5. Therefore, the omission of detection of passengers in the vicinity of the boundary of the floor surface 5 is suppressed. Further, the wall surface 6 and the car door 8 of the car 2 are flat surfaces having a clear boundary inside the car 2. Therefore, it becomes easy for the parameter setting unit 14 to set the parameters based on the first image and the second image.

Embodiment 3.
In the third embodiment, the differences from the examples disclosed in the first embodiment or the second embodiment will be described in detail. As for the features not described in the third embodiment, any of the features of the examples disclosed in the first embodiment or the second embodiment may be adopted.

FIG. 8 is a diagram showing an example of passenger detection in the passenger detection device according to the third embodiment.

FIG. 8 shows examples of the first image and the second image. In this example, the car door 8 is open. In this example, the passenger is standing on the floor where the car 2 is stopped. In the first image and the second image of FIG. 8, the thick solid line indicates the range of the floor surface 5. In the first and second images of FIG. 8, the dashed line indicates the closed area of the second plane. In this example, the second plane is part of the floor 5 of the landing. In this example, the second plane is a triangular plane.

The passenger detection device 4 receives a signal indicating that the car door 8 is open from, for example, the control panel 3 through the input unit 12. Alternatively, the passenger detection device 4 may detect that the car door 8 is open, for example, by image recognition.

Here, the conversion unit 13 performs the first image and the second image projected onto the second plane from the directions of the first camera 11a and the second camera 11b by homography conversion or the like by the same processing as the processing on the floor surface 5. To generate. At this time, the second plane is a plane at the same height parallel to the floor surface 5. Therefore, the conversion unit 13 may perform homography conversion based on the same parameters as the processing on the floor surface 5. Further, the portion cut out in the first image and the second image is the portion of the floor surface 5 of the landing. The determination unit 16 generates a difference image of the second plane with respect to the first image and the second image projected on the second plane.

The determination unit 16 determines that the dissimilarity calculated from the difference image of the floor surface 5 is larger than the preset threshold value, or the dissimilarity calculated from the difference image of the second plane is greater than the preset threshold value. If it is large, it is determined that there are passengers at the landing.

On the other hand, when the car door 8 is closed, the passenger detection device 4 receives a signal indicating that the car door 8 is closed from, for example, the control panel 3 through the input unit 12. Alternatively, the passenger detection device 4 may detect that the car door 8 is closed by, for example, image recognition. At this time, the passenger detection device 4 performs passenger detection with the wall surface 6 of the car 2 or the entire or part of the surface of the car door 8 as the second plane.

As described above, in the elevator system 1 according to the third embodiment, the conversion unit 13 is a landing on the floor where the car 2 is stopped by opening the car door 8 when the car door 8 is open. The homography transformation is performed with at least a part of the floor surface 5 of the above as the second plane. The determination unit 16 determines the presence or absence of passengers at the landing based on the difference in the range of the second plane.

As a result, the passenger detection device 4 can detect the passengers who are about to enter the car 2 or the passengers who have got out of the car 2. Therefore, the elevator system 1 can improve utilization efficiency or energy efficiency depending on the situation around the car 2. For example, the control panel 3 may shorten the opening time of the car door 8 when it is determined that there are no passengers inside the car 2 and in the landing.

The passenger detection system according to the present invention can be applied to an elevator system. The passenger detection system according to the present invention can be applied to, for example, a building having a plurality of floors.

1 elevator system, 2 car, 3 control panel, 4 passenger detection device, 5 floor surface, 6 wall surface, 7 ceiling, 8 car door, 9 lighting device, 10 air conditioner, 11a 1st camera, 11b 2nd camera, 12 Input unit, 13 conversion unit, 14 parameter setting unit, 15 parameter storage unit, 16 judgment unit, 17 output unit, 18 input device, 19 floor surface parameter setting unit, 20 distortion parameter setting unit, 21 marker, 22 edge, 4a hardware Hardware, 4b processor, 4c memory

Claims

The first image taken by the first camera provided in the car of the elevator and including the floor surface of the car, and the second camera provided in the car taken from a direction different from that of the first camera and including the floor surface of the car. An input unit that accepts the input of the second image,
Conversion that performs homography conversion on the first image and the second image so that the range of the floor surface of the car included in the first image and the range of the floor surface of the car included in the second image overlap each other. Department and
A determination unit that determines the presence or absence of passengers inside the car based on the difference in the range of the floor surface of the car that overlaps the first image and the second image after the homography conversion by the conversion unit.
Elevator passenger detection device equipped with.
The passenger detection device for an elevator according to claim 1, wherein the conversion unit corrects lens distortion for each of the first image and the second image before homography conversion.
A distortion parameter setting unit for setting distortion parameters based on the first image and the second image received by the input unit is provided.
The passenger detection device for an elevator according to claim 2, wherein the conversion unit corrects lens distortion based on the distortion parameter set by the distortion parameter setting unit.
Floor parameter setting for setting floor parameters that determine the range of the floor surface of the car included in the first image and the second image based on the first image and the second image received by the input unit. Equipped with a department
The passenger detection device for an elevator according to any one of claims 1 to 3, wherein the conversion unit performs homography conversion based on the floor surface parameters set by the floor surface parameter setting unit.
The passenger detection device for an elevator according to claim 4, wherein the floor surface parameter setting unit sets the floor surface parameters based on the positions of the markers when the markers are recognized in the first image and the second image. ..
From claim 1, when the determination unit detects the movement of a passenger in at least one of the first image and the second image, it determines that the passenger is inside the car before the homography conversion. The passenger detection device for an elevator according to any one of claims 5.
The determination unit determines the range of the floor surface of the car in the first image or the second image based on the deviation of the features derived from the structure of the car extracted from the first image and the second image. The passenger detection device for an elevator according to any one of claims 1 to 6, which detects a displacement of the position.
The conversion unit is such that the closed range of the second plane that does not overlap the floor surface included in the first image and the closed range of the second plane included in the second image overlap each other. Homography conversion is performed on the image and the second image,
The determination unit determines the presence or absence of passengers inside the car based on the difference in the range of the second plane in which the first image and the second image overlap each other after the homography conversion by the conversion unit. The passenger detection device for an elevator according to any one of claims 1 to 7.
The conversion unit performs homography conversion with at least a part of the wall surface of the car or the surface of the car door of the car as the second plane.
The passenger detection device for an elevator according to claim 8, wherein the determination unit determines the presence or absence of passengers inside the car based on the difference in the range of the second plane.
A car that transports passengers getting in and out of the interior through a car door that opens and closes by traveling inside a hoistway that spans multiple floors.
A control panel that controls the operation of the car based on the input determination result of the presence or absence of passengers inside the car.
A first image taken by a first camera provided in the car and including the floor surface of the car, and a second image taken by a second camera provided in the car from a direction different from that of the first camera and including the floor surface of the car. 2 Input section that accepts image input and
Conversion that performs homography conversion on the first image and the second image so that the range of the floor surface of the car included in the first image and the range of the floor surface of the car included in the second image overlap each other. Department and
A determination unit that determines the presence or absence of passengers inside the car based on the difference in the range of the floor surface of the car that overlaps the first image and the second image after the homography conversion by the conversion unit.
An output unit that outputs the determination result by the determination unit to the control panel,
Elevator system with.
The elevator system according to claim 10, wherein the control panel increases the traveling speed of the car when the input determination result indicates that there are no passengers inside the car.
The control panel indicates that there are no passengers inside the car as a determination result to be input when the landing call is not registered in the car on the floor where the car is stopped by opening the car door. The elevator system according to claim 10 or 11, wherein when represented, the car door is open for a shorter period of time.
The elevator system according to any one of claims 10 to 12, wherein the control panel limits the transition to diagnostic operation when the input determination result indicates that there are passengers inside the car. ..
The car is equipped with an air conditioner that regulates the air in the internal space.
The elevator according to any one of claims 10 to 13, wherein the control panel stops the operation of the air conditioner when the input determination result indicates that there are no passengers inside the car. system.
The car is equipped with a lighting device that can adjust the amount of light that illuminates the internal space.
The control panel adjusts the amount of light of the lighting device when the input determination result indicates that a passenger is inside the car.
The conversion unit performs homography conversion on the first image and the second image taken after adjusting the amount of light of the lighting device so that the range of the floor surface of the car overlaps with each other.
The determination unit again determines the presence or absence of passengers inside the car based on the difference in the range of the floor surface of the car that overlaps the first image and the second image after the homography conversion by the conversion unit. The elevator system according to any one of claims 10 to 14.
The conversion unit is such that the closed range of the second plane that does not overlap the floor surface included in the first image and the closed range of the second plane included in the second image overlap each other. Homography conversion is performed on the image and the second image,
The determination unit determines the presence or absence of passengers inside the car based on the difference in the range of the second plane in which the first image and the second image overlap each other after the homography conversion by the conversion unit. The elevator system according to any one of claims 10 to 15.
When the car door is open, the conversion unit performs homography conversion using at least a part of the floor surface of the landing on the floor where the car is stopped by opening the car door as the second plane. ,
The elevator system according to claim 16, wherein the determination unit determines the presence or absence of passengers at the landing based on the difference in the range of the second plane.