JP7322250B1 - elevator system - Google Patents

Abstract

To prevent miscalculation of the number of passengers by accurately detecting passengers in a car without being affected by images on installed objects such as mirrors and posters inside the car. Kind Code: A1 An elevator system according to an embodiment includes imaging means, person detection means, tracking means, and detection processing means. to shoot. The person detection means detects a person from the image obtained by the imaging means. The tracking means tracks the person detected by the person detection means. The detection processing means detects the user who got into the car based on the tracking distance and position of the person obtained by the tracking means. [Selection diagram] Fig. 1

Description

Embodiments of the present invention relate to an elevator system that uses a camera installed in the car to detect passengers.

Conventionally, a camera was installed inside the car of an elevator, and by processing the images taken by this camera, the number of passengers inside the car was detected. A system is known which is reflected in operation control.

In this type of system, it is necessary to accurately detect the user by image processing. However, if a mirror is installed in the car, the user reflected in the mirror may be erroneously detected. The same is true when a person's poster or the like is pasted inside the car, and the person on the poster may be erroneously detected as the user.

Japanese Patent No. 5230793 Japanese Patent No. 6611685

If images on objects such as mirrors and posters inside the car are falsely detected as users, the number of passengers will be counted more than the actual number, which will lead to misjudgment of full occupancy, for example, and reduce operation efficiency. .

The problem to be solved by the present invention is to accurately detect the number of passengers in the car without being affected by the images on the installed objects such as mirrors and posters inside the car, and to correct the miscalculation of the number of passengers. To provide an elevator system that can prevent

An elevator system according to one embodiment includes imaging means, person detection means, tracking means, and detection processing means. The person detection means detects a person from the image obtained by the imaging means. The tracking means tracks the person detected by the person detection means. The detection processing means determines whether the person is a user who got into the car based on the tracking distance indicating the movement distance from the start of tracking of the person by the tracking means to the present time and the current position. determine whether or not

FIG. 1 is a diagram showing the configuration of an elevator system according to one embodiment. FIG. 2 is a diagram showing the configuration of the entrance and exit peripheral portion in the car in the same embodiment. FIG. 3 is a diagram showing an example of an image captured by a camera in the same embodiment. FIG. 4 is a diagram showing an example of an image of frame N in the same embodiment. FIG. 5 is a diagram showing an example of an image of frame N+1 in the same embodiment. FIG. 6 is a diagram showing an example of a photographed image in the same embodiment, and is a diagram showing a state in which the user has boarded the car and then turned back to the landing. FIG. 7 is a diagram showing an example of a photographed image in the same embodiment, and is a diagram showing a state in which a person's post is attached inside the car. FIG. 8 is a flow chart for explaining the operation of the elevator system in the same embodiment. FIG. 9 is a flow chart showing details of the user detection process executed in step S16 of FIG. FIG. 10 is a flowchart for explaining switching to full operation as an application example. FIG. 11 is a flow chart for explaining the switching to full operation considering the load value as an application example. FIG. 12 is a flow chart for explaining failure determination as an application example.

Embodiments will be described below 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 the disclosure. In order to make the explanation clearer, in the drawings, the size, shape, etc. of each part may be changed from the actual embodiment and shown schematically. Corresponding elements in multiple drawings may be denoted by the same reference numerals and detailed descriptions thereof may be omitted.

FIG. 1 is a diagram showing the configuration of an elevator system according to one embodiment. Here, one car will be described as an example, but the configuration is the same for a plurality of cars.

A camera 12 used as imaging means is installed above the doorway of the car 11 . Specifically, the camera 12 is installed in the curtain board 11a covering the upper part of the doorway of the car 11 with the lens portion directed directly downward. The camera 12 has a super-wide-angle lens such as a fish-eye lens, and photographs a wide range of objects including the inside of the car 11 with a viewing angle of 180 degrees or more. The camera 12 can continuously shoot images at several frames per second (for example, 30 frames/second).

Note that the camera 12 may be installed near the car door 13 and not above the doorway of the car 11 . For example, the ceiling surface near the doorway of the car 11 may be a place where the entire inside of the car including the entire floor surface in the car 11 and the landing 15 near the doorway when the door is open can be photographed.

Further, a load detector 10 for detecting the load value inside the car 11 is installed at the bottom of the car 11 . The load value detected by the load detector 10 is sent to the elevator controller 30 via a transmission cable (tail cord) not shown.

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

Each image (video) captured continuously by the camera 12 is analyzed in real time by the image processing device 20 . Although FIG. 1 shows the image processing device 20 removed from the car 11 for the sake of convenience, the image processing device 20 is actually housed in the curtain plate 11a together with the camera 12. As shown in FIG.

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

The detection unit 22 is composed of, for example, a microprocessor, and detects a user in the car 11 or at the hall 15 using the image captured by the camera 12 . The detection unit 22 is functionally divided into a person detection unit 22a, a tracking unit 22b, and a detection processing unit 22c. Note that these may be implemented by software, hardware such as an IC (Integrated Circuit), or both software and hardware. Alternatively, the elevator control device 30 may have a part or all of the functions of the image processing device 20 .

The person detection unit 22 a detects a person from the image obtained by the camera 12 . The tracking unit 22b tracks the person detected by the person detection unit 22a. For example, a CoHOG (Co-Occurrence Histograms of Oriented Gradients) feature amount is used as a person detection method. Also, as a method of tracking a person, a method of tracking a person specified by a CoHOG feature amount between frame images, or the like is used.

The detection processing unit 22c detects the user who got into the car 11 based on the tracking distance and position of the person obtained by the tracking unit 22b. The “tracking distance” is the cumulative distance from the start of tracking the object on the captured image to the current time. "Position" is the x, y coordinate position of the object on the captured image, and includes at least the coordinate position in the Y direction (the direction orthogonal to the door opening/closing direction). The detection processing unit 22c has a function of counting the number of passengers when detecting a user who has boarded the car 11 .

Here, the "tracking distance" is the distance that the person has moved from the start of tracking of the person to the present time, regardless of the direction of movement. The detection processing unit 22c determines that the person is a user who got into the car 11 when the tracking distance and position of the person satisfy the following determination conditions.
・The tracking distance of the person is equal to or longer than a preset constant distance Th. ・The position of the person is lower than the reference position Py. (see Figure 4).

The elevator control device 30 is composed of a computer having a CPU, a ROM, a RAM, and the like. The elevator control device 30 includes an operation control section 31 , a door opening/closing control section 32 , a notification section 33 and a failure diagnosis section 34 .

The operation control unit 31 controls the operation of the car 11 . Specifically, when the number of passengers obtained from the captured image of the camera 12 exceeds a certain number of people, the operation control unit 31 performs operation control such as switching to a full operation that passes through the registered floor of the hall call. "The number of passengers obtained from the captured image of the camera 12" is the number of passengers counted by the detection processing unit 22c. The door opening/closing control unit 32 controls opening/closing of the car door 13 when the car 11 arrives at the hall 15 . Specifically, the door opening/closing control unit 32 opens the car door 13 when the car 11 arrives at the hall 15, and closes the car door 13 after a predetermined time has elapsed.

Here, for example, when the detection processing unit 22c detects a user near the car door 13 during the door opening operation of the car door 13, the door opening/closing control unit 32 detects a door accident (pulling into the door pocket). Door opening/closing control is performed to avoid accidents. Specifically, the door opening/closing control unit 32 temporarily stops the door opening operation of the car door 13, moves the car door 13 in the opposite direction (door closing direction), or slows down the door opening speed of the car door 13. The notification unit 33 calls the attention of the user in the car 11 based on the detection result of the detection processing unit 22c.

Further, the elevator control device 30 is provided with a failure diagnosis section 34 . The failure diagnosis unit 34 diagnoses the failure of the camera 12 or the load detector 10 based on the error between the number of passengers obtained from the captured image of the camera 12 and the number of passengers calculated from the load value of the car 11. .

FIG. 2 is a diagram showing the configuration of the entrance and exit peripheral portion in the car 11. As shown in FIG.
A car door 13 is provided at the doorway of the car 11 so as to be freely opened and closed. In the example of FIG. 2, a car door 13 of a two-door double-opening type is shown, and two door panels 13a and 13b constituting the car door 13 open and close in opposite directions along the frontage direction (horizontal direction). . Note that the “frontage” is the same as the doorway 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 board 11a. The "front pillar" is also called an entrance pillar or an entrance frame, and generally has a door pocket for housing the car door 13 on the back side. In the example of FIG. 2, when the car door 13 is opened, one door panel 13a is accommodated in the door pocket 42a provided on the back side of the front pillar 41a, and the other door panel 13b is provided on the back side of the front pillar 41b. It is housed in the door pocket 42b.

One or both of the front pillars 41a and 41b are provided with a display 43, an operation panel 45 having destination floor buttons 44, and a speaker 46. As shown in FIG. In the example of FIG. 2, a speaker 46 is installed on the front pillar 41a, and a display 43 and an operation panel 45 are installed on the front pillar 41b.

Further, as shown in FIG. 3, a rectangular mirror 50 is installed on the rear surface 49 of the car 11 at a location facing the entrance. This mirror 50 is used as a rearview mirror when a wheelchair user gets off the car 11, for example. The mirror 50 includes not only the "glass type" but also the "stainless steel mirror type".

A camera 12 having a super-wide-angle lens such as a fish-eye lens is installed in the center of the curtain plate 11a above the doorway of the car 11. As shown in FIG. The camera 12 photographs the inside of the car 11 and the landing 15 near the entrance at a predetermined frame rate (for example, 30 frames/second). An image captured by the camera 12 is supplied to the image processing device 20 shown in FIG. 1 and used for detection processing for detecting a user or an object.

FIG. 3 is a diagram showing an example of an image captured by the camera 12. As shown in FIG. With the car door 13 (door panels 13a, 13b) and the landing door 14 (door panels 14a, 14b) fully opened, the entire car interior and the landing 15 near the doorway are photographed at a viewing angle of 180 degrees or more from the upper part of the entrance of the car 11. indicates the case. The upper side is the landing 15 and the lower side is the inside of the car 11 .

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

Here, when the mirror 50 is installed in the car 11, there arises a problem that the mirror image of the user reflected in the mirror 50 is erroneously detected in the photographed image, and the number of passengers is double counted. . In this case, erroneous detection by the mirror 50 can be prevented by masking an area (mirror area) corresponding to the installation location of the mirror 50 on the captured image. However, in order to set the mirror area, it is necessary to provide the system with information (installation location, etc.) on the mirror 50 for each object in advance, which is extremely time-consuming.

In the following, a method for correctly counting the number of passengers by detecting users who have boarded the car 11 without being affected by the mirror image of the users reflected in the mirror 50 on the photographed image will be described.

FIG. 4 is a diagram showing an example of an image of frame N, and FIG. 5 is a diagram showing an example of an image of frame N+1 (N is an arbitrary integer). Note that the interval between the frame N and the frame N+1 is made longer here for the sake of convenience in order to make the change in the image easier to understand. P1 in the figure represents the user, and the dotted line represents the locus of movement of the user P1. A mirror 50 is installed at a position facing the doorway on the rear surface 49 of the car 11, and the mirror image of the user P1 is reflected in the mirror 50. - 特許庁

A person is detected from an image photographed by a camera 12 when a car 11 is open. For example, a “CoHOG feature amount” is used as a person detection method. "CoHOG feature quantity" creates a histogram from the combination of luminance gradient intensity at each pixel in the image, quantifies the combination of vertical, horizontal, and diagonal edges in the block, and connects the histograms obtained for each block. It is combined and vectorized. The shape of a person is learned in advance using this CoHOG feature amount, and the person is detected based on the learning result and the CoHOG feature amount extracted from the current image.

Assume that user P1 is detected as a person and given ID11 as identification information. The movement of the user P1 with the ID 11 is tracked from each image obtained from the camera 12 at a predetermined frame rate. As a method of tracking a person, a method of tracking the same person using CoHOG features between frame images is used.

Here, if a mirror 50 is installed in the car 11, there is a possibility that the mirror image of the user P1 reflected in this mirror 50 will also be erroneously detected as a person. This mirror image appears only in mirror 50 and is moving within mirror 50 . Therefore, when the movement of the mirror image is tracked, the distance obtained by the tracking process (tracking distance) is shorter than that of the real image. In this embodiment, attention is paid to the difference in tracking distance between the mirror image and the real image, and a person having a tracking distance equal to or greater than a certain distance Th is determined as the real image of the user P1. Note that the "fixed distance Th" is detected on the captured image in consideration of the position of the camera 12, the size of the car 11, the width of the frontage, the width of the sides of the jambs 17a and 17b in the Y direction, and the like. It is determined from the average distance from the landing 15 to the vicinity of the frontage of the car 11 by the user who is called.

Further, even if the real image of the user P1 can be determined by the tracking process, the user P1 may be moving around the boarding hall 15. FIG. Therefore, when the upper side of the photographed image is the landing 15, the coordinate position in the Y direction of one side portion of the car sill 47 on the car floor surface 19 side existing near the center of the photographed image is determined as the reference position Py. . If the position in the Y direction of the user P1 determined as a real image by tracking processing is below the reference position Py, the user P1 is recognized as a user who has boarded the car 11, and the number of passengers is counted.

In the example of FIG. 4, the tracking distance of the user P1 is shorter than the constant distance Th, and the position of the user P1 in the Y direction is above the reference position Py. At this point, the user P1 has not yet been recognized as a user who got into the car 11 . In the example of FIG. 5, the user P1 is at a certain distance Th or more, and the position of the user P1 in the Y direction is below the reference position Py. At this point, the user P1 is recognized as a user who has boarded the car 11, and the number of passengers is incremented by one.

On the other hand, as shown in FIG. 6, it is assumed that the user P2 to whom the identification information ID12 is assigned has boarded the car 11 and then turned back to the hall 15 . In this case, the tracking distance satisfies the constant distance Th condition, but the position of the user P2 in the Y direction is above the reference position Py. Therefore, user P2 is excluded from the number of passengers.

The installation position of the mirror 50 is not limited to the rear surface 49 of the car 11, and may be the side surfaces 48a and 48b. No matter where the mirror 50 is installed in the car 11, the movement of the mirror image of the person reflected in the mirror 50 is small. Therefore, depending on the tracking distance, the mirror image of the person reflected in the mirror 50 can be excluded from the detection target, and erroneous counting of the number of passengers can be prevented.

Further, as shown in FIG. 7, for example, when a person's poster 51 is pasted in the car 11, the same is true. Although there is a possibility that the person on the poster 51 is erroneously detected, since the person on the poster 51 does not move, it can be excluded from the detection targets depending on the tracking distance. The same applies when a monitor is installed inside the car 11 . When an image of a person is displayed on the monitor, the movement of the person is within the monitor screen, and the tracking distance obtained by tracking processing between frame images is small, so the person can be excluded from the detection targets.

Next, the operation of the elevator system according to this embodiment will be described.
FIG. 8 is a flow chart for explaining the operation of the elevator system. The processing shown in this flowchart is mainly executed by the image processing device 20 .

Assume now that the door of the car 11 is open at an arbitrary floor. A camera 12 installed in the car 11 photographs the inside of the car 11 and the landing 15 near the entrance at a predetermined frame rate. The images captured by the camera 12 are stored in the storage unit 21 of the image processing device 20 in chronological order.

When the car 11 is open (Yes in step S11), the detection unit 22 of the image processing device 20 reads each image stored in the storage unit 21 in chronological order, and detects a person from these images. (Step S12). For the person detection process and the tracking process, a generally known method such as the above-described "CoHOG feature amount" is used, and detailed description thereof will be omitted here.

Here, when a new person is detected (Yes in step S13), the detection unit 22 attaches identification information (ID) to the person and starts tracking the person (step S14). The detection unit 22 tracks the same person to whom the identification information is attached in each image obtained in chronological order from the camera 12 (step S15). The detection unit 22 detects the user who got into the car 11 based on the tracking distance and position of the person obtained by this tracking process (step S16).

Specifically, as shown in FIG. 9, the detection unit 22 first checks the tracking distance of the person, and determines whether or not the tracking distance is equal to or greater than a certain distance Th (step S21). If the tracking distance is less than the fixed distance Th (No in step S21), the detection unit 22 detects that the person being tracked is a mirror image of the person reflected in the mirror 50, or an image on an installation object such as a poster 51. and excludes the object from the detection target (step S24).

On the other hand, if the tracking distance is greater than or equal to the certain distance Th (Yes in step S21), the detection unit 22 determines whether the position of the person being tracked is below the reference position Py (step S22). ). As described above, the reference position Py is determined at the position in the Y direction of the car sill 47 that exists near the center of the captured image. If the position of the person being tracked in the Y direction is below the reference position Py (Yes in step S22), the detection unit 22 determines that the person is a user who got into the car 11 (step S23). ). If the position of the person being tracked in the Y direction is above the reference position Py (No in step S22), the detection unit 22 determines that the person is a user at the hall 15, and excludes the person from detection targets. (Step S24).

In this way, when the person being tracked is determined to be a user who got into the car 11, the detection unit 22 includes the user in the count of the number of passengers (step S17 in FIG. 8). . While the door of the car 11 is open, the above-described processing is repeated, and the number of passengers in the car 11 is counted. In this case, since the mirror image of the person reflected in the mirror 50 and the person on the poster 51 are excluded from the detection targets, the number of passengers is not erroneously counted.

Even after the user gets into the car 11, the tracking process continues. Therefore, as shown in FIG. 6, when the user P2 who has been counted as the number of passengers gets off from the car 11, the count value of the number of passengers can be decremented by -1 to correct the current number of passengers. . In this case, since the user is specified by the identification information, it is possible to determine who got off the vehicle. In addition, there is a case where a user riding near the door in the car 11 once goes out to the hall 15 and gets on again in order to get off the rear user. As described above, since the user is specified by the identification information, if the user is within the same image range, it recognizes that the user once exited the boarding hall 15 and boarded again, and counts the number of passengers. can be reflected correctly. In this case, the count value of the number of passengers is decremented by 1 when the user gets off the vehicle, and is incremented by 1 when the user gets on the vehicle again.

As described above, according to the present embodiment, the mirror 50 is installed in the car 11 by focusing on the tracking distance of the person detected on the captured image (accumulated distance after starting tracking). In this case, the mirror image of the person reflected in the mirror 50 can be excluded from the detection target. Therefore, there is no need to mask the mirror area on the captured image, and even if the person is not three-dimensionally tracked using, for example, a stereo camera, the tracking distance of the person obtained by only one camera 12 and the Based on the position, it is possible to accurately detect only the users who have boarded in the car 11 and reflect the detection result in the number of passengers.

This is the same even when a poster 51 is pasted inside the car 11 or a monitor is installed. It is possible to accurately detect only the users who have boarded the vehicle and reflect the detection results in the number of passengers.

In the above embodiment, the explanation is given on the assumption that the door of the car 11 is open, but the same is true when the door is closed. Only the user in the car 11 can be correctly detected by excluding the person on the top 51 from the detection target.

(Application example)
If the number of passengers is obtained from the image captured by the camera 12, the following can be realized.
(1) Display of Car Situation For example, an indicator (not shown) provided at the landing 15 displays the number of passengers as the car situation. Specifically, the elevator control device 30 acquires the number of passengers counted by the detection unit 22 from the image processing device 20, and displays the current number of passengers on the indicator of the hall 15 of the floor on which the car 11 is landing. is displayed as the status in the car. As a result, the users at the boarding point 15 can grasp the current number of passengers, and can take actions such as not boarding when the number of passengers is large, for example.

(2) Switching to full operation The number of passengers obtained from the photographed image of the camera 12 does not include the mirror image of the person reflected in the mirror 50 or the person on the poster 51, and only the users who are in the car 11. is counted correctly. Therefore, by using this number of passengers, it is possible to correctly judge the full state and switch to full operation in which the registered floor of the hall call is passed.

Specifically, as shown in FIG. 10, when the car 11 is closed, the elevator control device 30 acquires the number of passengers counted by the detector 22 from the image processing device 20 (step S31). If the number of passengers is within a certain number defined as the rated number of passengers of the car 11 (Yes in step S32), the elevator control device 30 stops the car 11 at the registered floor of the hall call and performs normal operation ( step S33). On the other hand, when the number of passengers exceeds a certain number (No in step S32), the elevator control device 30 switches to full operation, does not stop the car 11 at the registered floor of the hall call, and (step S33). It should be noted that the registered floor of the hall call is answered by another car, or after the user in the car 11 gets off at the destination floor.

(3) Switching to full operation considering the load value Even if the number of passengers obtained from the photographed image of the camera 12 correctly counts only the users in the car 11, for example, the weight of the users and the luggage For example, the load value of the car 11 changes. Therefore, it is preferable to include not only the number of passengers but also the loaded load value in the conditions for judging full occupancy.

Specifically, as shown in FIG. 11, when the car 11 is closed, the elevator control device 30 acquires the number of passengers counted by the detector 22 from the image processing device 20 (step S41). If the number of passengers is within the fixed number of people defined as the rated number of passengers of the car 11 (Yes in step S42), the elevator control device 30 acquires the current load value of the car 11 from the load detector 10 ( step S43). If the loaded load value is within the constant load value determined as the rated load value of the car 11 (Yes in step S44), the elevator control device 30 stops the car 11 at the registered floor of the hall call and resumes normal operation. (step S45). On the other hand, if the number of passengers exceeds a certain number (No in step S42) or if the load value exceeds a certain load value (No in step S44), the elevator control device 30 causes the passenger to pass through the registered floor of the hall call. Switch to full operation (step S46).

(4) Failure judgment By comparing the number of passengers obtained from the captured image of the camera 12 and the number of passengers calculated from the load value of the load detector 10, the failure judgment of the camera 12 or the load detector 10 is performed. be able to.

Specifically, as shown in FIG. 12, when the car 11 is closed, the elevator control device 30 acquires the current load value of the car 11 from the load detector 10 (step S51), The number of passengers is calculated from this load value (step S52). For example, when the load value is 500 kg and the average load of users is 60 kg, the number of passengers is calculated as 8 people.

Here, the elevator control device 30 compares the number of passengers calculated from the load value with the number of passengers obtained from the image processing device 20 (step S53). As a result, if there is an error of a certain value or more between the number of passengers on both sides (Yes in step S54), the elevator control device 30 determines that the camera 12 or the load detector 10 is out of order. This is dealt with by, for example, reporting to the center (step S55).

According to at least one embodiment described above, it is possible to accurately detect the number of passengers in the car without being affected by images on installed objects such as mirrors and posters inside the car, thereby increasing the number of passengers. It is possible to provide an elevator system that can prevent miscalculations.

It should be noted that although several embodiments of the invention have been described, these embodiments are provided by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the scope of the invention described in the claims and equivalents thereof.

DESCRIPTION OF SYMBOLS 10... Load detector 11... Car 11a... Curtain plate 12... Camera 13... Car door 14... Landing door 15... Landing hall 16... Landing hall floor 17a, 17b... Three-way frame 18... Hall sill 19 Floor surface of car 20 Image processing device 21 Storage unit 22 Detection unit 22a Human detection unit 22b Tracking unit 22c Detection processing unit 30 Elevator control device 31 operation control unit 32 door opening/closing control unit 33 notification unit 34 failure diagnosis unit 41a, 41b front pillar 41a-1, 41b-1 inner side surface of front pillar 42a, 42b door pocket , 43... Indicator, 44... Destination floor button, 45... Operation panel, 46... Speaker, 47... Car sill, 48a, 48b... Side, 49... Back, 50... Mirror, 51... Poster.

Claims (10)

an image capturing means for capturing an image of a range including the landing area near the entrance from inside the car;
a person detection means for detecting a person from the image obtained by the imaging means;
a tracking means for tracking the person detected by the person detection means;
Detection for determining whether or not the person is a user who has boarded the car based on the tracking distance indicating the moving distance from the start of tracking of the person by the tracking means to the current time and the current position. An elevator system comprising: processing means; The detection processing means is
If the tracking distance of the person is greater than or equal to a certain distance, and if the position of the person is below a preset reference position when the upper side of the image is the boarding hall, the person is moved to the boarding car. 2. The elevator system according to claim 1, wherein the determination is made as a user who has boarded the elevator. The detection processing means is
3. The elevator system according to claim 2, wherein if the tracking distance of said person is less than said predetermined distance, or if said person's position is above said reference position, said person is excluded from detection targets. The detection processing means is
4. The method according to claim 3, wherein when the tracking distance of the person is less than the predetermined distance, the image is determined to be an image on an installation including a mirror installed in the car, and is excluded from detection targets. elevator system. The detection processing means is
4. The elevator system according to claim 3, wherein when the position of the person is above the reference position, the person is determined to be the user in the hall. 3. An elevator system according to claim 2, wherein said reference position is defined as the position of said car sill on said image. The detection processing means is
2. The elevator system according to claim 1, wherein the number of passengers is counted when it is detected that a user has boarded the car. Provided with an operation control means for controlling the operation of the car,
The operation control means is
2. The elevator system according to claim 1, wherein when the number of passengers obtained from the image of said imaging means exceeds a predetermined number, the elevator system is switched to a full-occupancy operation in which the passenger passes through the registered floor of the hall call. Equipped with a load detection means provided in the car,
The operation control means is
9. The elevator system according to claim 8, wherein the elevator system is switched to the fully-occupied operation in consideration of the load value detected by the load detecting means. Equipped with a load detection means provided in the car,
Failure diagnosis for the imaging means or the load detecting means based on the error between the number of passengers obtained from the image of the imaging means and the number of passengers calculated from the load value detected by the load detecting means. 2. The elevator system of claim 1, further comprising diagnostic means.

Images