Image analysis system

Abstract

Provided is an image analysis system capable of determining an abnormal region in a captured image captured by a camera. The image analysis system (1) has an image acquisition unit (24) and an abnormality determination unit (32). The image acquisition unit (24) acquires a captured image from a camera (17) that captures a range of a hoisting device. The abnormality determination unit (32) determines an abnormality of a region in which a change amount of the captured image is smaller than a first threshold value in a captured image captured during a period in which the lighting of a lighting device (18) disposed toward the range is changed by a lighting control unit (29). Alternatively, the abnormality determination unit (32) determines an abnormality of a region in which a change amount of the captured image during a determination period is smaller than a second threshold value in a captured image captured during the determination period in a captured image acquired by the image acquisition unit (24), the region being located in a change region selected as a region in which there is a change in appearance due to the operation of the hoisting device.

Description

Technical Field

[0001] The present invention relates to an image analysis system. Background Art

[0002] Patent Document 1 discloses an example of a recording device. The recording device determines a time range within an image captured by a camera based on the results of detecting changes in the image. The recording device determines as abnormal any image whose recording time falls within a predetermined reference time.

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Laid-Open No. 2017-183916 Summary of the Invention

[0006] Problems to be solved by the invention

[0007] However, the recording device of Patent Document 1 determines an abnormality based on the length of a time range extracted from the entire image captured by the camera. Therefore, an abnormal area is not determined in the image captured by the camera.

[0008] The present invention is directed to solving such a problem and provides an image analysis system capable of determining an abnormal area in an image captured by a camera.

[0009] Means for solving problems

[0010] The image analysis system of the present invention comprises: an image acquisition unit, which acquires a captured image from a camera that captures a shooting range of a lifting device; a lighting control unit, which controls the lighting of a lighting device arranged toward the shooting range; and an abnormality determination unit, which determines that an abnormality is present in an area in the captured image acquired by the image acquisition unit and captured during the period when the lighting control unit changes the lighting of the lighting device, if the area has an amount of change in the captured image that is smaller than a pre-set first threshold value.

[0011] The image analysis system of the present invention comprises: an area selection unit which selects a changed area within the shooting range that has undergone a change in appearance due to the movement of the lifting equipment; and an abnormality determination unit which determines that an area in the captured images acquired by the image acquisition unit and captured within a predetermined judgment period is abnormal when the area in which the amount of change in the captured images during the judgment period is smaller than a predetermined second threshold value is located within the changed area.

[0012] Effects of the Invention

[0013] According to the image analysis system of the present invention, it is possible to determine an abnormal area in an image captured by a camera. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a configuration diagram of the image analysis system according to the first embodiment.

[0015] Figure 2 This is a diagram showing an example of an imaging range in the first embodiment.

[0016] Figure 3 This is a flowchart showing an example of the operation of the image analysis system according to the first embodiment.

[0017] Figure 4 This is a flowchart showing an example of the operation of the image analysis system according to the first embodiment.

[0018] Figure 5 This is a flowchart showing an example of the operation of the image analysis system according to the first embodiment.

[0019] Figure 6 This is a hardware configuration diagram of the main parts of the image analysis system according to the first embodiment. DETAILED DESCRIPTION

[0020] The embodiments of the present invention will be described with reference to the accompanying drawings. In the figures, identical or corresponding parts are denoted by the same reference numerals, and repeated descriptions are simplified or omitted as appropriate. The present invention is not limited to the following embodiments, and any structural elements of the embodiments may be modified or omitted without departing from the spirit of the present invention.

[0021] Implementation Method 1

[0022] Figure 1 This is a configuration diagram of the image analysis system 1 according to the first embodiment.

[0023] The image analysis system 1 is applied to a lifting device. The lifting device is applied to a building having multiple floors, etc. The lifting device is, for example, an elevator 2 .

[0024] A hoistway 3 is provided in the building where the elevator 2 is installed. The hoistway 3 is a vertically long space that spans multiple floors. A landing 4 is provided on each floor of the building. The landing 4 is adjacent to the hoistway 3. Each landing 4 is provided with a landing entrance 5. The landing entrance 5 is an opening leading from the landing 4 to the hoistway 3. The landing entrance 5 is an example of an entrance for the elevator 2. Each landing 4 is provided with a landing door 6. The landing door 6 is a door that separates the landing 4 from the hoistway 3. The landing door 6 is installed at the landing entrance 5. The landing door 6 is an example of a door for the elevator 2. Each landing 4 is provided with a landing display panel 7. The landing display panel 7 is a device that visually displays information to users of the elevator 2 located at the landing 4. The landing display panel 7 may also be provided integrally with a landing operating panel (not shown) that receives landing calls. The landing display panel 7 is an example of a display device for the elevator 2.

[0025] The elevator 2 includes a traction machine 8 , main ropes 9 , a car 10 , a counterweight 11 , and a control panel 12 .

[0026] The hoisting machine 8 is disposed, for example, above or below the hoistway 3. For example, when a machine room of the elevator 2 is provided above the hoistway 3, the hoisting machine 8 may be disposed in the machine room of the elevator 2. The hoisting machine 8 includes a motor that generates a driving force and a sheave that rotates by the driving force generated by the motor.

[0027] The main rope 9 is wound around the sheave of the hoisting machine 8. The main rope 9 supports the load of the car 10 on one side of the sheave of the hoisting machine 8. The main rope 9 supports the load of the counterweight 11 on the other side of the sheave of the hoisting machine 8. The main rope 9 moves by being wound around the sheave of the hoisting machine 8 or being fed out from the sheave of the hoisting machine 8, driven by the driving force generated by the motor of the hoisting machine 8.

[0028] The car 10 is a device that transports users of the elevator 2 and the like between multiple floors by traveling vertically in the hoistway 3. The counterweight 11 is a device that balances the load applied to both sides of the sheave of the traction machine 8 between the car 10 and the counterweight 11. The car 10 and the counterweight 11 travel in opposite directions vertically in the hoistway 3 in conjunction with the movement of the main ropes 9. The position of the car 10 and the direction of travel of the car 10 are displayed on, for example, a landing display panel 7.

[0029] The car 10 is provided with a car entrance 13. The car entrance 13 is an opening leading from the interior of the car 10 to the exterior of the car 10. The car entrance 13 is an example of an entrance of the elevator 2. The car 10 has a car door 14, a car display panel 15, a scale 16, a camera 17, and a lighting device 18. The car door 14 is a door that separates the inside and outside of the car 10. The car door 14 is provided at the car entrance 13. When the car 10 stops at any floor, the car door 14 opens and closes in conjunction with the landing door 6 on that floor, allowing users to travel between the landing 4 on that floor and the interior of the car 10. The car door 14 is an example of a door of the elevator 2. The car display panel 15 is a device that visually displays information to users of the elevator 2 located inside the car 10. The car display panel 15 may also be provided integrally with a car operating panel (not shown) that receives car calls. The car display panel 15 is an example of a display device for the elevator 2. The car display panel 15 is, for example, an indicator that displays the position of the car 10 or the direction of travel of the car 10. The scale 16 is a device that measures the load weight of the car 10. The camera 17 is a device that captures the range in which the camera 17 is directed. The images captured by the camera 17 can be either still images or moving images. The camera 17 is located inside the car 10. The camera 17 captures the interior of the car 10 as its capture range. In this example, the camera 17 is mounted inside the car 10 via a drive device 19. The drive device 19 is a device that has the function of moving the direction or position of the camera 17. The drive device 19 and the camera 17 may also be integrally formed. The lighting device 18 is a device that illuminates the range in which the lighting device 18 is directed. The lighting device 18 is located facing the interior of the car 10. The lighting device 18 is, for example, an LED (Light Emitting Diode).

[0030] The control panel 12 is a device that controls the movement of the elevator 2. The control panel 12 is, for example, located at the top or bottom of the shaft 3. For example, when a machine room for the elevator 2 is located above the shaft 3, the control panel 12 may be located in the machine room of the elevator 2. The movement of the elevator 2 controlled by the control panel 12 includes, for example, the travel of the car 10 and the control of the equipment installed in the car 10. The control of the equipment installed in the car 10 includes, for example, the opening and closing of the car door 14, the movement of the direction or position of the camera 17 by the drive device 19, or the control of the lighting by the lighting device 18. The control panel 12 is connected to the traction machine 8, the car 10, etc. in a manner that can output control signals for the elevator 2 and obtain status information of the elevator 2.

[0031] Elevator 2 utilizes a remote monitoring device 20. Remote monitoring device 20 monitors the status of elevator 2. Remote monitoring device 20 is installed, for example, in the building where elevator 2 is installed. Remote monitoring device 20 is connected to control panel 12. The remote control device monitors the status of elevator 2 via control panel 12 and other means. Remote monitoring device 20 is connected to a network 21, such as the Internet or a telephone network.

[0032] The status information of elevator 2 is managed, for example, by a management server 22. The management server 22 is equipped with functions such as storing and analyzing the status of elevator 2. The management server 22 is composed of, for example, one or more server devices. Some or all of these server devices are located, for example, in an information center. The information center is a base for collecting information such as the status of elevator 2. Some or all of the functions of the management server 22 may also be implemented using a virtual machine on a cloud service, or processing or storage resources. The management server 22 is connected to a network 21. The management server 22 collects information on the status of elevator 2 from, for example, a remote monitoring device 20 via the network 21.

[0033] Image analysis system 1 includes an image analysis device 23. Image analysis device 23 analyzes images captured by the elevator system to which image analysis system 1 is applied. In this example, image analysis device 23 analyzes images captured by camera 17 of elevator 2. Image analysis device 23 is comprised of, for example, one or more hardware components. Some or all of this hardware is located, for example, in the building where elevator 2 is installed. Some or all of the functions of image analysis device 23 may also be implemented using a virtual machine on a cloud service or processing or storage resources. Image analysis device 23 is connected to control panel 12 of elevator 2. Image analysis device 23 is connected to network 21, such as the Internet or a telephone network. Image analysis device 23 may also be integrated with remote monitoring device 20, for example. Image analysis device 23 includes an image acquisition unit 24, an image storage unit 25, a user detection unit 26, an operation input unit 27, an area selection unit 28, an illumination control unit 29, a drive control unit 30, a change calculation unit 31, an abnormality determination unit 32, and a notification processing unit 33.

[0034] The image acquisition unit 24 is a portion equipped with a function of acquiring an image captured by the camera 17 from the camera 17 .

[0035] The image storage unit 25 is a component equipped with a function of storing and accumulating the captured images acquired by the image acquisition unit 24. In this example, the image storage unit 25 sequentially stores the captured images acquired by the image acquisition unit 24. The image storage unit 25 may also appropriately delete the accumulated captured images, for example, depending on the time when the images were captured.

[0036] The user detection section 26 is a portion that detects whether or not a user of a lift 2 or the like is present. The user detection section 26 detects whether or not a user is present in the range of the camera 17. In this example, the user detection section 26 detects whether or not a user is present in the inside of the car 10. The user detection section 26 detects whether or not a user is present in the inside of the car 10, for example, based on a measured value of the load weight of the car 10 by the scale 16. Alternatively, the user detection section 26 can also detect whether or not a user is present in the range of the camera 17, for example, based on the captured image acquired by the image acquisition section 24.

[0037] The operation input section 27 is a portion that receives an input of an operation of an operator to the image analysis system 1. The operator is, for example, an owner or a manager of the lift 2, or an operator of a maintenance company that monitors the lift 2. The operation input section 27 receives an input of an operation performed by a terminal device 34. The terminal device 34 is, for example, a general-purpose information terminal such as a PC (Personal Computer), a tablet terminal, or a smartphone. The terminal device 34 is connected to the network 21.

[0038] The region selection section 28 is a portion that selects a change region from the range of the camera 17. The change region is a region in which there is a change in appearance in the range of the camera 17 due to the movement of the lift 2 or the like. The change region in the lift 2 is, for example, a region of an entrance of the lift 2 such as the landing entrance 5 or the car entrance 13. At this time, the appearance of the change region changes according to the opening and closing of the door of the lift 2 such as the landing door 6 or the car door 14. Alternatively, the change region in the lift 2 is, for example, a region of a display device of the lift 2 such as the landing display panel 7 or the car display panel 15. At this time, the appearance of the change region changes according to a change in the position or the direction of travel of the car 10 or the like. The region selection section 28 selects the change region, for example, according to an operation of the operator received by the operation input section 27. The operation is, for example, an operation of selecting a region of the car entrance 13 in which the car door 14 is provided on the captured image acquired by the image acquisition section 24. Alternatively, the region selection section 28 can automatically select the change region. The region selection section 28 can also automatically select a region of the car entrance 13 in which the car door 14 is provided, for example, by contour detection or the like on the captured image acquired by the image acquisition section 24.

[0039] The lighting control section 29 is a portion that controls the lighting of the lighting device 18. The lighting control section 29 remotely controls the lighting device 18, for example, by the control panel 12. The control by the lighting control section 29 includes, for example, turning on and off of the lighting of the lighting device 18, a change in the brightness or the amount of light, or a change in the color of the lighting, or the like.

[0040] The drive control unit 30 controls the drive device 19. The drive control unit 30 remotely controls the drive device 19 via the control panel 12. The control performed by the drive control unit 30 includes, for example, controlling the direction and position of the camera 17 by the drive device 19.

[0041] The variation calculation unit 31 is a part equipped with the function of calculating the variation in the captured image obtained by the image acquisition unit 24. The variation calculation unit 31 calculates the variation in the captured image for each pixel, for example. The variation calculated by the variation calculation unit 31 is, for example, the variation of the brightness value of each pixel. In the case where multiple color components are set for each pixel, the variation calculation unit 31 can also calculate the variation for each color component. Alternatively, the variation calculation unit 31 can also calculate the variation by the sum of the absolute values ​​or the sum of the squares of the variation of each color component. Alternatively, the variation calculation unit 31 can also calculate the variation in the captured image for each pre-set area. In addition, the variation calculation unit 31 can also calculate the variation over a set period. In this case, the variation calculation unit 31 calculates the variation over the period, for example, for each pixel, by the cumulative value or maximum value of the absolute values ​​of the variation within the period.

[0042] The abnormality determination unit 32 is a component that includes functions for determining whether the captured images acquired by the image acquisition unit 24 contain abnormalities, as well as functions for determining areas within the captured images acquired by the image acquisition unit 24 where abnormalities have occurred. Examples of abnormalities determined by the abnormality determination unit 32 include dirt or damage on the camera 17 or its cover, or defects in pixels within the camera 17. In the case of an abnormality such as dirt or damage, the abnormality is located closer to the camera 17's imaging element than the subject of the captured image, obstructing the image of the captured image in the area where the abnormality exists. Furthermore, in the case of an abnormality involving a defective pixel, the abnormality originates within the camera 17's imaging element itself, resulting in a loss of image content within the captured image. Therefore, even if there are changes in the appearance of the captured image, these changes are not reflected in the captured image of the area containing the abnormality. Therefore, the abnormality determination unit 32 detects areas in the captured image where the changes in the appearance of the captured image are not reflected, and determines the abnormality in those areas. The abnormality determination unit 32 makes this determination based on the amount of change in the captured image calculated by the amount of change calculation unit 31.

[0043] The notification processing unit 33 is a component equipped with a function for notifying the abnormality detected by the abnormality determination unit 32 when it is detected. The notification processing unit 33, for example, notifies the management server 22 of the abnormality. Alternatively, the notification processing unit 33 may also notify the terminal device 34 of the abnormality. The abnormality notification may include, for example, information about the area determined by the abnormality determination unit 32 to have an abnormality. The information about the area determined to have an abnormality may also include, for example, information such as the location and size of the area. Furthermore, the abnormality notification may also include, for example, information such as a captured image in which the abnormality determination unit 32 has detected an abnormality.

[0044] Based on the notification to the management server 22, etc., a maintenance worker is dispatched to the elevator 2. The maintenance worker checks the status of the reported abnormality, performs cleaning, repairs, replacement, or other measures.

[0045] Next, use Figure 2 An example of the imaging range of the camera 17 will be described.

[0046] Figure 2 This is a diagram showing an example of an imaging range in the first embodiment.

[0047] The camera 17 in this example takes the interior of the car 10 as the shooting range to shoot the image. The shooting range includes the car entrance 13 where the car door 14 is installed. The shooting range also includes the car display panel 15. In this example, the area of ​​the car entrance 13 is selected as the change area. The change area is Figure 2 Indicated by thick solid line.

[0048] Next, use Figures 3 to 5 An example of the operation of the image analysis system 1 will be described.

[0049] Figures 3 to 5 This is a flowchart showing an example of the operation of the image analysis system 1 according to the first embodiment.

[0050] exist Figure 3 2 shows an example of processing for determining abnormality using changes in illumination of the illumination device 18 .

[0051] exist Figure 4 hereinafter shows an example of processing for determining abnormality using a change in appearance in a change region.

[0052] exist Figure 5 2 shows an example of processing for determining abnormality by using the movement of the camera 17 by the driving device 19 .

[0053] Figures 3 to 5 The processes shown can be performed sequentially or in parallel. Figures 3 to 5 The processing shown can also be performed in a complex manner. In this case, Figures 3 to 5Repeated parts in the illustrated processing may be omitted or combined as appropriate.

[0054] exist Figure 3 In step S101, the user detection unit 26 detects the presence of a user within the imaging range of the camera 17. If the user detection unit 26 detects a user, the image analysis system 1 completes the process related to determining abnormalities in changes in illumination by the illumination device 18. On the other hand, if the user detection unit 26 does not detect a user, the image analysis system 1 proceeds to step S102.

[0055] In step S102, the lighting control unit 29 outputs a command to the control panel 12 to change the lighting of the lighting device 18. This command may include, for example, switching the lighting of the lighting device 18 on and off, changing the brightness or light intensity, or changing the lighting color. The change in the lighting device 18 may be continuous or discrete. Furthermore, the change in the lighting device 18 may be repeated multiple times. The image analysis system 1 then proceeds to step S103.

[0056] In step S103, the image acquisition unit 24 acquires images captured during the period when the lighting control unit 29 changes the lighting of the lighting device 18. The captured images acquired by the image acquisition unit 24 include, for example, images captured while the lighting of the lighting device 18 is on and images captured while the lighting of the lighting device 18 is off. Alternatively, the captured images acquired by the image acquisition unit 24 may include, for example, images captured when the brightness of the lighting device 18 is at the brightness during normal operation and images captured when the brightness of the lighting device 18 is lower than during normal operation or higher than during normal operation. The change amount calculation unit 31 calculates the amount of change in the captured images acquired by the image acquisition unit 24. The change amount calculation unit 31 calculates, for example, the amount of change in the captured images between when the lighting of the lighting device 18 is on and when the lighting of the lighting device 18 is off. Alternatively, the change amount calculation unit 31 may calculate the change amount in the captured image between when the brightness of the lighting device 18 is at the brightness during normal operation and when the brightness of the lighting device 18 is lower than the brightness during normal operation or higher than the brightness during normal operation. The image analysis system 1 then proceeds to step S104.

[0057] In step S104, the abnormality determination unit 32 determines whether there is an area in the captured image where the amount of change calculated by the amount of change calculation unit 31 is smaller than a first threshold. Here, the first threshold is a pre-set threshold for the amount of change. As the lighting control unit 29 implements changes in the illumination of the lighting device 18, changes in appearance occur within the captured range. Therefore, the abnormality determination unit 32 detects areas of the captured image that do not reflect these changes in appearance within the captured range and determines abnormalities in these areas. If the determination result is "No," the image analysis system 1 completes its processing related to abnormality determination based on changes in illumination from the lighting device 18. On the other hand, if the determination result is "Yes," the image analysis system 1 proceeds to step S105.

[0058] In step S105, the abnormality determination unit 32 determines that the region where the change is smaller than the first threshold is abnormal. The notification processing unit 33 notifies the management server 22 of the abnormality determined by the abnormality determination unit 32. The image analysis system 1 then completes the process of abnormality determination based on changes in illumination by the illumination device 18.

[0059] exist Figure 4 In step S201, the region selection unit 28 selects a changed region from the imaging range. In this example, the region selection unit 28 selects the changed region based on an operator operation inputted via an operation input. In this example, the region of the elevator car entrance 13 is selected as the changed region. The image analysis system 1 then proceeds to step S202.

[0060] In step S202, the image acquisition unit 24 acquires images captured during the determination period. In this example, the image storage unit 25 accumulates and stores the images acquired by the image acquisition unit 24. The determination period is a period pre-set in the image analysis system 1. For example, the determination period is set to be longer than the time a user uses a lifting device such as an elevator 2. For example, for an elevator 2, the determination period is set to be longer than the average time it takes for a user to board and disembark from a car 10. Alternatively, the determination period is set to be longer than the interval between users using a lifting device such as an elevator 2. For example, for an elevator 2, the determination period is set to be longer than the average interval between a user disembarking from a car 10 and another user boarding the car 10. Alternatively, the determination period is set to ensure that the probability of a user using a lifting device such as an elevator 2 at least once during the determination period exceeds a pre-set threshold. This probability is calculated, for example, based on the lifting device's usage history. The determination period is set to, for example, 24 hours. The variation calculation unit 31 calculates the variation of the captured images acquired by the image acquisition unit 24 over the elapsed determination period. For example, the variation calculation unit 31 calculates the variation over the elapsed determination period based on the captured images accumulated by the image accumulation unit 25 during the determination period. Alternatively, the variation calculation unit 31 may calculate the variation each time the image acquisition unit 24 acquires a captured image, thereby calculating the variation over the elapsed determination period. The image analysis system 1 then proceeds to step S203.

[0061] In step S203, the abnormality determination unit 32 determines whether there is an area within the change region of the captured image where the amount of change calculated by the amount of change calculation unit 31 over the determination period is less than a second threshold. Here, the second threshold is a pre-set threshold for the amount of change. Due to the operation of the elevator 2 or other lifting equipment during the determination period, the appearance of the change region changes. Therefore, the abnormality determination unit 32 detects areas of the captured image that do not reflect the appearance change within the captured range and determines an abnormality in that area. If the determination result is "No," the image analysis system 1 terminates its processing related to abnormality determination using appearance changes in the change region. On the other hand, if the determination result is "Yes," the image analysis system 1 proceeds to step S204.

[0062] In step S204, the abnormality determination unit 32 determines that an abnormality exists in the region where the amount of change during the determination period is less than the second threshold. The notification processing unit 33 notifies the management server 22 of the abnormality determined by the abnormality determination unit 32. The image analysis system 1 then completes the process of abnormality determination using the change in appearance within the change region.

[0063] exist Figure 5In step S301, the drive control unit 30 outputs a command to the control panel 12 to move the orientation or position of the camera 17 via the drive device 19. This command may include, for example, moving the imaging range by moving the orientation of the camera 17 and then returning it to its original position. The drive device 19 may repeat the movement of the camera 17 multiple times. The image analysis system 1 then proceeds to step S302.

[0064] In step S302, the image acquisition unit 24 acquires images captured while the drive control unit 30 is moving the imaging range of the camera 17 via the drive device 19. The images acquired by the image acquisition unit 24 may include, for example, images captured when the camera 17 is facing the imaging range during normal operation and images captured when the camera 17 is facing a direction different from the imaging range during normal operation. The change calculation unit 31 calculates the amount of change in the images acquired by the image acquisition unit 24. For example, the change calculation unit 31 calculates the amount of change in the images captured between when the camera 17 is facing the imaging range during normal operation and when the camera 17 is facing a direction different from the imaging range during normal operation. The image analysis system 1 then proceeds to step S303.

[0065] In step S303, the abnormality determination unit 32 determines whether there is an area in the captured image where the amount of change calculated by the amount of change calculation unit 31 is less than a third threshold value. Here, the third threshold value is a pre-set threshold value for the amount of change. Since the camera 17 is moved by the drive control unit 30, the capturing range itself moves. Therefore, the abnormality determination unit 32 detects areas of the captured image that do not reflect the changes caused by the movement of the capturing range and determines whether there is an abnormality in that area. If the determination result is "No," the image analysis system 1's processing related to the abnormality determination of the camera 17's movement by the drive unit 19 ends. On the other hand, if the determination result is "Yes," the image analysis system 1 proceeds to step S304.

[0066] In step S304, the abnormality determination unit 32 determines that an abnormality exists in the region where the amount of change is smaller than the third threshold value. The notification processing unit 33 notifies the management server 22 of the abnormality determined by the abnormality determination unit 32. The image analysis system 1 then completes the process of determining abnormality in the movement of the camera 17 by the drive unit 19.

[0067] As described above, the image analysis system 1 according to the first embodiment includes an image acquisition unit 24, a lighting control unit 29, and an abnormality determination unit 32. The image acquisition unit 24 acquires a captured image from the camera 17. The camera 17 captures the capture range of the elevator 2. The lighting control unit 29 controls the illumination of the lighting device 18. The lighting device 18 is positioned toward the capture range. If there is a region in the captured image acquired by the image acquisition unit 24, or in the captured image captured while the lighting control unit 29 is changing the illumination of the lighting device 18, where the amount of change in the captured image is smaller than a first threshold value, the abnormality determination unit 32 determines that the region is abnormal.

[0068] Furthermore, the image analysis system 1 of the first embodiment includes an image acquisition unit 24, an area selection unit 28, and an abnormality determination unit 32. The area selection unit 28 selects a changed area within the imaging range that has undergone a change in appearance due to the movement of the elevator 2. If an area in the captured images acquired by the image acquisition unit 24 and captured within the determination period, in which the amount of change in the captured images over the determination period is less than a second threshold, is within the changed area, the abnormality determination unit 32 determines that the area is abnormal.

[0069] According to this configuration, the occurrence of an abnormality is determined based on the amount of local change in the captured image, making it possible to identify the area in the captured image where the abnormality has occurred. This allows the occurrence of abnormalities such as dirt, damage, or pixel defects that affect only a portion of the captured image to be determined along with the area in which the abnormality has occurred. This makes it possible to more reliably determine the occurrence of an abnormality in the captured image caused by an abnormality occurring in the camera 17 or the like. Furthermore, since determination is made based on the amount of change in the captured image, the occurrence of an abnormality can be determined regardless of the color of the captured image of the area where the abnormality has occurred or the color of the captured image area that serves as the background. This allows the occurrence of an abnormality to be determined regardless of the design of the elevator 2, such as the interior of the car 10. Furthermore, when abnormality determination is based on changes in the illumination of the lighting device 18, the effects of the changes in illumination also extend across the entire captured image area, making it easy to detect the occurrence of an abnormality in the entire captured image. Furthermore, when abnormality determination is based on changes in the appearance of the changed area, the appearance changes in the changed area due to normal elevator 2 operation during the determination period, allowing the occurrence of an abnormality to be detected without affecting the operation of the elevator 2.

[0070] The image analysis system 1 also includes a user detection unit 26. The user detection unit 26 detects the presence of a user of the elevator 2 within the imaging range. When the user detection unit 26 does not detect a user, the lighting control unit 29 changes the lighting of the lighting device 18.

[0071] According to this configuration, the lighting control unit 29 changes the lighting of the lighting device 18 for determining abnormality when confirming that there is no user. Therefore, it is less likely that users using the elevator 2 will feel unsafe or uncomfortable.

[0072] The image analysis system 1 also includes an operation input unit 27. The operation input unit 27 receives an operation input by an operator via the terminal device 34. The region selection unit 28 selects a change region based on the operation received by the operation input unit 27.

[0073] According to this configuration, it is possible to easily and reliably select a change region in which an appearance change occurs due to the operation of the elevator 2. Therefore, the occurrence of an abnormality can be determined with higher accuracy.

[0074] The image analysis system 1 also includes an image storage unit 25. The image storage unit 25 stores and accumulates the captured images acquired by the image acquisition unit 24. In this case, the region selection unit 28 may select a change region based on the history of changes in the captured images stored by the image storage unit 25. For example, the change calculation unit 31 calculates the history of changes in the captured images based on the captured images stored by the image storage unit 25. The region selection unit 28 selects, as a change region, a region whose history of changes in the captured images exceeds a predetermined threshold.

[0075] This allows detection of abnormalities occurring after capturing images stored in the image storage unit 25 in a change region selected independently of the operator's operation. Therefore, the occurrence of abnormalities can be determined without requiring the operator to perform the labor and time of selecting a change region.

[0076] The image analysis system 1 also includes a drive control unit 30. The drive control unit 30 controls the drive device 19 that moves the camera 17. If there is a region in the captured images acquired by the image acquisition unit 24, which is captured while the drive control unit 30 is moving the imaging range of the camera 17 via the drive device 19, where the amount of change in the captured images is smaller than a third threshold value, the abnormality determination unit 32 determines that the region is abnormal.

[0077] According to this structure, the occurrence of an abnormality is determined based on the amount of local change in the captured image, thereby being able to determine the area in the captured image where the abnormality has occurred. In addition, the influence of the drive device 19 on the movement of the camera 17 also affects the entire captured range, so the occurrence of an abnormality can be easily detected in the entire captured image.

[0078] Furthermore, the first threshold, the second threshold, and the third threshold may have different values ​​of change. Alternatively, at least one of the first threshold, the second threshold, and the third threshold may have the same value of change.

[0079] Furthermore, part or all of the functions of the image analysis device 23, including the functions of the image acquisition unit 24, image storage unit 25, user detection unit 26, operation input unit 27, area selection unit 28, lighting control unit 29, drive control unit 30, change amount calculation unit 31, abnormality determination unit 32, and notification processing unit 33, may be implemented in a device other than the image analysis device 23. Part or all of the functions of the image analysis device 23 may also be implemented in, for example, the camera 17, the control panel 12, the remote monitoring device 20, or the management server 22.

[0080] Furthermore, the lifting device may be, for example, an escalator. An escalator is installed between an upper floor and a lower floor. An escalator includes steps that move in a cycle as users travel between the upper floor and the lower floor. In the case where the lifting device is an escalator, for example, an area of ​​steps that changes in appearance due to the cycle is selected as a change area. Furthermore, for an escalator, the determination period is set to a time that is longer than the average time it takes for a user to board a step on one of the upper and lower floors and to disembark on the other of the upper and lower floors. Alternatively, for an escalator, the determination period may be set to a time that is longer than the average usage interval from when a user disembarks a step to when another user boards the step.

[0081] Next, use Figure 6 An example of the hardware configuration of the image analysis system 1 will be described.

[0082] Figure 6 1 is a hardware configuration diagram of the main parts of the image analysis system 1 according to the first embodiment.

[0083] Each function of the image analysis system 1 can be realized by a processing circuit. The processing circuit includes at least one processor 100a and at least one memory 100b. The processing circuit may also include at least one dedicated hardware 200 together with or instead of the processor 100a and the memory 100b.

[0084] When the processing circuit includes a processor 100a and a memory 100b, the functions of the image analysis system 1 are implemented using software, firmware, or a combination of software and firmware. At least one of the software and firmware is described as a program. This program is stored in the memory 100b. The processor 100a reads and executes the program stored in the memory 100b, thereby implementing the functions of the image analysis system 1.

[0085] The processor 100a is also called a CPU (Central Processing Unit), a processing device, an arithmetic device, a microprocessor, a microcomputer, or a DSP. The memory 100b is composed of nonvolatile or volatile semiconductor memories such as RAM, ROM, flash memory, EPROM, and EEPROM.

[0086] In the case where the processing circuit has dedicated hardware 200, the processing circuit is implemented by, for example, a single circuit, a complex circuit, a programmed processor, parallel programmed processors, an ASIC, an FPGA, or a combination thereof.

[0087] Each processing function in the image analysis system 1 can be implemented separately by a processing circuit. Alternatively, each function of the image analysis system 1 can be implemented collectively by the processing circuit. Each function of the image analysis system 1 can also be partially implemented by dedicated hardware 200 and other portions implemented by software or firmware. In this way, the processing circuit implements each function of the image analysis system 1 using dedicated hardware 200, software, firmware, or a combination thereof.

[0088] Industrial applicability

[0089] The image analysis system of the present invention can be applied to lifting equipment such as elevators.

[0090] Description of labels

[0091] 1: Image analysis system; 2: Elevator; 3: Hoistway; 4: Landing; 5: Landing entrance and exit; 6: Landing door; 7: Landing display panel; 8: Hoisting machine; 9: Main rope; 10: Car; 11: Counterweight; 12: Control panel; 13: Car entrance and exit; 14: Car door; 15: Car display panel; 16: Scale; 17: Camera; 18: Lighting device; 19: Drive device; 20: Remote monitoring device; 21: Network; 22: Management server; 23: Image analysis device; 24: Image acquisition unit; 25: Image storage unit; 26: User detection unit; 27: Operation input unit; 28: Area selection unit; 29: Lighting control unit; 30: Drive control unit; 31: Change calculation unit; 32: Abnormality determination unit; 33: Notification processing unit; 34: Terminal device; 100a: Processor; 100b: Memory; 200: Dedicated hardware

Claims

1. An image analysis system, comprising: an image acquisition unit that acquires an image captured by a camera that captures a range of the lifting device; an area selection unit configured to select a changed area within the imaging range that has changed in appearance due to the movement of the lifting device; as well as an abnormality determination unit configured to determine that an abnormality exists in a captured image captured within a predetermined determination period, when a region in which an amount of change in the captured image over the determination period is smaller than a predetermined second threshold value is located within the change region, among the captured images captured by the image acquisition unit, The determination period is set to a time longer than an average usage interval from when a user of the lift facility gets off to when another user of the lift facility gets on.

2. The image analysis system according to claim 1, wherein: The lifting device is an elevator, The change area is an area of ​​the entrance and exit of the elevator.

3. The image analysis system according to claim 1, wherein: The lifting device is an elevator, The change area is an area of ​​a display device of the elevator.

4. The image analysis system according to claim 1, wherein: The lifting device is an escalator, The changing area is the area of ​​the steps of the escalator.

5. The image analysis system according to any one of claims 1 to 4, wherein: The image analysis system includes a lighting control unit that controls lighting of a lighting device disposed toward the imaging range. The abnormality determination unit determines that there is an abnormality in the captured images acquired by the image acquisition unit, which are captured during the period when the lighting control unit changes the lighting of the lighting device, if there is an area in which the change amount of the captured image is smaller than a preset first threshold.

6. The image analysis system according to claim 5, wherein: The image analysis system includes a user detection unit that detects whether a user of the lifting device is present within the imaging range. The lighting control unit changes the lighting of the lighting device when the user detection unit does not detect the user.

7. The image analysis system according to any one of claims 1 to 4, wherein: The image analysis system includes an operation input unit that receives an operation input by an operator via a terminal device. The region selection unit selects the change region according to the operation accepted by the operation input unit.

8. The image analysis system according to any one of claims 1 to 4, wherein: The image analysis system includes an image storage unit that stores and accumulates the captured images acquired by the image acquisition unit. The region selection unit selects the change region based on a history of changes in the captured images stored in the image storage unit.

9. The image analysis system according to any one of claims 1 to 4, wherein: The image analysis system includes a drive control unit that controls a drive device that moves the camera. In the captured images acquired by the image acquisition unit and captured during the period when the drive control unit moves the shooting range of the camera through the drive device, if there is an area in which the change in the captured image is smaller than a predetermined third threshold value, the abnormality judgment unit judges that the area is abnormal.

Images