JP6810914B2 - Elevator remote monitoring system - Google Patents

Description

The present invention relates to a remote monitoring system that remotely monitors an elevator.

Conventionally, a remote monitoring system for monitoring the operating status of an elevator has been provided. The remote monitoring system includes an elevator including a control microcomputer for controlling the operation, and a terminal communicably connected to the control microcomputer of the elevator and for remotely monitoring the operation of the elevator (see Patent Document 1).

In such a system, when an abnormality occurs in the elevator, the terminal (monitoring terminal) of the monitoring center notifies the monitoring staff of the monitoring center of the operating status of the elevator based on the signal from the elevator (control microcomputer). By the notification of this monitoring terminal, the observer recognizes that an abnormality has occurred in the elevator and requests the technician to be seconded to the elevator.

However, in the above system, since the monitoring terminal only notifies that an elevator abnormality or the like has occurred, the observer cannot grasp the cause of the elevator abnormality or the like.

Causes of elevator notifications include artificial ones, such as the act of blocking the door closing operation when loading and unloading cargo. Therefore, if there is a notification due to the above-mentioned artificial things, the technician who received the secondment request from the observer goes to the site to check the cause of the elevator abnormality, etc. At the time of arrival, the cause of the notification may have been resolved, and the secondment of the technician may be wasted.

Japanese Unexamined Patent Publication No. 2003-212447

Therefore, the present invention provides an elevator monitoring system capable of preventing notification due to the position or behavior of at least one of a person and an object.

The remote monitoring system for an elevator of the present invention has a control microcomputer arranged in the elevator, a monitoring terminal connected to the control microcomputer and capable of receiving abnormality information from the control microcomputer, and the inside of the elevator car over time. The model data includes an image pickup device for imaging, a processing unit for processing an image captured by the image pickup device, and a storage unit for storing model data to be compared with the image captured by the image pickup device. The processing unit includes a first process of extracting edges from at least two images of a plurality of images captured by the image pickup apparatus, and a first process of extracting edges from the at least two images, respectively, including a model pattern of at least one person. When the second process of applying the model pattern of the person to the edge of the image for the person among the extracted edges and the coordinates of the model pattern of the person applied in the second process are at the first specific coordinates, or When the change in the coordinates of the human model pattern in the images before and after the image to which the human model pattern is applied in the second process shows the first specific behavior, the control microcomputer is transferred to the monitoring terminal. It is characterized in that it performs a third process of transmitting anomalous information and preventing transmission of anomalous information due to the behavior of the person to which the model pattern of the person is applied.

In the remote monitoring system of the elevator, the position and behavior of a person can be properly recognized by the model pattern of the person. Therefore, when a person is staying at a position where the abnormality information is likely to be output, and when the person is performing a behavior with a high possibility that the abnormality information is output, that is, the person is from that position. When the cause of the output of abnormal information is eliminated by moving or stopping this behavior, it is caused by the position and behavior of these people (due to artificial causes). Notification (transmission of abnormal information from the control microcomputer to the monitoring terminal) can be prevented.

In the remote monitoring system of the elevator, the model data also includes a model pattern of the internal structure of at least one car, and the second process is a car at the edge extracted from one of the at least two images. The first step of applying the model pattern of the internal structure of the car to the edge of the image with respect to the internal structure of the above, and the edge other than the edge overlapping the model pattern of the internal structure of the car among the edges extracted from the one image. The second step of applying the model pattern of the person, and the edge other than the edge overlapping the model pattern of the internal structure of the car in the edge extracted from the image other than the one image of the at least two images. It may have a third step of fitting the model pattern of the person who fitted it in the second step.

According to this configuration, the human model pattern can be applied more appropriately by applying the human model pattern to the edges other than the edges that overlap the model pattern of the internal structure of the car among the edges extracted from the captured image. Because of this, the position and behavior of a person can be recognized more appropriately. As a result, it is possible to more appropriately prevent notifications caused by the position and behavior of a person.

In another elevator remote monitoring system of the present invention, a control microcomputer arranged in the elevator, a monitoring terminal connected to the control microcomputer and capable of receiving abnormality information from the control microcomputer, and the inside of the elevator car over time. The model includes an image pickup device that specifically captures an image, a processing unit that processes an image captured by the image pickup device, and a storage unit that stores model data to be compared with the image captured by the image pickup device. The data includes a model pattern of at least one object, and the processing unit includes a first process of extracting edges from at least two images out of a plurality of images captured by the image pickup apparatus, and at least two of the images. The second process of applying the model pattern of the object to the edge of the image with respect to the object among the edges extracted from the image, and the coordinates of the model pattern of the object applied in the second process become the second specific coordinates. At one time, or when the change in the coordinates of the model pattern of the object in the images before and after the image to which the model pattern of the object is applied in the second process shows the second specific behavior, the control microcomputer causes the above. It is characterized in that it performs a third process of transmitting anomalous information to a monitoring terminal and preventing transmission of anomalous information due to the position or behavior of the object to which the model pattern of the object is applied.

In the remote monitoring system of the elevator, the position and behavior of the object can be properly recognized by the model pattern of the object. Therefore, when the object is staying at a position where the abnormality information is likely to be output, and when the object is performing the behavior with which the abnormality information is likely to be output, that is, the object is from that position. When the cause of the output of abnormal information is resolved by moving or stopping this behavior, notification (from the control microcomputer to the monitoring terminal) caused by the position and behavior of these objects (Transmission of abnormal information) can be prevented.

In the remote monitoring system of the elevator, the model data also includes a model pattern of the internal structure of at least one car, and the second process is a car at the edge extracted from one of the at least two images. The first step of applying the model pattern of the internal structure of the car to the edge of the image with respect to the internal structure of the above, and the edge other than the edge overlapping the model pattern of the internal structure of the car in the edge extracted from the one image. The second step of applying the model pattern of the object and the second step of the edge other than the edge overlapping the model pattern of the internal structure of the car in the edge extracted from the image other than the one image of the at least two images. It may have a third step of fitting the model pattern of the fitted object in the step.

According to this configuration, by applying the model pattern of the object to the edges other than the edges that overlap the model pattern of the internal structure of the car among the edges extracted from the captured image, the model pattern of the object can be applied more appropriately. Therefore, the position and behavior of an object can be recognized more appropriately. As a result, it is possible to more appropriately prevent notification due to the position and behavior of the object.

In the remote monitoring system of the elevator, the model data also includes a model pattern of at least one object, and in the second process, the edge of the image with respect to the object among the edges extracted from the at least two images, respectively. When the model pattern of the object is applied and the coordinates of the model pattern of the object applied in the second process are at the second specific coordinates in the third process, or the model pattern of the object is applied in the second process. When the change in the coordinates of the model pattern of the object in the images before and after the fitted image shows the second specific behavior, the abnormality information is transmitted from the control microcomputer to the monitoring terminal. The transmission of the anomaly information due to the position or behavior of the object to which the model pattern of is applied may be blocked.

According to such a configuration, in addition to being able to properly recognize the position and behavior of a person by the model pattern of a person, the position and behavior of an object can be properly recognized by the model pattern of an object. Therefore, in addition to the notification caused by the position and behavior of a person, the notification caused by the position and behavior of an object can be prevented.

In the elevator remote monitoring system, the car comprises a door that opens and closes, and the second particular coordinate is in at least one region of the surface of the door and the region of the door in orbit. You may.

According to this configuration, when the coordinates of the model pattern of the object overlap with the area where the surface of the door exists (when the object and the door come into contact with each other), and when the coordinates of the model pattern of the object overlap with the area on the orbit of the door. When at least one of the overlapping cases (when an object is expected to come into contact with the door) is applicable, the transmission of abnormal information from the control microcomputer to the monitoring terminal is blocked, so that the opening and closing of the door is hindered by the object, etc. It is possible to prevent the notification caused by the above (notification when there is a high possibility that the cause of the notification has been resolved when the engineer arrives at the elevator). As a result, it is possible to prevent the secondment of technicians from being wasted.

In the remote monitoring system of the elevator, the change in the coordinates of the model pattern of the object in the images before and after the second process in the second specific behavior is a reciprocating motion in the vertical direction or the horizontal direction. May be good.

According to this configuration, when an object is reciprocating vertically or horizontally, for example, a load carried by a person falls, a person bounces a ball, or a person throws a ball at a wall. Since the transmission of abnormal information from the control microcomputer to the monitoring terminal is blocked during this time, the cause of the notification due to such an event (the cause of the notification may be eliminated when the technician arrives at the elevator). Notification in the case of high sex) can be prevented. As a result, it is possible to prevent the secondment of technicians from being wasted.

In the elevator remote monitoring system, the car comprises a door that opens and closes, and the first particular coordinate is in at least one region of the surface of the door and the region of the door in orbit. You may.

According to this configuration, when the coordinates of the human model pattern overlap with the area where the surface of the door exists (when the person comes into contact with the door), and when the coordinates of the human model pattern overlap with the area on the orbit of the door. When at least one of the times (when a person is expected to come into contact with the door) is applicable, the transmission of abnormal information from the control microcomputer to the monitoring terminal is blocked, which causes the person to obstruct the behavior of the door. It is possible to prevent the notification (notification when there is a high possibility that the cause of the notification has been resolved when the engineer arrives at the elevator). As a result, it is possible to prevent the secondment of technicians from being wasted.

In the remote monitoring system of the elevator, the change in the coordinates of the model pattern of the person in the images before and after the second process in the first specific behavior is a reciprocating motion in the vertical direction or the horizontal direction. May be good.

According to such a configuration, when a person is reciprocating in the vertical or horizontal direction, for example, when the person is shaking the car (for example, when the person is jumping), abnormality information is controlled. Since transmission from the microcomputer to the monitoring terminal is blocked, it is necessary to prevent notifications caused by jumping people (notifications when the cause of the notification is likely to have been resolved when the technician arrives at the elevator). Can be done. As a result, it is possible to prevent the secondment of technicians from being wasted.

From the above, according to the present invention, it is possible to prevent notification caused by the position and behavior of at least one of a person and an object.

FIG. 1 is a block diagram of an elevator remote monitoring system according to an embodiment of the present invention. FIG. 2 is a diagram showing a model pattern of a person used in the remote monitoring system of the elevator according to the embodiment. FIG. 3 is a diagram showing a model pattern of an object used in the remote monitoring system of the elevator according to the embodiment. FIG. 4 is a diagram showing a model pattern of the internal structure of the car used in the remote monitoring system of the elevator according to the same embodiment. FIG. 5 is a flowchart showing the processing of the remote monitoring system for the elevator according to the embodiment. FIG. 6 is a flowchart showing the processing of the remote monitoring system for the elevator according to the embodiment. FIG. 7 is a block diagram of an elevator remote monitoring system according to a modified example of the present invention.

Hereinafter, a remote monitoring system for an elevator according to the present invention (hereinafter, simply referred to as a remote monitoring system) will be described. The remote monitoring system is a system that remotely monitors the operating status of the elevator and notifies the monitoring staff of the monitoring center of the operating status of the elevator. In this remote monitoring system, the observer can recognize that an abnormality has occurred in the elevator by confirming the notification by the monitoring terminal, and can request the technician to be seconded to the elevator.

As shown in FIG. 1, the remote monitoring system includes a control microcomputer 20 arranged in the elevator 2, a camera (imaging device) 210 that images the inside of the car 21 of the elevator 2, and an image (captured image) captured by the camera 210. A processing unit 23 for processing the above, a storage unit 221 for storing model data to be compared with the captured image, and a monitoring terminal 3 connected to the control microcomputer 20 are provided.

In the remote monitoring system 1 of the present embodiment, the image recognition device 22 is connected to the camera 210. The storage unit 221 is provided in the image recognition device 22. Further, the processing unit 23 includes an image recognition processing unit 220 provided in the image recognition device 22, and a microcomputer processing unit 200 provided in the control microcomputer 20.

The remote monitoring system 1 of the present embodiment includes a first server 4 connected to the monitoring terminal 3 and a second server 5 connected to the first server 4. Further, the remote monitoring system 1 of the present embodiment includes a remote monitoring unit 6 connected between the control microcomputer 20 and the monitoring terminal 3. Further, the remote monitoring system 1 of the present embodiment includes an administrator terminal 7 and a technician terminal 8 that can be connected to the first server 4, respectively.

Although one elevator 2 is shown in FIG. 1, the remote monitoring system 1 of the present embodiment includes a plurality of elevators. Further, although one administrator terminal 7 and a technician terminal 8 are shown in FIG. 1, the remote monitoring system 1 of the present embodiment includes a plurality of administrator terminals 7 and a plurality of technician terminals 8.

The elevator 2 controls in addition to a car 21 that goes up and down the hoistway, a control microcomputer 20 that outputs information on the operating status of the elevator 2, and an image recognition device 22 that is connected between the control microcomputer 20 and the camera 210. It has a voice recognition device 24, a voice guidance device 25, and a display guidance device 26, which are connected to the microcomputer 20, respectively.

In addition to the camera 210, the car 21 is connected to, for example, a car frame including a ceiling, a wall, and a floor, a door that opens and closes, an operation panel including a floor button, and a voice recognition device 24, and sounds in the car 21. A microphone (sound collector) 211 that collects sound, a speaker 212 that is connected to the voice guidance device 25 and outputs sound in the car 21, and a display guidance device 26 that is connected to display character information and the like in the car 21. A display (display unit) 213 and the like are included. In the remote monitoring system 1 of the present embodiment, the car 21 is provided with various sensors capable of outputting information on the operating status of the elevator 2.

The camera 210 is arranged on the ceiling in the car 21, for example, and images the inside of the car 21 over time. Further, the camera 210 can output the captured images (a plurality of captured images) in the car 21 to the image recognition device 22. For example, one surveillance camera is provided in the car 21 for monitoring the inside of the car 21, and in the remote monitoring system 1 of the present embodiment, this surveillance camera is used as the camera 210.

Specifically, the camera 210 intermittently (for example, every second) repeatedly takes pictures in the car 21. The camera 210 may continuously take pictures in the car 21.

The image recognition device 22, the voice recognition device 24, the voice guidance device 25, and the display guidance device 26 are, for example, microcomputers provided outside the car 21. Specifically, the voice recognition device 24 can analyze the voice collected by the microphone 211 and output it to the remote monitoring unit 6 via the control microcomputer 20. The voice guidance device 25 can output voice from the speaker 212 based on the information input from the remote monitoring unit 6 via the control microcomputer 20. The display guidance device 26 can output, for example, character information from the display 213 based on the information input from the remote monitoring unit 6 via the control microcomputer 20.

The control microcomputer 20 is connected to the monitoring terminal 3 via the communication system R1. For example, the communication system R1 can communicate with the monitoring terminal 3 in order from the control microcomputer 20 via the remote monitoring unit 6 and the telephone line, and conversely from the monitoring terminal 3 via the telephone line and the remote monitoring unit 6. It is a communication system capable of communicating with the control microcomputer 20.

The microcomputer processing unit 200 can output, for example, an event code to the remote monitoring unit 6 as information regarding the operating status of the elevator 2. The event code output from the microcomputer processing unit 200 is a code associated with the operating status of the elevator 2 itself. Specifically, the event code indicates the position information of the car, the opening / closing information of the door of the car, the driving information of the motor for raising and lowering the car, the power failure, and the like. The event code includes a code indicating abnormality information of the elevator 2.

In the remote monitoring system 1 of the present embodiment, when the operating status of the elevator 2 is normal, the microcomputer processing unit 200 outputs an event code to that effect to the remote monitoring unit 6. Further, when the operating status of the elevator 2 is abnormal, the microcomputer processing unit 200 outputs information to that effect to the image recognition device 22, and the operating status of the elevator 2 is abnormal according to the determination result by the image recognition device 22. The event code indicating that the above is true, or the event code indicating that the operating status of the elevator 2 is not abnormal is output.

For example, the microcomputer processing unit 200 detects whether or not the operating status of the elevator 2 is abnormal based on the information output by various sensors provided in the car 21. In the remote monitoring system 1 of the present embodiment, when the microcomputer processing unit 200 detects that the operating status of the elevator 2 is abnormal, it outputs information to the effect that the operating status is abnormal to the image recognition device 22.

Further, after the microcomputer processing unit 200 outputs information to the image recognition device 22 that the operating status of the elevator 2 is abnormal, a person or an object is in contact with the door of the car 21, or the person or the object is in contact with the door. When the image recognition processing unit 220 inputs a determination result that a part of the elevator is reciprocating in the vertical direction or the horizontal direction, an event code indicating that the operating status of the elevator 2 is not abnormal is output to the remote monitoring unit 6. When the image recognition processing unit 220 inputs a determination result that the person or object is not in contact with the door of the car 21 and the person or object is not reciprocating in the vertical or horizontal direction, the elevator 2 operates. The event code indicating that the situation is abnormal is output to the remote monitoring unit 6.

In the remote monitoring system 1 of the present embodiment, the image recognition processing unit 220 inputs the determination result that a part of the person (for example, the knee) is reciprocating in the vertical direction or the horizontal direction in the microcomputer processing unit 200. Then, as an event code indicating that the operating status of the elevator 2 is not abnormal, for example, an event code indicating that a person's mischief may have occurred in the car 21 is output.

In the remote monitoring system 1 of the present embodiment, when the microcomputer processing unit 200 detects that the operating status of the elevator 2 is not abnormal, it outputs an event code indicating that the operating status is not abnormal to the remote monitoring unit 6. ..

In the remote monitoring system 1 of the present embodiment, the image recognition device 22 uses the image recognition processing unit 220 that detects a person from the captured image as model data to be compared with the captured image of a person and an object. The storage unit 221 that stores the model pattern and the model pattern of the internal structure of the car 21 of the elevator 2 is included.

The storage unit 221 stores the contours (edges) of the person, the object, and the car 21 as a model pattern of the internal structure of the person, the object, and the car 21, respectively. The model patterns of people and objects are set as, for example, model patterns common to each elevator. The model pattern of the internal structure of the car is set individually for each elevator, for example. The objects to be targeted here are objects such as luggage, animals and the like.

For example, the storage unit 221 stores a model pattern of a person having a different silhouette as a model pattern of the person. Specifically, the storage unit 221 stores a model pattern of a person with a general silhouette (general clothes), a model pattern of a person wearing a hat, a model pattern of a person wearing a kimono, and the like.

More specifically, the general human model pattern stored in the storage unit 221 is a simplified version of the human head, ears, torso, arms, and legs, as shown in FIG. It consists of lines (wire frames) connecting the contours. Further, as shown in FIG. 3, the model pattern of the object stored in the storage unit 221 is composed of lines connecting each side of the cube.

In the remote monitoring system 1 of the present embodiment, the storage unit 221 stores the model pattern of the internal structure of the car output from the first server 4. More specifically, as shown in FIG. 4, the model pattern of the internal structure of the car stored in the storage unit 221 is a line connecting the contours of the car frame 214 including the ceiling, the wall, and the floor, and the door 215 that opens and closes. It is composed of a line connecting the contours of the above and a line connecting the contours of the operation panel 216 including the floor button and the like.

In the remote monitoring system 1 of the present embodiment, the storage unit 221 stores information on the first specific coordinates and the first specific behavior as information on the position and behavior of the person, and stores the position and the object on the object. As information on the behavior of the second, the information on the second specific coordinates and the second specific behavior is stored. The coordinates here are the coordinates in the three-dimensional space with one point in the car as the origin.

The first specific coordinates are in at least one region of the surface of the door of the car 21 and the region on the trajectory of the door (the trajectory of opening and closing the door). The second specific coordinate is also in at least one region of the region where the surface of the door of the car 21 exists and the region on the trajectory of the door (the trajectory of opening and closing the door).

The first specific coordinate is an index for determining whether or not the behavior of the door is hindered by a person such as holding the door by a person, prying open the door, or hitting the door with the body. Similarly, the second specific coordinate is an index for determining whether or not an object collides with the door, an obstacle exists at the door opening, or the like causes obstruction of the door behavior. ..

The first particular behavior corresponds to a change in the coordinates of a person's model pattern as the person reciprocates in the vertical or horizontal direction (vertical or horizontal). The second particular behavior also corresponds to changes in the coordinates of the model pattern of the object as it reciprocates in the vertical or horizontal direction (vertical or horizontal). The first specific behavior is, for example, an index for determining whether or not the car 21 is shaken due to a person's jumping. The second specific behavior is, for example, an index for determining whether or not a load carried by a person has fallen or the car 21 has been shaken due to the person bouncing the ball.

When the image recognition processing unit 220 receives information from the control microcomputer 20 that the operating status of the elevator 2 is abnormal, the image recognition processing unit 220 captures images (a plurality of images) in the car 21 captured by the camera 210 over time in a certain period of time. An image) is acquired, and a process of detecting a person from this captured image is performed. The processes for detecting this person (first process and second process) will be described in detail below.

First, the image recognition processing unit 220 performs a first process of extracting edges from at least two of the acquired plurality of captured images. Specifically, the image recognition processing unit 220 performs preprocessing such as density correction, distortion correction, and noise removal for each of the acquired plurality of images, and then the brightness of each image suddenly increases. The boundary that changes to is extracted as an edge.

The image recognition processing unit 220 applies a person's model pattern to the edge of the image for a person among the edges extracted from at least two images (a plurality of images acquired in the remote monitoring system 1 of the present embodiment). Perform the second process. The image recognition processing unit 220 sets the size of each model pattern (model pattern of the internal structure of the car, the model pattern of a person, and the model pattern of an object) and the field of view of the camera 210 (of the camera 210) on the extracted edges. Each model pattern is applied to the edges extracted from the captured image by matching with the coordinates).

Specifically, the image recognition processing unit 220 is an image of the internal structure of the car 21 at the edge extracted from one image (hereinafter referred to as the first image) of the plurality of acquired images in the second process. The first step of applying the model pattern of the internal structure of the car 21 to the edge of the car 21 is performed. Next, in the second process, the image recognition processing unit 220 sets the edge of the image extracted from this one image as the edge of the image for a person among the edges other than the edge overlapping the model pattern of the internal structure of the car 21. Perform the second step of applying a human model pattern.

After that, in the second process, the image recognition processing unit 220 applies a human model pattern in the second step of at least two images (a plurality of acquired images in the remote monitoring system 1 of the present embodiment). Inside the cage 21 at the edge extracted from an image other than the first image (an image other than the first image among at least two images (a plurality of images acquired in the remote monitoring system 1 of the present embodiment)). The third step of applying the model pattern of the person applied in the second step to the edges other than the edges overlapping the model pattern of the structure is performed.

Further, in the remote monitoring system 1 of the present embodiment, the image recognition processing unit 220 is extracted from at least two images (a plurality of acquired images in the remote monitoring system 1 of the present embodiment) in the second processing. The model pattern of each object is applied to the edge of the image with respect to the object among the edges.

Specifically, in the remote monitoring system 1 of the present embodiment, the image recognition processing unit 220 overlaps with the model pattern of the internal structure of the car 21 among the edges extracted from the first image after the third step. The fourth step of applying the model pattern of the object to the edge that does not overlap the human model pattern (the edge to which the human model pattern does not apply in the third step) is performed. Further, after the fourth step, the image recognition processing unit 220 extracts from images other than the first image among at least two images (a plurality of images acquired in the remote monitoring system 1 of the present embodiment). The fifth step of applying the model pattern of the object applied in the fourth step to the edge that does not overlap with the model pattern of the internal structure of the car 21 and does not overlap with the human model pattern at the edge is performed.

Hereinafter, the first to fifth steps in the second process described above will be described in more detail. In the first step, the image recognition processing unit 220 superimposes the model pattern of the internal structure of the car on the edge extracted from the first image, and this overlapping portion (edge overlapping the model pattern of the internal structure of the car). Whether or not there is a human body characteristic (for example, whether or not there is a circular edge that overlaps the human head, whether or not there is a tubular edge that overlaps the torso, and whether or not there is an edge that overlaps the limbs. Whether or not there is) is judged. When the image recognition processing unit 220 determines that there is a circular edge or the like, it is assumed that the inside of the car 21 is manned (a person is detected in the car 21), and the circular edge and the model pattern of the person are displayed. The size of the human model pattern and the field of view of the camera 210 are matched so that the portions corresponding to the heads overlap, and the human model pattern is applied to the edges extracted from the first image.

In the second step, the image recognition processing unit 220 is based on the ground contact position of the model pattern of the person applied in the first image (specifically, the ground contact position between the model pattern of the person and the floor surface of the car 21). , Recognize the position of a person in the space and the space occupied by the person. When the ground contact position of the model pattern of the applied person in the first image cannot be confirmed, the image recognition processing unit 220 determines the existence position of the person and the space occupied by the person based on the estimated ground contact position. recognize. Next, the image recognition processing unit 220 calculates the coordinates of each point from the model pattern of the person applied to the edge extracted from the first image. The coordinates of the human model pattern are, for example, as shown in P1 of FIG. 2, such as the apex of the head, both ears, both shoulders, both elbows, the tips of both hands, both hips, both knees, both heels, and the toes of both legs. The coordinates.

In the third step, the image recognition processing unit 220 applies the model pattern of the person applied in the second step to the images other than the first image among at least the two images mentioned above. More specifically, in the third step, the image recognition processing unit 220 describes the internal structure of the basket 21 of the first image from the edges extracted from the images other than the first image among the plurality of acquired images. Except for the edge that overlaps the model pattern, the model pattern of the person who applied in the second step is applied to this edge. After that, the image recognition processing unit 220 calculates the coordinates of each point from the model pattern of the person applied to the image other than the first image.

In the fourth step, the image recognition processing unit 220 removes the edge that overlaps the model pattern of the internal structure of the car and the edge that overlaps the model pattern of the person from the edge extracted from the first image, and then remains. The edge is judged to be the edge of the image with respect to the object. When the image recognition processing unit 220 determines that there is an edge of the image with respect to the object (when it is determined that there is an object in the car 21), the image recognition processing unit 220 matches the size of the model pattern of the object with the field of view of the camera 210, and the second Apply the model pattern of the object to the edges extracted from one image. Further, the image recognition processing unit 220 calculates the coordinates of each point from the model pattern of the object applied to the edge extracted from the first image. The coordinates of each point in the model pattern of the object are, for example, the eight corners of the cube, as shown in P2 of FIG.

In the fifth step, the image recognition processing unit 220 applies the model pattern of the object applied in the fourth step to the images other than the first image among at least the two images mentioned above. More specifically, in the fifth step, the image recognition processing unit 220 describes the internal structure of the basket 21 of the first image from the edges extracted from the images other than the first image among the acquired plurality of images. The edge that overlaps the model pattern is removed, and the edge that overlaps the model pattern of the person in the first image is removed, and the model pattern of the person fitted in the second step is applied to this edge. After that, the image recognition processing unit 220 calculates the coordinates of each point from the model pattern of the object applied to the image other than the first image.

When the image recognition processing unit 220 determines that the edges extracted from each image do not have circular edges or the like, the image recognition processing unit 220 assumes that the inside of the car 21 is unmanned and applies a human model pattern to the edges extracted from each image. The process of is completed, and the model pattern of the object is applied to the edges extracted from each image. Further, when the image recognition processing unit 220 determines that the edge extracted from each image does not have an edge of the image for the object (when it is determined that there is no object in the car 21), the object for the edge extracted from each image. Finish the process of fitting the model pattern.

Hereinafter, the third process performed after the first process and the second process will be described. The image recognition processing unit 220 may use the second process when the coordinates of the model pattern of the person applied in the second process are at the first specific coordinates (for example, when the person is in contact with the door of the car 21) or the second. When the change in the coordinates of the human model pattern in the captured images before and after the captured image to which the human model pattern is applied in the processing shows the first specific behavior (that is, the person performs the action of shaking the car 21). At that time), a third process is performed to prevent transmission of abnormality information (for example, an event code indicating that the operating status of the elevator 2 is abnormal) from the control microcomputer 20 to the monitoring terminal 3. The captured images before and after the captured image to which the human model pattern is applied in the second process are the captured images to which the captured time is before and after the captured images to which the human model pattern is applied in the second process. Further, the transmission blocked here is the transmission of anomalous information due to the behavior of the person to which the human model pattern is applied.

Further, in the remote monitoring system 1 of the present embodiment, in the third process, the image recognition processing unit 220 indicates that the coordinates of the model pattern of the object applied in the second process are at the second specific coordinates (that is, the object). (When the door of the car 21 is in contact), or the change in the coordinates of the model pattern of the object in the captured images before and after the image captured by applying the model pattern of the object in the second process is the second specific behavior. (That is, when an object is moving so as to shake the car 21), abnormality information from the control microcomputer 20 to the monitoring terminal 3 (for example, an event code indicating that the operating status of the elevator 2 is abnormal). ) Is blocked. This blocked transmission is the transmission of anomalous information due to the behavior of the object to which the model pattern of the object is applied. The images captured before and after the captured image to which the model pattern of the object is applied in the second process are the captured images to which the model pattern of the object is applied in the second process and whose imaging times are before and after.

When there are three or more captured images before and after the captured image to which the human model pattern is applied in the second process, "when the coordinates of the human model pattern applied in the second process are at the first specific coordinates. In addition to when the coordinates of the human model pattern overlap with the first specific coordinates, the coordinates predicted to reach by movement (coordinates by motion line prediction) are the first identification. Including when it overlaps with the coordinates of. In addition, when there are three or more captured images before and after the captured image to which the model pattern of the object is applied in the second process, "when the coordinates of the model pattern of the object applied in the second process are at the second specific coordinates. ”Includes the case where the coordinates of the model pattern of the object are predicted to be reached by movement (coordinates by motion line prediction) overlap with the second specific coordinates.

In addition, the coordinates of the model pattern of the person or object applied in the second process (coordinates of each point in the model pattern of the person or object applied to the edge extracted from the first image or an image other than the first image). Is at the first and second specific coordinates is when the coordinates of each model pattern overlap with the first and second specific coordinates in a certain period of time.

As described above, in the second processing, the image recognition processing unit 220 applies the model pattern of the person or object to the image (the first image or the image other than the first image) to determine the position of the person or object. I can grasp it. In addition, the image recognition processing unit 220 applies a model pattern of a person or an object to different images (an image other than the first image and an image other than the first image) in the second process, so that the behavior of the person or the object (the person or the object) Changes in the movement of objects) can be grasped. Further, in the remote monitoring system 1 of the present embodiment, the image recognition processing unit 220 has a model pattern of a person or an object for three or more images captured before and after the captured image to which the model pattern of the object is applied in the second process. In order to calculate the coordinates of the points, in addition to grasping the behavior of the person or object by changing the coordinates of the model pattern of the person or object calculated in the second process, the behavior of the person or object can be predicted, that is, the person. It is possible to predict the flow line of objects and objects.

Further, in the remote monitoring system 1 of the present embodiment, the image recognition processing unit 220 makes the person or object in contact with the door of the car 21 or the person or object shake the car 21 in the third process. When it is determined that the device is moving, the determination result to that effect is output to the microcomputer processing unit 200, so that the abnormality information from the control microcomputer 20 to the monitoring terminal 3 (for example, the operating status of the elevator 2 is abnormal). Event code) is blocked. When the image recognition processing unit 220 determines in the third process that no person or object is in contact with the door of the car 21, or that the person or object is not moving in such a way as to shake the car 21, the microcomputer A determination result to this effect is output to the processing unit 200.

In the remote monitoring system 1 of the present embodiment, the image recognition processing unit 220 outputs such a determination result to the first server 4, and the first server 4 sends this determination to the administrator terminal 7 and the technician terminal 8. Information about the result can be output.

The monitoring terminal 3 monitors, for example, a large number of elevators installed in a plurality of areas. Further, the monitoring terminal 3 is installed in a monitoring center or the like, which is a building away from the target elevator. Further, the control microcomputer 20 can input abnormality information (for example, an event code indicating that the operating status of the elevator 2 is abnormal) to the monitoring terminal 3. In the remote monitoring system 1 of the present embodiment, the monitoring terminal 3 has a display unit that displays information such as an input event code.

An observer (operator) is stationed at the monitoring center of this embodiment. The observer can monitor the operating status of the elevator 2 by confirming the display of the event code or the like on the display unit of the monitoring terminal 3.

The second server 5 is connected to the first server 4 by, for example, a wired line, and is connected by, for example, P2P (Peer to Peer). Further, the second server 5 has a database 50. The database 50 stores information such as car design values in each elevator. Specifically, the database 50 sets the size of the car frame (dimensions inside the car) in the car, the position of the door in the car, the position of the control panel in the car, and the like as the design values of the car as the elevator identification number (for example,). It is stored in association with the elevator model number). The database 50 is rewritable. For example, when a new elevator is installed, information such as a car design value in the elevator can be added to the database 50.

In the remote monitoring system 1 of the present embodiment, the database 50 stores information (administrator's contact information and technician's contact information) regarding the administrator terminal 7 and the technician terminal 8 corresponding to each elevator. For example, since the database 50 outputs to the administrator terminal 7 and the engineer terminal 8 via the Internet, the IP address of the administrator terminal 7 and the IP address of the engineer terminal 8 are used as information about the administrator terminal 7 and the engineer terminal 8. I remember. The database 50 may store such information in association with the behavior of a person or an object.

The first server 4 is connected to the monitoring terminal 3 via the Internet, for example. Further, the first server 4 is connected to the control microcomputer 20 via the Internet, the monitoring terminal 3, and the communication system R1.

The first server 4 can be connected to the administrator terminal 7 via the communication system R2. The communication system R2 is, for example, a communication system in which the first server 4 can communicate with the administrator terminal 7 via the Internet, and the administrator terminal 7 can communicate with the first server 4 via the Internet. Further, the first server 4 can be connected to the technician terminal 8 via the communication system R3. The communication system R3 is, for example, a communication system capable of communicating from the first server 4 to the technician terminal 8 via the Internet and communicating from the technician terminal 8 to the first server 4 via the Internet. The communication systems R2 and R3 are common to some (Internet).

The first server 4 includes a server processing unit 40 that creates a model pattern of the internal structure of the car. For example, the server processing unit 40 may use the database before the first processing by the image recognition processing unit 220 (before the first series of processing from the first processing to the third processing described above) or when the car specifications are changed. A model pattern of the internal structure of the car is created based on the information such as the design value of the car stored in the car 50, and the created model pattern is output to the image recognition device 22.

Specifically, the server processing unit 40 acquires information such as design values of the car 21 from the database 50, and images the inside of the car in an unmanned state (empty car state) from the camera 210 via the image recognition device 22 or the like. Get an image. The server processing unit 40 acquires, for example, one captured image in an unmanned car.

The server processing unit 40 performs preprocessing such as noise removal on the acquired image captured in the unmanned car, and extracts edges from the captured image after the preprocessing. The server processing unit 40 uses the edges extracted from the captured image based on the shape characteristics of the walls, doors, floors, and ceilings of the car 21 obtained from the design values of the car 21, and the walls, doors, floors of the car 21. And recognize the positional relationship of the ceiling. Further, the server processing unit 40 specifies the position of the camera in the car 21 based on the positional relationship of the wall of the car 21 and the like recognized from the captured image. Further, the server processing unit 40 re-recognizes the positional relationship of the car wall and the like based on the specified camera position, determines the portion overlapping the outline of the car frame and the outline of the door, and coordinates the camera viewpoint (FIG. It calculates the P _C) at 4, to create a model pattern of the internal structure of the car (for example, the floor of the four corners, ceiling corners, door and control panel respective coordinates (P3 in FIG. 4) to calculate these Create a model pattern consisting of lines connecting the coordinates of).

The server processing unit 40 transmits the coordinates of the camera viewpoint to the image recognition device 22 as the field of view of the camera in the car, and as a model pattern of the internal structure of the car, for example, the four corners of the floor and the ceiling in the car. The coordinates of each of the four corners, the door, and the operation panel are output to the image recognition device 22.

The server processing unit 40 moves the determination result by the image recognition processing unit 220 in the third processing (whether or not a person or an object is in contact with the door of the car 21 or the person or the object moves so as to shake the car 21. When the determination result) is input from the microcomputer processing unit 200 via the communication system R1, the monitoring terminal 3, and the Internet, the administrator terminal 7 and the administrator terminal 7 according to the notification source (elevator 2) are transmitted from the database 50. Information about the technician terminal 8 (administrator's contact information and technician's contact information) is acquired, and for example, the determination results are output as character information to the administrator terminal 7 and output to the technician terminal 8. The output judgment result is, for example, a message such as "A person is jumping in the car. There is no problem with the elevator 2 itself."

The administrator terminal 7 and the technician terminal 8 are, for example, portable terminals such as PDAs (Personal Digital Assistants) and laptop computers, and terminals such as stationary personal computers, respectively. Each of the administrator terminal 7 and the technician terminal 8 has, for example, an output unit that outputs the input information. The output unit is a display when the output information is image information or character information, and is a speaker when the output information is audio information. In the remote monitoring system 1 of the present embodiment, the output units of the administrator terminal 7 and the technician terminal 8 are displays, and this display outputs the determination result input from the server processing unit 40.

The administrator terminal 7 is possessed by, for example, an administrator who manages the elevator 2. The technician terminal 8 is possessed by a technician who is seconded to the elevator 2 in order to deal with a trouble in the elevator 2, for example, when a request for secondment is received.

Hereinafter, the flow of processing related to the creation of the model pattern of the internal structure of the car by the server processing unit 40 will be described with reference to the flowchart of FIG.

The server processing unit 40 may use the database 50 before the first processing by the image recognition processing unit 220 (before the first series of processing from the first processing to the third processing described above) or when the specifications of the car 21 are changed. Acquire the design value of the basket (S01). Further, the server processing unit 40 acquires an image captured in the car 21 (an image captured in the car in an unmanned state (empty car state)) from the camera 210 via the image recognition device 22 or the like (S02). The server processing unit 40 extracts the edge of the internal structure of the car from the acquired captured image (S03).

The server processing unit 40 identifies the position of the camera 210 in the car based on the edge extracted from the captured image and the design value of the car acquired from the database 50, and creates a model pattern of the internal structure of the car ( S04).

After that, the server processing unit 40 outputs the information regarding the position of the camera 210 in the car 21 and the information regarding the model pattern of the internal structure of the car to the image recognition device 22 (image recognition processing unit 220) (S05). Specifically, the server processing unit 40 transmits the coordinates of the camera viewpoint to the image recognition device 22, and as a model pattern of the internal structure of the car, for example, the four corners of the floor, the four corners of the ceiling, the door, and the inside of the car. A model pattern composed of lines (wire frames) connecting the contours of each operation panel is output to the image recognition device 22. The storage unit 221 stores the output information regarding the position of the camera 210 and the information regarding the model pattern of the internal structure of the car.

Next, the determination process by the image recognition processing unit 220 will be described with reference to the flowchart of FIG. Hereinafter, a case where the edges extracted from the image include the edges of images of people and objects will be described.

When the control microcomputer 20 inputs information indicating that the operating status of the elevator 2 is abnormal (S10), the image recognition processing unit 220 captures images (plurality of images) in the car 21 captured over time by the camera 210. (Captured image) is acquired (S11).

The image recognition processing unit 220 performs a first process of extracting edges from at least two of the acquired plurality of captured images (in the remote monitoring system 1 of the present embodiment, the acquired plurality of images) (S12). ). Specifically, the image recognition processing unit 220 extracts edges after performing preprocessing such as noise removal on each of the acquired plurality of images.

The image recognition processing unit 220 applies a human model pattern to the edges extracted from the plurality of images whose edges have been extracted in the first process (S12) (S13).

Specifically, the image recognition processing unit 220 applies a model pattern of the internal structure of the car 21 to the edge of the image with respect to the internal structure of the car 21 at the edge extracted from the first image of the acquired plurality of images. (First step), the human model pattern was applied to the edges other than the edges that overlap the model pattern of the internal structure of the car 21 among the edges extracted from this one image (second step), and then acquired. The model pattern of the person applied in the second step is applied to the edges other than the edges that overlap the model pattern of the internal structure of the car 21 in the edges extracted from the images other than the first image among the plurality of images (third). Step). Further, the image recognition processing unit 220 calculates the coordinates of each point in the human model pattern from the human model pattern applied to the edges extracted from the acquired plurality of images.

Next, the image recognition processing unit 220 applies a model pattern of an object to the edges extracted from the plurality of images whose edges have been extracted in the first process (S12) (S14).

Specifically, the image recognition processing unit 220 sets the model pattern of the object on the edge extracted from the first image, which does not overlap the model pattern of the internal structure of the car 21 and does not overlap the model pattern of the person. (Fourth step), it does not overlap with the model pattern of the internal structure of the car 21 and does not overlap with the model pattern of the person at the edge extracted from the images other than the first image among the acquired multiple images. Apply the model pattern of the object applied in the 4th step to the edge (5th step). Further, the image recognition processing unit 220 calculates the coordinates of each point in the model pattern of the object from the model pattern of the object applied to the edges extracted from the plurality of acquired images.

The above processes S13 and S14 correspond to the second process.

The image recognition processing unit 220 determines the position of the person and the behavior of the person based on the coordinates of each point in the model pattern of the person applied to the edges extracted from the plurality of acquired images (S15). For example, the image recognition processing unit 220 uses the image recognition processing unit 220 to apply the coordinates of the model pattern of the person applied in the second process (the person applied to the edge extracted from the first image or an image other than the first image) in a certain period of time. When the coordinates of each point in the model pattern of the above are at the first specific coordinates, it is considered that the person and the door are in contact with each other, and it is determined that the elevator 2 has an abnormality due to the position of the person. ..

Further, in the image recognition processing unit 220, when the change in the coordinates of the human model pattern in the images before and after the captured image to which the human model pattern is applied in the second process shows the first specific behavior, the person It is considered that the car 21 is shaking, and it is determined that the elevator 2 has an abnormality caused by human behavior.

Similar to S15, the image recognition processing unit 220 determines the position of the object and the behavior of the object based on the coordinates of each point in the model pattern of the object applied to the edges extracted from the acquired plurality of images (S16). ). For example, the image recognition processing unit 220 sets the coordinates of the model pattern of the object applied in the second processing or the third processing (edges extracted from the first image or an image other than the first image) in a certain period. When the coordinates of each point of the model pattern of the object that applies to) are at the second specific coordinates, it is considered that the object and the door are in contact, and the elevator 2 has an abnormality due to the position of the object. judge.

Further, in the image recognition processing unit 220, when the change in the coordinates of the model pattern of the object in the images before and after the captured image to which the model pattern of the object is applied in the second process shows the second specific behavior, the object is moved. It is considered that the car 21 is moving so as to shake, and it is determined that the elevator 2 has an abnormality due to the behavior of an object.

The image recognition processing unit 220 outputs the determination results in S15 and S16 to the microcomputer processing unit 200 and the server processing unit 40 (S17). Specifically, the image recognition processing unit 220 causes the elevator 2 to have at least one of an abnormality caused by the position of a person, an abnormality caused by the behavior of a person, an abnormality caused by the position of an object, and an abnormality caused by the behavior of an object. When it is determined that one has occurred, this is output to the microcomputer processing unit 200 and the server processing unit 40. In the remote monitoring system 1 of the present embodiment, the image recognition processing unit 220 outputs such a determination result to the server processing unit 40 of the first server 4 from the server processing unit 40 to the administrator terminal 7. And the technician terminal 8 is made to output this determination result.

When the microcomputer processing unit 200 is input that an abnormality caused by the position of a person or an abnormality caused by the behavior of a person has occurred in the elevator 2 (Yes in S18), an event indicating that there is no abnormality in the elevator 2 occurs. The code is output to the monitoring terminal 3 (S19).

The microcomputer processing unit 200 does not input that an abnormality caused by the position of a person and an abnormality caused by the behavior of a person have occurred in the elevator 2 (No in S18), and is caused by the position of an object in the elevator 2. When it is input that an abnormality has occurred or an abnormality due to the behavior of an object has occurred (Yes in S20), an event code indicating that there is no abnormality in the elevator 2 is output to the monitoring terminal 3 (S19).

The microcomputer processing unit 200 does not input that an abnormality caused by the position of a person and an abnormality caused by the behavior of a person have occurred in the elevator 2 (No in S18), and is caused by the position of an object in the elevator 2. When it is not input that an abnormality or an abnormality caused by the behavior of an object has occurred (No in S20), an event code indicating that there is an abnormality in the elevator 2 is output to the monitoring terminal 3 (S21).

The series of processes S15 to S21 corresponds to the third process. When an abnormality caused by the position of a person or an object or an abnormality caused by the behavior of a person or an object occurs in the elevator 2 by the third process, the abnormality information (event code indicating that the elevator 2 has an abnormality) is provided. It is possible to prevent the output to the monitoring terminal 3.

In the above remote monitoring system 1, edges are extracted from at least two images captured by the camera 210, and a human model pattern is applied to the extracted edges, so that the coordinates of the applied person's model pattern are used to obtain a person's model pattern. The position and behavior can be recognized properly. Therefore, when a person is staying at a position where an event code indicating an abnormality of the elevator 2 is likely to be output, and when a person is performing a behavior with a high possibility of outputting an event code indicating an abnormality. When (when a person moves from that position or a person stops this behavior eliminates the cause of the output of the event code indicating an abnormality), it is caused by the position or behavior of the person. It is possible to prevent notification (due to an artificial cause) (transmission of an event code indicating an abnormality from the control microcomputer 20 to the monitoring terminal 3).

Since the first specific coordinates are in at least one area of the surface of the door of the car 21 and the area in the orbit of the door, the coordinates of each point in the human model pattern are the first specific. When it is at the coordinates of, that is, when a person comes into contact with the door and when a person is expected to come into contact with the door (when the person obstructs the behavior of the door), the notification caused by the obstruction of the behavior of the door by the person is sent. Can be prevented. As a result, it is possible to prevent the secondment of technicians from being wasted.

The change in the coordinates of the person's model pattern in the first specific behavior is a vertical or horizontal reciprocating movement, so that when the person's vertical or horizontal reciprocating movement occurs, that is, the person When the car is shaking (for example, when a person is jumping), it is possible to prevent notification caused by the person jumping or the like. As a result, it is possible to prevent the secondment of technicians from being wasted.

According to the remote monitoring system 1, edges are extracted from at least two images captured by the camera 210, and an object model pattern is applied to the extracted edges, so that the coordinates of the model pattern of the applied object can be used for a person. The position and behavior can be recognized properly. Therefore, when the object exists at a position where the event code indicating the abnormality of the elevator 2 is likely to be output, and the object is performing the behavior with which the event code indicating the abnormality is likely to be output. When (when an object moves from its position or an object stops this behavior, the cause of the output of the event code indicating an abnormality is eliminated), it is caused by the position or behavior of the object. Notification (transmission of an event code indicating an abnormality from the control microcomputer 20 to the monitoring terminal 3) can be prevented.

Since the second specific coordinates are in at least one of the area where the surface of the door of the car 21 exists and the area in the orbit of the door, the coordinates of each point of the model pattern of the object are the second specific. When the coordinates are, that is, when an object comes into contact with the door and when the object is expected to come into contact with the door (when the object obstructs the behavior of the door), the notification caused by the obstruction of the door behavior by the object is sent. Can be prevented. As a result, it is possible to prevent the secondment of technicians from being wasted.

Since the change in the coordinates of the model pattern of the object in the second specific behavior is a reciprocating motion in the vertical or horizontal direction, when the reciprocating motion in the vertical or horizontal direction of the object occurs, for example, a person Prevent notifications caused by shaking the car 21 due to objects when the baggage you are carrying falls and bounces, a person is bouncing the ball, or a person is throwing the ball at the wall inside the car 21. Can be done. As a result, it is possible to prevent the secondment of technicians from being wasted.

The image recognition processing unit 220 determines that, for example, when a person is reciprocating in the vertical or horizontal direction, the person is performing an operation such as shaking the car 21 (for example, the person is jumping). Then, this determination result is also output to the server processing unit 40 of the first server 4, and the server processing unit 40 causes the administrator terminal 7 and the engineer terminal 8 to output this determination result. As a result, the image recognition processing unit 220 can alert the administrator and the technician about the mischief of a person in the car 21.

In the remote monitoring system 1 of the present embodiment, since the processing unit 23 uses a simplified model pattern as a model pattern of a person or an object, the data capacity of the model pattern handled by the processing unit 23 uses a detailed model pattern. Smaller than the case. Therefore, processing can be performed by a microcomputer (control microcomputer 20) whose processing speed is not so high, which is used for controlling the elevator 2, that is, the existing control microcomputer 20 can be used without separately installing a microcomputer having a high processing speed. Can be used for processing.

Further, in the remote monitoring system 1 of the present embodiment, the image recognition processing unit 220 determines whether the coordinates of the model pattern of a person or an object are at the first and second specific coordinates for a certain period of time. For example, even if a person or an object temporarily comes into contact with the door, the output of abnormality information (event code indicating that an abnormality has occurred in the elevator 2) from the control microcomputer 20 to the monitoring terminal 3 may be blocked. Absent.

Further, in the remote monitoring system 1 of the present embodiment, the image recognition processing unit 220 is a person for a plurality of three or more images as the images before and after the captured image to which the model pattern of a person or an object is applied in the second processing. Since the change in the coordinates of the model pattern of the object can be determined, more accurate behavior of the person or object can be grasped.

In the remote monitoring system 1 of the present embodiment, the server processing unit 40 transmits the determination result (for example, a fallen person) by the image recognition processing unit 220 in the third processing to the administrator terminal 7, so that, for example, Even when the technician is staying in a place far from the site (elevator 2), the administrator can quickly respond to a fall or the like.

It should be noted that the remote monitoring system of the present invention is not limited to the above-described embodiment, and it goes without saying that various modifications can be made without departing from the gist of the present invention. For example, the configuration of one embodiment can be added to the configuration of another embodiment, and a part of the configuration of one embodiment can be replaced with the configuration of another embodiment. In addition, some of the configurations of certain embodiments can be deleted.

In the remote monitoring system 1 of the above embodiment, in the second processing, the image recognition processing unit 220 has an edge other than the edge that overlaps the model pattern of the internal structure of the car at the edge extracted from at least two images of the captured image. Although both the human model pattern and the object model pattern have been applied to, only one of the human model pattern and the object model pattern may be applied in the second process.

Even if the processing is performed in this way, when the human model pattern is applied, the transmission of abnormal information caused by the position and behavior of the person from the control microcomputer to the monitoring terminal is blocked, and the notification caused by these is prevented. be able to. Further, when the model pattern of the object is applied, it is possible to prevent the control microcomputer from transmitting the abnormality information due to the position and behavior of the object to the monitoring terminal, and prevent the notification caused by these.

Further, in the remote monitoring system 1 of the above embodiment, the image recognition processing unit 220 is a model of the internal structure of the cage at the edge extracted from at least one of two images in the second processing. After applying the pattern, apply the human model pattern (first step and second step), and the internal structure of the cage is applied to the edges extracted from images other than one of at least two of the captured images. Although the human model pattern was applied without applying the model pattern (third step), the internal structure of the cage was also applied to the edges extracted from images other than one of at least two of the captured images. You may apply a person's model pattern after applying the model pattern of. That is, every time a person's model pattern is applied to the edges extracted from at least two of the captured images, the person's model pattern may be applied after applying the model pattern of the internal structure of the car.

Further, in the remote monitoring system 1 of the above embodiment, in the second processing, the image recognition processing unit 220 overlaps the model pattern of the internal structure of the car among the edges extracted from at least two images of the captured images. The human model pattern and the object model pattern were applied to the edges other than the above, but the human model pattern and the object were applied to the edges extracted from at least two images without using the model pattern of the internal structure of the car. The model pattern of may be applied.

For example, the image recognition processing unit 220 causes some object to move into the car from the difference between at least two images of the plurality of images acquired from the camera 210 and the captured image in the unmanned car, and changes in these images. It may be detected that some or some object is expected to get in and out of the car.

Further, the image recognition processing unit 220 extracts an edge from the captured image in the unmanned car acquired from the camera 210 instead of creating a model pattern of the internal structure of the car, and the storage unit 221 adds the model data to the image. , The edge extracted from the captured image in the unmanned car may be stored. In this case, the storage unit 221 does not have to store the model pattern of the internal structure of the car 21.

In this case, if the image recognition processing unit 220 applies the model pattern of the person or object to the difference between the edge extracted from the first image and the edge extracted from the captured image in the unmanned car, the person or object Since the position and behavior of a person or object can be properly recognized by the model pattern of, it is possible to prevent the transmission of abnormal information caused by the position and behavior of a person from the control microcomputer to the monitoring terminal and prevent the notification caused by these. it can.

In the remote monitoring system 1 of the above embodiment, in the second process, a process (second step) of applying a human model pattern to the edge extracted from the first image out of at least two images from which the edge is extracted is performed, and then the process is performed. Then, a process of applying a human model pattern to the edges extracted from images other than the first image of the at least two images (third step) is performed, and further, the first image of the at least two images mentioned above is performed. The process of applying the model pattern of the object to the edge extracted from (fourth step) is performed, and finally, the process of applying the model pattern of the object to the edge extracted from the image other than the first image of at least the two images mentioned above. (Fifth step) was performed, but the order in which these steps are performed is not limited to this. For example, the fourth step may be performed after the second step, and then the third step and the fifth step may be performed in order.

Further, as described above, the fitting of the human model pattern and the fitting of the object model pattern to the edges extracted from at least two images from which the edges are extracted may be sequentially performed as separate processes, or the model patterns may be applied in order. The fitting of the model and the fitting of the model pattern of the object may be performed at the same time.

The processing unit 23 fits the model patterns of people and objects to the edges extracted from the plurality of captured images acquired in the first processing, but the present invention is not limited to this, and a plurality of edges acquired in the first processing are applied. The model pattern of a person or an object may be applied to the edges extracted from at least two of the captured images. Even in this case, the processing unit 23 can grasp the position and behavior of a person or an object.

The processing unit 23 used a model pattern commonly set for each elevator as a model pattern for a person and a model pattern for an object, but a model pattern individually set for each elevator may be used. For example, individual person model patterns may be added according to the silhouette of the user in the building where each elevator is installed.

The human model pattern was a simplified version of the human parts (head, body, etc.) and consisted of lines (wireframes) connecting the contours, but the human parts were drawn in some detail. It may be a model pattern composed of lines (wireframes) connecting the contours of objects. By using a detailed model pattern of a person, the position and behavior of the person can be grasped in more detail. For example, when a detailed human model pattern includes lines connecting contours such as the human pupil, nose, and mouth, the human pupil, nose, and the human eye, nose, among the human model patterns, are relative to the edges extracted from the captured image. By applying the parts corresponding to the and the mouth, it is possible to more reliably determine whether or not the inside of the car 21 is manned.

Further, although the model pattern of the object is a model pattern composed of lines connecting each side of the cube, a more detailed model pattern may be used. The model pattern of the object may include, for example, a model pattern composed of lines connecting the contours of a bag, a stroller, or the like.

The model data (model pattern of the internal structure of the car, model pattern of a person, model pattern of an object, etc.) is stored in a place other than the storage unit 221 of the image recognition device 22, for example, a place different from the elevator 2 (away from the elevator 2). It may be stored in a server or the like installed in the place).

The processing unit 23 includes an image recognition processing unit 220 provided in the image recognition device 22, and a microcomputer processing unit 200 provided in the control microcomputer 20, but the processing unit 23 is not limited to this, and all of the processing units 23 include. It may be provided in the control microcomputer 20 or in the image recognition device 22. Further, at least a part of the processing unit 23 is included in a configuration other than the elevator 2 (for example, a first server 4 or a server installed in a place different from the elevator 2 (a place away from the elevator 2)). You may.

For example, when the processing unit 23 uses a detailed human model pattern, a higher processing capacity is required as compared with the case where a simplified human model pattern is used. Therefore, the processing unit 23 and the storage unit 221 are combined with the elevator 2 It may be installed in a server installed in a place different from the above (a place away from the elevator 2).

A plurality of cameras 210 may be provided in the car 21. Further, as the camera 210, instead of using the surveillance camera, another camera other than the surveillance camera may be used. As such a camera, for example, a 360 ° camera capable of simultaneously photographing the entire surroundings may be used.

In the third process, the image recognition processing unit 220 determines the contact between the person and the door of the car 21 based on the coordinates of the model pattern of the person, and blocks the transmission of the output of the abnormal information. The positional relationship between the person and the door (distance between the person and the door, etc.), the positional relationship between the person and the wall of the car 21, the positional relationship between the person and the ceiling of the car 21, the positional relationship between the person and the floor of the car 21, and , Judging the positional relationship between the person and the operation panel, blocking the transmission of the output of abnormality information (for example, an event code indicating that an abnormality has occurred in the elevator 2) from the control microcomputer 20 to the monitoring terminal 3. May be good. For example, when it is determined that the coordinates of both shoulders and elbows of a person's model pattern are in contact with the floor of the car 21 for a certain period of time, it is determined that the person is lying down, and the control microcomputer 20 determines that the person is lying down. The transmission of the output of abnormality information (for example, an event code indicating that an abnormality has occurred in the elevator 2) to the monitoring terminal 3 may be blocked, and the output of information regarding a fall may be transmitted.

Although the server processing unit 40 has output the determination result by the image recognition processing unit 220 as character information to the administrator terminal 7 and the technician terminal 8, it may be output as voice information.

Further, the server processing unit 40 may output the determination result by the image recognition processing unit 220 to one of the administrator terminal 7 and the technician terminal 8. For example, by transmitting the possibility of mischief in the car 21 only to the administrator terminal 7, it is possible to call attention to the administrator and suppress interruption of work of a technician corresponding to another elevator.

The remote monitoring system 1 of the above embodiment includes a plurality of elevators, but may include one elevator. Further, although the remote monitoring system 1 includes a plurality of administrator terminals 7 and a plurality of technician terminals 8, it may be provided with one administrator terminal 7 and a plurality of technician terminals 8. A plurality of administrator terminals 7 and one technician terminal 8 may be provided.

Further, the remote monitoring system 1 may include a customer terminal that can be connected to the first server 4. The customer terminal is installed in, for example, a hospital or a nursing home for the elderly. In this case, the server processing unit 40 may output the determination result by the image recognition processing unit 220 to the customer terminal. For example, by transmitting information about a person's fall to a customer terminal installed in a hospital, a nursing home for the elderly, or the like, a nurse, a caregiver, or the like can appropriately respond to the person's fall. In order to perform such transmission, the database 50 may store information about the customer terminal corresponding to the elevator in association with the behavior of a person or an object (for example, contact of the nearest hospital of each elevator). You may remember the destination in association with the information about the fall).

Although the communication system R1 includes a telephone line, as shown in FIG. 7, the communication system R1 may include the Internet instead of the telephone line. For example, the communication system R1 can communicate with the monitoring terminal 3 from the control microcomputer 20 in order via the remote monitoring unit 6 and the Internet, and is controlled from the monitoring terminal 3 via the Internet and the remote monitoring unit 6. It is a communication system capable of communicating with the microcomputer 20. In this case, the communication systems R1, R2, and R3 are partly common (Internet).

Further, although the communication system R1 includes the remote monitoring unit 6, it may not be included. In this case, the control microcomputer 20 is connected to the first server 4 via the Internet.

1 ... remote monitoring system, 2 ... elevator, 20 ... control microcomputer, 200 ... microcomputer processing unit, 21 ... basket, 210 ... camera, 211 ... microphone, 212 ... speaker, 213 ... display, 22 ... image recognition device, 220 ... image Recognition processing unit, 221 ... storage unit, 23 ... processing unit, 24 ... voice recognition device, 25 ... voice guidance device, 26 ... display guidance device, 3 ... monitoring terminal, 4 ... first server, 40 ... server processing unit, 5 ... second server 50 ... database, 6 ... remote monitoring unit, 7 ... manager terminal, 8 ... technician terminal (technician mobile terminal), R1, R2, R3 ... communication line, P1, P2, P3, P C _... coordinates

Claims (2)

The control microcomputer placed in the elevator and
A monitoring terminal connected to the control microcomputer and capable of receiving abnormality information from the control microcomputer,
An image pickup device that images the inside of the elevator car over time,
A processing unit that processes the image captured by the image pickup device, and
A storage unit for storing model data to be compared with an image captured by the imaging device is provided.
The car includes a door that opens and closes
The model data includes a model pattern of at least one person.
The processing unit
The first process of extracting edges from at least two images out of a plurality of images captured by the image pickup apparatus, and
The second process of applying the model pattern of the person to the edge of the image for the person among the edges extracted from the at least two images, respectively.
When the coordinates of the model pattern of the person applied in the second process are at the first specific coordinates, the abnormal information is transmitted from the control microcomputer to the monitoring terminal, and the model pattern of the person is applied. Perform the third process to prevent the transmission of abnormal information due to the position of the person,
The first specific coordinate is in at least one region of the surface of the door and the region of the door in orbit.
A remote monitoring system for elevators that features this. The control microcomputer placed in the elevator and
A monitoring terminal connected to the control microcomputer and capable of receiving abnormality information from the control microcomputer,
An image pickup device that images the inside of the elevator car over time,
A processing unit that processes the image captured by the image pickup device, and
A storage unit for storing model data to be compared with an image captured by the imaging device is provided.
The model data includes a model pattern of at least one object.
The car includes a door that opens and closes
The processing unit
The first process of extracting edges from at least two images out of a plurality of images captured by the image pickup apparatus, and
A second process of applying the model pattern of the object to the edge of the image with respect to the object among the edges extracted from at least two images.
When the coordinates of the model pattern of the object applied in the second process are at the second specific coordinates, the model pattern of the object is applied by transmitting the abnormality information from the control microcomputer to the monitoring terminal. Perform the third process to prevent the transmission of abnormal information due to the position of the object,
The second specific coordinate is in at least one region of the surface of the door and the region of the door in orbit.
A remote monitoring system for elevators that features this.

Images