JP2001019338A - Man conveyor monitoring control device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To precisely detect the presence of passengers on a man conveyor by judging the presence of passengers on the basis of the extraction quantity determined from a plurality of images taken at an interval synchronous to the moving speed of the man conveyor in the monitoring of passengers on the basis of the photographed image of the man conveyor. SOLUTION: This device comprises a camera 1-a for taking the images of a man conveyor 2-a and its getting-on gate and a man conveyor 2-b and its getting-off gate and a camera 1-b for photographing the man conveyor 2-b and its getting-on gate, and the respective taken images are inputted to image processing devices 3-a, 3-b. The images are A/D converted into density data there and stored in an image memory 102. In an image processing part 100, processing such as space sum of product operation, image-to-image operation, binarization, shape conversion, histogram processing, or labeling is performed by use of the stored image data to display the result on a monitor 108 after D/A conversion, and the presence of passengers is judged on the basis of the processing result of the image processing part 100 to control the start and stop of the man conveyor.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a control device for monitoring a conveyor, and more particularly, to a control system for detecting the presence or absence of a passenger on the conveyor and appropriately controlling the operation of the conveyor.

[0002]

2. Description of the Related Art Conventionally, this kind of technology has been disclosed in
Japanese Patent Application Publication No. 0-236575 discloses a technique for controlling the start or stop of an escalator by using a sensor that captures an image of an escalator and its surroundings with a camera, recognizes an image including a passenger in a pattern, and determines whether or not there is a person in a monitoring area. Is disclosed.

[0003] Further, conventionally, there is known a technique in which a sensor is provided near an entrance in a man conveyor with a small traffic volume, the man conveyor is started when a passenger passes, and stopped after a predetermined time.

Further, conventionally, in order to cope with the weak, such as the elderly and children, a button is provided near the entrance, and the speed of the man conveyor is reduced when the passenger presses the button, and the speed returns to the original speed after a certain time. The technology is known.

[0005]

However, in the above-mentioned first prior art, remote monitoring of the moving guide device without starting a staff member to the place where the escalator is installed, and start / stop control can be performed. It is intended to obtain a device, and does not disclose specific means for detecting a passenger by image recognition. Further, in the second related art, the driving time after passing the sensor near the entrance / exit is set so as to move for a sufficient time in consideration of the time during which a normal passenger is on the man conveyor, but the sensor is not used. If there is an unusual use, such as stopping for a while and not riding immediately after passing, there is a problem that the vehicle stops halfway before getting off the man conveyor. In the third related art, the low-speed operation time after the passenger presses the button is set so that the man conveyor moves for a sufficient time in consideration of the time during which the normal passenger is riding. If there is an unusual use, such as stopping after being pressed for a while and then getting in, there is a problem that the man conveyor returns to the original speed while on the man conveyor after a certain period of time.

SUMMARY OF THE INVENTION In view of the above-mentioned various problems, an object of the present invention is to process an image photographed by an image pickup means such as a camera to automatically drive a man conveyor or for a weak person such as an elderly person or a child. It is an object of the present invention to provide a man-conveyor monitoring control device capable of detecting the presence or absence of a passenger on a man-conveyor with high accuracy when performing variable-speed operation.

[0007]

In order to achieve the above object, the present invention has the following measures.

In a man-conveyor monitoring and control device for photographing a man-conveyor and monitoring passengers on the man-conveyor based on the photographed image, the man-conveyor monitoring control device obtains a plurality of images taken at intervals synchronized with the moving speed of the man-conveyor. A passenger presence / absence determining means for determining the presence / absence of a passenger based on the extracted amount.

Further, in a man-conveyor monitoring control device for photographing a man-conveyor and monitoring passengers on the man-conveyor based on the photographed image, a standard multiple of a reference take-in interval based on a moving speed of the man-conveyor is provided. A passenger presence / absence determination means for determining the presence / absence of a passenger based on the amount of extraction obtained from the plurality of images captured at intervals of.

Further, in the man conveyor monitoring control apparatus according to claim 1 or 2, the area setting means for setting an area for detecting the presence or absence of a passenger on the man conveyor, and based on the moving speed or the moving speed of the man conveyor. Means for designating in advance the reference capture interval of the image.

[0011] In one embodiment of the present invention, one of the images for which the amount of extraction is obtained is the latest input image.

[0012] Further, in the re-conveyor monitoring and control apparatus according to claim 1, the passenger presence / absence determining means includes area information or area information of the extracted object obtained from the plurality of images and the vertical and horizontal directions of the extracted object. A means for determining whether or not the passenger is a passenger based on the ratio is provided.

[0013] Further, in the re-conveyor monitoring and control apparatus according to claim 1, the passenger presence / absence determining means determines that the extracted object obtained from the plurality of images is a passenger continuously for a predetermined number of times. When detected, it is determined that there is a passenger.

Further, claim 1 or 2, 3, 4, 5, 6
The above-mentioned man-conveyor monitoring and control device is characterized by comprising a man-conveyor control means for starting or stopping the man-conveyor based on the judgment result of the passenger presence / absence judgment means.

[0015]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS First, a first embodiment of the present invention will be described with reference to FIGS.

FIG. 1 is a diagram showing the overall configuration of a man-conveyor monitoring and control device according to the present embodiment.

In FIG. 1, 1-a and 1-b denote cameras for photographing the entrances and exits of the conveyors 2-a and 2-b, respectively. 2-a and 2-b denote a conveyor such as an escalator. 3-a and 3-b process images taken by the cameras 1-a and 1-b, and
2-b, an image processing device for sending a control signal such as start or stop, and 22 is a man-conveyor control device 21-a, 21
-B, an object detection sensor provided near the entrance, 21-
a, 21-b is a man conveyor control for starting or stopping the man conveyors 2-a, 2-b based on a control signal from the image processing devices 3-a, 3-b and a detection signal from the object detection sensor 22. Device.

The image processing devices 3-a and 3-b include an image processing unit 100 for processing the captured image data,
It exchanges information with the CPU 110 that controls the entire apparatus and processes the processing results in the image processing unit 100, the memory 109 that stores data and processing results related to the entire apparatus, and the man-conveyor control apparatuses 21-a and 21-b. The interface 111 includes a monitor 111 for displaying a processing result of the image processing unit 100, and a mouse 112 for setting a processing area and the like interactively by a human.

The image processing unit 100 includes an A / D converter 101, an image memory 102, and an inter-image operation circuit 103.
, A binarization circuit 104, and a histogram processing circuit 105
, A histogram memory 106 for storing the image projection distribution, density frequency distribution, and the like, and a D / A converter 107
, A spatial product-sum operation circuit 115, and a shape conversion circuit 116
And a labeling circuit 117.

Next, the operation of the man-conveyor monitoring and control device will be described. Here, assuming that the conveyor is a rising conveyor, the camera 1-a is connected to the conveyor 2-a.
The main body, the entrance of the conveyor 2-a, and the conveyor 2
The camera 1-b takes a picture of the exit of
-B Image the entrance of the main body and the conveyor 2-b. Images captured by the cameras 1-a and 1-b are input to the respective image processing devices 3-a and 3-b.

The image processing device 3-a fetches the photographed image, and the A / D converter 101 outputs, for example, 256
The data is converted into gradation density data and stored in the image memory 102. If the cameras 1-a and 1-b are color cameras, the three sets of A / D converters 101 store the R, G, and B color components in the image memory 102. Next, the image processing unit 100 uses the image data stored in the image memory 102 based on a command from the CPU 110,
In the spatial product-sum operation circuit 115, the inter-image operation circuit 103, the binarization circuit 104, the shape conversion circuit 116, the histogram processing circuit 105, and the labeling circuit 117, respectively, the spatial product-sum operation, the inter-image operation, the binarization, and the shape conversion , Histogram processing, labeling (numbering), and the like, and if necessary, converts the processing result, input image, and the like into a video signal via the D / A converter 107 and displays the video signal on the monitor 108.

The CPU 110 uses the data stored in the memory 109 to determine the presence or absence of a passenger based on the processing result of the image processing unit 100, and sends the passenger's presence to the man-conveyor control device 21-a or 21-b. The presence / absence signal is transmitted via the interface unit 111. The man conveyor control devices 21-a and 21-b are connected to the interface unit 1
The start-up or stop control of the conveyors 2-a and 2-b is performed based on a signal sent from the controller 11 and a signal from the object detection sensor 22.

FIG. 2 is a diagram showing the vicinity of a monitoring area monitored by the conveyor control device according to the present embodiment.

In the figure, reference numeral 20 denotes a passenger, 23-L, 2
3-R is a left handrail and a right handrail of the conveyor respectively, 26 is a passenger presence / absence detection area indicated by a hatched area, 27 is a platform of the conveyor,
The floorboard that constitutes the landing area, 28 is the treadboard of the man conveyor, 2
Reference numeral 9 denotes a demarcation line drawn in yellow or the like so as to stand out at the end of the tread plate 28.

In FIG. 1, the center axis of the field of view of the camera is provided between the handrails 23-L and 23-R on both sides of the conveyor, and the vicinity of the entrance and exit of the conveyor is viewed from the camera set above the entrance. FIG.

In order to detect the presence or absence of a passenger, an installer or a supervisor of the man-conveyor monitoring and control device is required to use a mouse 112 or the like in advance to detect the presence or absence of a passenger on the tread plate 28 of the man-conveyor. The passenger presence / absence detection area 26 is set as an appropriate area. The setting of the passenger presence / absence detection area 26 can be performed automatically from the area information of the tread (step) 28 by processing the captured image.

FIG. 3 shows an image processing apparatus 3 according to this embodiment.
It is a figure for explaining the judging method of the presence or absence of a passenger in. FIG. 3A is a diagram illustrating an input image captured by the camera 1 and captured at a predetermined time and stored in the image memory 102, and FIG. 3B is a diagram illustrating a case where a difference process is performed between synchronized input images. FIG. 3C is a diagram illustrating a value image, and FIG. 3C is a diagram illustrating a binary image when a difference process is performed between input images that are not synchronized.

In the figure, 500, 501, 502,
Reference numeral 503 denotes a time t- which is a predetermined image capturing interval.
Input images input to the image memory 102 at 3, t-2, t-1, and t, 504 and 505 are binary images obtained by performing difference processing between synchronized input images, and 506 and 507 are input images that are not synchronized. Is a binary image subjected to the difference processing. Each of the images 504 to 507 is a binary image, in which a white portion represents a value “0” and a black portion represents a value “1”.

FIG. 3 (a) shows that when the current time is t, the passenger 20 moves the tread plate 28 of the man-conveyor with time t-3, time t-2, time t-1, and time t. FIG. 3 schematically shows a state of moving upward substantially synchronously. Further, as shown in FIG. 3B, when the difference processing is performed between the synchronized input images, only the passenger 20 can be detected without being affected by the demarcation line.
As shown in FIG. 3C, when the difference processing is performed between the input images that are not synchronized, a demarcation line is detected in addition to the passenger 20, and the presence or absence of the passenger 20 cannot be determined.

Next, processing in the image processing apparatus 3 according to the present embodiment will be described with reference to FIGS. 1, 3 and 4.

FIG. 4 is a flowchart showing a processing procedure in the image processing apparatus 3. When the image processing apparatus 3 is started in step 200 in FIG.
2. The data in the histogram memory 106 is cleared and initialized. Next, in step 210, the camera 1
The image is taken from. In step 220, the passenger presence detection area 26 is set interactively using the mouse 112 based on the captured image, or the passenger presence detection area 26 is automatically set as described above, and , The moving speed of the conveyor (for example, 30 m / min) or a reference capturing interval (for example, 200 ms, 400 ms, or 800 ms) of an image corresponding to the moving speed is specified in advance.

Here, the time required for the demarcation line of the moving conveyor at 30 m / min to overlap the previous demarcation line is about 800 ms because the distance between adjacent demarcation lines is about 400 mm. A multiple of 100 ms, which is the least common multiple of the repetition time of the video frequency of 60 Hz and the power supply frequency of 50 Hz, is desirable because it is less susceptible to illumination fluctuation due to power fluctuation. Further, the reference capture interval of the image is determined in steps 230 to 300 shown in FIG. 4 or step 630 shown in FIG.
The processing time must be equal to or longer than the processing time of the loop from 690 to 690, and it is desired that the processing time be closest to 1 / n of the required time (for example, about 800 ms) and be a multiple of 100 ms. When the reference capturing interval is reduced, the time interval for determining the presence or absence of a passenger is shortened, but the number of images to be stored before the required time increases.

At step 220, here 400
ms is set as a reference capture interval of the image, these pieces of information are stored in the image memory 102, and monitoring is started. Next, in step 230, as shown in FIG. 3A, the previous time (time t−1; 4) already stored in the image memory 102 is used.
00 ms before) and twice before (time t-2; 800 ms)
The image captured in the previous step) is updated and stored as an image at each time. Then, the input image 503 at the current time t
Is stored in the image memory 102 and smoothed using the spatial product-sum operation circuit 115 to remove noise. Next, at step 240, the image data is fetched two times before (time t-2; 800 ms before) and
The image 501 stored in the inter-image operation circuit 10 is smoothed using the spatial product-sum operation circuit 115 to remove noise.
3, the difference process is performed between the image 501 and the image 503. Thereafter, in step 250, the image is binarized using the binarization circuit 104 to obtain a binary difference image. Then, in step 260, after removing the noise from the obtained difference binary image by the contraction process using the shape conversion circuit 116, the omission due to the overlapping of the objects is performed by the shaping process of expanding the pixel to the outside by 1 to 3 pixels by the expansion process. Fig. 3
As shown in (b), a dilated binary image 505 is obtained. Note that the image 50 is similarly stored at time t-1.
A binary difference image 504 is obtained from the second and image 500.

It should be noted here that if the input image is captured without being synchronized with the moving speed of the conveyor,
As shown in the images 506 and 507 in FIG. 3C, the demarcation line 29 is also detected together with the passenger 20, and it becomes difficult to distinguish between the passenger and noise. It is important to capture In addition, although it was shown that the difference between frames of the input image can remove the adverse effect of the demarcation line, the detection of passengers on the man conveyor requires no background image compared to the background difference processing, Inter-frame difference processing that does not require updating is effective.

Next, in step 270, the obtained image 505 is numbered to each object region using the labeling circuit 117, and a label image (an image having a different density value for each object region) is obtained. Next, in step 280, the label image is input to the histogram processing circuit 105, the density frequency distribution is obtained from the histogram memory 106, and the number of pixels having each density (corresponding to the label number) stored in the histogram memory 106 is obtained. By doing
The area for each object region (label) is obtained. Further, the label image is binarized using each label number as a threshold to obtain a binary image for each object region. The binary image is input to the histogram processing circuit 105, and the x-axis and y-axis projection is performed. By obtaining the distribution, the lengths of the x-axis and y-axis of the circumscribed rectangle of each object region, that is, the width and height of the object region are obtained. From this width and height, as shown in FIG.
The aspect ratio (width / height) of the object area is determined.

Next, in step 290, the presence or absence of a passenger is determined using the area or the area and the aspect ratio of each object area. If there is a passenger, step 300
, A passenger presence signal is sent to the conveyor control device 21-a via the interface unit 111, and the process returns to step 230. On the other hand, if there is no passenger, a passenger absence signal is sent to the conveyor control device 21-a via the interface unit 111, or the process returns to step 230 without sending a passenger presence signal, and the above-described processing is repeated.

Here, in the above determination, for example, if the area is equal to or more than a certain threshold value, or the area is equal to or more than a certain threshold value and the aspect ratio is less than 2, it is determined that there is a passenger instead of noise such as the demarcation line 29. judge.

Further, in order to avoid erroneous detection due to noise, a passenger presence signal is transmitted to the man-conveyor control device 21-a via the interface unit 111 only when a passenger presence state occurs n times in a row. You can also. n is specified by the user in advance with a mouse or the like, or a standard value is set by the apparatus itself.

In this embodiment, the conveyor control device 2
1-a activates the man conveyor when the object detection signal is input from the object detection sensor 22, and thereafter, receives the passenger presence signal from the interface unit 111,
The passenger conveyor is stopped when the passenger presence signal is interrupted or when a passenger absence signal is received. Alternatively, the passenger conveyor is stopped with a certain delay time from when the passenger presence signal is interrupted or when the passenger absence signal is received.

Next, a second embodiment of the present invention will be described with reference to FIG.

Note that the overall configuration of the man-conveyor monitoring and control device according to the present embodiment is the same as that shown in FIG.
2 and the processing procedure in the image processing apparatus 3 of the present embodiment is the same as the flowchart shown in FIG.

FIG. 6 is a diagram showing the vicinity of a monitoring area monitored by the conveyor control and control device according to the present embodiment.

In the figure, reference numeral 30 denotes a passenger presence / absence detection area indicated by a hatched area. The passenger presence / absence detection area 30 is set so as to extend to the floor board 27 that configures the landing and exit of the man conveyor, as compared to the case shown in FIG. 2 of the first embodiment.

This embodiment does not require the object detection sensor 22 provided in the first embodiment, and performs automatic operation and variable speed operation of the man conveyor based only on the processing result of the image obtained from the camera 1. For this purpose, in the present embodiment, the passenger presence / absence detection area 30 is set so as to be enlarged to the floor board 27 that constitutes the landing and exit of the man conveyor.

In this embodiment, the conveyor control device 2
1-a, when the passenger presence signal is input from the interface unit 111, activates the man conveyor, and thereafter, when the passenger presence signal from the interface unit 111 is interrupted, or when the passenger absence signal is received. Stop the conveyor. Alternatively, the passenger conveyor is stopped with a certain delay time when the passenger presence signal is interrupted or when the passenger absence signal is received.

Next, a third embodiment of the present invention will be described with reference to FIGS.

The overall configuration of the man-conveyor monitoring and control device according to this embodiment is the same as that shown in FIG. 1, and this embodiment is different from the first and second embodiments in that the movement of the man-conveyor is different. The difference is that the speed is unknown or the moving speed is variable.

When the moving speed is variable, for example, when the elderly person or child presses a designated button, the man conveyor control devices 21-a and 21-b lower the speed of the man conveyor by inverter control or the like to get on and off. It is conceivable to make it easier to return to the original reference speed when an old man or child gets off the man conveyor. For example, it is conceivable to reduce the reference speed of 30 m / min to a speed of 20 m / min or 15 m / min. In such a case, if processing is performed at the designated capture interval as in each of the above-described embodiments, a displacement of the demarcation line 29 occurs between the two captured images, and this is detected as noise. It is difficult to correctly determine the presence or absence of a passenger.

In order to solve this problem, images up to n times before the reference capture interval (for example, 400 ms) are always stored, these images are updated each time, and the difference result from the image at the current time is compared. Then, the presence or absence of a passenger is determined using the image with the smallest difference result.

FIG. 7 shows an image processing apparatus 3 according to this embodiment.
It is a diagram for explaining a method of determining the presence or absence of a passenger by the
7A shows a state before the passenger 20 gets on the conveyor, FIG. 7B shows a state where the passenger 20 gets on the conveyor, and FIG. 7C shows a state after the passenger 20 gets off the conveyor. Alternatively, it indicates that the passenger has disappeared from the camera view.

Each of the images shown in FIGS. 7A to 7C represents an image before the current time t and each time t−n (n = 1 to 4). The interval is 40
Considering a case where the reference speed is 0 ms and the reference speed is 30 m / min, but the speed is reduced to 15 m / min according to a passenger's instruction, in any of FIGS. 7A to 7C,
In the images at time t and time t-4, demarcation line 2 is used.
9, the position of the demarcation line 29 is shifted to the maximum in the images at the time t and the time t-2, and the position of the demarcation line 29 is shifted in the images at the time t and the time t-1 and the time t-3. It will be slightly off. The large, medium, and small differences indicate the total amount of the area of the object region obtained as a result of the difference processing between the input image at the current time and the input image before each time.

The determination of the presence or absence of a passenger before the passenger 20 gets on the man conveyor in FIG. 7A is based on the case where the difference is different only depending on the amount of deviation of the demarcation line 29, and is not yet obtained in the image at time t. The passenger is not on the conveyor, but the time t and the time t-1, t-2, t-3
Even if the difference processing is performed with each image of the
A large or medium difference amount occurs due to the positional deviation, and it cannot be determined that the passenger is not on board. However, when the difference processing is performed between the image at the time t and the image at the time t-4, the demarcation line 29 overlaps, and the difference amount becomes small. At this time, it can be determined that the passenger 20 is not boarding.

The determination of the presence or absence of the passenger when the passenger 20 is on the man conveyor in FIG. 7B depends on both the displacement amount of the demarcation line 29 and the passenger 20, and the passenger is on the board. Are time t and time t
−1, t−2, t−3, t−4 and the difference processing result in a large or medium difference amount, so it is determined that the passenger is on board regardless of the difference result at any time. can do.

In FIG. 7C, when the passenger 20 gets off the conveyer or disappears from the camera field of view, the determination of the presence or absence of the passenger is based on both the deviation amount of the demarcation line 29 and the deviation amount of the passenger 20. Although the passenger 20 has already descended from the conveyor in the image at time t, the image at time t and the times t-1, t-2, t-3, and t
-4, the difference from the image at the time t-1 or the time t-4 is minimized, but the difference from the image at the time t-1 is the displacement of the demarcation line 29. And there is no difference between the image at time t-4 and the difference between the image at time t-4 and the difference between the medium It is still not possible to determine that the quantity is present and the passenger has got off. However, when the time further elapses, the passenger 20 disappears from the image at the time t-4, and at that time, the difference between the image at the time t and the image at the time t-4 becomes minimum, and it is determined that the passenger has got off. it can. However,
In this case, since it is not possible to determine that the passenger has disembarked until there are no more passengers in the image at time t-4, the passenger presence signal is output slightly longer, but there is no particular problem.

As described above, in any of FIGS. 7A to 7C, it is possible to determine the presence or absence of a passenger using the difference binary image result at the time when the difference amount is the minimum. it can.

FIG. 8 shows an image processing apparatus 3 according to this embodiment.
6 is a flowchart showing a processing procedure in.

First, in step 600, when the image processing apparatus 3 is started, initialization such as clearing of the image memory 102 and the histogram memory 106 is performed, and in step 610, an image is captured from the camera 1. Based on this image, the passenger presence / absence detection area 26 is set interactively using the mouse 112, or as described above, the passenger presence / absence detection area 26 is automatically set by the present apparatus. Next, in step 620, the moving speed of the conveyor (for example, 30 m / min) or an image capturing interval (for example, 400 ms or 800 ms) corresponding to the moving speed is specified in advance, and the information is stored in the memory 109 and monitored. To start. The following processing is performed in the same manner as described above.
Only executed for Next, in step 630, the images that have been captured before each time are updated by sequentially copying them one time before, and the input image at the current time t is newly captured and stored in the image memory 102.
Next, in step 640, the updated time before each time {n × Δt (Δt: image capturing interval, n = 1 to 4)}.
Image of the current image and the input image at the current time
Then, the two images are subjected to difference processing using the inter-image calculation circuit 103, and then binarized using the binarization circuit 104 to obtain a difference binary image. After removing the noise from the obtained difference binary image by the contraction processing using the shape conversion circuit 116, the shaping processing of expanding the pixel to the outside by 1 to 3 pixels by the expansion processing reduces the omission due to the overlapping of the objects. obtain. Further, the obtained image is input to the histogram processing circuit 105, the density frequency distribution is obtained from the histogram memory 106, and the sum of the number of pixels of each density (label number) in the histogram memory 106 is obtained. The sum of the area (the number of pixels) of the object region is obtained. The above processing is performed on the image before each time.

Next, in step 650, the total sum of the areas of the object regions of the n images obtained by the above processing is compared to obtain a difference binary image before the time when the area becomes minimum. In step 660, the obtained difference binary image is numbered for each object region using the labeling circuit 117, and a label image (an image having a different density value for each object region) is obtained. Next, in step 670, the label image is input to the histogram processing circuit 105, the density frequency distribution is obtained from the histogram memory 106, and the number of pixels having each density (corresponding to the label number) stored in the histogram memory 106 is obtained. Thus, the area of each object region (label) can be obtained. Further, the label image is binarized using each label number as a threshold to obtain a binary image for each object region. The binary image is input to the histogram processing circuit 105, and the x-axis and y-axis projection is performed. The distribution is determined, and the lengths of the x-axis and the y-axis of the circumscribed rectangle of the object region, that is, the width and height of the object region are obtained. From this width and height, the aspect ratio (width / height: see FIG. 5) of the object area is obtained. Then, in step 680, the presence or absence of a passenger is determined using the area of each of the object regions or the area and the aspect ratio. If a passenger is present, in step 690, a passenger presence signal is sent to the man-conveyor control device 21-a via the interface unit 111, and the flow proceeds to step 690.
Return to 30. On the other hand, if there is no passenger, a passenger absence signal is sent to the conveyor control device 21-a via the interface unit 111, or the process returns to step 630 without sending a passenger presence signal, and the above-described processing is repeated.

Here, for example, when the area is equal to or more than a certain threshold value, or when the area is equal to or more than a certain threshold value and the aspect ratio is less than 2, it is determined that the vehicle is not a noise such as the demarcation line 29 but a passenger.

As described above, according to the first and second embodiments of the present invention, the difference image between the images captured at the capturing interval synchronized with the moving speed of the man conveyor is processed to reduce the noise. Can be obtained, and the presence or absence of a passenger can be determined with high accuracy.

Further, according to the third embodiment of the present invention, an image obtained at an interval which is a positive multiple of the reference acquisition interval determined from the moving speed or directly specified is stored, and stored before each time. By extracting an object in the area using the image and the current input image, the presence or absence of a passenger can be determined with high accuracy even in a variable-speed man conveyor.

Further, according to the embodiments of the present invention, by extracting an object using the difference image between the captured images, the object can be extracted without being affected by the brightness fluctuation around the man-conveyor. The presence or absence of a passenger can be determined.

Further, according to the invention of each embodiment, the presence / absence of a passenger can be determined simply and with high accuracy by determining that the passenger is a passenger using the area information of the object or the area information and the aspect ratio. Can be.

Further, according to the invention of each embodiment, when an extracted object is continuously detected a predetermined number of times, it is determined that there is a passenger. Can be determined.

[0065]

According to the present invention, image processing is performed between images captured at intervals associated with the moving speed of the man conveyor, so that the presence or absence of a passenger can be determined with high accuracy.

Further, according to the present invention, the image processing is performed between images obtained from the moving speed or at an interval of a positive multiple of the designated reference capturing interval, so that even a variable-speed man-conveyor can handle passengers. Can be determined with high accuracy.

[Brief description of the drawings]

FIG. 1 is a diagram showing an overall configuration of a man-conveyor monitoring and control device according to a first embodiment of the present invention.

FIG. 2 is a diagram showing the vicinity of a monitoring area monitored by a conveyor control device according to the first embodiment of the present invention.

FIG. 3 is an image processing apparatus 3 according to the first embodiment of the present invention.
It is a figure for explaining the judging method of the presence or absence of a passenger in.

FIG. 4 is an image processing apparatus 3 according to the first embodiment of the present invention.
6 is a flowchart showing a processing procedure in.

FIG. 5 is a diagram for explaining an aspect ratio (width / height) of an object area.

FIG. 6 is a diagram illustrating the vicinity of a monitoring area monitored by a conveyor control device according to a second embodiment of the present invention.

FIG. 7 is an image processing apparatus 3 according to a third embodiment of the present invention.
It is a figure for explaining the judging method of the presence or absence of a passenger in.

FIG. 8 is an image processing apparatus 3 according to a third embodiment of the present invention.
6 is a flowchart showing a processing procedure in.

[Explanation of symbols]

 1-a, 1-b Camera 2-a, 2-b Man conveyor 3-a, 3-b Image processing device 21-a, 21-b Man conveyor control device 22 Object detection sensor 23 Handrail 26, 30 Passenger presence / absence Detection area 100 Image processing unit 108 Monitor 109 Memory 110 CPU 111 Interface unit 112 Mouse

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) H04N 7/18 G06F 15/70 410 460E (72) Inventor Kenichi Yamashita 1070 Ma, Hitachinaka City, Ibaraki Pref. (70) Inventor Hisao Chiba 1070 Ma, Hitachinaka-shi, Ibaraki F-term (reference) 3F321 DC01 DC03 EA01 EB07 EC06 5B057 AA19 BA02 CA08 CA12 CA16 CB18 CC01 DB02 DB09 DC03 DC04 DC32 5C054 AA05 CA04 CC03 CH04 ED07 ED17 FC00 FC05 FC12 FC15 HA14 5L096 AA07 BA02 CA04 DA02 EA43 FA37 FA59 FA70 GA08 GA34

Claims (7)

[Claims] 1. A man-conveyor monitoring and control device for photographing a man-conveyor and monitoring passengers on the man-conveyor based on the photographed images, wherein a plurality of images taken at intervals synchronized with a moving speed of the man-conveyor. A passenger presence / absence determining means for determining the presence / absence of a passenger based on the extraction amount obtained from the vehicle. 2. A man-conveyor monitoring and control device for photographing a man-conveyor and monitoring passengers on the man-conveyor based on the photographed image, wherein the reference take-in interval based on a moving speed of the man-conveyor is a multiple of a positive number. A passenger conveyor monitoring and control device comprising: a passenger presence / absence determination means for determining the presence / absence of a passenger based on an extraction amount obtained from a plurality of images taken at intervals. 3. An area setting means for setting an area for detecting the presence or absence of a passenger on a man conveyor, and a means for previously specifying a moving speed of the man conveyor or a reference capturing interval of an image based on the moving speed. 3. The monitoring and control device for a conveyor according to claim 1, wherein: 4. The man-conveyor monitoring and control device according to claim 1, wherein one of the images for obtaining the extraction amount is a latest input image. 5. The passenger presence / absence determination means includes means for determining whether or not a passenger is a passenger based on area information or area information of an extracted object obtained from the plurality of images and an aspect ratio of the extracted object. The man-conveyor monitoring and control device according to claim 1, 2, 3, or 4. 6. The system according to claim 1, wherein said passenger presence / absence determination means determines that there is a passenger when the extracted object obtained from said plurality of images is detected as a passenger continuously for a predetermined number of times. , 3, 4, and 5. 7. A man conveyor control means for starting or stopping a man conveyor based on the judgment result of the passenger presence / absence judgment means. The conveyer monitoring and control device as described in the above.