JP2020027465A - Monitoring device, monitoring system, and program - Google Patents

Abstract

To provide a monitoring device, a monitoring system, and a program which can monitor a plurality of persons to determine whether the persons are not sleeping on their stomach.SOLUTION: In the monitoring system, a processor 30 includes: a setting unit 305 for setting ones of a plurality of persons who are in a sleeping posture to be targets to be monitored by using the result of analyzing images of persons taken by an imaging unit using infrared rays; and a notification unit 308 for issuing a warning when the images show that the targets are in a prone posture. The images show the thermal distribution in the imaging range of the imaging unit. The processor further includes a detection unit 301 for detecting children from the images according to the size of the heat sources in the images.SELECTED DRAWING: Figure 4

Description

  The present invention relates to a monitoring device, a monitoring system, and a program.

  Techniques for monitoring a child's condition are known. For example, in Patent Literature 1, it is determined that an abnormality is detected when the direction of the head detected by analyzing moving image information of an infant is prone or when the body temperature of the infant detected by the body temperature detecting means exceeds a threshold value. It is described that an emergency signal is output.

JP 2008-48819 A

For example, when a monitoring device is installed at the end of a child's bed and only captures an image of one child, one monitoring device can monitor only the status of one child. Particularly, in a facility such as a nursery school or a kindergarten where a plurality of children are present, such a monitoring device is difficult to use.
SUMMARY OF THE INVENTION It is an object of the present invention to simultaneously monitor whether a plurality of persons are sleeping in a prone state.

  The invention according to claim 1, a setting unit that sets a sleeping child among the plurality of persons as a monitoring target by using an analysis result of a plurality of people's images captured by the imaging unit using infrared rays, A monitoring unit that issues a warning when the image indicates that the monitoring target is in a prone state.

  According to a second aspect of the present invention, in the monitoring device according to the first aspect, the image indicates a heat distribution in an imaging range of the imaging unit, and the child is separated from the image by a size of a heat source included in the image. Is further provided.

  According to a third aspect of the present invention, in the monitoring device according to the second aspect, the posture is the sleeping posture according to a height relationship from a reference plane of a plurality of feature points indicating the posture of the child in the image. And a determining unit for determining whether or not the information is correct.

  According to a fourth aspect of the present invention, in the monitoring device according to any one of the first to third aspects, the image indicates a heat distribution of an imaging range of the imaging unit, and the monitoring target is monitored using the image. The apparatus further includes a measurement unit that measures a body temperature, and the notification unit further notifies the warning when an increase amount of the body temperature from a reference body temperature is equal to or greater than a threshold.

  According to a fifth aspect of the present invention, in the monitoring device according to the fourth aspect, the notifying unit changes a method of notifying the warning according to the amount of increase.

  The invention according to claim 6 is the monitoring device according to any one of claims 1 to 5, further comprising a face detection unit that detects the face image of the monitoring target from the image, wherein the notification unit is The warning is issued according to the detection status of the face image.

  According to a seventh aspect of the present invention, in the monitoring device according to the sixth aspect, when the state in which the face image is not detected continues for a set time or more, the notification section notifies the warning.

  According to an eighth aspect of the present invention, in the monitoring device according to any one of the first to seventh aspects, a position specifying unit that specifies a position of the monitoring target in a place where the plurality of people are located, using the image. And the notifying unit further notifies the position.

  The invention according to claim 9 is the monitoring device according to any one of claims 1 to 8, wherein the monitoring target face image is recognized from the image, and the monitoring target is identified based on the recognized face image. The notification unit further notifies the identification information of the monitoring target.

  The invention according to claim 10 is an imaging unit that captures images of a plurality of persons using infrared rays, and sets a child in a sleeping posture among the plurality of persons as a monitoring target using an analysis result of the images. A monitoring system comprising: a setting unit; and a notifying unit that notifies a warning when the image indicates that the monitoring target is in a prone state.

  The invention according to claim 11 is a step of setting, in the computer, a child in a sleeping posture among the plurality of persons as a monitoring target by using an analysis result of a plurality of images of the persons photographed by the imaging unit using infrared rays. And a step of issuing a warning when the image indicates that the monitoring target is in a prone state.

According to the first aspect of the present invention, it is possible to simultaneously monitor whether a plurality of persons are sleeping in a prone state.
According to the second aspect of the present invention, a child can be detected from an image showing a heat distribution.
According to the invention according to claim 3, it is possible to prevent a child who crawls and walks from being erroneously set as a monitoring target.
According to the fourth aspect of the present invention, it is possible to notice an increase in the child's body temperature without using a device for measuring the body temperature of each child.
According to the fifth aspect of the invention, the warning can be notified by a method according to the amount of increase in the child's body temperature.
According to the invention according to claim 6, the monitoring accuracy can be improved as compared with the case where it is monitored whether the subject is sleeping prone regardless of the detection state of the face image.
According to the invention according to claim 7, it is possible to prevent a warning from being issued when the sleeping posture is temporarily in a prone state.
According to the invention according to claim 8, it is possible to quickly cope with a child sleeping in a prone state.
According to the ninth aspect of the present invention, it is possible to quickly cope with a child sleeping in a prone state.
According to the tenth aspect, it is possible to simultaneously monitor whether or not a plurality of persons are sleeping in a prone state.
According to the eleventh aspect, it is possible to simultaneously monitor whether a plurality of persons are sleeping in a prone state.

It is a figure showing an example of monitoring system 1 concerning an embodiment. FIG. 2 is a diagram illustrating an example of a hardware configuration of a terminal device 20. FIG. 3 is a diagram illustrating an example of a hardware configuration of a processing device 30. FIG. 2 is a diagram illustrating an example of a functional configuration of a processing device 30. FIG. 6 is a diagram illustrating an example of a database 331. FIG. 9 is a diagram illustrating an example of a monitoring target list 332. FIG. 2 is a diagram illustrating an example of installation of the monitoring system 1. It is a flowchart which shows an example of the registration processing of a monitoring target. It is a flowchart which shows an example of the monitoring process of prone sleeping. FIG. 7 is a diagram showing an example of a screen 60 displayed on the display unit 26. It is a flow chart which shows an example of monitoring processing of body temperature rise. FIG. 7 is a diagram showing an example of a screen 70 displayed on the display unit 26.

1. Configuration FIG. 1 is a diagram illustrating an example of a monitoring system 1 according to the present embodiment. The monitoring system 1 is a system for monitoring a child's condition in order to prevent sudden infant death syndrome. The “child” here includes an infant and a toddler. As a method of preventing sudden infant death syndrome, for example, it is considered effective to prevent the patient from sleeping in a prone state or to prevent depression heat. The depression fever means a state in which the body temperature rises due to an abnormality in the external environment. The state of the child monitored by the monitoring system 1 includes the child sleeping in a prone state (hereinafter, referred to as “prone sleeping”) and an increase in the body temperature of the sleeping child.

  The monitoring system 1 includes an imaging device 10, a terminal device 20, and a processing device 30. These devices are connected via a communication line 40. The communication line 40 transmits communication between these devices. For the communication line 40, for example, a private network such as a LAN (Local Area Network) may be used.

  The imaging device 10 captures a heat distribution image of a place where a plurality of people are present by using infrared rays. As the imaging device 10, for example, an infrared camera may be used. The heat distribution image is also called thermography and is an image showing the heat distribution in the imaging range. The heat distribution image may be a moving image or a still image.

  FIG. 2 is a diagram illustrating an example of a hardware configuration of the terminal device 20. The terminal device 20 outputs an image or a sound for notifying a warning under the control of the processing device 30. As the terminal device 20, for example, a portable device such as a smartphone or a tablet terminal may be used. The terminal device 20 includes a processor 21, a memory 22, a storage 23, a communication unit 24, an operation unit 25, a display unit 26, and a sound output unit 27. The processor 21 executes various processes by reading the program into the memory 22 and executing the program. The processor 21 may be, for example, a CPU (Central Processing Unit). The memory 22 stores a program executed by the processor 21. For example, a ROM (Read Only Memory) and a RAM (Random Access Memory) may be used as the memory 22. The storage 23 stores various data and programs. For the storage 23, for example, a flash memory may be used. The communication unit 24 is connected to the communication line 40 and performs data communication via the communication line 40. The operation unit 25 is used for operating the terminal device 20. For example, an operation button or a touch sensor may be used for the operation unit 25. The display unit 26 displays various information. As the display unit 26, for example, a liquid crystal display may be used. The sound output unit 27 converts a sound signal into sound and emits the sound toward space. As the sound output unit 27, for example, a speaker may be used.

  FIG. 3 is a diagram illustrating an example of a hardware configuration of the processing device 30. The processing device 30 analyzes the heat distribution image captured by the imaging device 10 and performs a process of monitoring the state of the child using the analysis result. The processing device 30 issues a warning using the terminal device 20 when the child is lying on his / her face or when the body temperature of the sleeping child has risen. For example, a general-purpose computer may be used as the processing device 30. The processing device 30 includes a processor 31, a memory 32, a storage 33, a communication unit 34, an operation unit 35, and a display unit 36. The processor 31 executes various processes by reading the program into the memory 32 and executing the program. For example, a CPU may be used as the processor 31. The memory 32 stores a program executed by the processor 31. For example, a ROM and a RAM may be used as the memory 32. The storage 33 stores various data and programs. For the storage 33, for example, a hard disk drive or a solid state drive may be used. The communication unit 34 is connected to the communication line 40 and performs data communication via the communication line 40. The operation unit 35 is used for operating the processing device 30. For the operation unit 35, for example, a mouse and a keyboard may be used. The display unit 36 displays various information. As the display unit 36, for example, a liquid crystal display may be used.

  FIG. 4 is a diagram illustrating an example of a functional configuration of the processing device 30. The processing device 30 functions as a detection unit 301, an identification unit 302, a position identification unit 303, a determination unit 304, a setting unit 305, a face detection unit 306, a measurement unit 307, and a notification unit 308. These functions are realized by the processor 31 performing an operation or controlling the communication by the communication unit 34 in cooperation with the program stored in the memory 32 and the processor 31 executing the program.

  The detection unit 301 detects a child from a heat distribution image of a place where a plurality of people are captured by the imaging device 10. At this time, it may be determined whether or not a plurality of people are children based on the size of the heat source included in the heat distribution image. The size of the heat source included in the heat distribution image indicates the size of the human body corresponding to the heat source. Children are smaller than adults. Therefore, for example, when the size of the heat source included in the heat distribution image is equal to or smaller than a predetermined size, a child may be detected. The predetermined size may be, for example, a size that allows the person corresponding to the heat source to be considered a child.

  The identification unit 302 recognizes a child's face image from the heat distribution image, and identifies the child based on the recognized face image. The identification using the face image is also called face authentication. This identification may be performed, for example, by using a well-known face recognition technique and collating with a database 331 stored in the storage 33 in advance.

  FIG. 5 is a diagram illustrating an example of the database 331. The database 331 includes face data indicating a child's face image in association with an ID (Identification) for identifying a child. These pieces of information may be registered in advance by, for example, an administrator.

  The position specifying unit 303 specifies the position of each child at a location to be imaged by the imaging device 10 using the heat distribution image. As a method of specifying the position, for example, a method of converting the position coordinates of the heat source corresponding to each child in the heat distribution image into the position coordinates in the real space may be used.

  The determination unit 304 determines whether or not the child's posture is the sleeping posture based on the height relationship from the reference plane of the plurality of feature points indicating the child's posture in the heat distribution image. For example, a head, hands, and feet may be used as these feature points. For example, a floor surface may be used as the reference surface. For the measurement of the height, for example, a distance measurement technique using a known image may be used. When the child is in a sleeping position, the head, hands, and feet of the child are approximately the same height from the floor. Therefore, for example, when the difference between the heights of these feature points is equal to or less than the predetermined difference, the child's posture may be determined to be the sleeping posture. As the predetermined difference, for example, a difference in height at which a child's posture can be regarded as a sleeping posture may be used.

  The setting unit 305 sets the child in the sleeping posture as a monitoring target based on the determination result of the determination unit 304. The setting of the monitoring target may be performed by, for example, adding information indicating a child to be monitored to a monitoring target list 332 stored in the storage 33 in advance.

  FIG. 6 is a diagram illustrating an example of the monitoring target list 332. The monitoring target list 332 includes position information indicating the position of the child in association with the ID for identifying the child.

  The face detection unit 306 detects a face image of a child to be monitored from the heat distribution image. For the detection of the face image, for example, a well-known face recognition technology may be used.

  The measurement unit 307 measures the body temperature of the child to be monitored using the heat distribution image. As a method of measuring the body temperature, for example, a method of measuring the body temperature according to the temperature of the heat source included in the heat distribution image may be used. In this method, among the heat sources included in the heat distribution image, the temperature of a portion corresponding to the body part of the child may be used. This part may be, for example, the chest or the head.

  The notification unit 308 notifies the terminal device 20 of a warning when the detection status of the face image indicates that the child to be monitored is lying prone. The notification unit 308 notifies the terminal device 20 of a warning when the amount of increase in the child's body temperature from the reference body temperature is equal to or greater than a predetermined amount of increase. For example, the initial body temperature may be used as the reference body temperature. The notification of the warning may be realized by, for example, displaying a warning message on the terminal device 20.

2. Operation FIG. 7 is a diagram illustrating an example of installation of the monitoring system 1. In this example, the monitoring system 1 is installed in a facility such as a kindergarten or a nursery school. This facility includes a room 50 where a plurality of children 501 to 506 and a teacher 507 are present, and a room 51 where a teacher such as a gardener is resident. The imaging device 10 is installed in the room 50. The teacher 507 is carrying the terminal device 20. The processing device 30 is installed in the room 51. At the time of the nap, the children 501 to 506 sleep in the room 50. Meanwhile, teacher 507 watches over these children 501-506. However, even during the nap time, some of the children 501 to 506 may not sleep or may fall asleep once but get up.

2.1. Registration Processing FIG. 8 is a flowchart illustrating an example of monitoring target registration processing performed by the processing device 30. The imaging device 10 captures a heat distribution image of the room 50, and sequentially transmits image data indicating the captured heat distribution image to the processing device 30. The registration process is started, for example, when the processing device 30 receives image data from the imaging device 10.

  In step S11, the detection unit 301 searches for a heat source from a heat distribution image (hereinafter, referred to as a “target image”) indicated by the image data received from the imaging device 10. Specifically, a portion having a predetermined search width is scanned from the upper left start point of the target image to search for a heat source having a human body temperature.

  In step S12, it is determined whether the heat source has been detected by the search in step S11. For example, if no one is in the area of the room 50 corresponding to the portion searched in step S11, the determination in step S12 is NO. In this case, the process proceeds to step S20. On the other hand, in the example shown in FIG. 7, when at least one of the children 501 to 506 and the teacher 507 is present in the area of the room 50 corresponding to the portion searched in step S11, the heat source is detected. The determination in S12 is YES. In this case, the process proceeds to the next step S13.

  In step S13, the determination unit 304 determines whether the person corresponding to the heat source is a child or an adult based on the size of the heat source detected in step S12. In the example shown in FIG. 7, for example, when the heat source corresponding to the teacher 507 is detected, the size of the heat source becomes larger than the predetermined size, and thus the determination in step S13 is NO. In this case, the process proceeds to step S20. On the other hand, in the example shown in FIG. 7, for example, when a heat source corresponding to at least one of the children 501 to 506 is detected, the size of the heat source becomes equal to or smaller than a predetermined size, and thus the determination in step S13 is performed. Becomes YES. In this case, the process proceeds to step S14.

  In step S <b> 14, the identification unit 302 recognizes the child's face image, and matches the face data indicating the recognized face image with the database 331 to identify the child. In the example illustrated in FIG. 7, for example, when a heat source corresponding to the child 501 is detected from the target image, the face image of the child 501 is recognized, and the face data indicating the face image and the child included in the database 331 illustrated in FIG. Is compared with the face data. This comparison may be performed using, for example, a feature value extracted from face data. For example, when the similarity between the face data of the child 501 and the face data of the child associated with the ID “001” is higher than the threshold, the child 501 is identified by the ID “001”.

  In step S15, the determination unit 304 determines whether the child is sleeping or awake from the posture of the child. In the example illustrated in FIG. 7, for example, when a heat source corresponding to any of the children 501 to 504 is detected from the target image, since the bodies of the children 501 to 504 are all in the brim, the child is detected from the target image. Although the heads 501 to 504 are detected, the hands and feet are not detected. In this case, since the postures of the children 501 to 504 can be regarded as the sleeping postures, the determination in step S15 is YES. In addition, when the heat source corresponding to the child 505 is detected from the target image, the head, hand, and foot of the child 505 are detected from the target image because the body of the child 505 is coming out of the hanging kamadan. In this case, the height of the head, the height of the hand, and the height of the foot from the floor are measured using the target image. As shown in FIG. 7, when the child 505 is sleeping on a mattress, their heights are substantially the same, so that the difference is less than a predetermined difference. In this case, the determination in step S15 is YES to indicate that the posture of the child 505 is the sleeping posture. As described above, when the determination in Step S15 is YES, the process proceeds to Step S16.

  In step S16, it is determined whether a sleeping child is set as a monitoring target. Specifically, the position specifying unit 303 first specifies the position of the child in the room 50. Subsequently, it is determined whether or not the position information indicating the specified position is included in the monitoring target list 332. When this position information is included in the monitoring target list 332, the determination in step S16 is YES. In this case, the process proceeds to step S20 without performing step S17. On the other hand, when this position information is not included in the monitoring target list 332, the determination in step S16 is NO. In this case, the process proceeds to step S17.

  In step S17, the setting unit 305 sets a sleeping child as a monitoring target. Specifically, position information indicating the position of the child is added to the monitoring target list 332. In the example illustrated in FIG. 7, for example, when the child 501 is not set as the monitoring target, as illustrated in FIG. 6, the ID “001” of the child 501 and the position information (x1, y1) indicating the position of the child 501 include Is added to the monitoring target list 332.

  On the other hand, in the example shown in FIG. 7, for example, when the heat source corresponding to the child 506 is detected from the target image, the child 506 has come out of the brim, and thus the head of the child 506 is detected from the target image in step S15 described above. The part P1, the hand P2, and the foot P3 are detected. In this case, the height of the head P1, the height of the hand P2, and the height of the foot P3 from the floor are measured. When the child 506 is crawling on the floor, the height of the hand P2 and the height of the foot P3 are almost the same, but the height of the head P1 is the height of the hand P2 or the height of the foot P3. Becomes larger than height. Therefore, the difference between the height of the head P1 and the height of the hand P2 or the height of the foot P3 is equal to or larger than a predetermined difference. In this case, the determination in step S15 is NO to indicate that the child 506 is awake. As described above, when the determination in step S15 is NO, the process proceeds to step S18.

  In step S18, it is determined whether the awake child is set as a monitoring target. Specifically, it is determined whether or not the position information indicating the position of the child is included in the monitoring target list 332. If this position information is not included in the monitoring target list 332, it indicates that the child has already been excluded from the monitoring target, and the determination in step S18 is NO. As described above, when the determination in step S18 is NO, the process proceeds to step S20. On the other hand, when this position information is included in the monitoring target list 332, it indicates that the child is still set as the monitoring target, so the determination in step S18 is YES. As described above, when the determination in Step S18 is YES, the process proceeds to Step S19.

  In step S19, the awake child is excluded from the monitoring target. Specifically, the child's ID and position information are deleted from the monitoring target list 332. In the example illustrated in FIG. 7, for example, when the child 506 is set as a monitoring target, the ID “006” of the child 506 and the position information (x6, y6) indicating the position of the child 506 from the monitoring target list 332 illustrated in FIG. And are deleted.

  In step S20, it is determined whether the search for the heat source has been completed up to the right end of the target image. If the search for the heat source has not been completed up to the right end of the target image, the determination in step S20 is NO. In this case, the process proceeds to step S21.

  In step S21, the scanning position is changed to the next scanning position along the main scanning direction from the left end to the right end of the target image. Then, a heat source is searched again from the changed scanning position in the same manner as in step S11 described above.

  When the search for the heat source is completed up to the right end of the target image by repeating the processing of steps S11 to S21 in this way, the determination in step S20 described above becomes YES. In this case, the process proceeds to step S22.

  In step S22, it is determined whether the search for the heat source has been completed up to the lower right end point of the target image. If the search for the heat source has not been completed up to the end point of the target image, the determination in step S22 is NO. In this case, the process proceeds to step S23.

  In step S23, the search start position is changed to the next search start position along the sub-scanning direction from the upper end to the lower end of the target image. Then, from the search start position after the change, the heat source is searched again as in step S11 described above.

  By repeating the processing of steps S11 to S23 in this manner, the sleeping children 501 to 505 are set as the monitoring targets, and the awake children 506 are removed from the monitoring targets. When the search for the heat source is completed up to the lower right end point of the target image, the determination in step S22 described above becomes YES. In this case, the process proceeds to step S24.

  In step S24, it is determined whether or not the monitoring of the state of the child is to be ended. For example, when the monitoring end instruction is not issued, the determination in step S24 is NO. In this case, the process returns to step S11. Then, based on the heat distribution image indicated by the new image data received from the imaging device 10, for example, the processes of steps S11 to S24 described above are performed. On the other hand, for example, when an operation for instructing termination of monitoring is performed using the operation unit 35, the determination in step S24 is YES. In this case, the process ends.

2.2. FIG. 9 is a flowchart illustrating an example of the prone monitoring process performed by the processing device 30. This monitoring process is performed for each child set as a monitoring target. In the above-described registration process, when a child is set as a monitoring target, a prone monitoring process for the child is started. This monitoring process may be performed in parallel with the above-described registration process.

  In step S31, it is determined whether the face detection unit 306 has detected the face image of the child to be monitored. Specifically, the face image is detected based on the position indicated by the position information of the monitoring target child included in the monitoring target list 332. In the example illustrated in FIG. 7, for example, when the child 501 is a monitoring target, a predetermined range is scanned from the position indicated by the position coordinates (x1, y1), and the face image of the child 501 is detected. Will be If the face image of the child 501 has been detected, the determination in step S31 is YES. In this case, the process proceeds to step S35. On the other hand, when the face image of the child 501 is not detected, the determination in step S31 is NO. In this case, the process proceeds to step S32.

  In step S32, it is determined whether the number of times that the face image of the child to be monitored has not been continuously detected (hereinafter, referred to as the “number of non-detections”) is equal to or greater than a set number. For example, when the set number is five, and when the number of non-detection of the face image of the child 501 is four or less, the determination in step S32 is NO. In this case, the process proceeds to step S33.

  In step S33, the number of times of non-detection is incremented by one. For example, if the number of non-detections is one, the number of non-detections is two.

  On the other hand, in step S32 described above, for example, when the number of non-detections of the face image of the child 501 is five, the number of non-detections is equal to or greater than the set number, and the determination in step S32 is YES. In this case, the process proceeds to step S34.

  In step S34, the notification unit 308 performs a process of notifying a warning from the terminal device 20. Specifically, a message warning of prone sleeping is transmitted. In addition, the ID and the position information of the child lying prone are read from the monitoring target list 332 and transmitted together with the message. As a result, the display unit 26 of the terminal device 20 displays the screen 60 corresponding to the message, the ID, and the position information.

  FIG. 10 is a diagram illustrating an example of the screen 60 displayed on the display unit 26. Here, it is assumed that the child 501 is lying prone. In this case, the screen 60 includes a message “I'm lying face down”. The screen 60 includes the name of the child 501 corresponding to the ID “001”. Further, the screen 60 includes an image indicating the position of the child 501 in the room 50 based on the position information (x1, y1) of the child 501.

  In step S35, it is determined whether or not the child to be monitored has already been excluded from the monitoring target. Specifically, it is determined whether or not the ID and the position information of the monitoring target child are included in the monitoring target list 332. If the ID and the position information of the monitoring target child are included in the monitoring target list 332, the determination in step S35 is NO to indicate that the monitoring target child is still set as the monitoring target. In this case, the process returns to step S31. Then, based on the heat distribution image indicated by the new image data received from the imaging device 10, for example, the processes of steps S31 to S35 described above are performed. On the other hand, when the ID and the position information of the monitoring target child are not included in the monitoring target list 332, it indicates that the monitoring target child has already been excluded from the monitoring target, and thus the determination in step S35 is YES. In this case, the process proceeds to step S36.

  In step S36, it is determined whether or not the child to be monitored is set as a monitoring target again. For example, some children tend to get up while sleeping, or tend to get up and sleep again. Even if such a child is excluded from the monitoring target in the above-described registration processing, it is preferable to perform the monitoring processing only once more, just in case. Therefore, the ID of such a child is stored in the storage 33 in advance, and when the ID of the child to be monitored is stored in the storage 33, it is determined that the child is set as the monitoring target again. Is also good. In this case, the determination in step S36 is YES, and the process returns to step S31. Then, for example, based on the heat distribution image indicated by the new image data received from the imaging device 10, the processes of steps S31 to S36 described above are performed. On the other hand, if the child's ID is not stored in the storage 33 or if the child has already been reset as a monitoring target, the determination in step S36 is NO. In this case, this processing ends.

2.3. FIG. 11 is a flowchart illustrating an example of monitoring processing of a rise in body temperature performed by the processing device 30. This monitoring process is performed for each child set as a monitoring target. In the above-described registration processing, when a child is set as a monitoring target, monitoring processing of a rise in body temperature is started for the child. This monitoring process may be performed in parallel with the above-described registration process and the prone monitoring process.

  In step S41, the initial body temperature of the child to be monitored is registered. Specifically, in the measuring unit 307, the body temperature of the child to be monitored is changed according to the temperature of the heat source detected from the target image with reference to the position indicated by the position information of the child to be monitored included in the monitoring target list 332. Measured. Then, the measured body temperature is stored in the storage 33 as an initial body temperature.

  In step S42, similarly to step S35 described above, it is determined whether the child to be monitored has already been excluded from the monitoring target. If the child to be monitored is still set as a monitoring target, the determination in step S42 is NO. In this case, the process proceeds to step S43.

  In step S43, it is determined whether the body temperature of the child to be monitored has risen from the initial body temperature. Specifically, similarly to step S41 described above, the measurement unit 307 measures the current body temperature of the child to be monitored. Subsequently, it is determined whether the current body temperature is higher than the initial body temperature stored in the storage 33. For example, when the current body temperature is equal to or lower than the initial body temperature, it indicates that the body temperature of the child to be monitored has not risen from the initial body temperature, and thus the determination in step S43 is NO. In this case, the process returns to step S42. On the other hand, when the current body temperature is higher than the initial body temperature, it indicates that the body temperature of the child to be monitored has risen from the initial body temperature, and thus the determination in step S43 is YES. In this case, the process proceeds to step S44.

  In step S44, it is determined whether the amount of increase in body temperature is equal to or greater than a threshold. For example, when the threshold value is 3 minutes, and when the difference between the current body temperature and the initial body temperature is smaller than 3 minutes, the amount of increase in the body temperature is less than the threshold value, so the determination in step S44 is NO. In this case, the process proceeds to step S45.

  In step S45, the notification unit 308 performs a process of notifying the terminal device 20 of a weak warning. Specifically, a message warning of an increase in body temperature is transmitted. The ID and the position information of the child whose body temperature has risen are read from the monitoring target list 332 and transmitted together with the message. As a result, a screen 70 corresponding to the message, the ID, and the position information is displayed on the display unit 26 of the terminal device 20.

  FIG. 12 is a diagram illustrating an example of a screen 70 displayed on the display unit 26. Here, it is assumed that the body temperature of the child 501 has increased. In this case, the screen 70 includes a message “body temperature is rising”. Also, the screen 70 includes the name of the child 501 corresponding to the ID “001”. Further, the screen 70 includes an image indicating the position of the child 501 in the room 50 based on the position information (x1, y1) of the child 501.

  On the other hand, if the difference between the current body temperature and the initial body temperature is 3 minutes or more in step S44 described above, the determination in step S44 is YES because the amount of increase in body temperature is equal to or greater than the threshold. In this case, the process proceeds to step S46.

  In step S46, the notifying unit 308 performs a process of notifying a strong warning from the terminal device 20. Specifically, as in step S45 described above, a message warning of an increase in body temperature and the ID and position information of the child whose body temperature has increased are transmitted. In addition, an audio signal indicating a warning sound is transmitted to the terminal device 20. Thereby, in the terminal device 20, a screen 70 shown in FIG. 12 is displayed on the display unit 26, and a warning sound is output from the sound output unit 27.

  In step S47, similarly to step S36 described above, it is determined whether or not the child that was the monitoring target is set as the monitoring target again. If it is determined that this child is to be set as the monitoring target again, the determination in step S47 is YES. In this case, the process returns to step S41. Then, based on the heat distribution image indicated by the new image data received from the imaging device 10, for example, the processes of steps S41 to S47 described above are performed. On the other hand, when it is determined that this child is not set as the monitoring target again, the determination in step S47 is NO. In this case, this processing ends.

  In the embodiment described above, the “processing device 30”, the “imaging device 10”, and the “ID” are used as the “monitoring device”, the “imaging unit”, and the “identification information” according to the present invention, respectively.

  According to the embodiment described above, the imaging device 10 captures a heat distribution image of a room where a plurality of children are present, and monitors the prone sleeping using the heat distribution image. Is also monitored. In addition, since an adult and a child are determined based on the size of the heat source, even when an adult is included in the room, only a child is set as a monitoring target. That is, an adult is prevented from being set as a monitoring target. Furthermore, since the child who does not take a sleeping posture is excluded from the monitoring target, it is possible to prevent a child who crawls and walks from being mistakenly set as the monitoring target. Furthermore, monitoring processing of the rise in body temperature is performed using the heat distribution image captured by the imaging device 10, and a warning is issued when the body temperature of the child is rising. Therefore, a device for measuring the body temperature of each child. Without using, the teacher notices that the child's temperature rises. Further, a weak warning is issued when the amount of increase in the child's body temperature is less than the threshold, and a strong warning is issued when the amount of increase in the child's temperature is equal to or greater than the threshold. In this way, by changing the notification method according to the amount of increase in the body temperature of the child, for example, when the amount of increase in the body temperature is small, a warning is issued in a notification method that does not wake up the sleeping child, and the amount of increase in the body temperature is reduced. If the number is large, a warning may be given by a notification method that is easy for the teacher to notice. Furthermore, since it is determined that the child is lying prone when the face image of the child to be monitored is not detected, compared to monitoring whether the child is lying prone regardless of the detection state of the face image, Monitoring accuracy is improved. Furthermore, since a warning is issued only when the number of times of detection of the face image of the child to be monitored is equal to or greater than the set number, a warning is issued when the sleeping posture is temporarily prone. Is prevented. Further, in the notification of the warning, the position and ID of the target child are also notified, so that the teacher can easily recognize the child lying prone or the child whose body temperature has risen among a plurality of children in the room. Become. As a result, these children are dealt with quickly.

3. Modifications The embodiment described above is an example of the present invention. The invention is not limited to the embodiments described above. For example, the above-described embodiment may be modified as follows. Further, two or more of the following modifications may be combined.

  In the embodiment described above, a plurality of imaging devices 10 may be used. In this case, the plurality of imaging devices 10 may include the imaging device 10 that captures an image using visible light. In this case, one imaging device 10 included in the plurality of imaging devices 10 may capture an image of the entire room 50, and another imaging device 10 may capture an image of a child to be monitored. In this case, one imaging device 10 may capture an image using infrared light, and another imaging device 10 may capture an image using visible light. When the room 50 is large or the number of children in the room 50 is large, it is difficult to recognize the state of each child from the image of the room 50. However, according to this modification, for example, another imaging device 10 may enlarge and photograph a child to be monitored. Therefore, the above-described prone monitoring process using an image photographed by another imaging device 10 may be performed. By performing the monitoring process for the rise in body temperature, the state of the child to be monitored can be easily recognized. As a result, the accuracy of these monitoring processes is improved.

  In the above-described embodiment, when it is determined that a child has occurred, a process of notifying the user using the terminal device 20 may be performed. In this case, similarly to the above-described warning, for example, a message notifying that a child has occurred and the ID and position information of the child may be transmitted from the processing device 30 to the terminal device 20. As a result, a screen corresponding to the information is displayed on the display unit 26 of the terminal device 20. According to this modification, the teacher can easily notice that the child has awakened.

  In the above-described embodiment, the set number of times may be different depending on the characteristics of the monitoring target. For example, the setting number of the child 501 may be five, and the setting number of the child 502 may be three. Further, instead of the number of times of non-detection, the time during which the face image is not detected may be used. In this case, the set time may be used instead of the set number of times.

  In the above-described embodiment, the plurality of feature points indicating the posture of the child are not limited to the head, the hands, and the feet. These features may include, for example, shoulders or hips. That is, the feature point may be any point that indicates a body part indicating the posture of the child.

  In the embodiment described above, the database 331 or the monitoring target list 332 may be stored in an external device different from the processing device 30. This external device is connected to the processing device 30 via a communication line 40. For example, the external device may be a cloud server that provides a data storage service using cloud computing. In this case, the processing device 30 accesses the database 331 or the monitoring target list 332 stored in the external device via the communication line 40, thereby performing the above-described registration processing, prone monitoring processing, and body temperature monitoring processing. May be performed.

  In the above-described embodiment, the method of notifying the warning is not limited to displaying an image or outputting a sound. For example, a warning may be notified by light emission. In this case, the terminal device 20 may include a light emitting unit.

  In the above-described embodiment, the target on which the monitoring system 1 is installed is not limited to a kindergarten or a nursery school. The monitoring system 1 may be installed anywhere where a plurality of children sleep.

  In the above-described embodiment, the monitoring system 1 does not necessarily need to perform both the monitoring process of prone sleeping and the monitoring process of body temperature rise. For example, the monitoring system 1 may perform only one of the monitoring process of prone sleeping and the monitoring process of body temperature rise.

  In the above-described embodiment, the imaging device 10 is provided in an image processing device having a plurality of functions such as a print function, a scan function, a copy function, and a facsimile function, and may be detached from the image processing device and used. .

  The steps of the processing performed in the monitoring system 1 are not limited to the example described in the above embodiment. The steps of this process may be interchanged as long as there is no inconsistency. In addition, the present invention may be provided as a method including steps of processing performed in the monitoring system 1.

  The present invention may be provided as a program executed in the imaging device 10, the terminal device 20, or the processing device 30. This program may be downloaded via a communication line such as the Internet, or may be a computer such as a magnetic recording medium (such as a magnetic tape or a magnetic disk), an optical recording medium (such as an optical disk), a magneto-optical recording medium, or a semiconductor memory. May be provided in a state recorded on a readable recording medium.

1: monitoring system, 10: imaging device, 20: terminal device, 30: processing device, 301: detection unit, 302: identification unit, 303: position identification unit, 304: discrimination unit, 305: setting unit, 306: face detection Section, 307: measurement section, 308: notification section

Claims (11)

A setting unit that sets a child in a sleeping posture to be a monitoring target among the plurality of people, using an analysis result of images of the plurality of people captured by the imaging unit using infrared light,
And a notifying unit for notifying a warning when the image indicates that the monitoring target is in a prone state. The image shows a heat distribution in an imaging range of the imaging unit,
The monitoring device according to claim 1, further comprising a detection unit configured to detect the child from the image based on a size of a heat source included in the image. The monitoring device according to claim 2, further comprising a determination unit configured to determine whether the posture is the sleeping posture based on a height relationship from a reference plane of a plurality of feature points indicating the posture of the child in the image. The image shows a heat distribution in an imaging range of the imaging unit,
Further comprising a measurement unit for measuring the body temperature of the monitoring target using the image,
The monitoring device according to any one of claims 1 to 3, wherein the notification unit further notifies the warning when an increase amount of the body temperature from a reference body temperature is equal to or more than a threshold. The monitoring device according to claim 4, wherein the notification unit changes a method of notifying the warning according to the amount of increase. Further comprising a face detection unit for detecting the face image of the monitoring target from the image,
The monitoring device according to any one of claims 1 to 5, wherein the notification unit notifies the warning according to a detection state of the face image. The monitoring device according to claim 6, wherein the notification unit notifies the warning when the state in which the face image is not detected continues for a set time or more. Using the image, further comprising a position identification unit that identifies the position of the monitoring target in the place where the plurality of people are,
The monitoring device according to any one of claims 1 to 7, wherein the notification unit further notifies the position. The image processing apparatus further includes an identification unit that recognizes the monitoring target face image from the image, and identifies the monitoring target based on the recognized face image,
The monitoring device according to claim 1, wherein the notification unit further notifies the identification information of the monitoring target. An imaging unit that captures images of a plurality of people using infrared light,
Using the analysis result of the image, a setting unit that sets a child in a sleeping posture as a monitoring target among the plurality of people,
And a notification unit that issues a warning when the image indicates that the monitoring target is in a prone state. On the computer,
Using the analysis results of the images of a plurality of people that the imaging unit has photographed using infrared rays, setting a child in a sleeping posture as a monitoring target among the plurality of people,
And a step of issuing a warning when the image indicates that the monitoring target is in a prone state.

Images