JP2019021002A - Watching support system, and control method thereof - Google Patents

Abstract

To provide a technique capable of suppressing unnecessary notification, and of obtaining effects such as load reduction and privacy protection for a system user.SOLUTION: A watching support system for supporting watching of an object person on a bed comprises: an image acquisition unit 110 for acquiring an image photographed by an imaging device 10; a watching determination unit 112 for determining whether or not the object person is watched by another person on the basis of the image in a determination region as not only a partial region of the photographed image but also a region including the bed; a behavior determination unit 113 for determining a state of the object person, on the basis of the photographed image; and an output unit 114 for giving notice according to a determination result obtained in the behavior determination unit. The output unit omits the notice when it is determined by the watching determination unit that the object person is watched by another person.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a technique for supporting watching of a subject on a bed.

  In order to prevent accidents such as falling from a bed, a system for supporting patient watching in a hospital or a nursing facility is known. Patent Document 1 proposes a system that detects a patient from an image (captured image) captured by a camera, determines a patient's action based on the detection result, and performs notification according to the determination result.

JP 2012-071003 A

  As described above, attempts have been made in the past to detect a target person from a captured image and watch the detection result for use in support. However, when the subject is directly watched by others, the notification is unnecessary, but the method of performing notification according to a predetermined operation as in Patent Document 1 does not require such notification. Notifications may occur. The occurrence of an unnecessary notification leads to an increase in the burden on the system user who confirms the notification. Furthermore, in the method of notifying a photographed image in accordance with a predetermined operation, an unnecessary notice may infringe on the privacy of another person appearing in the photographed image.

  The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a technology capable of suppressing unnecessary notifications and obtaining effects such as reduction of burden on a system user and protection of privacy. To do.

  In order to achieve the above object, according to the present invention, it is determined whether or not the subject is watched by others based on the judgment region of the image (captured image) taken by the imaging device. A method is adopted in which notification is omitted when it is determined that the person is watching.

  Specifically, the first aspect of the present invention is a monitoring support system that supports watching of a subject on a bed, and an image acquisition unit that acquires an image captured by an imaging device, and the captured image A monitoring determination unit that determines whether or not the subject is being watched by others based on an image of a determination region that is a part of the region and includes the bed; A state determination unit that determines a state of the subject based on an image; and an output unit that performs notification according to a determination result of the state determination unit. A watch support system is provided in which the notice is omitted when the watch determination unit determines that the watch is being watched by a person.

According to this configuration, it is determined whether or not the subject is being watched by another person from the images of the bed area and the surrounding area. Here, a case is considered in which a subject such as a patient or a care recipient is watched by another person such as a nurse or a caregiver. In this case, the target person is likely to be in the bed, and the other person is likely to be around the bed. Therefore, according to the said structure, it can be determined with high precision whether the subject is watched by others. The notification is necessary for indirectly watching the target person who is not directly watched, and is not necessary when the target person is watched directly by others. According to the above configuration, notification is omitted when it is determined that the subject is being watched by others. As a result, unnecessary notifications can be suppressed, and effects such as reducing the burden on the system user and protecting the privacy can be obtained. For example, it is possible to save the trouble of the system user confirming unnecessary notifications. In addition, it is possible to suppress unnecessary notification of an image of another person who is not involved in the use of the system such as a visitor, and it is possible to protect the privacy of the other person.

  The watching determination unit may determine that the target person is being watched by the other person when two or more persons exist in the determination region. This is because there is a high possibility that the target person and others watching over the target person are included in the two or more persons.

  When the first person existing in the bed and the second person facing the first person are present in the determination area, the watching determination unit determines that the target person is the other person. It may be determined that it is being watched over by. The first person present on the bed is likely to be the target person, and the second person facing the target person (first person) is likely to be the person watching over the target person. is there.

  The watching determination unit determines, as the second person facing the first person, a person whose angle between a face-facing vector and a vector heading for the first person is equal to or less than a threshold value Good. This is because a person whose angle between the face-facing vector and the vector heading to the first person is equal to or smaller than the threshold is likely to face the first person.

  The watching determination unit determines that the target person is watched by the other person when the person performing the watching operation and the person performing the watching operation exist in the determination area. Also good. Because the person performing the watched action is likely to be the target person watched by others, the person performing the watch action is likely to be the other person watching the target person It is.

  The present invention can be understood as a watching support system having at least a part of the above configuration or function. The present invention also includes a monitoring support method or a monitoring support system control method including at least a part of the above processing, a program for causing a computer to execute these methods, or such a program non-temporarily. It can also be understood as a recorded computer-readable recording medium. Each of the above configurations and processes can be combined with each other to constitute the present invention as long as there is no technical contradiction.

  According to the present invention, unnecessary notifications can be suppressed, and effects such as reduction of the burden on the system user and protection of privacy can be obtained.

FIG. 1 is a block diagram schematically showing a hardware configuration and a functional configuration of the watching support system. FIG. 2 is a diagram illustrating an installation example of the imaging apparatus. 3A is an example of a captured image, FIGS. 3B and 3D are examples of watching determination areas, and FIG. 3C is an example of action determination areas. FIG. 4 is a flowchart of the state monitoring process. FIG. 5 is a flowchart of the watching determination process. 6A and 6B are examples of captured images. FIG. 7 is a flowchart of the watching determination process (first modification). 8A and 8B are examples of captured images. FIG. 9 is a flowchart of the watching determination process (second modification).

  The present invention relates to a technique for supporting watching of a subject on a bed. This technology can be applied to a system that automatically detects a getting-away / wake-up action of a patient or a care recipient in a hospital or a care facility, and performs a necessary notification when a dangerous state occurs. This system can be preferably used for, for example, watching support for elderly people, dementia patients, children, and the like.

  Hereinafter, an example of a preferable mode for carrying out the present invention will be described with reference to the drawings. However, the configurations and operations of the devices described in the following embodiments are merely examples, and are not intended to limit the scope of the present invention.

(System configuration)
With reference to FIG. 1 and FIG. 2, the structure of the watching support system which concerns on embodiment of this invention is demonstrated. FIG. 1 is a block diagram schematically illustrating a hardware configuration and a functional configuration of the watching support system 1, and FIG. 2 is a diagram illustrating an installation example of an imaging apparatus.

  The watching support system 1 includes an imaging device 10 and an information processing device 11 as main hardware configurations. The imaging device 10 and the information processing device 11 are connected by wire or wireless. Although only one imaging device 10 is shown in FIG. 1, a plurality of imaging devices 10 may be connected to the information processing device 11.

  The imaging device 10 is a device for capturing a subject image on a bed and capturing image data. As the imaging device 10, a monochrome or color visible light camera, an infrared camera, a three-dimensional camera, or the like can be used. In the present embodiment, the imaging device 10 including the infrared LED illumination 100 and the near-infrared camera 101 is employed in order to allow the subject to be watched even at night (even when the room is dark). As shown in FIG. 2, the imaging device 10 is installed so as to look down on the entire bed 20 from the upper side of the bed 20 toward the foot side. The imaging device 10 captures images at a predetermined time interval (for example, 30 fps), and the image data is sequentially taken into the information processing device 11. Note that the orientation of the imaging device 10 is not particularly limited. The imaging device 10 may be installed in the orientation from the foot side of the bed 20, or the imaging device 10 may be installed in the orientation from the side surface side of the bed 20.

  The information processing apparatus 11 has a function of analyzing image data captured from the imaging apparatus 10 in real time, automatically detecting the rising state and the leaving state of the target person 21 on the bed 20, and notifying when necessary. It is. The information processing apparatus 11 includes an image acquisition unit 110, a detection unit 111, a watching determination unit 112, an action determination unit 113, an output unit 114, an area setting unit 115, and a storage unit 116 as specific functions. The information processing apparatus 11 according to the present embodiment includes a CPU (processor), memory, storage (HDD, SSD, etc.), input device (keyboard, mouse, touch panel, etc.), output device (display, speaker, etc.), communication interface, and the like. Each function of the information processing apparatus 11 described above is realized by the CPU executing a program stored in the storage or memory. However, the configuration of the information processing apparatus 11 is not limited to this example. For example, distributed computing by a plurality of computers may be performed, a part of the above functions may be executed by a cloud server, or a part of the above functions may be executed by a circuit such as an ASIC or FPGA. Also good.

The image acquisition unit 110 has a function of acquiring an image (captured image) captured by the imaging device 10. The image data input from the image acquisition unit 110 is temporarily recorded in a memory or storage, and used for processing such as the detection unit 111, the watching determination unit 112, and the behavior determination unit 113.

  The detection unit 111 analyzes the captured image acquired by the image acquisition unit 110, and detects the watching target person 21 and others (such as a nurse and a caregiver) from the captured image. For example, the detection unit 111 detects a human body or a part thereof (head, face, upper body, etc.). Any method may be used as a method for detecting a human body or a part thereof from a captured image. For example, a classifier using a classic Haar-like feature quantity or HoG feature quantity or an object detection algorithm using a recent Faster R-CNN technique can be preferably used. The detection unit 111 according to the present embodiment detects a head (a portion above the neck; for example, the head 22 of the subject 21) by a discriminator using Haar-like features, and the position of the head is detected as a detection result. Output (x, y) and size (number of vertical and horizontal pixels). The position (x, y) of the head is represented by, for example, image coordinates of the center point of a rectangular frame surrounding the head. The detection unit 111 of the present embodiment outputs the detection result in the position / size of the image coordinate system. However, the detection unit 111 converts the image coordinate system into a spatial coordinate system, A three-dimensional size may be output.

  The watching determination unit 112 is a partial area of the captured image acquired by the image acquisition unit 110 and the monitoring target determination area 112 is an area including the bed 20. This is a function to determine whether or not In the present embodiment, the watching determination unit 112 determines whether or not the target person 21 is watched by another person based on the detection result of the detection unit 111 for the watching determination region. The processing of the watching determination unit 112 (watching determination processing) will be described later.

  The behavior determination unit 113 is a function that determines the state and behavior of the target person 21 based on the captured image acquired by the image acquisition unit 110. In the present embodiment, the behavior determination unit 113 performs a wake-up determination, a get-off determination, and the like based on the detection result of the detection unit 111 for the entire captured image.

  The output unit 114 is a function that performs notification according to the determination result of the behavior determination unit 113. In the present embodiment, the output unit 114 performs a necessary notification when the action determination unit 113 detects the wake-up operation or the leaving operation of the subject 21. The output unit 114 determines whether notification is necessary (for example, notification is performed only in a dangerous state), notification content (for example, message content), notification means (for example, voice) according to the degree of danger of the operation of the target person 21. , Mail, buzzer, warning light), notification destination (for example, nurse, doctor), notification frequency, and the like. In the present embodiment, the output unit 114 omits the notification when the watching determination unit 112 determines that the subject 21 is being watched by others.

  The area setting unit 115 is a function for setting a determination area (a watching determination area or an action determination area) for a captured image captured by the imaging apparatus 10. Since the watching support system 1 is intended to monitor the state of the subject 21 on the bed 20, the determination area is set based on the area of the bed 20 in the captured image. The determination area may be set manually or automatically. In the case of manual setting, the area setting unit 115 may provide a user interface for allowing the user to input a bed area or a determination area itself in the captured image. In the case of automatic setting, the area setting unit 115 may detect a bed area from a captured image by object recognition processing.

3A is an example of a captured image, and FIG. 3B is an example of a watching determination area set for the captured image of FIG. 3A. FIG. 3C is an example of an action determination area set for the captured image of FIG. 3A. In the present embodiment, the area setting unit 115 sets the watching determination area A0 and the action determination areas A1 to A3 with the bed area 30 as a reference. The watching determination area A0 is an area composed of the bed area 30 and its periphery, and corresponds to a range where the target person 21 and the other person can exist when the target person 21 is watched by others. The action determination area A1 is an area set on the head side of the bed 20, and corresponds to a range in which the head 22 of the subject 21 can exist at the time of bedtime (when the subject 21 is sleeping on the bed 20). (Hereinafter referred to as bedded area A1). The action determination area A2 is an area set on the foot side of the bed 20, and corresponds to a range where the head 22 of the subject 21 can exist when getting up (when the subject 21 is in the posture of raising the upper body). (Hereinafter referred to as a wake-up area A2). In the present embodiment, the relative positions and sizes of the determination areas A0 to A2 with respect to the bed area 30 are determined in advance. If the bed area 30 is specified, the ranges of the determination areas A0 to A2 are determined by calculation. And The action determination area A3 is an area other than the action determination areas A1 and A2. At the time of getting out of the bed (when the subject 21 is away from the bed 20), the head 22 of the subject 21 is present in the action determination area A3 (hereinafter referred to as the getting-off area A3).

  In the present embodiment, the watching determination unit 112 determines whether or not two or more head detection positions belong to the watching determination region A0. Then, the watching determination unit 112 determines that the target person 21 is being watched by another person when two or more head detection positions belong to the watching determination area A0. Is determined not to be watched by others.

  Moreover, in this embodiment, the action determination part 113 determines whether the detection position of a head belongs to action determination area | region A1-A3, and classifies the state of the subject person 21. FIG. Here, the case where the head is detected in the awakening area A1 is “awakening state”, the case where the head is detected in the awakening area A2 is “awakening state”, and the case where the head is detected in the awakening area A3 is “awakening” Called “state”. Then, the behavior determination unit 113 detects a state change from the “sleeping state” to the “wake-up state” as a wake-up operation, and detects a state change from the “wake-up state” to the “get-off state” as a wake-up operation.

  The storage unit 116 has a function of storing various data used for processing by the watching support system 1. The storage unit 116 stores at least various parameters (threshold value, etc.) used in wake-up determination, getting-off determination, etc., determination area setting information, past multiple frames of image data or detection results (for calculation of moving speed and moving direction). A storage area for storing is provided.

(Status monitoring process)
An example of the status monitoring process of this system will be described with reference to FIG. The processing flow in FIG. 4 is executed every time one frame image is captured from the imaging apparatus 10.

  First, in step S <b> 40, the image acquisition unit 110 captures a captured image of one frame from the imaging device 10. The acquired captured image is temporarily recorded in the storage unit 116.

  Next, in step S41, the detection unit 111 detects the head from the captured image acquired in step S40. Information on the detected position of the head (xy coordinates) is recorded in the storage unit 116 in association with the information on the shooting time of the captured image acquired in step S40 or the frame number of the captured image.

  In step S42, the watch determination unit 112 performs a watch determination process using the detection result in step S41.

  Next, in step S43, the processing is switched according to the determination result in step S42. If it is determined that the subject 21 is being watched by others, the process proceeds to step S44. If it is not determined that the target person 21 is being watched by another person, the processes of step S44 and step S45 are omitted, and this flowchart is ended.

In step S44, the behavior determination unit 113 determines the state and behavior of the target person 21 using the detection result in step S41. In step S45, the output unit 114 performs notification according to the determination result in step S44.

(Monitoring judgment process)
With reference to FIG. 5, FIG. 6A, and FIG. 6B, an example of the watching determination process in step S42 will be described. FIG. 5 is a flowchart of the watching determination process executed by the watching determination unit 112, and FIGS. 6A and 6B are examples of captured images acquired by the image acquisition unit 110.

  First, in step S50, the watching determination unit 112 determines whether two or more heads are detected in the watching determination region A0. If two or more heads are detected in the watching determination area A0, the process proceeds to step S51. If only one head is detected in the watching determination area A0, the process proceeds to step S52. Processing proceeds.

  In step S <b> 51, the watching determination unit 112 determines that the target person 21 is watched by another person (watching determination).

  In step S <b> 52, the watching determination unit 112 determines that the target person 21 is not watched by others (no watching watching determination).

  Here, consider a case where the captured image 60 of FIG. 6A is acquired in step S40. In this case, in step S41, only the head 61 of the subject 21 is detected as the head in the watching determination area A0. Therefore, it is determined that the target person 21 is not watched by others (step S52), and notification is made according to the state and behavior of the target person 21 (steps S44 and S45).

  Next, consider a case where the captured image 62 of FIG. 6B is acquired in step S40. In this case, in step S41, the head 61 of the subject 21 and the head 63 of another watching the subject 21 are detected as heads in the watching determination area A0. Therefore, it is determined that the target person 21 is being watched by others (step S51), and the notification in step S45 is omitted.

  As described above, according to the present embodiment, it is determined whether or not the subject is being watched by others from the images obtained by capturing the bed area and the surrounding area. Here, a case is considered in which a subject such as a patient or a care recipient is watched by another person such as a nurse or a caregiver. In this case, the target person is likely to be in the bed, and the other person is likely to be around the bed. Therefore, according to the said structure, it can be determined with high precision whether the subject is watched by others.

  Specifically, it is determined that the target person is watched by others only when there are two or more persons in the watch determination area. Since there is a high possibility that the target person and others watching over the target person are included in two or more persons, this configuration ensures that the target person is watched over by the other person with high accuracy. Can be detected. Furthermore, when two or more persons are captured in the captured image, the state of the other person may be erroneously detected as the state of the target person. In the present embodiment, such erroneous detection is suppressed. You can also.

  The notification is necessary for indirectly watching the target person who is not directly watched, and is not necessary when the target person is watched directly by others. According to this embodiment, notification is omitted when it is determined that the subject is being watched by others. As a result, unnecessary notifications can be suppressed, and effects such as reducing the burden on the system user and protecting the privacy can be obtained. For example, it is possible to save the trouble of the system user confirming unnecessary notifications. Moreover, it can suppress that an image of others is notified unnecessarily, and can protect others' privacy.

<Others>
The above description of the embodiments is merely illustrative of the present invention. The present invention is not limited to the specific form described above, and various modifications are possible within the scope of the technical idea. For example, in the above embodiment, an example in which the trapezoid watching determination area A0 (FIG. 3B) is set has been described, but the shape and size of the watching determination area A0 are not particularly limited. For example, as shown in FIG. 3D, a hexagonal watching determination area A0 may be set.

  Further, the flowchart of the watching determination process is not limited to the flowchart of FIG. Below, the modification of the watching determination process is demonstrated.

(First modification)
With reference to FIG. 7, FIG. 8A, and FIG. 8B, a first modification of the watching determination process will be described. FIG. 7 is a flowchart of the watching determination process executed by the watching determination unit 112, and FIGS. 8A and 8B are examples of captured images acquired by the image acquisition unit 110.

  First, in step S70, the watching determination unit 112 determines whether two or more heads are detected in the watching determination region A0. If two or more heads are detected in the watching determination area A0, the process proceeds to step S71. If only one head is detected in the watching determination area A0, the process proceeds to step S75. Processing proceeds.

  In step S <b> 71, the watching determination unit 112 detects a face from the watching determination region A <b> 0 of the captured image using the captured image acquired by the image acquisition unit 110. Basically, the face is detected in the area where the head is detected. However, in the area such as the back of the head, since the face is not shown, the head is detected, but the face is not detected.

  Next, in step S72, the watching determination unit 112 determines whether or not one or more faces are detected in step S71. If one or more faces are detected, the process proceeds to step S73. If no face is detected, the process proceeds to step S75.

  In step S73, the watching determination unit 112 monitors the first person existing on the bed 20 and the second person facing the first person based on the detection results of steps S41 and S72. It is determined whether or not it exists in the determination area A0. Here, since it is considered that the first person is watched by the second person, hereinafter, the first person will be described as “watched person” and the second person will be described as “watcher”. . If there is a watched person and a watcher, the process proceeds to step S74, and if not, the process proceeds to step S75.

  In step S <b> 74, the watching determination unit 112 determines that the target person 21 is being watched by others (determination with watching).

  In step S <b> 75, the watching determination unit 112 determines that the target person 21 is not watched by another person (no-watching determination).

  Here, consider a case where the captured image 80 in FIG. 8A is acquired in step S40. In this case, in step S41, the head 81 of the target person 21 and the head 82 of another person who does not watch the target person 21 are detected as heads in the watching determination area A0. In step S71, the other person's face 83 is detected.

Thereafter, in step S73, the following processing is performed. First, the watch determination unit 112
Determines the head 81 detected in the bed 20 as the head of the watched person. Next, the watching determination unit 112 calculates a vector 84 of the direction of the face 83 and a vector 85 from the face 83 (head 82) to the head 81. Then, the watching determination unit 112 determines whether or not an angle θ1 (≦ 180 degrees) formed by the vector 84 and the vector 85 is equal to or less than a threshold value. The threshold is an angle for determining whether or not the person being watched is facing, for example, 45 degrees.

  Since the angle θ1 is larger than the threshold value (45 degrees), the watching determination unit 112 determines the person of the face 83 as a person who is not facing the watched person and not the watcher. That is, the watching determination unit 112 determines that the watched person exists in the watching determination area A0, but does not exist in the watching determination area A0. Therefore, it is determined that the target person 21 is not watched by others (step S75), and notification is made according to the state and behavior of the target person 21 (steps S44 and S45).

  Next, consider a case where the captured image 86 of FIG. 8B is acquired in step S40. In this case, in step S <b> 41, the head 81 of the subject 21 and the head 87 of the other watching the subject 21 are detected as the head in the watching determination area A <b> 0. In step S71, the other person's face 88 is detected.

  Thereafter, in step S73, the following processing is performed. First, the watching determination unit 112 determines the head 81 detected in the bed 20 as the head of the watched person. Next, the watching determination unit 112 calculates a vector 89 of the direction of the face 88 and a vector 90 from the face 88 (head 87) to the head 81. Then, the watching determination unit 112 determines whether or not an angle θ2 (≦ 180 degrees) formed by the vector 89 and the vector 90 is equal to or less than a threshold value.

  Since the angle θ2 is equal to or smaller than the threshold value (45 degrees), the watching determination unit 112 determines the person of the face 88 as a watching person. That is, the watching determination unit 112 determines that the watched person and the watching person exist in the watching determination area A0. Therefore, it is determined that the target person 21 is being watched by others (step S74), and the notification in step S45 is omitted.

  As described above, according to the first modification, the watched person (first person) existing in the bed and the watcher (second person) facing the watched person are watching. Only when it exists in the determination area, it is determined that the subject is being watched by others. There is a high possibility that the watched person existing in the bed is a target person, and the watch person facing the target person (watched person) is likely to be a person watching the target person. Even if the other person is near the target person, it is difficult to say that the other person is watching over the target person when the other person is not facing the target person. Therefore, according to this configuration, it can be determined with higher accuracy whether or not the subject is being watched by others.

  Further, according to the first modification, a person whose angle formed by the face-facing vector and the vector heading toward the watched person is equal to or smaller than the threshold is determined as the watcher. There is a high possibility that a person whose angle between the face-facing vector and the vector heading to the watched person is equal to or less than the threshold is facing the watched person. Therefore, according to this configuration, a watcher can be detected with high accuracy.

(Second modification)
With reference to FIG. 9, a second modification of the watching determination process will be described. FIG. 9 is a flowchart of the watching determination process executed by the watching determination unit 112.

First, in step S90, the watching determination unit 112 determines whether two or more heads are detected in the watching determination region A0. If two or more heads are detected in the watching determination area A0, the process proceeds to step S91. If only one head is detected in the watching determination area A0, the process proceeds to step S94. Processing proceeds.

  In step S91, the watching determination unit 112 uses the captured image acquired by the image acquisition unit 110 to perform the watching operation with the watching operator performing the watching operation from the watching determination region A0 of the captured image. Detects the watch operator who is performing. The actions to be watched are actions such as assistance for getting up and sleeping, assistance for meals, assistance for changing clothes, and actions to watch are actions such as assistance for getting up and sleeping, assistance for meals, assistance for changing clothes, and the like. The watched person and the watch person are detected by, for example, an object detection algorithm using a classifier using HoG feature and a technique based on Faster R-CNN.

  Next, in step S92, the watching determination unit 112 determines whether or not both the watching operator and the watching operator are detected in step S91. If both the watched operator and the watch operator are detected, the process proceeds to step S93; otherwise, the process proceeds to step S94.

  In step S <b> 93, the watching determination unit 112 determines that the subject 21 is watched by another person (watching determination).

  In step S94, the watching determination unit 112 determines that the subject 21 is not being watched by others (no watching determination).

  As described above, according to the second modification, the target person is the other person only when the person performing the watching operation and the person performing the watching operation exist in the watching determination area. It is determined that it is being watched by. A person who is performing an action to be watched is likely to be a target person being watched by another person, and a person who is performing the action to be watched is likely to be another person watching the target person. Even if the other person is near the target person, it is difficult to say that the other person is watching the target person when the other person is not performing the watching operation. Therefore, according to this configuration, it can be determined with higher accuracy whether or not the subject is being watched by others.

1: Watching support system 10: Imaging device 11: Information processing device 110: Image acquisition unit 111: Detection unit 112: Watching determination unit 113: Action determination unit 114: Output unit 115: Area setting unit 116: Storage unit 100: Infrared LED Illumination 101: Near-infrared camera 20: Bed 21: Target person 22: Head 30: Bed area A0: Watching determination area A1: Bed area (behavior determination area) A2: Wake-up area (behavior determination area) A3: Bed leaving area ( Action judgment area)
60: Captured image 61: Head 62: Captured image 63: Head 80: Captured image 81: Head 82: Head 83: Face 84: Vector 85: Vector 86: Captured image 87: Head 88: Face 89: Vector 90: Vector θ1: Angle θ2: Angle

Claims (7)

A monitoring support system that supports watching of a target person on a bed,
An image acquisition unit that acquires an image captured by the imaging device;
A watching determination unit that determines whether or not the subject is watched by another person based on an image of a determination region that is a partial region of the captured image and that includes the bed; ,
A state determination unit that determines the state of the subject based on the captured image;
An output unit that performs notification according to the determination result of the state determination unit;
Have
The monitoring support system, wherein the output unit omits the notification when the watching determination unit determines that the target person is being watched by the other person. The monitoring support system according to claim 1, wherein the watching determination unit determines that the target person is watched by the other person when two or more persons exist in the determination region. . When the first person existing in the bed and the second person facing the first person are present in the determination area, the watching determination unit determines that the target person is the other person. The watching support system according to claim 1, wherein it is determined that the watch is being watched by the user. The watching determination unit determines, as the second person facing the first person, a person whose angle between a face-facing vector and a vector heading for the first person is equal to or less than a threshold value The watching support system according to claim 3, wherein: The watching determination unit determines that the target person is watched by the other person when the person performing the watching operation and the person performing the watching operation exist in the determination area. The monitoring support system according to claim 1, wherein: A method for controlling a watching support system that supports watching a subject on a bed,
Obtaining an image taken by an imaging device;
Determining whether or not the subject is watched by others based on an image of a determination region that is a partial region of the captured image and that includes the bed;
Determining the state of the subject based on the captured image;
Performing notification according to the determination result of the state of the target person;
Have
The control method of the watching support system, wherein the notification is omitted when it is determined that the target person is watched by the other person.   The program for making a computer perform each step of the control method of the monitoring assistance system of Claim 6.

Images