Nurse call system, and state determination system

Abstract

To provide a nurse call system which can detect the state change of a patient with high accuracy based on a photographed image of a camera independently of an orientation of a bed.SOLUTION: A nurse call system comprises: a nurse call slave unit; a nurse call master unit; a camera which images a patient on a bed from above the bed; and a state determination unit which analyzes a photographed image of the camera to detect the state change of the patient. The state determination unit detects an orientation of the bed on the basis of the photographed image, detects the state change of the patient in a first mode when the bed is in a vertical orientation, and detects the state change of the patient in a second mode different from the first mode when the bed is in a horizontal orientation. The nurse call master unit has a notification unit which executes a notification operation by receiving determination that the state change of the patient has occurred.SELECTED DRAWING: Figure 5

Description

Technical Field

[0001] The present invention relates to a nurse call system and a state determination system.

Background Art

[0002] When a patient or care recipient on a bed attempts to get up or leave the bed, there is a risk of falling or toppling from the bed. Therefore, in Patent Document 1 and Patent Document 2, when a patient on a bed is imaged by a camera and a state where the patient has raised the upper body or a state where the patient has left the bed is detected from the captured image, a warning state generation signal is output from the corridor light to the nurse call master unit, and a system that displays the patient video on the display unit of the nurse call master unit is disclosed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Patent Document 3

Non-Patent Documents

[0004]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Generally, hospital beds are arranged vertically with the short side on the patient's head side along the wall of the ward. In Patent Document 1, a camera for imaging the patient is installed above the bed arranged with the patient's head side along the wall of the ward, specifically above the patient's head. And in Patent Document 2, when analyzing the video based on the captured image of the camera, a specific area for determining the patient's getting out of bed is set within the angle of view of the camera, and it is determined that getting out of bed has occurred when the patient moves out of the specific area. By the way, in a hospital, there is a desire to arrange the bed horizontally with the side of the bed along the wall. In the configurations of Patent Document 1 and Patent Document 2, since they are configured to determine the patient's state when the bed is arranged vertically, it was not possible to correctly determine the patient's state when the bed is horizontal.

[0006] Therefore, an object of the present invention is to provide a nurse call system and a state determination system that can detect changes in the patient's state with high accuracy based on the captured image of the camera regardless of the orientation of the bed.

Means for Solving the Problems

[0007] To achieve the above object, the nurse call system of the present invention is a nurse call system having a nurse call sub-unit installed on the bed for the patient to call a nurse and a nurse call main unit installed at the nurse station to respond to the call by the nurse call sub-unit, a camera for imaging the patient on the bed from above the bed, and a state determination unit that analyzes the captured image of the camera to detect changes in the state of the patient, and is provided with The state determination unit detects the orientation of the bed based on the captured image, and when the bed is vertical, detects changes in the state of the patient in the first mode, When the bed is in the lateral position, the state change of the patient is detected in a second mode different from the first mode. configured as The nurse call master unit has a notification unit that executes a notification operation upon receiving a determination that the state change has occurred.

[0008] According to this configuration, regardless of the orientation of the bed, the state change of the patient can be detected with high accuracy based on the captured image of the camera. Thereby, it is possible to prevent the patient from falling or toppling from the bed.

[0009] Also, in the nurse call system of the present invention, The state change of the patient may include at least one of a state in which the patient raises the upper body, a state in which the patient assumes an upright sitting position, a state in which the patient leaves the bed, and a state in which the patient removes the bed railing.

[0010] By detecting the state change of the patient as described above, the nurse can appropriately grasp the dangerous behaviors that may lead to the patient falling or toppling from the bed.

[0011] Also, in the nurse call system of the present invention, The state determination unit In the first mode, a first specific area is set as a specific area for detecting the state change of the patient within the angle of view of the camera, and in the second mode, a second specific area different from the first specific area is set. When the patient moves out of the first specific area or the second specific area, it is determined that the patient has left the bed. configured as The nurse call master unit may execute the notification operation upon receiving a determination that the patient has left the bed.

[0012] According to this configuration, by changing the range of the specific area according to the orientation of the bed, it is possible to suppress false detection while maintaining the detection of the state change of the patient with high accuracy.

[0013] In addition, in the nurse call system of the present invention, the nurse call master unit may further include a setting unit capable of changing the first specific area and the second specific area.

[0014] According to this configuration, by appropriately changing the first specific area and the second specific area according to various situations such as the attributes of the patient and the shape of the bed, false detection can be further suppressed.

[0015] In addition, the nurse call system of the present invention a mobile terminal carried by the nurse to respond to a call from the nurse call slave unit, a communication control means for transmitting the captured image to the mobile terminal upon receiving a determination that the state change has occurred, may further be provided.

[0016] According to this configuration, even if the nurse is not at the nurse station, the nurse can be notified of the patient's dangerous behavior, so that the nurse can take appropriate measures.

[0017] In addition, in order to achieve the above object, the state determination system of the present invention a camera for imaging a person on the bed from above the bed, a state determination unit that analyzes the captured image of the camera and detects a state change of the person, a notification unit that executes a notification operation upon receiving the detection of the state change, is provided with the state determination unit detects the orientation of the bed based on the captured image, when the bed is in the vertical orientation, detects the state change of the person in the first mode, when the bed is in the horizontal orientation, detects the state change of the person in a second mode different from the first mode, is configured as such.

[0018] According to this configuration, regardless of the orientation of the bed, it is possible to detect the getting-out-of-bed movement of a person on the bed with high accuracy based on the captured image of the camera.

Effects of the Invention

[0019] According to the present invention, it is possible to provide a nurse call system and a state determination system capable of detecting changes in the state of a patient with high accuracy based on the captured image of a camera regardless of the orientation of the bed.

Brief Description of the Drawings

[0020]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Modes for Carrying Out the Invention

[0021] Hereinafter, the nurse call system according to the present invention will be described with reference to the drawings.

[0022] FIG. 1 is a configuration diagram showing an example of a nurse call system 100 according to the present invention. As shown in FIG. 1, the nurse call system 100 includes a nurse call sub-unit 1 installed for each bed in a hospital room for a patient to call a nurse and communicate, a corridor light 2 installed at the entrance and exit of each hospital room and including an indicator light 2a for notifying the occurrence of a call from a patient and a patient name display unit 2b, a nurse call master unit 3 installed at a nurse station for receiving and responding to a call from a patient, and a controller 4 for controlling communication between devices. The nurse call system 100 further includes a camera 5 installed for each bed for imaging a patient, a mobile terminal 6 carried by a nurse for responding to a call from a patient, and a switch 7 for managing communication of the mobile terminal 6 via a base station 8.

[0023] The corridor light 2, the nurse call master unit 3, the controller 4, the camera 5, etc. are each connected to a LAN via a HUB 10, and the nurse call sub-unit 1 is connected to the corridor light 2 for each hospital room via a transmission line L1. Also, the switch 7 is connected to the controller 4 via a transmission line L2.

[0024] The nurse call sub-unit 1 has a call button 1a and a plate sub-unit 1b installed on a wall surface. The plate sub-unit 1b includes a connection part of the call button 1a and a communication part for communicating with a nurse.

[0025] FIG. 2 is a schematic diagram showing the arrangement of the camera 5. As shown in FIG. 2, the camera 5 is installed above the bed 9, specifically on the upper wall surface above the head of the patient M lying prone on the bed 9, and is installed to image around the head of the patient.

[0026] FIG. 3 is a functional block diagram of the camera 5. As shown in FIG. 3, the camera 5 includes a camera CPU 21 for controlling the camera 5, a state determination unit 22 for determining the state of a patient from a captured image, a storage unit 23 for storing various information, an imaging unit 25, an illumination unit 26, and a communication interface (communication IF) 24 for connecting to other nurse call devices and a HUB 10 via a LAN.

[0027] The camera CPU 21 is constituted by, for example, an electronic control unit (ECU: Electronic Control Unit). The electronic control unit includes a microcontroller including a processor and a memory, and other electronic circuits (for example, transistors, etc.). The processor is, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), and / or a GPU (Graphics Processing Unit). The memory includes a ROM (Read Only Memory) in which various control programs (for example, artificial intelligence (AI) programs, etc.) are stored, and a RAM (Random Access Memory) in which various control data are temporarily stored. The processor is configured to expand a program specified from various control programs stored in the ROM onto the RAM and execute various processes in cooperation with the RAM.

[0028] The state determination unit 22 grasps the bed area and detects the orientation of the bed from the captured image captured by the imaging unit 25. As a method for grasping the bed area, for example, the bed area grasping method disclosed in Patent Document 3 may be used, or the method for estimating the bed position by machine learning in Non-Patent Document 1 may be used.

[0029] Further, the state determination unit 22 detects changes in the patient's state in a plurality of modes according to the orientation of the bed. The change in the patient's state is determined by extracting the shape of the patient based on the captured image. As an algorithm for extracting the shape of the patient, for example, a known moving object detection method, a discrimination method using feature amounts by SIFT (Scale Invariant Feature Transform), or SURF (Speeded-Up Robust Features), or Deep Learning may be used. Alternatively, the state determination unit 22 may determine a change in the patient's state by detecting information regarding the human skeleton of the patient reflected in the image captured by the camera 5. Specifically, the state determination unit 22 estimates the skeleton and joints of the patient based on the captured image. As a method for estimating the skeleton and joints, for example, existing skeleton tracking technologies can be used. Note that the state determination unit 22 may estimate only one of the skeleton and joints of the target person as skeleton information.

[0030] The storage unit 23 stores learning data, setting values, etc. as a database for determining the state of the patient. In the example of FIG. 3, the state determination unit 22 and the storage unit 23 are provided separately from the camera CPU 21, but the camera CPU 21 may be configured to have the functions of the state determination unit 22 and the storage unit 23.

[0031] The imaging unit 25 is composed of, for example, a camera module provided with a filter that also transmits infrared rays. The illumination unit 26 is composed of, for example, a light-emitting element such as an infrared LED.

[0032] As shown in FIG. 1, the nurse call master unit 3 includes a handset and a call unit 3a having a sound notification unit for communicating with and broadcasting to patients, a display unit 3b for displaying various types of information, and a board unit 3c on which patient information displays M of individual patients are listed. The display unit 3b uses, for example, a 7-inch liquid crystal monitor and is arranged near the call unit 3a.

[0033] FIG. 4 shows a functional block diagram of the main part of the nurse call master unit 3. As shown in FIG. 4, the nurse call master unit 3 includes a master unit CPU 31 that controls the entire nurse call master unit 3, a video processing unit 32, a touch panel 33 as an operation unit assembled to the display unit 3b, an information storage unit 35, an audio processing unit 37, a notification lamp 38, and a communication interface (communication IF) 39.

[0034] The image processing unit 32 controls the image or video to be displayed on the display unit 3b. Specifically, the image processing unit 32 processes the video of the patient M on the bed captured by the camera 5 and generates a display image to be displayed on the display unit 3b.

[0035] The touch panel 33 can receive operations by the nurse on the display unit 3b. The touch panel 33 functions as, for example, a setting unit 34 capable of setting a predetermined range on the bed detected by the state determination unit 22, or a setting unit 34 capable of changing the display range of the patient image displayed on the display unit 3b.

[0036] The information storage unit 35 stores information regarding the correspondence between the nurse call sub-unit 1 and the camera 5, various setting information, and further patient videos, etc. Specifically, the information storage unit 35 stores a correspondence table between the nurse call sub-unit 1 and the bed number, a correspondence table between the nurse call sub-unit 1 and the patient, a responsible nurse table, patient information such as the patient's name and gender, a correspondence table between the nurse call sub-unit 1 and the camera 5, and a predetermined range on the bed set by the setting unit 34, etc.

[0037] The voice processing unit 37 processes the voice signal that is announced by the communication unit 3a or input from the communication unit 3a. The notification lamp 38 is provided on the board unit 3c and emits light to notify the calling source. The communication IF 39 is an interface for LAN connection with other nurse call devices.

[0038] Regarding the operation of the nurse call system 100 configured as described above, with reference to FIG. 5, it will be described in detail below. Note that the operation in which the corridor lamp 2 performs a notification operation in response to the call operation of the nurse call sub-unit 1 and the nurse call main unit 3 or the mobile terminal 6 responds is the same as the conventional one, so the description is omitted, and the description will be centered on the "watching setting" that operates the state determination unit 22. FIG. 5 is a flowchart for executing the watching operation in the present embodiment. Note that the order of each process constituting the flowchart described below is arbitrary as long as there is no contradiction or inconsistency in the processing content. Also, the processing executed by each device may be executed by other devices as long as there is no contradiction.

[0039] As shown in FIG. 5, first, a nurse performs a predetermined operation on the touch panel 33 to set the start of the monitoring operation for an arbitrary patient (step S1). In response to the monitoring setting in step S1, the master unit CPU 31 keeps the camera 5 associated with the monitored patient in the imaging state at all times and activates the state determination unit 22 (step S2).

[0040] Next, the activated state determination unit 22 detects the bed area based on the learning data stored in the storage unit 23 for the video imaged by the imaging unit 25 (step S3). FIG. 6 is a diagram showing an imaging video C1 in a state where the bed 9 is arranged vertically with respect to the camera 5, and FIG. 7 is a diagram showing an imaging video C2 in a state where the bed 9 is arranged horizontally with respect to the camera 5.

[0041] Next, the state determination unit 22 determines whether the bed 9 is vertical based on the bed area detected in step S3 (step S4). The determination of whether the bed 9 is vertical is made based on, for example, the aspect ratio of the bed 9 in the imaging videos C1 and C2. For example, as shown in FIG. 6, in the case where the bed 9 is arranged vertically with respect to the camera 5, the aspect ratio of the bed 9 derived from the detected bed area often becomes 1 (vertical): a value below the decimal point (horizontal). Therefore, when the aspect ratio of the bed 9 is vertical > horizontal, it can be determined that the bed 9 is arranged vertically. On the other hand, when the aspect ratio of the bed 9 is vertical < horizontal, it can be determined that the bed 9 is arranged horizontally. Alternatively, learning data as a result of learning a large amount of vertical bed videos and horizontal bed videos such as the imaging videos C1 and C2 may be stored in the storage unit 23 and used for the determination.

[0042] In step S4, when it is determined that the bed 9 is arranged vertically (Yes in step S4), the state determination unit 22 sets a first specific area E1 for determining the patient M's getting out of bed corresponding to the vertically arranged bed 9 (step S5). Specifically, the state determination unit 22 draws four lines T1 to T4 along the contour line of the bed 9 in the image data, and sets the area inside these four lines T1 to T4 as the specific area E1 in the first mode. The positions of the lines T1 to T4 are stored in the storage unit 23.

[0043] Next, the state determination unit 22 determines the state of the patient M in the first mode based on the learning data imaged by the camera 5 and stored in the storage unit 23 (step S6). Specifically, the state determination unit 22 determines whether the patient M is in a state of lying prone on the bed 9 (i.e., a supine position or a lateral position), a state of sitting up, or a state of leaving the bed 9 (getting out of bed state). Whether the patient M is in a state of lying prone on the bed 9 is determined, for example, from the position of the patient M's head in the captured video C1. That is, in the first mode where the bed 9 is arranged vertically, when the patient M's head is located within a predetermined area on the lower side of the captured video C1, it can be determined that the patient M is in a state of lying prone on the bed 9. Also, whether the patient M is in a state of sitting up is determined by detecting that the upper body has been raised from the state of lying prone on the bed, indicating that a sitting-up motion has occurred. Furthermore, whether the patient M is in a getting-out-of-bed state is determined by detecting the patient M's sitting-up motion and then determining that getting out of bed has occurred if the patient M has moved outside the specific area E1 in the first mode. That is, the state determination unit 22 determines that the patient M has gotten out of bed if the patient M has moved to the left of the left line T1 or to the right of the right line T2.

[0044] Next, the case where the bed 9 is arranged horizontally with respect to the camera 5 will be described by returning to step S4. As shown in FIG. 7, in the case where the bed 9 is arranged horizontally with respect to the camera 5, in step S4, the state determination unit 22 detects the bed area based on the captured video C2 and determines that the bed 9 is not arranged vertically (No in step S4).

[0045] Next, the state determination unit 22 sets a second specific area E2 for determining the patient M's getting out of bed corresponding to the horizontally arranged bed 9 (step S7). Specifically, the state determination unit 22 draws four lines T5 to T8 along the contour line of the bed 9 in the image data, and sets the area inside these four lines T5 to T8 as the specific area E2 in the second mode. The positions of the lines T5 to T8 are stored in the storage unit 23 in the same manner as the lines T1 to T4.

[0046] Next, the state determination unit 22 determines the state of the patient M in the second mode based on the learning data captured by the camera 5 and stored in the storage unit 23 (step S8). Specifically, the state determination unit 22 determines, in the same manner as in the first mode, whether the patient M is in a state of lying prone on the bed (i.e., the supine position or the lateral position), a state of getting up, or a state of leaving the bed (getting out of bed). In the second mode where the bed 9 is horizontally arranged, the state determination unit 22 determines that the patient M is in a state of lying prone on the bed when the head of the patient M is located within a predetermined area on the left or right side of the captured video C2. Also, in the second mode, after detecting the patient M's getting-up motion, the state determination unit 22 determines that getting out of bed has occurred if the patient M moves outside the specific area E2 in the second mode. That is, the state determination unit 22 determines that the patient M has gotten out of bed if the patient M moves above the upper line T7 or below the lower line T8. Note that when the bed 9 is horizontally arranged, the line T8 side of the bed 9 in FIG. 7 is often installed to abut against the wall surface of the hospital room. Therefore, in the second mode, the state determination unit 22 may determine that the patient M has gotten out of bed only when the patient M moves above the line T7.

[0047] Following step S6 or step S8, the state determination unit 22 determines whether a specific state change has occurred in the patient M being monitored (step S9). If it is determined that a specific state change has occurred (Yes in step S9), a warning state occurrence signal is output to the nurse call master unit 3 and the control unit 4, and at the same time, the captured video (patient video) of the camera 5 is transmitted to the nurse call master unit 3 (step S10). Specifically, when the state determination unit 22 determines that the patient M has risen or has moved outside the bed 9, it outputs a warning state occurrence signal to the nurse call master unit 3 and transmits the captured video (patient video data) of the patient M.

[0048] In addition, when determining the state where the patient M has risen, it is preferable to output a warning state occurrence signal if the body posture is maintained for a certain period of time (for example, 5 seconds). This can prevent malfunction such as misjudging the action of turning over as a rising action. Also, as the occurrence of a specific state for outputting the warning state occurrence signal, in the above example, the state of raising the upper body or the state of moving outside the bed 9 is cited, but a warning state occurrence signal may be output when both the state of raising the upper body and the state of moving outside the bed 9 occur. Also, the specific state is not limited to the state where the patient M raises the upper body or the state of no longer being on the bed. For example, the state where the patient sits on the edge of the bed (semi-recumbent position) or the state where the patient removes the bed rail S (Figure 2) attached to the bed may be included in the specific state. Whether the patient M is in the semi-recumbent position is determined as the semi-recumbent position by detecting that the patient M has extended the feet from the state of rising on the bed and then sat on the bed 9 from the state of rising on the bed 9.

[0049] Next, the nurse call master unit 3 that has received the warning state occurrence signal sounds an alarm from the alarm sound unit provided in the communication unit 3a (step S11). While sounding the alarm from the alarm sound unit, the notification lamp 38 may be lit to notify the occurrence of the warning state.

[0050] Next, the nurse call master unit 3 reads the camera ID information included in the signal under the control of the master unit CPU 31, identifies the patient who is the source of the notification with reference to the information storage unit 35, and displays the patient information of the identified patient on the display unit 3b. At the same time, the transmitted video is displayed on the display unit 3b (step S12). Also, the nurse call master unit 3 stores the patient video data transmitted from the camera 5 in the information storage unit 35.

[0051] FIG. 8 is a diagram showing a state in which the video of the patient transmitted from the camera 5 is displayed on the display unit 3b. As shown in FIG. 8, on the display unit 3b, there are provided a source information display unit D1 for displaying source information such as the ward number P1, the patient's name P2, and further the medical department P3, a video display unit D2 for displaying the video of the patient, and further a display area such as a message display unit D3. In the message display unit D3, for example, "Attention behavior has occurred" is displayed, indicating that a video is being displayed due to the occurrence of an attention state. Note that the video displayed on the video display unit D2 in FIG. 8 is an imaging image captured by the camera 5 when the bed 9 is arranged vertically. Also, on the right side of the screen of the display unit 3b, there is arranged an operation button D4 for the recorded video that is automatically started.

[0052] Next, the control unit 4 that has received the attention state generation signal obtains and reads the associated nurse information and mobile terminal information from the ID information included in the signal with reference to the information storage unit 35 of the nurse call master unit 3, and transmits, to the mobile terminal 6 that has been read, that is, the mobile terminal 6 carried by the assigned nurse, a signal notifying the occurrence of the attention state, together with the source information such as the ward number, and the imaging video of the camera 5 (step S13). The mobile terminal 6 that has received the signal from the control unit 4 displays the source information, the imaging video of the camera 5, and the message on the display unit 6a in the same manner as the display of the nurse call master unit 3 (not shown).

[0053] As described above, the nurse call system 100 according to the present embodiment includes a nurse call sub-unit 1, a corridor light 2, a nurse call main unit 3 installed at a nurse station, and a camera 5 that images a patient M on a bed 9 from above the bed. The camera 5 has a state determination unit 22 for analyzing captured images C1 and C2 to detect a change in the state of the patient M. The state determination unit 22 detects the orientation of the bed 9 based on the captured images C1 and C2, and when the bed 9 is in the longitudinal orientation, it detects a change in the state of the patient M in a first mode, and when the bed 9 is in the lateral orientation, it is configured to detect a change in the state of the patient M in a second mode different from the first mode. The nurse call main unit 3 has a notification unit that executes a notification operation upon receiving a determination that a change in the state of the patient M has occurred. According to this, regardless of the orientation of the bed 9, a change in the state of the patient M can be detected with high accuracy based on the captured images C1 and C2 of the camera 5. Thereby, it is possible to prevent the patient M from falling or toppling from the bed 9.

[0054] Further, in the nurse call system 100 of the present invention, the change in the state of the patient M may include at least one of a state in which the patient M on the bed raises the upper body, a state in which the patient M assumes an upright sitting position, a state in which the patient M leaves the bed, and a state in which the patient M removes the bed railing S. As the change in the state of the patient, for example, by detecting the above-described states, a nurse can appropriately grasp a dangerous behavior that may lead to the patient M falling or toppling from the bed 9.

[0055] Also, in the nurse call system 100 of the present invention, in the first mode, the state determination unit 22 sets a first specific area E1 as a specific area for detecting a change in the patient's state within the viewing angle of the camera 5, and in the second mode, sets a second specific area E2 different from the first specific area E1. Then, the state determination unit 22 is configured to determine that the patient has left the bed when the patient moves out of the first specific area E1 or the second specific area E2, and the nurse call master unit 3 outputs a warning sound in the communication unit 3a upon receiving the determination that the patient has gotten out of bed. According to this configuration, by changing the ranges of the specific areas E1 and E2 according to the orientation of the bed, false detection can be suppressed while maintaining high-precision detection of changes in the patient's state.

[0056] Further, the nurse call system 100 of the present invention may further include a portable terminal 6 carried by a nurse to respond to a call from the nurse call slave unit 1, and communication control means for transmitting an imaging image of the patient by the camera 5 to the portable terminal 6 upon receiving a determination that a change in the patient's state has occurred. According to this configuration, even if the nurse is not at the nurse station, the nurse can be notified of the patient's dangerous behavior, so that the nurse can take appropriate measures.

[0057] In the above embodiment, the case where the camera 5 is installed above the head of the patient lying prone on the bed has been described. However, the mounting position of the camera 5 may be above the bed. For example, the camera 5 may be installed above the feet of the patient lying prone on the bed. By imaging from above the bed, the video imaged from above the bed does not change even if there are people around the bed, so malfunction can be prevented.

[0058] Also, the nurse call master unit 3 may further include a setting unit that can manually change the specific area E1 in the first mode and the specific area E2 in the second mode. According to this configuration, the nurse can further suppress false detection by appropriately changing the specific area E1 and the specific area E2 according to various situations such as the patient's attributes and the shape of the bed.

[0059] In addition, the patient video displayed on the video display unit D2 of the display unit 3b is not limited to a single video. When the attention state occurrence signal is transmitted overlappingly from a plurality of cameras 5, a plurality of corresponding videos may be displayed on the display unit 3b.

[0060] Also, in the above embodiment, the state determination unit 22 is provided in the camera 5, but it is not limited to this example. The camera 5 may be configured to be able to constantly receive the video of the camera 5 by a dedicated server, and the state determination unit 22 may be provided in the server.

[0061] Also, in the above embodiment, the monitoring operation of the patient in the nurse call system 100 has been described, but it is not limited to this example. For example, the monitoring operation in the present embodiment may be configured as a state determination system that images a patient on a bed, detects a change in the state of the patient in different modes according to the orientation of the bed, and notifies a predetermined related person. In this case, the state determination system can be easily configured by combining a camera and a control device (for example, a computer, etc.) including a state determination unit and a notification unit.

[0062] Note that the present invention is not limited to the above-described embodiments, and can be freely modified, improved, etc. as appropriate. In addition, the material, shape, dimensions, numerical values, form, number, arrangement location, etc. of each component in the above-described embodiments are arbitrary as long as the present invention can be achieved, and are not limited.

Explanation of Reference Numerals

[0063] 1: Nurse call sub-unit, 2: Corridor light, 3: Nurse call main unit, 3a: Communication unit (an example of a notification unit), 3b: Display unit, 3c: Board unit, 4: Control unit, 5: Camera, 6: Mobile terminal, 6a: Display unit, 7: Switch, 8: Base station, 9: Bed, 21: Camera CPU, 22: State determination unit, 23: Storage unit, 24, 39: Communication interface (communication IF), 31: Main unit CPU, 32: Video processing unit, 33: Touch panel, 34: Setting unit, 35: Information storage unit, 37: Audio processing unit, 38: Notification light, 100: Nurse call system

Claims

1. A nurse call system having a nurse call sub-unit installed on a bed for a patient to call a nurse, and a nurse call main unit installed at a nurse station to respond to a call by the nurse call sub-unit, a camera for imaging the patient on the bed from above the bed, a state determination unit for analyzing an imaging image of the camera and detecting a change in the state of the patient, comprising: the state determination unit detects the orientation of the bed based on the imaging image, when the bed is in the vertical orientation, a first specific area along the contour line of the vertically oriented bed is set as a specific area for detecting a change in the state of the patient within the angle of view of the camera, and a change in the state of the patient in the first specific area is detected, when the bed is in the horizontal orientation, a second specific area along the contour line of the horizontally oriented bed is set as the specific area within the angle of view of the camera, and a change in the state of the patient in the second specific area is detected, configured as such, the nurse call main unit includes a notification unit that executes a notification operation upon receiving a determination that the state change has occurred, and a setting unit that can manually change the size of the first specific area and the size of the second specific area, a nurse call system.

2. The change in the state of the patient includes at least one of a state in which the patient raises the upper body, a state in which the patient assumes an upright sitting position, a state in which the patient leaves the bed, and a state in which the patient removes the bed railing, the nurse call system according to claim 1.

3. The state determination unit is configured to determine that the patient has left the bed when the patient moves outside the first specific area or the second specific area, the nurse call main unit executes the notification operation upon receiving a determination that the patient has left the bed, the nurse call system according to claim 1 or 2.

4. a mobile terminal carried by the nurse to respond to a call from the nurse call sub-unit, communication control means for transmitting the imaging image to the mobile terminal upon receiving a determination that the state change has occurred, further comprising, the nurse call system according to any one of claims 1 to 3.

5. a camera for imaging a person on a bed from above the bed, a state determination unit for analyzing an imaging image of the camera and detecting a change in the state of the person, A notification unit that executes a notification operation in response to detection of the state change; comprising; the state determination unit; detects the orientation of the bed based on the captured image; when the bed is in the vertical orientation, a first specific area along the contour line of the vertical bed is set as a specific area for detecting a state change of the person within the angle of view of the camera, and the state change of the person in the first specific area is detected; when the bed is in the horizontal orientation, a second specific area along the contour line of the horizontal bed is set as the specific area within the angle of view of the camera, and the state change of the person in the second specific area is detected; is configured as; A state determination system further comprising a setting unit capable of manually changing the size of the first specific area and the size of the second specific area.

Images