JP7234931B2 - Sensor Device of Monitored Person Monitoring Support System, Processing Method of Sensor Device, and Monitored Person Monitoring Support System - Google Patents

Description

The present invention relates to a sensor device in a monitored person monitoring support system for supporting monitoring of a monitored person, a processing method for the sensor device , and the monitored person monitoring support system.

In recent years, with the progress of an aging society, techniques for supplementing work in the nursing industry and the nursing care industry have been researched and developed. The nurse call system disclosed in Patent Document 1 includes a nurse call slave unit installed in a bed for a patient to call a nurse, and a nurse call slave unit installed in a nurse station for responding to the call by the nurse call slave unit. A nurse call system having a nurse call master unit, wherein a camera captures an image of a patient on the bed from above the bed, and a state in which the upper body of the patient is raised and a state in which the patient is separated from the bed from images captured by the camera. a state determining means for determining the occurrence of at least one of the above and outputting a caution state occurrence signal; and the nurse call master device has notifying means for performing a notification operation upon receiving the caution state occurrence signal. The nurse call master unit has a monitor for displaying an image, and an image control unit for displaying an image picked up by the camera on the monitor when the caution state occurrence signal is received.

By the way, the nurse call system disclosed in Patent Literature 1 judges occurrence of at least one of the state in which the patient sits upright and the state in which the patient leaves the bed from the image captured by the camera. However, depending on the actual condition of the patient and the type of condition, it may be difficult to make a determination based on the captured image. In such a case, more detailed analysis processing is required for the captured image in order to determine the patient's condition, but the more detailed analysis processing increases the amount of information processing. For this reason, it takes a long time to make the determination, and there is a risk that the monitoring interruption time will become longer. In particular, when monitoring a plurality of people with one device, if one of the plurality of people is in a difficult state of judgment, the monitoring of the remaining persons is interrupted until the judgment is completed.

JP 2014-90913 A

The present invention has been made in view of the above-mentioned circumstances, and its object is to provide a sensor device of a monitored person monitoring support system capable of shortening the interruption of monitoring, a processing method of the sensor device , and a monitored person. It is to provide a monitoring support system.

In order to achieve the above object, a sensor device and a processing method thereof reflecting one aspect of the present invention detect an event by a first algorithm based on an image generated by an imaging unit, 2 algorithms determine the need to detect the event based on the image, and transmit the image to a central processing unit when necessary. A central processing unit that reflects one aspect of the present invention detects the event based on the image and notifies the terminal device of the event when the image is received from the sensor device. A monitored person monitoring support system that reflects one aspect of the present invention includes the sensor device, the central management device, and the terminal device as described above.

The advantages and features provided by one or more embodiments of the invention will be fully appreciated from the detailed description given below and the accompanying drawings. These detailed descriptions and accompanying drawings are given by way of example only and are not intended as a definition of the limits of the invention.

It is a figure which shows the structure of the monitored person monitoring assistance system in embodiment. It is a figure which shows the structure of the sensor apparatus in the said monitored person monitoring support system. It is a figure which shows the structure of the management server apparatus in the said monitored person monitoring support system. It is a figure which shows the structure of the monitoring information table memorize|stored in the said management server apparatus. 4 is a diagram showing the configuration of an inter-device information table stored in the management server device; FIG. It is a figure which shows the structure of the sensor information table memorize|stored in the said management server apparatus. 4 is a flow chart showing the operation of the sensor device; FIG. 8 is a flow chart showing the operation of detection request processing in the flow chart shown in FIG. 7 ; FIG. It is a flow chart which shows operation of the above-mentioned management server device. FIG. 10 is a flow chart showing the operation of advanced behavior detection processing in the flow chart shown in FIG. 9 ; FIG. It is a figure which shows an example of the monitoring information screen displayed on the portable terminal device in the said monitored person monitoring support system.

One or more embodiments of the invention are described below with reference to the drawings. However, the scope of the invention is not limited to the disclosed embodiments. It should be noted that the configurations denoted by the same reference numerals in each figure indicate the same configuration, and the description thereof will be omitted as appropriate. In this specification, reference numerals with suffixes omitted are used when referring to generic components, and reference numerals with suffixes are used when referring to individual configurations.

The monitored person monitoring support system in the present embodiment is a system that supports monitoring when monitoring a monitored person (watching target) Ob who is a monitoring target (watching target) to be monitored (watched over). . In this embodiment, the monitored person monitoring support system is provided corresponding to the monitored person Ob, is connected to a sensor device for detecting a predetermined event related to the monitored person Ob, and is communicably connected to the sensor device. a central processing unit for managing events detected by a sensor device and received from the sensor device; A receiving terminal is provided. The sensor device includes an imaging unit that generates an image; a first detection processing unit that detects the predetermined event based on the image generated by the imaging unit using a first algorithm that detects the predetermined event; A second algorithm different from the first algorithm for detecting the predetermined event when the first detection processing unit does not detect the predetermined event, based on the image generated by the imaging unit. a necessity determination unit for determining the necessity of detecting a predetermined event; and when the necessity determination unit determines that the predetermined event needs to be detected, the an image transmission unit configured to transmit an image generated by the imaging unit to the central processing unit; The sensor device may monitor the monitored person Ob on a one-to-one basis, and may monitor a plurality of monitored persons Ob on a one-to-many basis. a sensor device that monitors a person Ob, a sensor device that monitors a plurality of monitored persons Ob in a one-to-many manner, and a sensor device that monitors a plurality of monitored persons Ob in a one-to-one relationship; In addition, it may be configured with a mixture of sensor devices that monitor a plurality of monitored persons Ob in a one-to-many manner. The central processing unit includes a second detection processing unit that detects the predetermined event based on the received image when an image is received from the sensor device for detecting the predetermined event; When the detection processing unit detects the predetermined event, the detected predetermined event is sent to the terminal device that receives the notification of the event detected by the sensor device that transmitted the image for detecting the predetermined event. and a notification processing unit that notifies. The second detection processing section may detect the predetermined event based on the received image using the second algorithm. The terminal device may be one type of device, but in this embodiment, the terminal device is two types of devices, a fixed terminal device and a mobile terminal device. The main difference between these fixed terminal devices and mobile terminal devices is that while fixed terminal devices are used on a fixed basis, mobile terminal devices are carried by supervisors (service providers, users) such as nurses and caregivers. These fixed terminal devices and portable terminal devices are substantially the same. In such a monitored person monitoring support system, as an example of the predetermined event (phenomenon), a predetermined action and a nurse call in the monitored person Ob are given, and an example of the central processing unit is a management server. The device SV will be taken up and explained in more detail below.

FIG. 1 is a diagram showing the configuration of a monitored person monitoring support system according to an embodiment. FIG. 2 is a diagram showing the configuration of a sensor device in the monitored person monitoring support system. FIG. 3 is a diagram showing the configuration of a management server device in the monitored person monitoring support system. FIG. 4 is a diagram showing the configuration of a monitoring information table stored in the management server device. FIG. 5 is a diagram showing the configuration of an inter-device information table stored in the management server device. FIG. 5A shows a notification destination correspondence information table, and FIG. 5B shows a communication address correspondence information table. FIG. 6 is a diagram showing the structure of a sensor information table stored in the management server device.

The monitored person monitoring support system MS in the embodiment is a system for supporting the monitoring of the monitored person Ob. For example, as shown in FIG. 1, one or more sensor devices SU (SU-1 to SU-3) , a management server device SV, a fixed terminal device SP, one or more mobile terminal devices TA (TA-1, TA-2), and a private branch exchange (PBX, Private branch exchange) CX, which are Wired or wirelessly, they are communicably connected via a network (network, communication line) NW such as a LAN (Local Area Network). The network NW may be provided with repeaters such as repeaters, bridges and routers for relaying communication signals. In the example shown in FIG. 1, the plurality of sensor devices SU-1 to SU-3, the management server device SV, the fixed terminal device SP, the plurality of mobile terminal devices TA-1 and TA-2, and the private branch exchange CX are L2 switches. are communicably connected to each other by a mixed wired and wireless LAN (for example, a LAN conforming to the IEEE 802.11 standard) NW including a line concentrator (hub, HUB) LS and an access point AP. More specifically, a plurality of sensor devices SU-1 to SU-3, a management server device SV, a fixed terminal device SP and a private branch exchange CX are connected to a line concentrator LS, and connected to a plurality of mobile terminal devices TA-1 and TA-2. is connected to the concentrator LS via an access point AP. The network NW constitutes a so-called intranet by using Internet protocols such as TCP (Transmission control protocol) and IP (Internet protocol).

The private branch exchange (circuit switch) CX is connected to the network NW, controls extension calls such as outgoing calls, incoming calls, and conversations between the mobile terminal devices TA, implements extension calls between the mobile terminal devices TA, and , for example, is connected to an outside line telephone TL such as a fixed telephone or a mobile telephone via a public telephone network PN such as a fixed telephone network or a mobile telephone network, and originating, receiving and calling between the outside telephone TL and the portable terminal device TA. etc., to carry out an outside line call between the outside line telephone TL and the mobile terminal device TA. The private branch exchange CX is, for example, a digital exchange or an IP-PBX (Internet Protocol Private Branch Exchange).

The monitored person monitoring support system MS is arranged at an appropriate place according to the monitored person Ob. The monitored person (person to be watched over) Ob is, for example, a person who needs nursing care due to illness or injury, a person who needs nursing care due to a decline in physical ability, a solitary person living alone, or the like. In particular, from the viewpoint of enabling early detection and early countermeasures, the monitored person Ob should be a person who needs to be found when a predetermined inconvenient event, such as an abnormal condition, occurs to him or her. preferable. Therefore, the monitored person monitoring support system MS is preferably installed in buildings such as hospitals, welfare facilities for the elderly, and dwelling units according to the type of the monitored person Ob. In the example shown in FIG. 1, the monitored person monitoring support system MS is installed in a building of a nursing care facility having a plurality of rooms RM in which a plurality of monitored persons Ob reside and a plurality of rooms such as a nurse station. .

The sensor device SU has a communication function or the like to communicate with other devices SV, SP, and TA via the network NW, detects a predetermined action of the monitored person Ob as an example of the predetermined event, and outputs the detection result. transmits to the management server device SV, receives a nurse call, detects it as another example of the predetermined event, transmits that effect to the management server device SV, performs a voice call between the terminal devices SP and TA, It is a device that generates an image including a moving image and distributes the moving image to the terminal devices SP and TA.

As an example, FIG. 1 shows three first to third sensor units SU-1 to SU-3. The second sensor unit SU-2 is arranged in the room RM-1 (not shown) of Ob-1, and the second sensor unit SU-2 is arranged in the room RM-2 (not shown) of Mr. B Ob-2, who is one of the monitored persons Ob. The third sensor unit SU-3 is arranged in a living room RM-3 (not shown) of Mr. C Ob-3 who is one of the monitored persons Ob and Mr. D Ob-4 who is one of the monitored persons Ob. is set. That is, in the present embodiment, the first sensor device SU-1 monitors Mr. A Ob-1 of the monitored person on a one-to-one basis, and the second sensor device SU-2 monitors the monitored person on a one-to-one basis. Mr. B Ob-2 is monitored, and the third sensor unit SU-3 monitors Mr. C Ob-3 and Mr. D Ob-4 on a one-to-many basis.

For example, as shown in FIG. 2, such a sensor device SU includes an imaging unit 11, a sound input/output unit 12, a nurse call reception operation unit 13, and a sensor-side control processing unit (SU control processing unit) 14. , a sensor-side communication interface unit (SU communication IF unit) 15 and a sensor-side storage unit (SU storage unit) 16 .

The imaging unit 11 is a device that is connected to the SU control processing unit 14 and generates an image (image data) under the control of the SU control processing unit 14 . The images include still images (still image data) and moving images (moving image data). The imaging unit 11 is arranged so as to be able to monitor a space (located space, in the example shown in FIG. 1, a living room (room) RM at the installation location) where the monitored person Ob, who is a monitoring target to be monitored, is scheduled to reside. , the location space is imaged from above as an imaging target, a bird's-eye view image (image data) of the imaging target is generated, and the image of the imaging target (target image) is output to the SU control processing unit 14 . Preferably, when the sensor unit SU monitors the monitored person Ob on a one-to-one basis, there is a high probability that the entire monitored person Ob to be monitored can be imaged. (for example, a bed) so that the object to be imaged can be imaged from directly above the predetermined head position (usually, the position of the pillow) where the head of the person to be monitored Ob is expected to be located. be done. Further, preferably, when the sensor device SU monitors a plurality of monitored persons Ob in a one-to-many manner, there is a high probability that the entirety of the plurality of monitored persons Ob to be monitored can be imaged. ) It is arranged, for example, at a substantially central position on the ceiling surface, or at a corner position formed by two side wall surfaces and the ceiling surface adjacent to each other, so that the entire RM can be imaged from above to below. The imaging unit 11 of the sensor unit SU captures an image of the monitored person Ob captured from above the monitored person Ob, preferably a bird's-eye view of the imaging target directly above the expected head position, or preferably an oblique image. A bird's-eye view image of the imaging target is acquired from above.

In this embodiment, as will be described later, the imaging unit 11 is different from each other in order to detect the predetermined behavior of the monitored person Ob based on the images generated by the imaging unit 11 using the first and second algorithms. It is configured to generate the image at multiple resolutions. For example, the imaging unit 11 generates an image with a first resolution, and thins out pixels from the image with the first resolution to generate an image with a second resolution that is lower than the first resolution. Further, for example, the imaging unit 11 generates an image with a second resolution, and generates an image with a first resolution higher than the second resolution by interpolating pixels from the image with the second resolution. Further, for example, the imaging unit 11 generates a plurality of time-series images at a second resolution, and performs a resolution enhancement process (super-resolution technology) on the plurality of images at the second resolution to obtain a resolution higher than the second resolution. generates an image of a first resolution of .

Such an imaging unit 11 may be a device that generates a visible light image, but in this embodiment, it is a device that generates an infrared image so that the monitored person Ob can be monitored even in relatively dark conditions. . For example, in the present embodiment, such an imaging unit 11 includes an imaging optical system that forms an infrared optical image of an object to be imaged on a predetermined imaging plane, and a light receiving surface that coincides with the imaging plane. An area image sensor arranged to convert an infrared optical image of the imaging target into an electrical signal, and data representing an infrared image of the imaging target by image processing the output of the area image sensor. It is a digital infrared camera provided with an image processing section for generating image data. In this embodiment, the imaging optical system of the imaging unit 11 is preferably a wide-angle optical system (a so-called wide-angle lens (including a fisheye lens)) capable of imaging the entire living room RM in which it is installed. .

The sound input/output unit 12 is a circuit for inputting/outputting sound. That is, the sound input/output unit 12 is a circuit connected to the SU control processing unit 14 for generating and outputting a sound corresponding to an electrical signal representing sound under the control of the SU control processing unit 14. It is a circuit for acquiring sound and inputting it to the sensor device SU. The sound input/output unit 12 includes, for example, a speaker that converts an electrical signal of sound (sound data) into a mechanical vibration signal of sound (acoustic signal), and a microphone that converts the mechanical vibration signal of sound in the audible range into an electrical signal. and The sound input/output unit 12 outputs an electrical signal representing an external sound to the SU control processing unit 14, converts the electrical signal input from the SU control processing unit 14 into a mechanical vibration signal of sound, and outputs the mechanical vibration signal.

The nurse call reception operation unit 13 is connected to the SU control processing unit 14 and is a switch circuit such as a push button switch for inputting a nurse call to the sensor unit SU. The nurse call reception operation unit 13 may be connected to the SU control processing unit 14 by wire, or may be connected to the SU control processing unit 14 by short-range wireless communication such as the Bluetooth (registered trademark) standard.

The SU communication IF unit 15 is a communication circuit that is connected to the SU control processing unit 14 and performs communication under the control of the SU control processing unit 14 . SU communication IF unit 15 generates a communication signal containing data to be transferred input from SU control processing unit 14 according to a communication protocol used in network NW of monitored person monitoring system MS, and transmits the generated communication signal. Signals are sent to other devices SV, SP, TA via the network NW. The SU communication IF unit 15 receives communication signals from other devices SV, SP, and TA via the network NW, extracts data from the received communication signals, and the SU control processing unit 14 can process the extracted data. format data and output to the SU control processing unit 14 . The SU communication IF unit 15 includes, for example, a communication interface circuit complying with the IEEE802.11 standard.

The SU storage unit 16 is a circuit that is connected to the SU control processing unit 14 and stores various prescribed programs and various prescribed data under the control of the SU control processing unit 14 . The various predetermined programs include, for example, an SU control program for controlling the units 11 to 13, 15, and 16 of the sensor device SU according to the functions of the respective units, and a predetermined information processing program for monitoring the monitored person Ob. includes a control processing program such as an SU monitoring processing program that executes In the SU monitoring processing program, a predetermined action of the monitored person Ob is detected as an example of the predetermined event by the first algorithm based on the image generated by the imaging unit 11, and the detection result is sent to the management server device. A first detection processing program for notifying predetermined terminal devices SP and TA via SV, and when the predetermined action is not detected by the first detection processing program, the predetermined action is detected as the event of the predetermined event. A necessity determination program for determining the necessity of detecting the predetermined behavior based on an image generated by the imaging unit 11 by a second algorithm different from the first algorithm, and the necessity determination program, as an example. When it is determined that the predetermined action needs to be detected, the image generated by the imaging unit 11 is transmitted to the management server device SV in order to detect the predetermined action as an example of the predetermined event. When a nurse call is received by the image transmission program and the nurse call reception operation unit 13, the fact is notified to the management server device SV as another example of the predetermined event. It includes a nurse call processing program for making voice calls with the devices SP and TA, and a streaming processing program for delivering moving images generated by the imaging unit 11 to the terminal devices SP and TA that requested the moving images. The various predetermined data include a sensor device identifier (sensor ID), which is an identifier for specifying and identifying the sensor device SU, and the communication address of the management server device SV. It contains the data necessary for The SU storage unit 16 includes, for example, a ROM (Read Only Memory) that is a non-volatile storage element, an EEPROM (Electrically Erasable Programmable Read Only Memory) that is a rewritable non-volatile storage element, and the like. The SU storage unit 16 includes a RAM (Random Access Memory) or the like that serves as a so-called working memory of the SU control processing unit 14 that stores data generated during execution of the predetermined program.

The SU control processing unit 14 controls each unit 11 to 13, 15, 16 of the sensor unit SU according to the function of each unit, and sends a predetermined event related to the monitored person Ob to the management server unit SV. This is the circuit for notification. More specifically, in the present embodiment, the SU control processing unit 14 uses the first algorithm to determine the predetermined behavior of the monitored person Ob as an example of the predetermined event, based on the image generated by the imaging unit 11 . Detecting and notifying (notifying or transmitting) the detection result to the management server apparatus SV, and detecting the predetermined action as an example of the predetermined event when the predetermined action is not detected by the first algorithm. Then, a second algorithm different from the first algorithm determines the necessity of detecting the predetermined behavior based on the image generated by the imaging unit 11, and as a result, it is necessary to detect the predetermined behavior. When it is determined that the predetermined action is detected as an example of the predetermined event, an image generated by the imaging unit 11 is transmitted to the management server device SV, a nurse call is received, and the nurse call is sent to the management server device SV. As another example of the predetermined event, the management server device SV is notified (reported, transmitted), voice communication is performed between the terminal devices SP and TA, an image including a moving image is generated, and the moving image is sent to the terminal devices SP and TA. deliver. The SU control processing unit 14 is composed of, for example, a CPU (Central Processing Unit) and its peripheral circuits. By executing the control processing program, the SU control processing unit 14 includes a sensor-side control unit (SU control unit) 141, a sensor-side detection processing unit (SU detection processing unit) 142, a necessity determination unit 143, an image transmission It functionally includes a unit 144 , a nurse call processing unit 145 and a streaming processing unit 146 .

The SU control section 141 controls each section of the sensor device SU according to the function of each section, and governs the overall control of the sensor device SU.

The SU detection processing unit 142 detects a preset predetermined action of the monitored person Ob based on the image generated by the imaging unit 11 using the first algorithm as an example of the predetermined event, and detects the detection. The result is notified to the management server device SV. More specifically, in the present embodiment, the predetermined action included in the predetermined event is, for example, waking up by the monitored person Ob, leaving the bed by the monitored person Ob leaving the bed, The five behaviors are a fall of the person Ob from the bedding, a fall of the monitored person Ob, and writhing and writhing movements of the monitored person Ob in pain. In this embodiment, getting up, getting out of bed, falling, and falling are detected by the first algorithm, and the struggle is detected by the second algorithm. For example, as the first algorithm, the SU detection processing unit 142 detects the head of the monitored person Ob based on the target image captured by the imaging unit 11, and determines the size of the detected head of the monitored person Ob. The monitored person Ob's getting up, getting out of bed, falling, and falling are detected based on the time change of . More specifically, first, the location area of the bedding BD and the first to third threshold values Th1 to Th3 are stored in advance in the SU storage unit 16 as one of the various predetermined data. The first threshold Th1 is a threshold for distinguishing between the size of the head in the lying posture and the size of the head in the sitting posture in the area where the bedding BD is located. The second threshold Th2 is a threshold for identifying whether or not the size of the head is in the standing posture in the living room RM excluding the area where the bedding BD is located. The third threshold Th3 is a threshold for identifying whether or not the size of the head in the recumbent posture in the living room RM excluding the area where the bedding BD is located. Then, the SU detection processing unit 142 extracts a moving object area as a human area of the person to be monitored Ob from the target image by, for example, the background subtraction method or the frame subtraction method. The head region of the monitored person Ob is extracted by conversion, by pattern matching using a head model prepared in advance, for example, by a neural network trained for head detection, and this extracted head Detects getting up, leaving the bed, falling and falling from the position and size of For example, the SU detection processing unit 142 determines that the position of the extracted head is within the location area of the bedding BD and the size of the extracted head is the size of the lying posture by using the first threshold value Th1. to the size of the sitting posture over time, it is determined that the user is getting up, and the above-mentioned getting up is detected. For example, the SU detection processing unit 142 detects that the position of the extracted head changes over time from within the location area of the bedding BD to outside the location area of the bedding, and the size of the extracted head is the second size. By using the threshold value Th2, when the size changes from a certain size to the size of the standing posture over time, it is determined that the person is getting out of bed, and the above-mentioned getting out of bed is detected. For example, the SU detection processing unit 142 detects that the position of the extracted head changes from within the location area of the bedding BD to outside the location area of the bedding BD, and the size of the extracted head is the third size. By using the threshold value Th3, when the size changes from a certain size to the size of the lying posture over time, it is determined that the fall has occurred, and the fall is detected. For example, the SU detection processing unit 142 determines that the position of the extracted head is within the living room RM excluding the location area of the bedding BD, and the size of the extracted head is a certain size by using the third threshold Th3. When the size of the body changes from the size of the standing posture to the size of the lying posture over time, it is determined that a fall has occurred, and the fall is detected.

When the sensor unit SU monitors a plurality of monitored persons Ob in a one-to-many manner, the SU detection processing unit 142 uses the background subtraction method from the target image to obtain a plurality of human regions for the plurality of monitored persons Ob. are extracted, and a label (identification code) is attached to each of the plurality of moving object areas. Each time the SU detection processing unit 142 extracts a moving object area from the target image by the background subtraction method, it attaches the same label to the moving object areas at the closest positions on the target image. Then, the SU detection processing unit 142 performs each of the above-described processes on each of the labeled moving body regions, and detects getting up, getting out of bed, falling, and falling.

When the predetermined behavior is detected in this way, the SU detection processing unit 142 stores event information (event information) representing the content of a predetermined event (phenomenon) related to the monitored person Ob, to notify the event. The SU communication IF unit 15 notifies the management server device SV of the first event notification communication signal. More specifically, the SU detection processing unit 142 generates a communication signal (first event notification communication signal ) to the management server device SV via the SU communication IF unit 15 . In the present embodiment, the event information is one or more of getting up, getting out of bed, falling, falling, and a nurse call (NC). One or more of the falls are included as the event information in the first event notification communication signal. The image may be at least one of a still image and a moving image. In the present embodiment, as will be described later, the still image is first notified, and the moving image is distributed according to the user's request. First, a moving image may be distributed, or a still image and a moving image may be transmitted, and the still image and the moving image may be displayed on the terminal devices SP and TA by splitting the screen.

The necessity determination unit 143 detects the predetermined behavior of the monitored person Ob as an example of the predetermined event when the SU detection processing unit 142 does not detect the predetermined behavior as an example of the predetermined event. , a second algorithm that is different from the first algorithm, and determines the necessity of detecting the predetermined behavior based on the image generated by the imaging unit 11 . More specifically, the necessity determination unit 143 does not satisfy the first condition for determining that the predetermined event has occurred in the monitored person Ob, but the predetermined event has occurred in the monitored person Ob. The necessity of detecting the predetermined event is determined depending on whether or not the third condition, which does not satisfy the second condition, is satisfied. In the present embodiment, since the predetermined action is given as an example of the predetermined event, the necessity determination unit 143 determines that the person to be monitored Ob has fallen and fallen among the predetermined actions. Depending on whether or not the third condition, which does not satisfy the first condition to be determined but does not satisfy the second condition to determine that the person to be monitored Ob has fallen and that the person to be monitored Ob has not fallen, determine the need to detect the struggle of More specifically, first, a threshold for determining whether or not a fall has occurred (a fall determination time threshold) and a threshold for determining the necessity of struggling detection are set with respect to the change over time used to determine whether a fall has occurred. A (first necessity determination threshold) is set, and a threshold (fall determination time threshold) for determining whether or not a fall has occurred with respect to the time change used for determining a fall, and the need for detection of struggling. A threshold value (second necessity determination threshold value) for determining is set. The fall determination time threshold and the first necessity determination threshold are appropriately set in advance from a plurality of samples, and the fall determination time threshold is set to a value smaller than the first necessity determination threshold ((the fall determination time threshold)<(said first necessity determination threshold)). The fall determination time threshold and the second necessity determination threshold are appropriately set in advance from a plurality of samples, and the fall determination time threshold is set to a value smaller than the second necessity determination threshold ((the fall determination time threshold)<(second necessity determination threshold)). Therefore, the SU detection processing unit 142 detects that the position of the extracted head changes from inside the location area of the bedding BD to outside the location area of the bedding BD, and the size of the extracted head is the third size. By using the threshold Th3, when the time (first change time) until the size changes from a certain size to the size of the lying posture is equal to or less than the fall determination time threshold, the fall is determined and the fall is detected. do. The necessity determination unit 143 detects struggling when the first change time is greater (longer) than the fall determination time threshold and when the first change time is equal to or less than the first necessity determination threshold. It is determined that there is a need for The SU detection processing unit 142 detects that the position of the extracted head is within the living room RM excluding the location area of the bedding BD and the size of the extracted head is a certain size by using the third threshold Th3. When the time (second change time) until the size changes from the low position to the size of the lying posture is equal to or less than the fall determination time threshold, it is determined that the fall has occurred, and the fall is detected. The necessity determination unit 143 determines whether it is necessary to detect a struggle when the second change time is greater than the fall determination time threshold and when the second change time is equal to or less than the second necessity determination threshold. It is determined that there is Then, the necessity determination unit 143 determines, for example, when the first change time is greater (longer) than the first necessity determination threshold, and when the second change time is greater than the second necessity determination threshold. It is determined that there is no need for detection of struggle except when there is a need for detection of struggle.

When the necessity determination unit 143 determines that detection of the predetermined behavior (struggling in the present embodiment) is necessary, the image transmission unit 144 sets the predetermined behavior as an example of the predetermined event to another event. An image generated by the imaging unit 11 is transmitted to the management server device SV in order for the device (in this embodiment, the management server device SV) to detect it. More specifically, when the necessity determination unit 143 determines that the detection of the predetermined behavior is necessary, the image transmission unit 144 transmits the sensor ID of the device itself and an instruction to detect the predetermined behavior ( command) and a communication signal (detection request communication signal) containing an image generated by the imaging unit 11, and transmits the generated detection request communication signal to the management server device SV. The image contained in the detection request communication signal is used in the first algorithm as an example of the predetermined event in order to perform more detailed analysis processing in the management server device SV in the second algorithm. It is an image with a resolution higher than that of the image used for detection. For this reason, when the necessity determination unit 143 determines that the detection of the predetermined behavior is necessary, the image transmission unit 144 reduces the resolution of the image used for detecting the predetermined behavior by the first algorithm. The imaging unit 11 is caused to generate an image with a higher resolution. The image contained in the detection request communication signal may be a still image. is a moving image of a predetermined time length. The predetermined length of time is appropriately set in advance as a time necessary for detecting the struggle, and is, for example, several seconds to ten and several seconds such as 3 seconds, 5 seconds, 10 seconds and 15 seconds.

When the nurse call reception operation unit 13 receives a nurse call, the nurse call processing unit 145 notifies the management server device SV of a first event notification communication signal containing the fact as another example of the predetermined event, Voice communication is performed between the terminal devices SP and TA by using the sound input/output unit 12 and the like. More specifically, when the nurse call reception operation unit 13 is operated for input, the nurse call processing unit 143 transmits the first event notification communication signal containing the nurse call as the sensor ID of the device itself and the event information by SU communication. It is transmitted to the management server device SV via the IF section 15 . Then, the nurse call processing unit 143 uses the sound input/output unit 12 and the like to make a voice call with the terminal devices SP and TA by, for example, VoIP (Voice over Internet Protocol).

When a video distribution request is received from the fixed terminal SP or the mobile terminal TA via the communication IF section 3, the streaming processing section 146 sends the request to the fixed terminal SP or the mobile terminal TA, A moving image (for example, a live moving image) generated by the imaging unit 11 is distributed via the SU communication IF unit 15 by streaming reproduction.

The management server device SV has a communication function to communicate with other devices SU, TA, and SP via the network NW, and upon receiving notification of the predetermined event from the sensor device SU, information ( Monitoring information (in this embodiment, for example, the predetermined event (type of predetermined action detected by the sensor device SU, nurse call received by the sensor device SU), image (still image and moving image) of the monitored person Ob, and time of receiving the notification, etc.)), notifies (re-notify, re-notify, or transmits) the predetermined event to predetermined terminal devices SP and TA, and clients (terminal devices SP, TA, etc. in this embodiment). ) to the client, and manages the monitored person monitoring system MS as a whole. Then, in this embodiment, when the management server device SV receives an image from the sensor device SU for detecting the predetermined event, the management server device SV detects the predetermined event based on the received image, and detects the predetermined event. when the event is detected, the detected predetermined event is managed as the monitoring information, and the detected predetermined event is detected by the sensor device SU which transmitted an image for detecting the predetermined event. Notifies the terminal devices SP and TA that receive notification of the event. Such a management server device SV includes, for example, a server-side communication interface unit (SV communication IF unit) 21, a server-side control processing unit (SV control processing unit) 22, and a server-side storage unit, as shown in FIG. (SV storage unit) 23 .

The SV communication IF unit 21 is a communication circuit that is connected to the SV control processing unit 22 and performs communication under the control of the SV control processing unit 22, like the SU communication IF unit 15 is. The SV communication IF section 21 is configured with a communication interface circuit conforming to the IEEE802.11 standard, for example.

The SV storage unit 23 is a circuit that is connected to the SV control processing unit 22 and stores various predetermined programs and various predetermined data under the control of the SV control processing unit 22 . The various predetermined programs include, for example, an SV control program that controls the respective units 21 and 23 of the management server apparatus SV according to the functions of the respective units, and a predetermined information processing related to monitoring of the monitored person Ob. A control processing program such as an SV monitoring processing program is included. The SV monitoring processing program manages monitoring information relating to monitoring of the monitored person Ob upon receiving notification of the predetermined event from the sensor device SU, and monitors to notify the predetermined event to the predetermined terminal devices SP and TA. a processing program, an SV detection processing program for detecting the predetermined event based on the received image when an image is received from the sensor device SU for detecting the predetermined event, and the SV detection processing program When the predetermined event is detected, the detected predetermined event is sent to the terminal devices SP and TA that receive notification of the event detected by the sensor device SU that transmitted the image for detecting the predetermined event. A notification processing program for notification is included. The various predetermined data include a server identifier (server ID) for specifying and identifying the management server device SV, the monitoring information of the monitored person Ob, and the predetermined data. It includes inter-device information representing information between the devices SU, SP, TA such as event notification destinations, and data necessary for executing each program such as sensor information regarding the sensor device SU. The SV storage unit 23 functionally includes a monitoring information storage unit 231, an inter-device information storage unit 232, and a sensor information storage unit 233 in order to store the monitoring information, inter-device information, and sensor information, respectively.

The monitoring information storage unit 231 stores the monitoring information of the monitored person Ob transmitted and received with each of the devices SU, SP, and TA. More specifically, in the monitoring information storage unit 231, in this embodiment, as the monitoring information, sensor ID, event information (event information, in this embodiment, getting up, getting out of bed, falling, falling, struggling, and nurse call), reception time, target image (still image and video), and whether or not to deal with (whether or not to accept response) They are stored in association with each other.

This monitoring information is stored in the monitoring information storage unit 321 in the form of a table in this embodiment. For example, as shown in FIG. 4, the monitoring information table MT for registering this monitoring information includes a sensor ID field 2311 for registering the sensor ID contained in the communication signal received from each of the devices SU, SP, and TA; an event field (event field) 2312 for registering an event detected by a second algorithm as described later based on event information contained in the received communication signal or an image contained in the received communication signal; a reception time field 2313 for registering the reception time of the communication signal; a still image field 2314 for registering the still image included in the received communication signal or a still image based on the image included in the received communication signal; A video field 2315 for registering the communication address (for example, IP address, etc.) of the sensor device SU corresponding to the sensor ID contained in the received communication signal and the A response field 2316 for registering whether or not a response to event information is accepted is provided, and a record is provided for each received communication signal (each event). In the still image field 2314, for example, still image data may be registered, and for example, the file name of the still image image data may be registered. The response field 2316 indicates whether or not the terminal devices SP and TA have received an intention (“to respond”) to the event information contained in the received communication signal. Flags (correspondence flags) are registered. For example, in the present embodiment, in the correspondence field 2316, the terminal indicates that it intends to deal with the event information contained in the received communication signal (event information registered in the event field 2312) (“correspond”). The response flag "1", which means that the devices SP and TA have accepted it, or the terminal devices SP and TA indicate that there is an intention to deal with the event information contained in the received communication signal ("support"). A correspondence flag "0" is registered, which means that the request is not accepted. By default, the corresponding flag “0” is registered in the corresponding field 2316 to indicate non-acceptance. If the first event notification communication signal contains the detection time at which the predetermined behavior is detected or the nurse call reception time at which the nurse call is received, the detection time or the nurse call acceptance time is replaced with the reception time. A call acceptance time may be registered.

The inter-device information storage unit 232 stores, as the inter-device information, in this embodiment, the correspondence between notification destinations, the correspondence between communication addresses, and the like. The notification destination correspondence relationship includes the predetermined event contained in the first event notification communication signal transmitted from the sensor device SU, and the predetermined event detected based on the image contained in the detection request communication signal. It is a correspondence relationship between a sensor ID that is a transmission source and a terminal ID that is a notification destination (re-notification destination). The terminal ID is a terminal identifier for specifying the terminal devices SP and TA and identifying the terminal devices SP and TA. The communication address correspondence relationship is a correspondence relationship between the IDs (sensor IDs, terminal IDs) of the devices SU, SP, and TA and their communication addresses.

These notification destination correspondence and communication address correspondence are respectively stored in the inter-device information storage unit 232 in the form of a table in this embodiment. The notification destination correspondence information table AT for registering this notification destination correspondence is, for example, as shown in FIG. The sensor ID (sensor A record is provided for each device (SU). The communication address correspondence information table DT for registering the communication address correspondence is registered in a terminal ID field 2323 for registering the terminal IDs of the terminal devices SP and TA, and a terminal ID field 2323, for example, as shown in FIG. 5B. and a communication address field 2324 for registering the communication addresses of the terminal devices SP and TA corresponding to the terminal ID, and a record is provided for each terminal ID (terminal device SP and TA).

Each of the sensor ID, server ID, and terminal ID may be, for example, a serial number or the like consisting of a predetermined symbol string, or may be, for example, a communication address (in this case, communication address correspondence can be omitted).

The sensor information storage unit 233 stores the sensor information. In this embodiment, the sensor information is information about the sensor device SU, and is information in which the sensor ID of the sensor device SU and the monitored person name of the monitored person Ob are associated with each other.

Such sensor information is stored in the sensor information storage unit 233 in the form of a table in this embodiment. More specifically, the sensor information table ST for registering sensor information includes, for example, a sensor ID field 2331 for registering sensor IDs and sensor IDs registered in the sensor ID field 2331, as shown in FIG. and a monitored person Ob monitored by the sensor device SU having the sensor ID registered in the sensor ID field 2331 (that is, the sensor ID field 2331). A monitored person name field 2333 for registering the monitored person name of the monitored person Ob) who is at the installation location of the sensor device SU having the sensor ID registered in 2331 and the sensor ID field 2331 registered in the sensor ID field 2331 . It has a remarks field 2334 for registering remarks on the sensor device SU having the sensor ID, its installation location, and the monitored person Ob, and has a record for each sensor ID (that is, the sensor device SU). In the monitored person name field 2333, one monitored person name is registered when the sensor unit SU monitors the monitored person Ob one-to-one, and the sensor unit SU monitors the monitored person Ob one-to-many. When monitoring , a plurality of monitored person names are registered.

The SV control processing unit 22 controls the respective units 21 and 23 of the management server device SV according to the functions of the respective units, and upon receiving notification of the predetermined event from the sensor device SU, performs monitoring related to monitoring of the monitored person Ob. A circuit for managing information, notifying the predetermined event to the predetermined terminal devices SP and TA, providing data according to the client's request to the client, and managing the monitored person monitoring support system MS as a whole. be. Then, in the present embodiment, when an image is received from the sensor device SU for detecting the predetermined event, the SV control processing unit 22 detects the predetermined event based on the received image, and When a predetermined event is detected, the detected predetermined event is managed as the monitoring information, and the detected predetermined event is detected by the sensor device SU that has transmitted an image for detecting the predetermined event. Notifies the terminal devices SP and TA that receive notification of the event. As described above, the predetermined event is a struggle detected by the second algorithm based on the image received from the sensor unit SU in this embodiment. The SV control processing unit 22 is configured including, for example, a CPU and its peripheral circuits. By executing the control processing program, the SV control processing unit 22 performs a server-side control unit (SV control unit) 221, a monitoring processing unit 222, a server-side detection processing unit 223 (SV detection processing unit) 223, and a notification process. A unit 224 is functionally provided.

The SV control unit 221 controls the units 21 and 23 of the management server device SV according to the functions of the respective units, and governs the overall control of the management server device SV.

The monitoring processing unit 222 manages monitoring information related to monitoring of the monitored person Ob upon receiving notification of the predetermined event from the sensor device SU, and notifies the predetermined event to the predetermined terminal devices SP and TA. . More specifically, when the monitoring processing unit 222 receives the first event notification communication signal from the sensor unit SU, the monitoring processing unit 222 obtains the monitoring information regarding the monitoring of the monitored person Ob contained in the received first event notification communication signal. is stored (recorded) in the monitoring information storage unit 231 . The monitoring processing unit 222 stores the notification destination (re-notification destination, forwarding destination, transmission destination) corresponding to the sensor device SU that transmitted the received first event notification communication signal from the inter-device information storage unit 232 . A second event notification communication signal is generated based on the selection result, and the SV communication IF section 21 transmits the generated second event notification communication signal. The selection (searching process) of the terminal devices SP and TA of the notification destination is performed by the sensor ID corresponding to the sensor device SU that transmitted the received first event notification communication signal (sensor ID contained in the first event notification communication signal). ID). If the event information contained in the first event notification communication signal is the predetermined action (one or more of getting up, getting out of bed, falling, and falling), the second event notification communication signal includes: Contains the sensor ID, event information, and target image contained in one event notification communication signal, and the communication address corresponding to the sensor device SU having the sensor ID contained in the first event notification communication signal as the download destination of the moving image. be done. This communication address is selected (searched) from the communication address correspondence based on the sensor ID corresponding to the sensor device SU that transmitted the received first event notification communication signal. When the event information contained in the first event notification communication signal is the nurse call, the second event notification communication signal contains the sensor ID and the event information contained in the first event notification communication signal. be done.

The SV detection processing unit 223 detects the predetermined event based on the received image when an image is received from the sensor unit SU for detecting the predetermined event. More specifically, when the SV detection processing unit 223 receives a detection request communication signal from the sensor unit SU, the SV detection processing unit 223 uses the second algorithm to perform the predetermined action (this Struggling in the embodiment) is detected as an example of the predetermined event.

In this embodiment, the struggle is performed in a plurality of time-series still images, in which the trunk of the monitored person Ob is at a substantially fixed position, and the monitored person Ob is at a substantially periodic position centered on the trunk of the monitored person Ob. It is detected by whether it moves (vibrates) repeatedly. More specifically, the SV detection processing unit 223 performs the following processing as the second algorithm for each frame in the moving image of a predetermined length contained in the detection request communication signal, thereby reducing the difficulty of struggling. Determine presence/absence. First, the SV detection processing unit 223 extracts the person area of the monitored person Ob from the frame image by, for example, the background subtraction method. Next, the SV detection processing unit 223 detects the center position and outline of the extracted person area. For example, the SV detection processing unit 223 obtains a circumscribing circle that circumscribes the person area, and obtains the center of the obtained circumscribing circle as the central position of the person area. Further, for example, the SV detection processing unit 223 obtains a circumscribing rectangle that circumscribes the person area, and obtains the intersection of the diagonal lines of the obtained circumscribing rectangle as the center position of the person area. On the other hand, for example, the SV detection processing unit 223 obtains the edge of the person area as the outline of the person area by an edge filter. Then, the SV detection processing unit 223 determines whether or not the monitored person Ob is struggling based on each center position of each person area and each outline of each person area in each frame. For example, the SV detection processing unit 223 determines that each center position of each person region in each frame exists within a predetermined range set in advance with respect to the average position of each center position, and each frame When the movement of each outline of each person region in the above is repeatedly moving (vibrating) substantially periodically, it is determined that the monitored person Ob is struggling, the struggling is detected, and other than this case In this case, it is determined that the monitored person Ob is not struggling.

The information processing time of the second algorithm is longer than the information processing time of the first algorithm when information processing is performed by an information processing apparatus having the same performance. In particular, as described above, when detecting a struggle based on whether or not the monitored person Ob is repeatedly moving (vibrating) approximately periodically around the body trunk of the monitored person Ob, a moving image of a predetermined length of time is generated. Since the analysis is necessary, the information processing time of the second algorithm is longer than that of the first algorithm when information processing is performed by an information processing apparatus having the same performance. On the other hand, the management server device SV can use information processing components with higher performance than the information processing components of the sensor device SU in terms of cost, or because the information processing components of the sensor device SU can be used in terms of the amount of information processing. Since it is necessary to use an information processing component with higher performance than the component, it is possible to shorten the information processing time of the second algorithm.

When the sensor unit SU monitors a plurality of monitored persons Ob in a one-to-many manner, the SV detection processing unit 223 extracts the human area of the monitored person Ob from the frame image by, for example, the background subtraction method, A label (identification code) is attached to each of the plurality of person areas. Each time the SV detection processing unit 223 extracts a person area from the frame image by the background subtraction method, the SV detection processing unit 223 attaches the same label to the person areas at the closest positions on the frame image. Then, the SV detection processing unit 223 performs each of the above-described processes on each of the labeled human regions to detect the struggle.

When the SV detection processing unit 223 detects the predetermined event (struggle in this embodiment), the sensor ID contained in the received detection request communication signal and the detected predetermined event (in this embodiment event information representing a struggle), the reception time of the received detection request communication signal, the image of any frame of the moving image contained in the received detection request communication signal, the received detection request communication signal contained The communication address corresponding to the sensor device SU having the sensor ID and the corresponding flag "0" are registered in fields 2311 to 2316 of the record newly added to the monitoring information table MT. As a result, the SV detection processing unit 223 stores and manages the monitoring information of the monitored person Ob in the monitoring information storage unit 231 of the SV storage unit 23 . Note that this processing is performed by the monitoring processing unit 222 instead of the SV detection processing unit 223 when the monitoring processing unit 222 receives notification of detection of the predetermined event (struggle in this embodiment) from the SV detection processing unit 223. can be Then, the SV detection processing unit 223 notifies the notification processing unit 224 that the predetermined event (struggle in this embodiment) has been detected.

When the SV detection processing unit 223 detects the predetermined event (struggle in this embodiment), the notification processing unit 224 sends an image to detect the predetermined event. The event detected by the sensor device SU is notified to the terminal devices SP and TA that receive the notification. More specifically, when receiving notification from the SV detection processing unit 223 that the predetermined event (struggling in the present embodiment) has been detected, the event is used to detect the predetermined event (struggling in the present embodiment). selects (searches) the notification destination corresponding to the sensor device SU that has transmitted the detection request communication signal containing the image (moving image in this embodiment) from the notification destination correspondence relationship stored in the inter-device information storage unit 232. , the second event notification communication signal is generated based on this selection result, and the SV communication IF unit 21 transmits the generated second event notification communication signal. The second event notification communication signal includes the sensor ID contained in the detection request communication signal, event information representing the detected predetermined event (struggle in this embodiment), and the moving image contained in the detection request communication signal. The communication address corresponding to the sensor device SU having the sensor ID contained in the detection request communication signal is contained as the download destination of the image of any frame of the above and the moving image.

3, the management server device SV is further connected to the SV control processing unit 22 as necessary, and a server side input unit (SV input unit ) 24, a server-side output unit (SV output unit) 25 for outputting various commands and data input by the SV input unit 24 and monitoring information related to monitoring of the monitored person Ob, and data exchange with external devices. A server-side interface unit (SVIF unit) 26 or the like for inputting and outputting data may be provided.

Such a management server device SV can be configured by, for example, a computer with a communication function.

The fixed terminal device SP has a communication function to communicate with other devices SU, SV, and TA via the network NW, a display function to display predetermined information, and an input function to input predetermined instructions and data. By inputting predetermined instructions and data given to the management server device SV and the portable terminal device TA, and displaying the monitoring information obtained by the sensor device SU, the user interface of the monitored person monitoring support system MS ( It is a device that functions as a UI). Such a fixed terminal device SP can be composed of, for example, a computer with a communication function.

The mobile terminal device TA has a communication function of communicating with other devices SV, SP, and SU via the network NW, a display function of displaying predetermined information, an input function of inputting predetermined instructions and data, and a voice call. inputting predetermined instructions and data given to the management server device SV and the sensor device SU, displaying the monitoring information obtained by the sensor device SU in response to a notification from the management server device SV, It is a device for responding to a nurse call or calling out to the sensor unit SU through voice communication.

Such a mobile terminal device TA can be configured by a portable communication terminal device such as a so-called tablet computer, smart phone, or mobile phone.

Next, the operation of this embodiment will be described. FIG. 7 is a flow chart showing the operation of the sensor device. FIG. 8 is a flow chart showing the operation of detection request processing in the flow chart shown in FIG. FIG. 9 is a flow chart showing the operation of the management server device. FIG. 10 is a flow chart showing the operation of advanced action detection processing in the flow chart shown in FIG.

In the monitored person monitoring support system MS configured as described above, each device SU, SV, SP, and TA initializes each necessary part when the power is turned on, and starts its operation. In the sensor unit SU, by executing the control processing program, the SU control processing unit 14 includes an SU control unit 141, an SU detection processing unit 142, a necessity determination unit 143, an image transmission unit 144, a nurse call processing unit 145, and a streaming unit. A processing unit 146 is functionally configured. In the management server device SV, the SV control processing unit 21 is functionally configured with an SV control unit 211, a monitoring processing unit 222, an SV detection processing unit 223, and a notification processing unit 224 by executing the control processing program.

First, the operation of the sensor device SU will be described. The sensor unit SU operates as follows for each frame or every few frames, thereby detecting a predetermined action of the person to be monitored Ob and determining whether or not a nurse call has been received. there is

In FIG. 7, first, the sensor unit SU acquires an image (image data) for one frame from the imaging unit 11 as the target image by the SU control unit 141 of the SU control processing unit 14 (S11).

Next, the sensor unit SU causes the SU detection processing unit 142 of the SU control processing unit 14 to perform the first detection processing for detecting a predetermined action of the monitored person Ob as an example of the predetermined event using the first algorithm. It is executed based on the target image acquired in S11 (S12). More specifically, the SU detection processing unit 142 determines success or failure in getting up, determines success or failure in getting out of bed, determines success or failure in falling, and determines success or failure in falling, using the first algorithm.

Next, the sensor unit SU determines whether or not the SU detection processing unit 142 detects a predetermined action of the monitored person Ob in the first detection processing S12. In the present embodiment, the SU detection processing unit 142 determines whether or not at least one of getting up, getting out of bed, falling, and tumbling of the monitored person Ob has been detected in the first detection processing S12. As a result of this determination, if the predetermined behavior has not been detected (No), the sensor device SU next executes the processing S15 and then the processing S16, while the predetermined behavior is detected. If so (Yes), the sensor device SU executes the next process S14 and then executes the process S16.

In this processing S14, the sensor device SU causes the SU detection processing unit 142 to notify the predetermined behavior detected in the processing S12 and the processing S13 to the predetermined terminal devices SP and TA via the management server device SV. As a predetermined event, a first event notification communication signal regarding detection of the predetermined action is transmitted to the management server device SV. More specifically, the SU detection processing unit 142 detects the sensor ID of the device itself, the predetermined event (here, one or more of getting up, getting out of bed, falling, and falling), and the first event containing the target image. An event notification communication signal is transmitted to the management server device SV via the SU communication IF section 15 .

In the process S15, the sensor unit SU performs a detection request process for requesting the management server SV to detect the predetermined action by the SU control processing unit 14 according to necessity, using a second algorithm different from the first algorithm. to run.

More specifically, each process shown in FIG. 8 is executed in this detection request process. In FIG. 8, first, the sensor unit SU uses a second algorithm different from the first algorithm for detecting a predetermined action of the monitored person Ob as an example of the predetermined event by the necessity determination unit 143, and the imaging unit 11, the necessity of detecting the predetermined action is determined (S151). In this embodiment, the predetermined behavior detected by the second algorithm is the struggle of the monitored person Ob, as described above. First, the necessity determination unit 143 determines that the position of the head extracted as described above changes from within the location area of the bedding BD to outside the location area of the bedding BD, and the size of the extracted head is By using the third threshold Th3, the first change time from a certain size to the size of the lying posture is compared with each of the fall determination time threshold and the first necessity determination threshold, and The position of the extracted head is within the living room RM excluding the location area of the bedding BD, and the size of the extracted head varies from a certain size to the size of the lying posture by using the third threshold value Th3. A second change time until the change to , is compared with each of the turnover determination time threshold and the second necessity determination threshold. As a result of these comparisons, the necessity determination unit 143 determines that the first change time is greater (longer) than the fall determination time threshold and the first change time is equal to or less than the first necessity determination threshold. Alternatively, when the second change time is greater than the fall determination time threshold and the second change time is equal to or less than the second necessity determination threshold, it is determined that there is a need to detect a struggle ( Yes), then the process S152 is executed by the image transmitting unit 144, and on the other hand, if the first change time is larger (longer) than the first necessity determination threshold, and if the second change time is greater than the second change time In other cases, excluding the case where it is determined that there is a need to detect the struggle, such as when the threshold is greater than the necessity determination threshold, it is determined that there is no need to detect the struggle (No), and this process ends.

In the process S152, the image transmission unit 144 causes the imaging unit 11 to generate an image with a resolution higher than the resolution of the image used for detecting the predetermined action in the first algorithm, and obtains an image with a higher resolution. . In the present embodiment, the high-resolution image is a moving image, and the image transmission unit 144 causes the imaging unit 11 to generate and acquire a high-resolution moving image of a predetermined length of time.

After processing S152, the image transmission unit 144 generates a detection request communication signal based on the high-resolution moving image of a predetermined length of time, and transmits the generated detection request communication signal to the management server device SV. (S153), and the process ends. Note that the image transmission unit 144 may, for example, after generating a moving image of a predetermined length of time, transmit the moving image to the management server device SV with a detection request communication signal composed of one or a plurality of communication signals. From the viewpoint of shortening the interruption, the moving image may be transmitted to the management server device SV by a detection request communication signal composed of a plurality of communication signals generated at appropriate time intervals during the generation of the moving image having a predetermined length of time.

During the execution of each of the processes S152 and S153, the monitoring of the monitored person Ob is interrupted (the process shown in FIG. 7 cannot be executed for each preset frame or every several frames). Since the second algorithm does not perform detection processing for detecting a predetermined event (struggle in this embodiment), it is possible to monitor the monitored person Ob immediately after the image is transmitted. In particular, it is effective when the first execution time for executing each process of the process S152 and the process S153 is shorter than the second execution time for executing the detection process by the second algorithm.

In the process S16, the sensor unit SU determines whether or not a nurse call is accepted by the nurse call processing unit 145. FIG. That is, the processes S11 to S14 or the processes S11 to S15 shown in FIG. 7 are repeatedly executed for each frame or every several frames. Until the execution of S14 or S15 (including all combinations of the previous execution of S14 and S15 and the current execution of S14 and S15), the nurse call reception operation unit 13 operates It is determined whether or not If the result of this determination is that the nurse call reception operation unit 13 has not been operated and the nurse call has not been received (No), the sensor unit SU ends this processing, while the nurse call reception operation unit 13 is operated to receive a nurse call (Yes), the sensor device SU executes the next process S17, and then ends this process.

In this processing S17, the sensor device SU is controlled by the nurse call processing unit 145 to notify the predetermined terminal devices SP and TA of the nurse call whose reception has been found in the processing S16 via the management server device SV. event, a first event notification communication signal regarding a nurse call is transmitted to the management server device SV. More specifically, the nurse call processing unit 145 transmits a first event notification communication signal containing the sensor ID of its own device and the nurse call reception information to the management server device SV via the SU communication IF unit 15 .

The sensor unit SU operates as described above in relation to detection of a predetermined action of the monitored person Ob and reception of a nurse call.

Next, the operation of the management server device SV will be explained. On the other hand, in FIG. 9, the management server device SV determines whether or not the SV communication IF section 21 has received a communication signal by the SV control section 221 of the SV control processing section 22 (S21). As a result of this determination, if the communication signal has not been received (No), the management server device SV returns the processing to S21. The management server device SV executes the following process S22. That is, the management server device SV waits for reception of a communication signal.

In process S22, the management server device SV uses the SV control unit 221 to determine the type of the received communication signal. As a result of this determination, if the received communication signal is the first event notification communication signal (first event notification), the management server device SV executes the processing S26 after executing the processing S23. If the communication signal is the detection request communication signal (detection request), the process S24 is executed and then the process S26 is executed, and the received communication signal is the first event notification communication signal and the detection request communication signal. If it is neither (other), the process S26 is executed after the process S25 is executed.

In the processing S23, the management server device SV uses the monitoring processing unit 222 of the SV control processing unit 22 to process the first event notification communication signal received from the sensor device SU in the processing S21. More specifically, first, the monitoring processing unit 222 stores the monitoring information regarding the monitoring of the monitored person Ob contained in the first event notification communication signal received from the sensor unit SU in the process S21, in the monitoring information storage unit 231. Memorize (record). Then, the monitoring processing unit 222 selects (searches for) the notification destination corresponding to the sensor device SU that transmitted the first event notification communication signal received in step S21 from the notification destination correspondence relationship stored in the inter-device information storage unit 232. )do. Next, the monitoring processing unit 222 generates and transmits a second event notification communication signal resulting from the first event notification communication signal received in the process S21 to the selected notification destination terminal devices SP and TA. .

In the process S24, the SV control processing unit 22 of the management server device SV executes advanced action detection processing for processing the detection request communication signal received from the sensor device SU in the process S21.

In this advanced behavior detection processing, more detailed analysis processing than the behavior analysis processing performed in the sensor device SU as described above is performed, and by more advanced information processing than the behavior detection information processing in the sensor device SU, Action is detected. More specifically, each process shown in FIG. 10 is executed. In FIG. 10 , first, the management server device SV executes the second detection processing by the SV detection processing section 223 of the SV control processing section 22 . More specifically, the SV detection processing unit 223 determines the success or failure of the struggle using the second algorithm. More specifically, the SV detection processing unit 223 performs the following processes using the second algorithm for each frame in the moving image of a predetermined length contained in the detection request communication signal received in the process S21. First, the SV detection processing unit 223 extracts the person area of the monitored person Ob from the frame image by, for example, the background subtraction method. Next, the SV detection processing unit 223 detects the center position and outline of the extracted person area. Then, the SV detection processing unit 223 determines whether or not the monitored person Ob is struggling based on each center position of each person area and each contour of each person area in each frame. For example, the SV detection processing unit 223 determines that each center position of each person region in each frame exists within a predetermined range set in advance with respect to the average position of each center position, and each frame When the movement of each contour of each person region in the above is repeatedly moving (vibrating) substantially periodically, it is determined that the monitored person Ob is struggling, the struggling is detected, and other than this case In this case, it is determined that the monitored person Ob is not struggling.

Next, the management server device SV determines whether or not the SV detection processing unit 223 detects a predetermined action of the monitored person Ob in the second detection processing S241 (S242). In this embodiment, the SV detection processing unit 142 determines whether or not the struggle of the monitored person Ob is detected in the second detection processing S241. As a result of this determination, if the predetermined behavior (here, struggle) is not detected (No), this process is terminated, and if the predetermined behavior (here, struggle) is detected ( Yes), the sensor unit SU terminates this process after sequentially executing the process S243 and the process S244.

In this process S243, the management server apparatus SV causes the SV detection processing unit 223 to monitor the SV storage unit 23 for the monitoring information regarding the predetermined behavior (here, struggling) of the monitored person Ob detected in the second detection processing S241. Stored in the information storage unit 231 . More specifically, in this embodiment, the SV detection processing unit 223 receives the sensor ID contained in the detection request communication signal received in the process S21, and the event information indicating the detected predetermined event (here, struggle). , the reception time of the received detection request communication signal, an image of any frame of the moving image contained in the received detection request communication signal, and a sensor having a sensor ID contained in the received detection request communication signal. The communication address corresponding to the device SU and the corresponding flag "0" are registered in fields 2311 to 2316 of the record newly added to the monitoring information table MT. Thereby, the SV detection processing unit 223 stores and manages the monitoring information of the monitored person Ob in the monitoring information storage unit 231 .

In a process S244 executed after the process S243, the management server device SV causes the notification processing unit 224 to transmit an image for detecting the predetermined behavior (here, struggle) detected in the process S241. The terminal devices SP and TA are notified of the event detected by the sensor device SU. More specifically, the information processing unit 224 sets the notification destination corresponding to the sensor device SU that transmitted the detection request communication signal received in the process S21, that is, the sensor ID contained in the detection request communication signal. The notification destination is selected (searched) from the notification destination correspondence relationship stored in the inter-device information storage unit 232, and based on the selection result, A second event notification communication signal is generated, and the SV communication IF unit 21 transmits the generated second event notification communication signal.

Returning to FIG. 9, in the process S25, the management server device SV causes the SV control processing unit 22 to perform appropriate processes according to the communication signal received in the process S21.

Then, in the process S26 executed after each of the processes S23 to S25, the management server apparatus SV uses the SV control processing unit 22 to determine whether or not the operation is finished (stopped). As a result of this determination, if the operation is to end (stop) (Yes), the management server device SV ends this process. The server device SV returns the process to process S21.

In the above description, the SV control processing unit 22 further sends back the second detection processing result to the processing sensor device SU that transmitted the detection request communication signal received in step S21 in step S241, The sensor device SU may further skip (omit) the execution of the process S15 until the SU control processing unit 14 receives a response from the management server device SV after transmitting the detection request communication signal.

With respect to the first event notification communication signal, the detection request communication signal, etc. received from the sensor device SU, the monitoring server device SV operates as described above. In this embodiment, the predetermined event relating to the monitored person Ob is defined in advance, and in this embodiment, includes a predetermined action and a nurse call in the monitored person Ob. The predetermined behavior of the monitored person Ob is defined in advance, and includes getting up, getting out of bed, falling, falling, and struggling in this embodiment. Then, in the present embodiment, among the rising, leaving the bed, falling, falling, and struggling, getting up, leaving the bed, falling, and falling (part of the predetermined actions) are detected by the sensor device SU using the first algorithm. , waking up, getting out of bed, falling, falling, and struggling (the other part (or the remainder) of the predetermined behavior) are detected by the management server device SV, which receives a detection request from the sensor device SU. Algorithmically detected.

On the other hand, the fixed terminal device SP and the portable terminal device TA are waiting for reception of a communication signal, and upon receiving the second event notification communication signal from the management server device SV via the network NW, the second event notification communication signal Each information such as the sensor ID and the event information stored in is stored (recorded) as monitoring information of the monitored person Ob monitored by the sensor device SU having this sensor ID, and the monitoring information is displayed.

FIG. 11 shows an example of a monitoring information screen for displaying the monitoring information regarding the monitoring of this monitored person Ob. For example, as shown in FIG. 11, the monitoring information screen 52 includes a menu bar area 511, an arrangement location of the sensor device SU having the sensor ID contained in the received second event notification communication signal, and the sensor ID. from the monitored person name area 521 that displays the name of the monitored person Ob monitored by the sensor device SU, and the reception time of the received second event notification communication signal (or the detection time of the predetermined action) and the event information (detection result of the predetermined action) contained in the received second event notification communication signal; and the received second event notification communication signal. , an image area 523 displaying an image (that is, a target image captured by the sensor device SU having the sensor ID) (here, a still image), a “correspond” button 524, and a “talk” button 525 and a "Watch LIVE" button 526, which are displayed on the touch panel.

In order to display the installation location of the sensor unit SU and the name of the monitored person Ob in the monitored person name area 521, the sensor information is received from the management server SV in the mobile terminal device TA, and is displayed in FIG. A table similar to the sensor information table ST is stored, and using the sensor ID contained in the received second event notification communication signal as a search key, the installation location of the sensor unit SU and the name of the monitored person Ob are retrieved from the table. searched and displayed. In the detection information display area 522, the detection result contained in the received second event notification communication signal (in this embodiment, each name of getting in bed, getting up, getting out of bed, falling, and struggling) may be displayed as it is. Although it is good, in this embodiment, the detection result is displayed by an icon that symbolically represents it. In order to display with this icon, each action and an icon symbolically representing the action are stored in advance in the mobile terminal device TA in association with each other. In the example shown in FIG. 11, the detection information display area 522 displays a wake-up icon symbolically representing wake-up. A "respond" button 524 on the monitoring information screen 52 executes a predetermined response (coping, treatment, measures) such as lifesaving, nursing care, nursing care, and assistance for the detection result displayed on the monitoring information screen 52. This is a button for inputting to the mobile terminal device TA that the intention is the user of the mobile terminal device TA. The "talk" button 525 is a button for requesting a voice call, and is for inputting an instruction to connect the sensor device SU with the sensor ID and the mobile terminal device TA so that they can talk via the network NW. button. The "Watch LIVE" button 526 is a button for requesting a live moving image, and is a button for inputting an instruction to display a moving image captured by the sensor device SU with the sensor ID.

When the mobile terminal device TA receives a predetermined input operation while the monitoring information screen 52 is being displayed, the mobile terminal device TA executes an appropriate process according to the content of the predetermined input operation, and terminates this process. , and waits for the next communication signal addressed to itself.

For example, when the portable terminal device TA accepts the input operation of the "correspond" button 524, it first accepts "correspond" for the monitoring information of the monitored person Ob currently displayed on the monitoring information screen 52. Memorize it with a note. Then, the portable terminal device TA transmits the sensor ID corresponding to the monitoring information of the monitored person Ob displayed on the monitoring information screen 52, the event information, and the information indicating that "respond" has been received (corresponding meaningful information). The accommodated communication signal (correspondence intention notification communication signal) is transmitted to the management server device SV. The management server device SV, which has received this intention-to-handle notification communication signal, first, as an example of processing S25 shown in FIG. in the sensor ID field 2311 and the event field 2312, respectively, and the corresponding flag "0" is registered in the corresponding field 2316. A response flag "1" indicating reception of response is registered in the response field 2316 of the record in which the response is received. A signal (corresponding intention notifying communication signal) is transmitted to the terminal devices SP and TA by broadcast communication. As a result, with respect to the sensor ID corresponding to the monitoring information of the monitored person Ob displayed on the monitoring information screen 52, the terminal devices SP and TA are synchronized to the effect that "support" has been received.

Further, for example, when the mobile terminal device TA accepts the input operation of the “Talk” button 525, it requests the sensor device SU monitoring the monitored person Ob currently displayed on the monitoring information screen 52 to make a voice call. A communication signal (a call request communication signal) including information such as the above is transmitted, and the corresponding sensor unit SU is connected via the network NW so as to be able to make a voice call. This enables voice communication between the mobile terminal device TA and the sensor device SU. When the mobile terminal device TA receives an input operation of an unillustrated "end" button, which is a button for inputting an instruction to end the voice call, the monitored person Ob displayed on the monitoring information screen 52 is terminated. A communication signal containing information such as a request to end the voice call (call end communication signal) is transmitted to the sensor device SU to be monitored. This terminates the voice call between the mobile terminal device TA and the sensor device SU.

Further, for example, when the mobile terminal device TA receives the input operation of the “Watch LIVE” button 526, the mobile terminal device TA sends the live video to the sensor device SU monitoring the monitored person Ob currently displayed on the monitoring information screen 52. a communication signal (moving image distribution request communication signal) containing information such as a request for distribution of the above, and in response to this, the sensor device SU is connected to the sensor device SU via the network NW so that the moving image can be downloaded, and the sensor device SU Receive live video distribution from , and display the video that has received this distribution in streaming playback. On the monitoring information screen 52 that displays the live moving image, the moving image is displayed in the image area 523, and an unillustrated “End LIVE” button is displayed instead of the “Watch LIVE” button 526. FIG. As a result, live moving images are displayed on the mobile terminal device TA. The unillustrated "END LIVE" button is a button for requesting the end of the moving image, and terminates (stops) the distribution of the moving image captured by the sensor device SU of the sensor ID and terminates (stops) the display. ) is a button for inputting an instruction to When the mobile terminal device TA receives the input operation of the "END LIVE" button, it requests the sensor device SU monitoring the monitored person Ob currently displayed on the monitoring information screen 52 to end the video distribution. A communication signal (moving image delivery end communication signal) containing the information of is transmitted, and a still image is displayed. As a result, the mobile terminal device TA terminates live video display.

Through such operations, the monitored person monitoring support system MS detects the predetermined behavior of each monitored person Ob by means of the sensor devices SU, the management server device SV, the fixed terminal device SP, and the mobile terminal device TA. , receives a nurse call and supports the monitoring of each monitored person Ob.

As described above, the sensor device SU in the embodiment, the processing method of the sensor device SU implemented in the sensor device SU, and the monitored person monitoring support system MS use the second algorithm to detect a predetermined event (struggle in the above example). When it is determined that detection is necessary, instead of detecting the predetermined event by the second algorithm, the image generated by the imaging unit 11 is transmitted to the management server device SV which is an example of the central processing unit do. Therefore, even if the detection processing of the SU detection processing unit 142 is interrupted for image transmission, the second algorithm does not perform the detection processing for detecting the predetermined event. The detection processing of the detection processing unit 142 can be performed, and the interruption of monitoring can be shortened. In particular, when there are a plurality of monitored persons Ob, and the sensor units SU monitor the plurality of monitored persons Ob in a one-to-many manner, one of the plurality of monitored persons Ob is selected by the second algorithm. , the monitoring of the remaining monitored person Ob can be interrupted in a shorter time. In particular, even if the information processing time of the second algorithm is longer than the information processing time of the first algorithm when information processing is performed by an information processing device having the same performance, the sensor device detects a predetermined event using SU and the second algorithm. Since detection processing for detection is not performed, an information processing device having performance capable of performing detection processing for detecting a predetermined event using the first algorithm can be used as the sensor device SU, and an information processing device with higher performance is not required. . Therefore, the cost can be reduced accordingly.

The sensor unit SU, its processing method, and monitored person monitoring support system MS have a resolution higher than that of images used for detecting predetermined events (in the above example, getting up, getting out of bed, falling, and falling) in the first algorithm. image to the management server device SV. Therefore, in the management server device SV, more detailed analysis processing can be performed in order to detect the predetermined event (struggle in the above example). Therefore, it is possible to improve the detection performance of detecting the predetermined event (struggle in the above example), and to increase the types of detectable events.

In the present embodiment, the management server device SV and the monitored person monitoring system MS, which are examples of the central processing unit, receive an image from the sensor device SU in order to detect the predetermined event (struggle in the above example). and detecting the predetermined event based on the received image. Therefore, the management server device SV and the monitored person monitoring support system MS can share the detection processing of detecting the predetermined event with the sensor device SU, and the interruption of monitoring in the sensor device SU can be shortened. It can be done in a timely manner, and therefore, an optimal monitored person monitoring support system MS can be constructed with the right person in the right place.

In the above-described embodiment, a condition that the torso region of the moving body region extracted as described above does not move for several tens of seconds is added to the conditions for determining that detection is necessary in step S151. can be The trunk region is detected from the moving body region, for example, by pattern matching using a prepared trunk model, or by, for example, a neural network trained for trunk detection. Alternatively, the condition that the trunk region of the moving body region does not move for several tens of seconds may be a condition that the central position of the moving body region stays within a predetermined range set in advance for several tens of seconds.

Further, in the above-described embodiment, the writhing of the monitored person Ob is detected in the second detection process of the process S241, but the fainting of the monitored person Ob may be detected. In this case, in the second detection process of step S241, the body trunk of the monitored person Ob is at a substantially fixed position, and the monitored person Ob moves approximately periodically and repeatedly around the body trunk of the monitored person Ob ( (vibration), further depending on whether or not the time (fixed position time) during which the trunk of the monitored person Ob is in a substantially fixed position is equal to or longer than a preset time (fixed position determination time threshold). The syncope is detected. More specifically, the time length of the moving image is appropriately set in advance to the time required for detecting the fainting, which is longer than the time required for detecting the writhing. Further, when it is determined that the monitored person Ob is not struggling, each center position of each person area is detected for each subsequent frame, and each center position of each person area in each of these frames is determined as follows: It is determined whether or not the position exists within a predetermined range set in advance with respect to the average position of the center positions for a period equal to or longer than the fixed position determination time threshold. As a result of this determination, when each of the center positions exists for the predetermined position determination time threshold or longer, it is determined that the monitored person Ob has fainted. When each center position is less than the fixed position determination time threshold and exceeds the predetermined range with respect to the average position of each center position), it is determined that the monitored person Ob is not fainting but that the monitored person Ob is acting intentionally.

Although this specification discloses various aspects of the technology as described above, the main technologies are summarized below.

A sensor device according to one aspect includes: a sensor device provided corresponding to a monitored person who is a monitoring target, detecting a predetermined event related to the monitored person; and a terminal that is communicatively connected to the central processing unit and receives notification of the event detected by the sensor device via the central processing unit. The sensor device of the monitored person monitoring support system for assisting the monitoring of the monitored person, comprising: an imaging unit for generating an image; and a first algorithm for detecting the predetermined event, a first detection processing unit for detecting the predetermined event based on the image generated by the imaging unit; and detecting the predetermined event when the first detection processing unit does not detect the predetermined event. a necessity determination unit that determines the necessity of detecting the predetermined event based on the image generated by the imaging unit, using a second algorithm different from the first algorithm; an image transmission unit configured to transmit an image generated by the imaging unit to the central processing unit in order to detect the predetermined event when it is determined that event detection is necessary. Preferably, in the sensor device described above, there are a plurality of monitored persons, and the sensor device monitors the plurality of monitored persons on a one-to-many basis. Preferably, in the sensor device described above, the predetermined event includes a plurality of types, and the first and second algorithms detect different types of events. Preferably, in the sensor device described above, the information processing time of the second algorithm is longer than the information processing time of the first algorithm when information processing is performed by an information processing device having the same performance. Preferably, in the sensor device described above, the image transmission unit issues a command to detect the predetermined event when the necessity determination unit determines that the predetermined event needs to be detected. A communication signal (detection request communication signal) containing the information to be represented and the image generated by the imaging unit is generated, and the generated communication signal (detection request communication signal) is transmitted to the central processing unit. Preferably, in the sensor device described above, the image is a moving image of a predetermined time.

In such a sensor device, when the second algorithm determines that it is necessary to detect a predetermined event, instead of detecting the predetermined event with the second algorithm, the image generated by the imaging unit is centered. Send to processor. Therefore, even if the detection processing of the first detection processing unit is interrupted for image transmission, the detection processing for detecting a predetermined event by the second algorithm is not performed. The detection processing of the detection processing unit can be performed, and the interruption of monitoring can be shortened. In particular, when there are a plurality of monitored persons and the sensor devices monitor the plurality of monitored persons in a one-to-many manner, one of the plurality of monitored persons detects a predetermined event by the second algorithm. Even if it falls into a necessary state, it is possible to interrupt the monitoring of the remaining persons to be monitored in a shorter time. In particular, even if the information processing time of the second algorithm is longer than the information processing time of the first algorithm when information processing is performed by an information processing device having the same performance, the sensor device detects a predetermined event using the second algorithm. Therefore, an information processing device capable of performing detection processing for detecting a predetermined event using the first algorithm can be used as the sensor device, and an information processing device with higher performance is not required. Therefore, the cost can be reduced accordingly.

In another aspect, in the sensor device described above, the imaging unit generates the images with a plurality of mutually different resolutions, and the image transmission unit generates the images used for detecting the predetermined event in the first algorithm. to the central processing unit. Preferably, in the sensor device described above, when the necessity determination unit determines that the detection of the predetermined event is necessary, the image transmission unit uses the first algorithm to detect the predetermined event. The imaging unit is caused to generate an image with a resolution higher than the resolution of the image to be used, and the generated high-resolution image is transmitted to the central processing unit.

Such a sensor device transmits to the central processing unit an image with a higher resolution than the image used for detecting the predetermined event in the first algorithm. Therefore, the central processing unit can perform more detailed analysis processing in order to detect the predetermined event. Therefore, it is possible to improve the detection performance for detecting the predetermined event, and to increase the types of detectable events.

A processing method for a sensor device according to one aspect includes a sensor device provided corresponding to a monitored person to be monitored and detecting a predetermined event related to the monitored person; A central processing unit for managing events detected by the sensor device and received from the sensor device, and a notification of the event detected by the sensor device via the central processing unit communicably connected to the central processing unit. A method of processing the sensor device of a monitored person monitoring support system for assisting monitoring of the monitored person, comprising a terminal device receiving a a detection processing step of detecting the predetermined event based on the image generated in the imaging step; and detecting the predetermined event if the predetermined event is not detected in the detection processing step. a necessity determination step of determining the necessity of detecting the predetermined event based on the image generated in the imaging step by a second algorithm different from the first algorithm; an image transmission step of transmitting the image generated in the imaging step to the central processing unit in order to detect the predetermined event when it is determined that the predetermined event needs to be detected.

In such a sensor device processing method, when the second algorithm determines that the predetermined event needs to be detected, the event generated in the imaging process is not detected by the second algorithm. Send the image to the central processing unit. Therefore, even if the detection processing of the first detection processing step is interrupted for image transmission, the detection processing for detecting a predetermined event by the second algorithm is not executed. The detection process of the detection process can be performed, and the interruption of monitoring can be shortened. In particular, when there are a plurality of monitored persons and the sensor devices monitor the plurality of monitored persons in a one-to-many manner, one of the plurality of monitored persons detects a predetermined event by the second algorithm. Even if it falls into a necessary state, it is possible to interrupt the monitoring of the remaining persons to be monitored in a shorter time. In particular, even if the information processing time of the second algorithm is longer than the information processing time of the first algorithm when information processing is performed by an information processing device having the same performance, the sensor device detects a predetermined event using the second algorithm. Therefore, an information processing device capable of performing detection processing for detecting a predetermined event using the first algorithm can be used as the sensor device, and an information processing device with higher performance is not required. Therefore, the cost can be reduced accordingly.

A central processing unit according to another aspect includes a sensor device that is provided corresponding to a monitored person who is a monitoring target, detects a predetermined event related to the monitored person, and is communicably connected to the sensor device, A central processing unit for managing events detected by the sensor device and received from the sensor device, and a notification of the event detected by the sensor device via the central processing unit communicably connected to the central processing unit. the central processing unit of a monitored person monitoring support system for supporting monitoring of the monitored person, wherein an image is received from the sensor device for detecting the predetermined event a second detection processing unit for detecting the predetermined event based on the received image; and when the second detection processing unit detects the predetermined event, the detected predetermined event is a notification processing unit that notifies a terminal device that receives notification of an event detected by the sensor device that has transmitted an image for detecting a predetermined event. Preferably, in the central processing unit described above, the sensor device of the monitored person monitoring support system is any one of the sensor devices described above.

Such a central processing unit detects the predetermined event based on the received image when an image is received from the sensor device for detecting the predetermined event. Therefore, the central processing unit can share the detection processing for detecting the predetermined event with the sensor device, and the interruption of monitoring by the sensor device can be shortened. A monitored person monitoring support system can be constructed.

A monitored person monitoring support system according to another aspect includes a sensor device that is provided corresponding to a monitored person to be monitored, detects a predetermined event related to the monitored person, and is capable of communicating with the sensor device. a central processing unit connected to manage events detected by the sensor device and received from the sensor device; and a central processing unit communicatively connected to the central processing unit and detected by the sensor device via the central processing unit. A monitored person monitoring support system comprising a terminal device for receiving notification of an event and for supporting monitoring of said monitored person, wherein said sensor device is any one of the above-described sensor devices, and said central processing unit The device is the central processing unit according to claim 3, wherein the second detection processing unit detects the predetermined event based on the received image with the second algorithm.

In such a monitored person monitoring support system, the sensor device detects a predetermined event using a first algorithm, and the central processing unit detects a predetermined event using a second algorithm. Therefore, in the monitored person monitoring support system, the detection process for detecting the predetermined event can be shared between the sensor device and the central processing unit, and the interruption of monitoring by the sensor device can be shortened. Therefore, it is possible to construct an optimal monitored person monitoring support system with the right person in the right place.

This application is based on Japanese Patent Application No. 2017-199066 filed on October 13, 2017, the content of which is included in the present application.

While embodiments of the present invention have been illustrated and described in detail, this is done by way of illustration and example only, and not limitation. The scope of the invention should be construed by the language of the appended claims.

Although the present invention has been adequately and fully described above through embodiments with reference to the drawings in order to express the present invention, modifications and/or improvements to the above-described embodiments can be easily made by those skilled in the art. It should be recognized that it is possible. Therefore, to the extent that modifications or improvements made by those skilled in the art do not depart from the scope of the claims set forth in the claims, such modifications or improvements do not fall within the scope of the claims. is interpreted to be subsumed by

According to the present invention, it is possible to provide a sensor device, a central processing unit, a processing method of the sensor device, and the monitored person monitoring support system in a monitored person monitoring support system for supporting monitoring of a monitored person.

Claims (4)

a sensor device provided corresponding to a monitored person to be monitored and detecting a predetermined event related to the monitored person; a central processing unit that manages received events; and a terminal device that is communicably connected to the central processing unit and receives notification of an event detected by the sensor device via the central processing unit, the monitored person The sensor device of the monitored person monitoring support system for supporting the monitoring of
an imaging unit that generates an image;
a first detection processing unit for detecting the predetermined event based on the image generated by the imaging unit using a first algorithm for detecting the predetermined event;
A second algorithm different from the first algorithm for detecting the predetermined event when the first detection processing unit does not detect the predetermined event, based on the image generated by the imaging unit. a necessity determination unit that determines the necessity of detecting a predetermined event;
Image transmission for transmitting an image generated by the imaging unit to the central processing unit for detecting the predetermined event when the necessity determining unit determines that the predetermined event needs to be detected. and
sensor device. The imaging unit generates the images at a plurality of resolutions different from each other,
The image transmission unit transmits to the central processing unit an image having a resolution higher than that of the image used for detecting the predetermined event in the first algorithm.
A sensor device according to claim 1 . a sensor device provided corresponding to a monitored person to be monitored and detecting a predetermined event related to the monitored person; a central processing unit that manages received events; and a terminal device that is communicably connected to the central processing unit and receives notification of an event detected by the sensor device via the central processing unit, the monitored person A method of processing the sensor device of a monitored person monitoring support system for supporting the monitoring of
an imaging step to generate an image;
a detection processing step of detecting the predetermined event based on the image generated in the imaging step with a first algorithm for detecting the predetermined event;
A second algorithm different from the first algorithm for detecting the predetermined event when the predetermined event is not detected in the detection processing step, and detecting the predetermined event based on the image generated in the imaging step a necessity determination step of determining the necessity of detecting an event;
Image transmission for transmitting an image generated in the imaging step to the central processing unit for detecting the predetermined event when the necessity determining step determines that the predetermined event needs to be detected. and
A method of processing a sensor device. a sensor device provided corresponding to a monitored person to be monitored and detecting a predetermined event related to the monitored person; a central processing unit that manages received events; and a terminal device that is communicably connected to the central processing unit and receives notification of an event detected by the sensor device via the central processing unit, the monitored person A monitored person monitoring support system for supporting the monitoring of
The sensor device is the sensor device according to claim 1 or claim 2,
The central processing unit includes a second detection processing unit that detects the predetermined event based on the received image when an image is received from the sensor device for detecting the predetermined event; When the detection processing unit detects the predetermined event, the detected predetermined event is sent to the terminal device that receives the notification of the event detected by the sensor device that transmitted the image for detecting the predetermined event. A notification processing unit that notifies ,
The second detection processing unit detects the predetermined event based on the received image with the second algorithm.
Monitored person monitoring support system.

Images