WO2016175109A1

WO2016175109A1 - Monitoring device, monitoring method, monitoring program, and monitoring system

Info

Publication number: WO2016175109A1
Application number: PCT/JP2016/062576
Authority: WO
Inventors: 俊之青木
Original assignee: コニカミノルタ株式会社
Priority date: 2015-04-27
Filing date: 2016-04-21
Publication date: 2016-11-03
Also published as: JPWO2016175109A1; JP6683199B2

Abstract

With the monitoring device, monitoring method, monitoring program, and monitoring system according to the present invention: a plurality of problem determination thresholds is associated with each of a plurality of image sensors which is disposed in each of a plurality of sites and generates images; prescribed postures of a monitored subject are determined on the basis of the images of the image sensors; and if the prescribed postures of the monitored subject have exceeded the problem determination thresholds which are associated with the image sensors, it is determined that a problem has occurred with the monitored subject.

Description

Monitoring device, monitoring method, monitoring program, and monitoring system

The present invention relates to a monitoring device, a monitoring method, a monitoring program, and the monitoring system used in a monitoring system that monitors a monitored person to be monitored with a plurality of devices.

Japan (Japan) is an aging society, more specifically the ratio of population over 65 years old to the total population due to the improvement of living standards accompanying the post-war high economic growth, improvement of sanitary environment and improvement of medical standards, etc. It is a super-aging society with an aging rate exceeding 21%. In 2005, the total population was about 126.5 million, while the elderly population over the age of 65 was about 25.56 million. In 2020, the total population was about 124.11 million. There is also a prediction that the elderly population will be about 34.56 million. In such an aging society, nurses who need nursing or nursing care due to illness, injury, elderly age, etc., or those who need nursing care (such as those who require nursing care) are those who need nursing in a normal society that is not an aging society. This is expected to increase more than

Such nurses are required to enter nursing facilities such as hospitals and welfare facilities for the elderly (Japanese elderly law short-term entrance facilities, nursing homes for the elderly and special nursing homes for the elderly, etc.). In facilities such as hospitals and welfare facilities for the elderly, nurses and caregivers regularly check their safety by patroling them so that nurses who need them can stay comfortably and with peace of mind. However, labor savings are required, and the work load per person increases because the number of nurses, caregivers, etc. decreases in the semi-night work and night work hours compared to the day work hours. Reduction of is demanded. For this reason, in recent years, a monitored person monitoring device that monitors a monitored person to be monitored, such as a care recipient, has been researched and developed.

As one of such techniques, for example, there is a life reaction determination device disclosed in Patent Document 1. The living reaction determination device disclosed in Patent Document 1 sets watch items that divide the state of living behavior into awake, wash, meal, clean, rest, toilet, bathing, bedtime, etc., and for each watch item Life response detection means for detecting the start time and end time of actions for each watch item by the installed sensor, the number of actions, and input information storage means for inputting and storing the output from the life reaction detection means for each item, On the other hand, determination information in which determination information including sensor numbers of the sensors installed for each of the monitoring items and processing symbols indicating the presence or absence of the behavior or the excess or deficiency of the behavior as symbols is input in advance. Input means, determination information storage means for storing the determination information input by the determination information input means, input information from the input information storage means, and the determination information storage means And an item for each information extraction means for taking out the determination information from the provided items each determination means perform abnormality determination or normal determination based on the input information and the determination information retrieved by said item every information extraction means. More specifically, in Patent Document 1, there are sensors that can detect the behavior start, behavior end, and the number of behaviors, with the status of living behavior classified into waking up, washing, meal, cleaning, rest, toilet, bathing, and sleeping. Each item is provided for each item. For example, human sensors, door sensors, floor sensors, mat sensors, and the like are used. Then, based on a predetermined start time, end time, and action count determination value, the abnormal contents of the presence of action, the absence of action, the excessive action, and the insufficient action are determined using a predetermined determination calculation formula.

On the other hand, in terms of safety confirmation, a single person living alone is the same as the care recipient and the like and is a subject to be monitored.

By the way, in the patent document 1, the state of the living behavior is classified into items, and the abnormality content is based on the behavior number determination value set in advance by the number of times from the start time to the end time set in advance for each item. It has been judged. For this reason, in Patent Document 1, if the resident of the care facility does not perform the living behavior of the preset item between the preset start time and the end time, the abnormal content is accurately determined. Can not.

In addition, since the sensors are selected and arranged according to the items, if a plurality of types of sensors provided for each item are arranged, if the installation location is wrong, the contents of the abnormality are erroneously determined. Will end up. Since a plurality of types of sensors are required in this way, hardware and software must be prepared for each type of sensor, which complicates the apparatus.

JP 2006-48461 A

The present invention has been made in view of the above-described circumstances, and an object of the present invention is to provide a monitoring device, a monitoring method, a monitoring program, and a monitoring system that can determine an abnormality of a monitored person more accurately with a simpler configuration. Is to provide.

In the monitoring device, the monitoring method, the monitoring program, and the monitoring system according to the present invention, a plurality of abnormality determination thresholds are associated with each of a plurality of image sensors that are arranged at a plurality of locations and generate images, and images of the image sensors. If the predetermined posture of the monitored person is determined based on the image and the predetermined posture of the monitored person exceeds an abnormality determination threshold value associated with the image sensor, an abnormality has occurred in the monitored person Determined. Therefore, the monitoring device, the monitoring method, the monitoring program, and the monitoring system according to the present invention can determine the abnormality of the monitored person more accurately with a simpler configuration.

The above and other objects, features and advantages of the present invention will become apparent from the following detailed description and the accompanying drawings.

It is a figure which shows the structure of the to-be-monitored person monitoring system in embodiment. It is a block diagram which shows the structure of the monitoring person monitoring central processing apparatus in the said monitoring person monitoring system. It is a figure which shows the abnormality determination threshold value table memorize | stored in the said to-be-monitored person monitoring central processing unit. It is a figure which shows the structure of the image sensor in the said to-be-monitored person monitoring system. It is a flowchart which shows operation | movement of the monitoring person monitoring central processing apparatus in the said monitoring person monitoring system. It is a figure which shows the mode of the intruder's invasion.

Hereinafter, an embodiment according to the present invention will be described with reference to the drawings. In addition, the structure which attached | subjected the same code | symbol in each figure shows that it is the same structure, The description is abbreviate | omitted suitably. In this specification, when referring generically, it shows with the reference symbol which abbreviate | omitted the suffix, and when referring to an individual structure, it shows with the reference symbol which attached the suffix.

FIG. 1 is a diagram illustrating a configuration of a monitored person monitoring system according to the embodiment. FIG. 2 is a block diagram illustrating a configuration of a monitored person monitoring central processing unit in the monitored person monitoring system according to the embodiment. FIG. 3 is a diagram showing an abnormality determination threshold value table stored in the monitored person monitoring central processing unit. FIG. 4 is a diagram illustrating a configuration of the image sensor in the monitored person monitoring system according to the embodiment.

The monitored person monitoring system S in the embodiment is a system that monitors a monitored person (watched person) to be monitored (watched) with a plurality of devices connected to be communicable with each other. It is. The monitored person monitoring system S is disposed at an appropriate place according to the monitored person. The monitored person (person to be watched over) is, for example, a person who needs nursing due to illness or injury, a person who needs care due to a decrease in physical ability, or a single person living alone. In particular, from the viewpoint of enabling early detection and early action, the monitored person is preferably a person who needs to be detected when a predetermined inconvenient event such as an abnormal state occurs in the person. . For this reason, the monitored person monitoring system S is suitably arranged in a building such as a hospital, a welfare facility for the elderly, and a dwelling unit according to the type of the monitored person.

In the example illustrated in FIG. 1, the monitored person monitoring system S includes a plurality of image sensors D that are arranged at a plurality of locations and generate images, and are connected to each of the plurality of image sensors so as to communicate with each other. And a monitored person monitoring central processing unit SV that monitors the monitored person Ob based on the image generated in step (b). The monitored person monitoring system S is disposed in the residence of the monitored person Ob, and includes the entrance R-1, the living room R-2, the bedroom R-3, the toilet R-4, the kitchen R-5, the kitchen R-5, and the dressing room R. In order to monitor the monitored person Ob by individually disposing the image sensor D in each of the seven locations of −6 and the corridor R-7, seven first to seventh image sensors D-1 to D With -7.

These entrances R-1, living room R-2, bedroom R-3, toilet R-4, kitchen R-5, dressing room R-6, and corridor R-7 are corridor with entrance R-1 serving as an entrance to the outside. Via R-7, the living room R-2 and the toilet R-4 are connected to each of the doors, and the living room R-2 passes through the doors to the bedroom R-3, the kitchen R-5 and the dressing room R-6, respectively. The dressing room R-6 is arranged so as to communicate with the bathroom R-8 through the door. A first image sensor D-1 is disposed in the entrance R-1, a second image sensor D-2 is disposed in the living room R-2, and a third image sensor D is disposed in the bedroom R-3. -3, a fourth image sensor D-4 is disposed in the toilet R-4, a fifth image sensor D-5 is disposed in the kitchen R-5, and a dressing room R-6 Includes a sixth image sensor D-6, and a corridor R-7 includes a seventh image sensor D-7.

These first to seventh image sensors D-1 to D-7 are connected to each other and to the monitored person central processing unit SV by wired or wireless, LAN (Local Area Network), telephone network, data communication network, etc. Communication via a network (network, communication line). The network may be provided with relay stations such as repeaters, bridges, routers, and cross-connects that relay communication signals. In the example shown in FIG. 1, the first to seventh image sensors D-1 to D-7 and the monitored person monitoring central processing unit SV are communicably connected to each other by, for example, a wireless LAN according to the IEEE 802.11 standard. Yes.

In this way, each of the image sensors D-1 to D-7 disposed in each of the rooms R-1 to R-7 generates an image for each of the rooms R-1 to R-7. Then, the generated image is transmitted to the monitored person monitoring central processing unit SV via the network.

These first to seventh image sensors D-1 to D-7 have the same configuration. For example, as shown in FIG. 4, the imaging unit 11 and the sensor-side control processing unit (D control processing unit) ) 12, sensor side input unit (D input unit) 13, sensor side output unit (D output unit) 14, sensor side interface unit (DIF unit) 15, and sensor side communication interface unit (D communication IF unit) 16, a sensor-side storage unit (D storage unit) 17, an illumination unit 18, and a power supply unit 19.

The imaging unit 11 is an apparatus that is connected to the D control processing unit 12 and images a predetermined range of imaging target under the control of the D control processing unit 12 to generate an image (image data) of the imaging target. The imaging unit 11 may be a device that generates a visible light image, but in the present embodiment, it is a device that generates an infrared image so that the monitored person Ob can be monitored even in a relatively dark place. For example, in this embodiment, the imaging unit 11 has an imaging optical system that forms an infrared optical image of an imaging target on a predetermined imaging surface, and a light receiving surface that matches the imaging surface. An image sensor that is arranged and converts an infrared optical image in the imaging target into an electrical signal, and image data that represents an infrared image in the imaging target by performing image processing on the output of the image sensor And an image signal processor (ISP) that converts the data format of image data output from the digital camera into a data format that can be handled by the D control processing unit 12 or JPEG / An MPEG4 converter is provided. In the image forming optical system of the digital camera, in this embodiment, the object to be imaged is a room R such as the entrance R-1, the living room R-2, and the corridor R-7. It is preferable that the optical system has a wide-angle optical system (so-called wide-angle lens (including a fisheye lens)) having an angle of view that can capture the entire R, and from this point of view, the digital camera includes a room in which the image sensor D is disposed. It is preferable that the imaging optical system can be exchanged according to the size (width) of equal R, that is, according to the range (width) of the imaging target to be imaged.

The D input unit 13 is connected to the D control processing unit 12 and is a device that inputs a predetermined instruction to the image sensor D, for example, one or a plurality of switches assigned a predetermined function. More specifically, for example, in this embodiment, the D input unit 13 includes a shutdown switch for shutting down the image sensor D, a reset switch for resetting the image sensor D, and the like. The D output unit 14 is an apparatus that is connected to the D control processing unit 12 and displays the operating state of the image sensor D according to the control of the D control processing unit 12. For example, the D output unit 14 functions as an indicator and has a predetermined color (for example, green) Or red) or one or a plurality of light emitting diodes (LEDs) that emit light in a predetermined light emitting state (for example, continuous lighting or blinking). Note that the D output unit 14 may be omitted.

The DIF unit 15 is a circuit that is connected to the D control processing unit 12 and inputs / outputs data to / from an external device under the control of the D control processing unit 2. For example, an SD standard SD interface circuit, serial communication RS-232C interface circuit, Bluetooth (registered trademark) standard interface circuit, IrDA (Infrared Data Association) standard interface circuit, and USB (Universal Serial Bus) standard Interface circuit and the like. For example, in the present embodiment, the DIF unit 15 includes a microSD connector for inputting / outputting data to / from a microSD memory card.

The D communication IF unit 16 is connected to the D control processing unit 12, and is monitored by a wired or wireless network via a network such as a LAN, a telephone network, and a data communication network according to the control of the D control processing unit 12. This is a communication device for performing communication with the monitoring central processing unit SV. The D communication IF unit 16 generates a communication signal containing data to be transferred input from the D control processing unit 12 in accordance with a communication protocol used in the network, and the generated communication signal is received via the network. It transmits to the supervisor monitoring central processing unit SV. The D communication IF unit 16 receives a communication signal from the monitored person monitoring central processing unit SV via the network, extracts data from the received communication signal, and the D control processing unit 12 can process the extracted data. The data is converted into data in a proper format and output to the D control processing unit 12. For example, in this embodiment, the D communication IF unit 16 transmits and receives communication signals according to the Wi-Fi (Wireless Fidelity) standard, which is one of the wireless LAN standards, and is compatible with IEEE 802.11b / g / n. It is configured with Fi Module (communication card).

The illumination unit 18 is an apparatus that is connected to the D control processing unit 12 and illuminates the imaging target in accordance with the control of the D control processing unit 12. For example, in this embodiment, the illumination unit 18 includes an infrared LED that is configured to include an infrared LED that emits infrared light and an infrared LED driver that is a circuit for driving the infrared LED. It is configured with.

The power supply unit 19 is a device that is connected to the D control processing unit 12 and supplies power to each unit of the image sensor D that requires power in accordance with the control of the D control processing unit 12. For example, in the present embodiment, the power supply unit 19 converts a power supplied from an AC adapter connected to a commercial power supply into a power suitable for each part of the image sensor D (for example, a voltage suitable for each part). It is configured with.

The D storage unit 17 is a circuit that is connected to the D control processing unit 12 and stores various predetermined programs and various predetermined data under the control of the D control processing unit 12. The various predetermined programs include, for example, control processing programs such as an image transmission program for transmitting the image to be imaged generated by the imaging unit 1 at a predetermined sampling interval to the monitored person central processing unit SV. It is. The various kinds of predetermined data include an image sensor identifier (sensor ID) of the own device for identifying and identifying the image sensor D, and a communication address of the monitored person monitoring central processing unit SV which is the transmission destination of the image (For example, an IP address). The D storage unit 17 includes, for example, a ROM (Read Only Memory) that is a nonvolatile storage element and an EEPROM (Electrically Erasable Programmable Read Only Memory) such as a flash ROM that is a rewritable nonvolatile storage element. The D storage unit 17 is, for example, a DD3 SDRAM (Double-Data-Rate 3 Synchronous Dynamic Random Access) serving as a working memory of a CPU (Central Processing Unit) that stores data generated during execution of the predetermined program. RAM (Random Access Memory) etc. are included.

The D control processing unit 12 controls each unit of the image sensor D according to the function of each unit, generates an image of the installation location by the control unit 11, and generates the generated image of the installation location as the D communication IF unit. 16 is transmitted to the monitored person central processing unit SV via the network. The D control processing unit 12 includes, for example, a CPU (Central Processing Unit) and a PMIC (Power Management Integrated Circuit). The PMIC is a so-called integrated circuit that controls power feeding in order to save power.

On the other hand, the monitored person monitoring central processing unit SV is connected to each of the plurality of image sensors D so as to communicate with each other, and monitors the monitored person Ob based on each image generated by each image sensor D. In the present embodiment, the monitored person monitoring central processing unit SV is further communicably connected to an external terminal apparatus TA via a public communication network, and when it is determined that an abnormality has occurred in the monitored person Ob, that fact In addition, the terminal device TA is notified of the image, and the terminal device TA is connected to the terminal device TA so that a voice call can be made with the terminal device TA. The monitored person monitoring central processing unit SV also monitors intruders. The monitored person monitoring central processing unit SV manages monitoring information related to monitoring of the monitored person Ob, and for example, a server that returns the requested data to the client in response to a request from a client such as an external terminal device TA. Has function.

The terminal device TA includes a communication function for communicating with other devices, a display function for displaying predetermined information, an input function for inputting predetermined instructions and data, a call function for performing a voice call, and the like. This is a device that displays information notified from the monitoring central processing unit SV and enables voice communication with the image sensor D via the monitored central processing unit SV if necessary. Such a terminal device TA is, for example, a portable communication terminal device such as a so-called tablet computer, a smartphone, or a mobile phone.

For example, as shown in FIG. 2, the monitored person monitoring central processing unit SV includes a server communication interface unit (SV communication IF unit) 1, a server control processing unit (SV control processing unit) 2, and a server. And a storage unit (SV storage unit) 3.

Similar to the D communication IF unit 16, the SV communication IF unit 1 is connected to the SV control processing unit 2, and according to the control of the SV control processing unit 2, a wired or wireless network such as a LAN, a telephone network, and a data communication network. This is a communication device for performing communication with each image sensor D and with an external terminal device TA via (network). The SV communication IF unit 1 generates a communication signal containing data to be transferred input from the SV control processing unit 2 in accordance with a communication protocol used in the network, and generates the generated communication signal through the network. It transmits to image sensor D and terminal unit TA. The SV communication IF unit 1 receives a communication signal from each image sensor D or terminal device TA via the network, extracts data from the received communication signal, and the SV control processing unit 2 can process the extracted data. The data is converted into data in a proper format and output to the SV control processing unit 2. For example, in the present embodiment, the SV communication IF unit 1 transmits and receives communication signals according to the Wi-Fi (Wireless Fidelity) standard, which is one of the wireless LAN standards, and is compatible with IEEE 802.11b / g / n. It is configured with a Fi Module (communication card), an Ethernet MAC (communication card) that transmits and receives communication signals according to the Ethernet standard, and the like. Ethernet is a registered trademark. The SV communication IF unit 1 is connected to a public communication network via an access point (not shown).

The SV storage unit 3 is a circuit that is connected to the SV control processing unit 2 and stores various predetermined programs and various predetermined data in accordance with the control of the SV control processing unit 2, similarly to the D storage unit 17. Examples of the various predetermined programs include a person detection program that detects a person (person area) based on an image from the image sensor D, and a posture detection that detects a predetermined posture of the person detected by the person detection program. A program, a person position detection program for detecting the position of the person detected by the person detection program, an abnormality determination program for determining whether or not an abnormality has occurred in the monitored person Ob based on an image from the image sensor D, When it is determined by the abnormality determination program that an abnormality has occurred in the monitored person Ob, an abnormality notification processing program for transmitting the fact to a predetermined communication device (for example, the terminal device TA), an image sensor, and the predetermined communication device (For example, the above-mentioned terminal device TA, etc.) A voice relay processing program that relays voice calls to each other, and whether or not an intruder has intruded is determined. When it is determined that there is an intruder by the intruder determination processing program or the intruder determination processing program, an intruder notification processing program that transmits the fact to a predetermined communication device (for example, the terminal device TA) or the like In the embodiment, a control processing program such as a server program that provides data corresponding to a request from the terminal device TA or the like to the client is included. The various predetermined data include a plurality of abnormality determination threshold values set according to respective arrangement locations in the plurality of image sensors D and associated with the plurality of image sensors, and the predetermined communication device (described above). In this case, data necessary for monitoring the monitored person Ob, such as a communication address (for example, an IP address) in the terminal device TA or the like, is included. The SV storage unit 3 includes, for example, a ROM and an EEPROM. The SV storage unit 3 includes a RAM serving as a working memory for the so-called SV control processing unit 2 that stores data generated during execution of the predetermined program.

And the SV storage unit 3 functionally includes an abnormality determination threshold value storage unit 31 in order to store the plurality of abnormality determination threshold values. The abnormality determination threshold value is a threshold value for determining whether an abnormality has occurred in the monitored person Ob from the image generated by the image sensor D. In the present embodiment, the abnormality determination threshold value is determined from the image generated by the image sensor D. In order to determine that an abnormality has occurred in the monitored person Ob when the determined posture of the monitored person Ob continues for a predetermined time or more, it is expressed in time (abnormality detection time, minutes). The plurality of abnormality determination threshold values (minutes) are set according to the respective arrangement locations in the plurality of image sensors D, and are associated with the plurality of image sensors D, respectively. Furthermore, in this embodiment, the monitored person monitoring system S (monitored person monitoring central processing unit SV) is configured to be able to vary the abnormality determination threshold value for each type of posture of the monitored person Ob, and the plurality Each abnormality determination threshold value is provided for each type of posture.

In the present embodiment, information related to the abnormality determination threshold value is stored in the abnormality determination threshold value storage unit 31 in a table format. The abnormality determination threshold information table TB for registering information relating to the abnormality determination threshold is, for example, as shown in FIG. 4, a sensor ID field 311 for registering an image sensor identifier (sensor ID) for identifying and identifying the image sensor D. A placement location field 312 for registering placement location information representing the placement location where the image sensor D corresponding to the sensor ID registered in the sensor ID field 311 is placed, and a posture for registering posture information representing the posture. A field 313; and an abnormality determination threshold field 314 for registering an abnormality determination threshold corresponding to the location of the image sensor D corresponding to the sensor ID registered in the sensor ID field 311 and the type of posture of the monitored person Ob. A main record is provided for each sensor ID (for each location), and each main record has a posture. Equipped with a sub-record in the door. In the example shown in FIG. 4, for example, in the first main record, “D-1” and “entrance” are registered in the sensor ID field 311 and the installation location field 312, respectively. In the sub-record, “standing / walking” and “60” are registered in the posture field 313 and the abnormality determination threshold field 314, respectively. In the second sub-record, the posture field 313 and the abnormality determination threshold field 314 are stored. “Sitting position” and “60” are registered in each, and “lie down” and “30” are registered in the posture field 313 and the abnormality determination threshold field 314 in the third sub-record, respectively. Has been. Further, for example, in the fourth main record, “D-3” and “bedroom” are registered in the sensor ID field 311 and the arrangement location field 312, respectively. In the first sub-record, the posture field 313 is registered. “Standing / walking” and “240” are registered in each of the abnormality determination threshold field 314, and in the second sub-record, “post sitting” is stored in each of the posture field 313 and the abnormality determination threshold field 314. And “240” are registered, and in the third sub-record, “lie down” and “600” are registered in the posture field 313 and the abnormality determination threshold field 314, respectively. Therefore, by the operation described below, the sitting position of the monitored person Ob is determined to be abnormal in the entrance R-1 if the sitting position continues for 60 minutes or more, while in the bedroom R-3, the sitting position is abnormal in 60 minutes. If it is not determined and the sitting position continues for 240 minutes or more, an abnormality is determined.

Furthermore, the SV storage unit 3 functionally includes an intruder determination area storage unit 32 for storing intruder determination information for determining whether or not an intruder has invaded. The intruder determination information is an intruder intrusion determination area that is determined to be an intruder intrusion within the range of the plurality of locations, or an intruder non-intrusion that is determined not to be an intruder in the range of the plurality of locations. This is information representing an intrusion determination area. Usually, a person enters the room indoors from the entrance or back door (hand entrance), so the intruder intrusion determination area excludes, for example, the entrance and back door (hand entrance) that is normally scheduled for such entry and exit, For example, it is set in a bedroom R-3, a toilet R-4, a dressing room R-6, and the like. In addition, since it is thought that it penetrate | invades from a window, the area | region near these windows may be set as an intruder determination area | region. The intruder non-intrusion determination area is set to an area that is not an intruder intrusion determination area. The intruder intrusion determination area or the intruder non-determination area is stored in the intruder determination area storage unit 32 at a pixel position on the image, for example. In addition, for example, the correspondence between each pixel position of the image and each position of the room is stored in advance in the intruder determination area storage unit 32, and the intruder intrusion determination area or the intruder non-determination area is a position in the room. It is stored in the determination area storage unit 32.

Similar to the D control processing unit 12, the SV control processing unit 2 controls each unit of the monitored person monitoring central processing unit SV according to the function of each unit, and based on each image generated by each image sensor D. This is a circuit for monitoring the monitored person Ob. The SV control processing unit 2 includes, for example, a CPU and its peripheral circuits. In the SV control processing unit 2, a control processing program is executed, whereby a server control unit (SV control unit) 21, a detection processing unit 22, an abnormality determination unit 23, an abnormality notification processing unit 24, a voice relay processing unit 25, The intruder determination processing unit 26 and the intruder notification processing unit 27 are functionally provided, and the detection processing unit 22 includes a person detection unit 221, a posture detection unit 222, and a person position detection unit 223.

The SV control unit 21 controls each part of the monitored person monitoring central processing unit SV according to the function of each part, and governs overall control of the monitored person monitoring central processing unit SV.

The detection processing unit 22 detects a person (person area), the posture of the person, and the position of the person based on the image from the image sensor D received by the SV communication IF unit 1. Therefore, in the present embodiment, the detection processing unit 22 functionally includes, for example, a person detection unit 221, a posture detection unit 222, and a person position detection unit 223.

The person detection unit 221 detects a person (person area) based on the image from the image sensor D received by the SV communication IF unit 1. More specifically, the person detection unit 221 detects a person region by detecting a moving object by using, for example, a background subtraction method or the like from the image at the arrangement location generated by the image sensor D. In this background subtraction method, a background image is obtained in advance and stored in advance in the storage unit 3 as one of the various predetermined data, and the image at the arrangement location generated by the image sensor D, the background image, The presence / absence of a moving object is determined from the difference image, and if there is a moving object as a result of this determination, the area of the moving object is set as a person area.

The posture detection unit 222 detects a predetermined posture in the person (person area) detected by the person detection unit 221. In this embodiment, since the abnormality determination threshold is set for each posture type, the posture detection unit 222 further detects the posture type of the monitored person Ob. More specifically, the posture detection unit 222 includes, for example, one or a plurality of human body patterns (for example, a standing posture (standing / walking), a sitting posture, a lying posture (representing a human body) including a head, a trunk, and both feet). (Including a human body pattern such as lying) is stored in the storage unit 3 in advance as one of the various predetermined data, and the posture detection unit 222 is a pattern of the human region detected by the human detection unit 221 and the human body pattern. Based on the matching, the posture of the monitored person Ob (for example, standing / walking, sitting, lying down, etc.) is determined. Further, for example, the posture detection unit 222 determines the posture of the monitored person Ob from the aspect ratio of the person area detected by the person detection unit 221. Further, for example, the posture detection unit 222 obtains the height of the head of the monitored person Ob from the size of the head region (apparent size (size)) in the person region detected by the person detection unit 221, and obtains the height. The posture of the monitored person Ob is determined from the height.

The person detection unit 221 and the posture detection unit 222 correspond to an example of a posture determination unit that determines a predetermined posture of the monitored person Ob based on an image from the image sensor D.

The person position detection unit 223 detects the position of the person detected by the person detection unit 221. More specifically, for example, the person position detection unit 223 obtains an arrangement location corresponding to the image sensor D that generated the image in which the person is detected by the person detection unit 221, and uses the obtained arrangement location as the person. Detect as the position of. Further, for example, the correspondence relationship between each pixel position of the image and each position of the room is stored in advance in the SV storage unit 3, and the detection processing unit 22 first detects the person by the person detection unit 221 as described above. The position of the room corresponding to the image sensor D that generated the image is obtained, the position of the room at the position of the person is obtained from the pixel position of the detected person area, and the position of the room obtained is determined as the position of the person. Detect as.

The abnormality determination unit 23 searches the abnormality determination threshold value associated with the image sensor D received by the SV communication IF unit 1 from the plurality of abnormality determination threshold values stored in the abnormality determination threshold value storage unit 31, and the posture detection unit When the predetermined posture of the monitored person Ob detected in 222 exceeds the searched abnormality determination threshold, it is determined that an abnormality has occurred in the monitored person Ob. In this embodiment, the abnormality determination threshold is set for each posture type, and the posture detection unit 222 also detects the posture type. Therefore, the abnormality determination unit 23 receives the SV communication IF unit 1. The abnormality determination threshold associated with the image sensor D is searched from the plurality of abnormality determination thresholds stored in the abnormality determination threshold storage unit 31, and the type of posture detected by the posture detection unit 222 from the retrieved abnormality determination value When the predetermined posture of the monitored person Ob detected by the posture detection unit 222 exceeds the selected abnormality determination threshold, it is determined that an abnormality has occurred in the monitored person Ob. Yes.

The abnormality notification processing unit 24 contains abnormality determination information indicating that it is determined that an abnormality has occurred in the monitored person Ob when the abnormality determining unit 23 determines that an abnormality has occurred in the monitored person Ob. The signal is transmitted by the SV communication IF unit 1 to a predetermined communication device, in the example shown in FIG. 1, to an external terminal device TA. In this embodiment, the abnormality notification processing unit 24 outputs an abnormality determination image communication signal containing an image used when the abnormality determination unit 23 determines that an abnormality has occurred in the monitored person Ob, to the SV communication IF unit. 1 is transmitted to a predetermined communication device, in the example shown in FIG.

When the abnormality determination unit 23 determines that an abnormality has occurred in the monitored person Ob, the voice relay processing unit 25 transmits an image used when the abnormality determination unit 23 determines that an abnormality has occurred in the monitored person Ob. The voice communication is relayed between the image sensor D and the predetermined communication device (terminal device TA in FIG. 1) that has transmitted the abnormality determination notification communication signal.

The intruder determination processing unit 26 detects a person as a first person (corresponding to the monitored person Ob) by the person detection unit 221, and then uses the person detection unit 221 to set a person different from the first person as a second person. When it is detected that the position of the second person who first detected the second person is determined to be within the intruder intrusion determination area stored in the intruder determination area storage unit 32, or When it is determined that the position of the second person who first detected two persons is outside the intruder non-intrusion determination area stored in the intruder determination area storage unit 32, the second person is determined to be an intruder. Judgment.

When the intruder determination processing unit 26 determines that there is an intruder, the intruder notification processing unit 27 sends an intruder notification communication signal containing intruder determination information indicating that it has been determined that there is an intruder. 1 is transmitted to a predetermined communication device, in the example shown in FIG. 1, to an external terminal device TA. In the present embodiment, the intruder notification processing unit 27 transmits the intruder determination image communication signal containing the image used when the intruder determination processing unit 26 determines that there is an intruder, to the SV communication IF unit 1. Is transmitted to a predetermined communication device, which is the terminal device TA in the example shown in FIG.

As shown by a broken line in FIG. 2, the monitored person monitoring central processing unit SV is further connected to the SV control processing unit 2 as necessary, for example, a server input unit (for example, inputting various commands and various data). SV input unit 4, a server output unit (SV output unit) 5 that outputs various commands and various data input by the SV input unit 4 and information (monitoring information) related to monitoring of the monitored person Ob, and an external device A server interface unit (SVIF unit) 6 or the like for inputting / outputting data between them may be provided.

Next, operations of the monitored person monitoring system S and the monitored person monitoring central processing unit SV in the embodiment will be described. FIG. 5 is a flowchart showing the operation of the monitored person monitoring central processing unit in the monitored person monitoring system of the embodiment. FIG. 6 is a diagram illustrating an intruder invading state.

In the monitored person monitoring system S having such a configuration, when the image sensor D is connected to an AC adapter connected to a commercial power source, and power is supplied from the AC adapter to the image sensor D, the D control processing unit 12 Performs initialization of each necessary part, causes the imaging unit 11 to generate an image of the location of the image sensor D by executing the control processing program, and the image sensor generated by the imaging unit 11 A communication signal (image sending communication signal) containing the image of the location of D and the sensor ID of the own device is generated, and this image sending communication signal is sent to the monitored person monitoring central processing unit SV by the D communication IF unit 16. Send. The image sensor D repeatedly generates an image of such an arrangement location and transmits the image with an image transmission communication signal, or executes it in response to a request of the monitored person monitoring central processing unit SV. .

On the other hand, in the monitored person monitoring central processing unit SV, when the power is turned on, necessary parts are initialized, and the SV control processing unit 2 includes the SV control unit 21 by executing the control processing program. The detection processing unit 22, the abnormality determination unit 23, the abnormality notification processing unit 24, the voice relay processing unit 25, the intruder determination processing unit 26, and the intruder notification processing unit 27 are functionally configured. The person detection unit 221, the posture detection unit 222, and the person position detection unit 223 are functionally configured. The monitored person monitoring central processing unit SV configured as described above monitors the monitored person Ob by the following operation.

In FIG. 5, the SV control processing unit 2 of the monitored person monitoring central processing unit SV receives image sending communication signals from the image sensors D-1 to D-7 by the SV communication IF unit 1, and the detection processing unit 22 A process of detecting a person (person area) is executed by the person detection unit 221 for each of all images obtained from the respective image sensors D-1 to D-7 (S1).

Next, the SV control processing unit 2 refers to the detection result of the processing S1 by the detection processing unit 22, and determines whether or not there is anyone (S2). If no person (person area) is detected from any of the images at the respective locations in the image sensors D-1 to D-7 in the process S1, the SV control process is determined in the determination of the process S2. The unit 2 determines that there is no one by the detection processing unit 22 (Y), and the SV control processing unit 2 receives each of the image sensors D-1 to D received via the SV communication IF unit 1 at the next timing. In order to process the image sending communication signal from -7, the processing is returned to S1. On the other hand, when a person (person area) is detected in any one of the images at the respective arrangement locations in the image sensors D-1 to D-7 in the process S1, the determination in the process S2 indicates that the SV The control processing unit 2 determines that there is no one (someone is present) by the detection processing unit 22 (N), and the SV control processing unit 2 executes the next processing S3.

In this process S3, the SV control processing unit 2 refers to the detection result of the process S1 by the detection processing unit 22, and determines whether there are two or more persons. When a plurality of persons (person areas) are detected in any one of the images at the respective locations in the image sensors D-1 to D-7 in the process S1 (a plurality of persons (person areas) in one image ) And when at least one person (person area) is detected in each of the plurality of images), the SV control processing unit 2 determines that the detection processing unit 22, it is determined that there are two or more persons (Y), and the SV control processing unit 2 returns the process to S1. When two or more people are detected, for example, there are persons other than the monitored person Ob, such as a nurse, a caregiver, and a family member, a guest, etc., so the other person can monitor the monitored person Ob. Therefore, it is not always necessary to monitor the monitored person Ob. On the other hand, when one person area is detected in any of the images at the respective arrangement locations in the image sensors D-1 to D-7 in the process S1, the SV control is performed in the determination of the process S3. The processing unit 2 determines that there are not two or more by the detection processing unit 22 (Y), and the SV control processing unit 2 executes the next processing S4. If it is determined that there are not two or more persons, that is, only one person, this person is estimated to be a monitored person Ob that should be monitored.

In this process S4, the SV control processing unit 2 uses the detection processing unit 22 to restart an abnormality detection timer for measuring the posture maintenance time (starts counting after resetting).

Next, the SV control processing unit 2 executes a process of detecting the posture by the detection processing unit 22, and stores the detected posture in the SV storage unit 3 with a detection time (S5). More specifically, the SV control processing unit 2 receives image sending communication signals from the image sensors D-1 to D-7 at the SV communication IF unit 1, and the person detection unit 221 receives the image sensors D-1. A process of detecting a person (person area) is executed for each of all images obtained from each of D-7, and the posture detection unit 222 uses, for example, the above-described human body for the image in which the person is detected by the person detection unit 221. The posture of the person (monitored person Ob) is detected by pattern matching with the pattern, the aspect ratio of the person area, the size of the head area, etc. (for example, standing posture (standing / walking), sitting posture, lying down) The posture (lie down) is determined), and the detected posture is stored in the SV storage unit 3 with a detection time.

Next, the SV control processing unit 2 compares the posture determined last time with the posture determined this time by referring to the SV storage unit 3 by the abnormality determination unit 23, and determines whether or not the posture has changed. Determine (S6). As a result of the comparison, if the posture determined last time is different from the posture determined this time, the determination in step S6 is determined that there is a change in posture (N), and the SV control processing unit 2 22, the abnormality detection timer is restarted (S10), and the process returns to the process S5. On the other hand, as a result of the comparison, if the posture determined last time is the same as the posture determined this time, the determination in step S6 is determined that there is no change in posture (Y), and the SV control processing unit 2 Then, the next process S7 is executed.

In this process S7, the SV control processing unit 2 detects the room where the person (monitored person Ob) is present by the abnormality determination unit 23, and stores the detected room in the SV storage unit 3 with the detection time. . More specifically, the abnormality determination unit 23 detects the presence of a person (monitored person Ob) in the process S5 and detects the sensor ID stored in the image sending communication signal that stores the image used for the posture determination in the process S6. Is obtained from the abnormality determination threshold value information table TB stored in the abnormality determination threshold value storage unit 31 using the acquired sensor ID as a search key to search for an arrangement location corresponding to the acquired sensor ID. The room where the monitored person Ob) is present is detected, and the detected room is stored in the SV storage unit 3 with the detection time.

Next, the SV control processing unit 2 compares the previously determined room with the currently determined room by referring to the SV storage unit 3 and determines whether the rooms are the same by the abnormality determination unit 23. (S8). As a result of the comparison, if the previously determined room is different from the currently determined room, the determination of the process S8 is determined that the rooms are not the same (N), and the SV control processing unit 2 22, the above-described process S10 is executed, and the process returns to process S5. On the other hand, as a result of the comparison, if the previously determined room is the same as the currently determined room, the determination in the process S8 determines that the room is the same (Y), and the SV control processing unit 2 Then, the next process S9 is executed.

In this process S9, the SV control processing unit 2 stores the abnormality determination threshold corresponding to the posture of the person (monitored person Ob) detected in the process S5 and the room detected in the process S7 by the abnormality determination unit 23. It is acquired from the unit 31, and the acquired abnormality determination threshold value is compared with the elapsed time of the abnormality detection timer. More specifically, the abnormality determination unit 23 detects from the abnormality determination threshold value information table TB stored in the abnormality determination threshold value storage unit 31 the posture of the person (monitored person Ob) detected in the process S5 and the process S7. Using the retrieved room as a search key, the abnormality determination threshold corresponding to the posture and the room is searched, and the detected abnormality determination threshold is compared with the elapsed time of the abnormality detection timer.

For example, as shown in FIG. 1, when the monitored person Ob falls in the kitchen, the posture of the monitored person Ob is detected as lie in the process S5, and the room where the monitored person Ob is located in the kitchen R in the process S5. In step S9, in the example shown in FIG. 4, the abnormality determination threshold value is retrieved from the abnormality determination threshold value information table TB as 30 minutes and acquired.

Next, the SV control processing unit 2 uses the abnormality determination unit 23 to determine whether the person (monitored person Ob) is abnormal (S11). More specifically, the abnormality determination unit 23 compares the retrieved abnormality determination threshold with the elapsed time of the abnormality detection timer in step S9, and as a result, the elapsed time of the abnormality detection timer exceeds the retrieved abnormality determination threshold. If yes, it is determined that an abnormality has occurred in the person (monitored person Ob) (Y), and then step S16 is executed. On the other hand, if the abnormality determination unit 23 compares the retrieved abnormality determination threshold in step S9 with the elapsed time of the abnormality detection timer, the elapsed time of the abnormality detection timer does not exceed the retrieved abnormality determination threshold, that is, If the elapsed time of the abnormality detection timer is equal to or less than the searched abnormality determination threshold, it is determined that no abnormality has occurred in the person (monitored person Ob) (N), and then processing S12 is executed.

Even if the monitored person Ob is in a normal state (non-abnormal state), the posture of the posture varies depending on the use of the room R. For example, the duration of lie is usually considered to be relatively short in the kitchen R-5, while relatively long in the bedroom R-3. For this reason, if the abnormality determination threshold value is set uniformly regardless of the room R, a determination error may occur. However, in the present embodiment, as described above with reference to FIG. 3, the abnormality determination threshold is set according to the location where the image sensor D is arranged, that is, the abnormality determination threshold is set according to the room. By the processes S1 to S11, particularly the processes S9 and S11, the abnormality can be determined more accurately. Further, in the kitchen R-5, it is generally considered that the standing time is relatively long, and the lying time is relatively short. For this reason, if the abnormality determination threshold value is uniformly set regardless of the posture, an erroneous determination may occur. However, in the present embodiment, as shown in FIG. 3 and as described above, the abnormality determination threshold value is set according to the type of posture, so that each of the above-described processes S1 to S11, particularly the processes S9 and S11, respectively. By processing, the abnormality can be determined more accurately.

Returning to FIG. 5, in this process 16, the SV control processing unit 2 issues an abnormality of the person (monitored person Ob) by the abnormality notification processing unit 24, and returns the process to the process S <b> 1. More specifically, the abnormality notification processing unit 24 uses the SV communication IF unit 1 to transmit an abnormality determination notification communication signal containing abnormality determination information indicating that an abnormality has occurred in the monitored person Ob to a predetermined communication device, FIG. In the example shown in FIG. Then, the abnormality notification processing unit 24 receives an abnormality determination image communication signal containing an image (for example, an image used in the process S5) used when the abnormality determination unit 23 determines that an abnormality has occurred in the monitored person Ob. The SV communication IF unit 1 transmits the data to a predetermined communication device, in this example, the terminal device TA. Then, the SV control processing unit 2 returns the process to the process S1. The communication device (the terminal device TA in this example) that has received the abnormality determination notification communication signal outputs the abnormality determination information to the outside by, for example, sound, voice, message display, etc., and a user (monitor) of the communication device By recognizing the output, the user (monitoring person) can recognize that it is determined that an abnormality has occurred in the monitored person Ob. The communication device displays the image by receiving the abnormality determination image communication signal, and the user (monitoring person) of the communication device refers to the image, so that the user (monitoring person) The state of Ob can be visually recognized. The abnormality determination image communication signal may also be used as the abnormality determination notification communication signal. That is, the abnormality determination information and the communication signal that contains the image used when it is determined that an abnormality has occurred in the monitored person Ob, the abnormality determination of the monitored person Ob and the image are the predetermined communication device (described above). In this example, it is transmitted to the terminal device TA).

The user (monitoring person) who has recognized that it has been determined that an abnormality has occurred in the monitored person Ob by the communication apparatus that has received the abnormality determination notification communication signal is sent to the communication apparatus (terminal apparatus TA in this example). A predetermined operation for requesting a voice call may be executed. When the predetermined operation for requesting the voice call is received, the communication device receives a communication signal (voice) containing a request for a voice call with the image sensor D that has generated an image of the monitored person Ob. A call request communication signal) is transmitted to the monitored person central processing unit SV. The monitored person monitoring central processing unit SV that has received the voice call request communication signal by the SV communication IF unit 1 causes the abnormality determination unit 23 to detect an abnormality in the monitored person Ob by the voice relay processing unit 25 of the SV control processing unit 2. A voice call is relayed between the image sensor D that has transmitted the image used when it is determined to have occurred and the communication device (in this example, the terminal device TA) that has transmitted the abnormality determination notification communication signal. To do. As a result, the user (monitoring person) can speak to the monitored person Ob, for example, "Is it all right?"

Referring back to FIG. 5, in this process 12, the SV control processing unit 2 executes a process of detecting a person (second person) other than the already detected person (first person, monitored person Ob). More specifically, the SV control processing unit 2 receives image transmission communication signals from the image sensors D-1 to D-7 at the SV communication IF unit 1, and the person detection unit 221 uses the image sensor D-1 to receive image transmission communication signals. A process of detecting a person (person area) is executed for each of all images obtained from each of D-7.

Next, the SV control processing unit 2 refers to the detection result of the processing S12 by the intruder determination processing unit 26 and determines whether or not the second person other than the already detected first person has been detected. Determine (S13). More specifically, the intruder determination processing unit 26 determines whether or not the person (person area) detected in process S12 matches the first person (first person area) already detected in process S5. judge. As a result of the determination, if the two persons match, the SV control processing unit 2 determines that the second person is not detected by the intruder determination processing unit 26 as a result of the determination in step S13. (N), the SV control processing unit 2 returns the process to S5. On the other hand, as a result of the determination, if the two persons do not match (does not match), the SV control processing unit 2 uses the intruder determination processing unit 26 as the second person as a result of the determination in step S13. Is detected (Y), and the SV control processing unit 2 executes the next process S14.

In this process S14, the SV control processing unit 2 determines whether or not the second person (second person region) detected in the process S12 is an intruder by the intruder determination processing unit 26. As can be seen from the above, this process S14 is performed after the person detection unit 221 detects a person as the first person (corresponding to the monitored person Ob), and then the person detection unit 221 detects a person other than the first person. This is executed when two persons are detected. More specifically, the intruder determination processing unit 26 determines whether the position of the second person who first detected the second person (the position of the person detected in process S12 (pixel position in the person area)) is determined as an intruder. It is determined whether or not it is within the intruder intrusion determination area stored in the area storage unit 32 (or the intruder determination processing unit 26 detects the position of the second person who first detected the second person (processing It is determined whether or not the position of the person detected at S12 (pixel position of the person area) is outside the intruder non-intrusion determination area stored in the intruder determination area storage unit 32. As a result of the determination, When the position of the second person who first detected two persons is not within the intruder intrusion determination area (or the position of the second person who first detected the second person is the intruder non-intrusion determination area If it is outside), the determination result of process S14 and In step S1, the SV control processing unit 2 returns the process to step S1.On the other hand, as a result of the determination, the position of the second person who first detected the second person is When it is within the intruder intrusion determination area (or when the position of the second person who first detected the second person is not outside the intruder non-intrusion determination area), the determination result of process S14 Then, it is determined that the person is an intruder (Y), and the SV control processing unit 2 executes the next process S15.

For example, as shown in FIG. 6, when the monitored person Ob-1 stands in the kitchen, the monitored person Ob-1 is monitored by each of the processes S1 to S11, and the process goes to the bedroom R-3. When the intruder Ob-2 enters, a person Ob-2 other than the monitored person Ob-1 is detected in the processes S12 and S13, and it is determined in the process S14 that the person Ob-2 is the intruder Ob-2. The

Referring back to FIG. 5, in this process S15, the SV control processing unit 2 reports the detection of the intruder by the intruder notification processing unit 27, and returns the process to the process S1. More specifically, the intruder notification processing unit 27 sends an intruder notification communication signal containing intruder determination information indicating that it is determined that there is an intruder to a predetermined communication device, FIG. In the example shown, the data is transmitted to the external terminal device TA. Then, the intruder notification processing unit 27 receives the intruder determination image communication signal containing the image (for example, the image used in step S14) used when the intruder determination processing unit 26 determines that there is an intruder. The SV communication IF unit 1 transmits the data to a predetermined communication device, in this example, the terminal device TA. Then, the SV control processing unit 2 returns the process to the process S1. The communication device (in this example, the terminal device TA) that has received the intruder notification communication signal outputs the intruder constant information to the outside by, for example, sound, voice, and message display, and the user (monitor) of the communication device By recognizing the output, the user (monitoring person) can recognize that it is determined that there is an intruder. The communication device displays the image by receiving the intruder determination image communication signal, and the user (monitorer) of the communication device refers to the image so that the user (monitorer) The presence or absence and state of it can be visually recognized. The intruder determination image communication signal may also be used as an intruder notification communication signal. That is, intrusion determination information and a communication signal containing the image used when it is determined that there is an intruder, the abnormality determination that there is an intruder and the image are the predetermined communication device (the terminal device in the above example). TA).

As described above, the monitored person monitoring system S according to the present embodiment, the monitored person monitoring central processing unit SV, and the method and the program used therefor are obtained from the same type of sensors as the plurality of image sensors D. Since the abnormality of the monitored person Ob is determined based on a plurality of images, it is not necessary to prepare hardware and software for each type of sensor, and a simpler configuration can be realized. The monitored person monitoring system S in the present embodiment, the monitored person monitoring central processing unit SV, and the method and the program used therefor have an abnormality determination threshold value used when determining an abnormality of the monitored person Ob. Since it can be set according to the arrangement location in the image sensor D, the abnormality of the monitored person Ob can be determined more accurately. Therefore, the monitored person monitoring system S, the monitored person monitoring central processing unit SV, and the method and the program used for this in the present embodiment have a simpler configuration and more accurately the abnormality of the monitored person Ob. Can be determined.

The monitored person monitoring system S in the present embodiment, the monitored person monitoring central processing unit SV, and the method and the program used therefor have an abnormality determination threshold value used when determining an abnormality of the monitored person Ob. Since it can be finely set according to the posture of the monitored person Ob, the abnormality of the monitored person Ob can be determined more accurately.

The monitored person monitoring system S, the monitored person monitoring central processing unit SV, and the method and the program used therefor indicate that an abnormality has occurred in the monitored person Ob. (The terminal device TA in the example shown in FIG. 1) can be transmitted, and a user (monitorer) who handles the predetermined communication device can be notified that it has been determined that an abnormality has occurred in the monitored person Ob.

When the monitored person monitoring system S, the monitored person monitoring central processing unit SV and the method and the program used therefor in the present embodiment determine that an abnormality has occurred in the monitored person Ob in the abnormality determining unit 23 1 can be transmitted to an external predetermined communication device (terminal device TA in the example shown in FIG. 1), and a user (monitorer) who handles the predetermined communication device can visually recognize the state of the monitored person Ob. Can be made. Therefore, the user (monitoring person) can determine the abnormality of the monitored person Ob more accurately by visually checking the state of the monitored person Ob with the image.

In the present embodiment, the monitored person monitoring system S, the monitored person monitoring central processing unit SV, and the method and the program used therefor, the user (monitoring person) is transferred to the monitored person Ob by voice relay processing. For example, it is possible to realize a voice call such as “Are you all right?”

The monitored person monitoring system S, the monitored person monitoring central processing unit SV, and the method and the program used therefor are not only monitored by the intruder determination process but also intruders. Can be monitored.

This specification discloses various modes of technology as described above, and the main technologies are summarized below.

A monitoring device according to one aspect is set according to a communication unit for communicating with a plurality of image sensors arranged in a plurality of locations and generating images, and according to each placement location in each of the plurality of image sensors. An abnormality determination threshold value storage unit that stores a plurality of abnormality determination threshold values in association with each of the plurality of image sensors, and determines a predetermined posture of the monitored person based on images from the image sensor received by the communication unit. A posture determination unit and an abnormality determination threshold associated with the image sensor received by the communication unit are searched from the plurality of abnormality determination thresholds stored in the abnormality determination threshold storage unit, and are determined by the posture determination unit. And an abnormality determining unit that determines that an abnormality has occurred in the monitored person when a predetermined posture of the monitored person exceeds the searched abnormality determining threshold.

Since such a monitoring apparatus determines the abnormality of the monitored person based on a plurality of images from the same type of sensor called a plurality of image sensors, it is not necessary to prepare hardware and software for each type of sensor. A simple configuration can be realized. Since the monitoring apparatus can set the abnormality determination threshold used when determining the abnormality of the monitored person according to the arrangement location in the image sensor, the abnormality of the monitored person can be determined more accurately. Therefore, the monitoring device can determine the abnormality of the monitored person more accurately with a simpler configuration.

In another aspect, in the above monitoring device, the abnormality determination threshold is provided for each type of posture, the posture determination unit further determines the type of posture of the monitored person, and the abnormality determination unit includes: The abnormality determination threshold value associated with the image sensor received by the communication unit is searched from the plurality of abnormality determination threshold values stored in the abnormality determination threshold value storage unit, and the posture determination unit is determined from the searched abnormality determination value. When an abnormality determination threshold value corresponding to the type of posture determined in (1) is selected and the predetermined posture of the monitored person determined by the posture determination unit exceeds the selected abnormality determination threshold value, an abnormality is detected in the monitored person. Is determined to have occurred.

Such a monitoring apparatus can finely set the abnormality determination threshold used when determining the abnormality of the monitored person according to the attitude of the monitored person, and therefore can determine the abnormality of the monitored person more accurately.

In another aspect, in the above-described monitoring devices, abnormality determination information indicating that it is determined that an abnormality has occurred in the monitored person Ob when the abnormality determining unit determines that an abnormality has occurred in the monitored person Ob Is further provided with an abnormality notification processing unit that transmits an abnormality determination notification communication signal containing the signal to a predetermined communication device by the communication unit.

Such a monitoring device can transmit to the external predetermined communication device that an abnormality has occurred in the monitored person, and has determined that an abnormality has occurred in the monitored person to a person handling the predetermined communication device. Can be notified.

In another aspect, in the above-described monitoring apparatus, the abnormality notification processing unit receives an abnormality determination image communication signal containing an image used when the abnormality determination unit determines that an abnormality has occurred in the monitored person. The communication unit transmits to the predetermined communication device.

Such a monitoring device can transmit an image used when the abnormality determination unit determines that an abnormality has occurred in the monitored person to an external predetermined communication device, and to a person who handles the predetermined communication device. The state of the monitored person can be visually recognized. Therefore, the person who handles the predetermined communication device can more accurately determine the abnormality of the monitored person by visually recognizing the state of the monitored person with the image.

In another aspect, in the above-described monitoring devices, when the abnormality determination unit determines that an abnormality has occurred in the monitored person, the abnormality determination unit determines that an abnormality has occurred in the monitored person. A voice relay processing unit that relays a voice call between the image sensor that has transmitted the used image and the predetermined communication device that has transmitted the abnormality determination notification communication signal is further provided.

Such a monitoring device can realize a call to a person who handles the predetermined communication device calls the monitored person, for example, “Is it all right?”.

In another mode, in these above-mentioned monitoring devices, it is not an intruder intrusion determination area or an intruder intrusion within the range of the plurality of places that is determined to be an intruder intrusion within the range of the plurality of places. An intruder determination area storage unit that stores an intruder non-intrusion determination area that is determined to be, a person detection unit that detects a person based on an image from the image sensor received by the communication unit, and a detection by the person detection unit A position detection unit that detects the position of the person who has detected the person and the person detection unit detects a person as the first person, and then the person detection unit detects a person other than the first person as the second person. In addition, when it is determined that the position of the second person that first detected the second person is within the intruder intrusion determination area stored in the intruder determination area storage unit, or the second person is Said first detected An intruder determination processing unit that determines that the second person is an intruder when it is determined that the position of the two persons is outside the intruder non-intrusion determination region stored in the intruder determination region storage unit; Further prepare.

Such a monitoring device can monitor not only the monitored person but also the intruder.

The monitoring method according to another aspect includes a reception step of receiving images from a plurality of image sensors individually arranged at a plurality of locations and generating images, and a reception step from the image sensor received in the reception step. A posture detection step for detecting a predetermined posture of the person to be monitored based on an image, and a plurality of abnormality determination threshold values set in accordance with each placement location in the plurality of image sensors individually. An abnormality determination threshold associated with the image sensor that generated the image received in the reception step is searched from the plurality of abnormality determination thresholds stored in the abnormality determination threshold storage unit attached and stored, and the posture detection step And an abnormality determination step of determining that an abnormality has occurred in the monitored person when the predetermined posture of the monitored person detected in (1) exceeds the searched abnormality determination threshold value.

A monitoring program according to another aspect includes a receiving step of receiving images from a plurality of image sensors individually arranged in a plurality of locations and generating images on a computer, and the image received in the receiving step. A plurality of image sensors each having a plurality of abnormality determination thresholds set in accordance with a position detection step for detecting a predetermined posture of the person to be monitored based on an image from the sensor; Search the abnormality determination threshold associated with the image sensor that generated the image received in the reception step from the plurality of abnormality determination thresholds stored in the abnormality determination threshold storage unit individually associated and stored, An abnormality that determines that an abnormality has occurred in the monitored person when a predetermined posture of the monitored person detected in the posture detection step exceeds the searched abnormality determination threshold value Is a program for executing a constant step.

A monitoring system according to another aspect includes a plurality of image sensors arranged at a plurality of locations and generating images, and connected to each of the plurality of image sensors so as to communicate with each other. And a monitoring device that monitors a person to be monitored based on the monitoring device, and the monitoring device is any one of the above-described monitoring devices.

Such a monitoring method, monitoring program, and monitoring system can determine the abnormality of the monitored person more accurately with a simpler configuration.

This application is based on Japanese Patent Application No. 2015-90506 filed on April 27, 2015, the contents of which are included in this application.

In order to express the present invention, the present invention has been properly and fully described through the embodiments with reference to the drawings. However, those skilled in the art can easily change and / or improve the above-described embodiments. It should be recognized that this is possible. Therefore, unless the modifications or improvements implemented by those skilled in the art are at a level that departs from the scope of the claims recited in the claims, the modifications or improvements are not covered by the claims. To be construed as inclusive.

According to the present invention, a monitoring device, a monitoring method, a monitoring program, and a monitoring system can be provided.

Claims

A communication unit for communicating with a plurality of image sensors arranged in a plurality of places and generating images;
An abnormality determination threshold value storage unit that stores a plurality of abnormality determination threshold values that are set according to each arrangement location in each of the plurality of image sensors in association with each of the plurality of image sensors;
A posture determination unit that determines a predetermined posture of the monitored person based on an image from the image sensor received by the communication unit;
An abnormality determination threshold associated with the image sensor received by the communication unit is searched from the plurality of abnormality determination thresholds stored in the abnormality determination threshold storage unit, and the monitored person determined by the posture determination unit An abnormality determination unit that determines that an abnormality has occurred in the monitored person when a predetermined posture exceeds the searched abnormality determination threshold;
Monitoring device.
The abnormality determination threshold is provided for each type of posture,
The posture determination unit further determines the type of posture of the monitored person;
The abnormality determination unit searches the abnormality determination threshold stored in the abnormality determination threshold storage unit for an abnormality determination threshold associated with the image sensor received by the communication unit, and the searched abnormality determination value When the abnormality determination threshold corresponding to the type of posture determined by the posture determination unit is selected, and when a predetermined posture of the monitored person determined by the posture determination unit exceeds the selected abnormality determination threshold, Determining that an abnormality has occurred in the monitored person,
The monitoring apparatus according to claim 1.
When the abnormality determination unit determines that an abnormality has occurred in the monitored person, an abnormality determination notification communication signal containing abnormality determination information indicating that it has been determined that an abnormality has occurred in the monitored person Ob is transmitted by the communication unit. Further comprising an abnormality notification processing unit for transmitting to a predetermined communication device;
The monitoring apparatus according to claim 1 or 2.
The abnormality notification processing unit transmits an abnormality determination image communication signal containing an image used when the abnormality determination unit determines that an abnormality has occurred in the monitored person to the predetermined communication device by the communication unit. ,
The monitoring device according to claim 3.
When the abnormality determination unit determines that an abnormality has occurred in the monitored person, the image sensor that has transmitted the image used when the abnormality determination unit determines that an abnormality has occurred in the monitored person; and A voice relay processing unit that relays a voice call to and from the predetermined communication device that has transmitted the abnormality determination notification communication signal;
The monitoring device according to claim 3 or 4.
Intrusion storing an intruder intrusion determination area that is determined to be an intruder intrusion within the range of the plurality of places or an intruder non-intrusion determination area that is determined not to be an intruder intrusion within the range of the plurality of places A person determination area storage unit;
A person detection unit for detecting a person based on an image from the image sensor received by the communication unit;
A person position detecting unit for detecting the position of the person detected by the person detecting unit;
After the person is detected as the first person by the person detection unit, and the person detection unit detects a person other than the first person as the second person, the second person is detected first. When it is determined that the positions of the two persons are within the intruder intrusion determination area stored in the intruder determination area storage unit, or the position of the second person that first detected the second person is the intruder An intruder determination processing unit that determines that the second person is an intruder when determined to be outside the intruder non-intrusion determination region stored in the intruder determination region storage unit,
The monitoring device according to any one of claims 1 to 5.
A receiving step of receiving images from a plurality of image sensors individually arranged at a plurality of locations and generating images;
A posture detection step of detecting a predetermined posture of the monitored person based on the image from the image sensor received in the reception step;
The plurality of abnormality determination threshold values stored in an abnormality determination threshold value storage unit that stores a plurality of abnormality determination threshold values set in accordance with each arrangement location in each of the plurality of image sensors in association with each of the plurality of image sensors. The abnormality determination threshold value associated with the image sensor that generated the image received in the reception step is searched, and the predetermined posture of the monitored person detected in the posture detection step is the detected abnormality determination threshold value. An abnormality determination step for determining that an abnormality has occurred in the monitored person when exceeding,
Monitoring method.
On the computer,
A receiving step of receiving images from a plurality of image sensors individually arranged at a plurality of locations and generating images;
A posture detection step of detecting a predetermined posture of the monitored person based on the image from the image sensor received in the reception step;
The plurality of abnormality determination threshold values stored in an abnormality determination threshold value storage unit that stores a plurality of abnormality determination threshold values set in accordance with each arrangement location in each of the plurality of image sensors in association with each of the plurality of image sensors. The abnormality determination threshold value associated with the image sensor that generated the image received in the reception step is searched, and the predetermined posture of the monitored person detected in the posture detection step is the detected abnormality determination threshold value. A monitoring program for executing an abnormality determination step of determining that an abnormality has occurred in the monitored person when exceeding.
A plurality of image sensors arranged at a plurality of locations to generate images, and a monitoring device that monitors the person to be monitored based on the images generated by the image sensors connected to the plurality of image sensors. A monitoring system comprising:
The monitoring device is the monitoring device according to any one of claims 1 to 6.
Monitoring system.