JP6737355B2 - Head detection device, head detection method, and monitored person monitoring device - Google Patents

Description

The present invention relates to a head detecting device and a head detecting method for detecting a head of a monitored person who is a monitoring target to be monitored. The present invention also relates to a monitored person monitoring device using this head detecting device.

Japan has an aging society due to the improvement of living standards, the improvement of hygiene environment and the improvement of medical care, etc. accompanying the post-war high economic growth. Is over 21% in an aging society. In 2005, the total population was 127.65 million and the number of elderly people aged 65 and over was 255.6 million. In 2020, the total population was 124.11 million. It is predicted that the elderly population will be approximately 3,456,000. In such an aging society, the number is expected to increase more than the number of nurses requiring nursing care or nursing due to illness, injury, aging, etc. that occur in a normal society that is not an aging society. Japan is also a declining birthrate society with a total fertility rate of 1.43 in 2013, for example. For this reason, elderly care is also occurring in which elderly family members (spouse, children, brothers) take care of elderly people who need nursing care.

Nursing and care recipients are admitted to hospitals and other facilities such as welfare facilities for the aged (short-term nursing homes for the elderly, nursing homes and special nursing homes, etc. under Japanese law) for nursing and care. In such a facility, there is a problem that a nurse or the like suffers an injury due to a fall from a bed, a fall while walking, or the like, getting out of the bed and wandering around. It is necessary to respond to such a situation as soon as possible, and if such a situation is left untreated, it may develop into a larger problem. And caregivers check the safety and condition by regularly patrol.

However, the increase in the number of nurses and the like cannot keep up with the increase in the number of nurses and the like, and there is a chronic labor shortage in the nursing industry and the nursing care industry. Further, the number of nurses, caregivers and the like decreases in the semi-night shift and night shift hours compared to the day shift hours, and the work load per person increases. Therefore, it is required to reduce the work load. In addition, the situation of the old-age care is not an exception even in the above-mentioned facilities, and elderly nurses and the like often take care of elderly care recipients and the like. In general, physical strength deteriorates as a person ages, so even if they are healthy, the burden of nursing, etc. will be heavier than that of young nurses, and their movements and judgment will be slow.

In order to reduce the labor shortage and the burden on nurses, there is a demand for technology that complements nursing work and nursing care work. For this reason, in recent years, a monitored person monitoring device for monitoring (monitoring) a monitored person, such as a nurse requiring care, to be monitored has been studied and developed.

As one of such techniques, there is a fall detection device disclosed in Patent Document 1, for example. The fall detection device disclosed in Patent Document 1 includes a camera, an image processing unit that captures a video signal output from the camera and performs difference processing on the captured image, and a difference region obtained by the difference processing. And a determination means for detecting a fall motion of the human body based on the area. More specifically, the determination means determines the presence or absence of a fall based on a change in the area of the human body per unit time.

On the other hand, in terms of safety confirmation, a single person living alone is the same as the above-mentioned nursing-requiring person, etc., and is to be monitored.

JP, 2000-207665, A

By the way, since the size of the region of the human body shown in the image changes depending on the presence/absence of a fall, the fall detection device disclosed in Patent Document 1 detects a fall by a change in the area of the human body region per unit time. Since the size of the head region shown in the image also changes depending on the presence/absence of a fall, a method of detecting a fall based on the size of the head region can be considered. In this method, in the image captured from above, the head appears in a substantially circular shape, so that a circular area is detected as the head area from the image. However, since a substantially circular object other than the head such as a pillow, a washbasin, a ball, a trash can, and a futon handle is also reflected in the actual image, the areas of these objects are erroneously detected as the head area, A fall may be erroneously detected.

On the other hand, if these objects are present at fixed positions, the false detection can be avoided by excluding the regions of these objects at fixed positions from the region for detecting the head in advance. However, these objects do not always exist at fixed positions.

The present invention is made in view of the above circumstances, and an object thereof is a head detecting device and a head capable of detecting the head of a monitored person more accurately based on an image obtained by capturing the monitored person from above. It is intended to provide a part detection method and a monitored person monitoring device using the head detecting device.

As a result of various studies, the present inventor has found that the above object can be achieved by the present invention described below. That is, the head detecting apparatus according to an aspect of the present invention, a monitored person is monitored, an image acquisition unit that acquires an image captured from above of the monitored person, acquired by the image acquisition portion and the Based on the image, a marker detection unit that detects a predetermined marker, and from the remaining region excluding the region having the marker detected by the marker detection unit from the image acquired by the image acquisition unit, a substantially circular region From the circular area extracted by the circular area extraction unit and the circular area extraction unit for extracting as a circular area, an area having a predetermined reflectance or less for infrared light is extracted as a low reflectance area. A low reflectance region extraction unit, and a head selection unit for selecting the region of the head based on the low reflectance region extracted by the low reflectance region extraction unit to detect the head, the marker , it said a only be identified by infrared light, and wherein the reflectance to the infrared light is beyond a predetermined reflectance. Preferably, in the head detecting device described above, since there is a high probability that the entire monitored person can be imaged, the image is expected to be the head of the monitored person in the bedding in which the monitored person lies down. The image is taken from directly above the preset planned head position.

As a result of various studies, the inventor has found that the head has a relatively low reflectance for infrared light (infrared rays). From this knowledge, since the head detecting device detects the head not only in a substantially circular shape but also in consideration of the reflectance with respect to infrared light, the head of the monitored person is detected based on the image of the monitored person from above. The part can be detected more accurately. Further, since the marker is also taken into consideration, the head of the monitored person can be detected with higher accuracy. In addition, by providing a marker to a head that is not a head, the head detecting device removes the circular area and the low reflectance area having the marker, thereby the circular area. The circular region extracted by the extraction unit and the low-reflectance region extracted by the low-reflectance region extraction unit can exclude the above-mentioned non-head region, and the head of the monitored person can be detected more accurately. Further, by using a marker that can be identified only by infrared light, it is possible to reduce erroneous detection at the marker detection unit. Since the marker cannot be seen, the head detecting device, when mounted on the monitored person monitoring device, does not make the monitored person recognize the presence of the marker and does not give a sense of discomfort. Further, since the circular area extracted by the circular area extraction unit is narrowed down as a candidate for the head area (head area), the head is detected from the narrowed down candidates in consideration of the reflectance to infrared light. As compared with the case where the low reflectance region is extracted from the entire image acquired by the image acquisition unit, it is possible to reduce erroneous detection of a low reflectance region.

Further , the head detecting apparatus according to one aspect of the present invention includes an image acquisition unit that acquires an image of a monitored person who is a monitoring target taken from above the monitored person, and the image acquisition unit that acquires the image. Based on the image, a marker detection unit that detects a predetermined marker, and the remaining area excluding the area having the marker detected by the marker detection unit from the image acquired by the image acquisition unit, to infrared light circular and the low reflectance region extraction unit that extracts a predetermined reflectance following areas as a low reflectance area, from the low reflectance region extracted in the previous SL low reflectance region extraction unit, a substantially circular region Te A circular region extracting unit for extracting as a region, and a head selecting unit for selecting the region of the head based on the circular region extracted by the circular region extracting unit to detect the head, The marker is identifiable only by the infrared light, and has a reflectance with respect to the infrared light that exceeds the predetermined reflectance .

As a result of various studies, the inventor has found that the head has a relatively low reflectance for infrared light (infrared rays). From this knowledge, since the head detecting device detects the head not only in a substantially circular shape but also in consideration of the reflectance with respect to infrared light, the head of the monitored person is detected based on the image of the monitored person from above. The part can be detected more accurately. Further, since the marker is also taken into consideration, the head of the monitored person can be detected with higher accuracy. In addition, by providing a marker to a head that is not a head, the head detecting device removes the circular area and the low reflectance area having the marker, thereby the circular area. The circular region extracted by the extraction unit and the low-reflectance region extracted by the low-reflectance region extraction unit can exclude the above-mentioned non-head region, and the head of the monitored person can be detected more accurately. Further, by using a marker that can be identified only by infrared light, it is possible to reduce erroneous detection at the marker detection unit. Since the marker cannot be seen, the head detecting device, when mounted on the monitored person monitoring device, does not make the monitored person recognize the presence of the marker and does not give a sense of discomfort. Further, the low reflectance region extracted by the low reflectance region extraction unit is narrowed down as a candidate for the head region, and the head is detected in consideration of the substantially circular shape from the narrowed down candidates, so the image acquisition unit acquires it. The amount of information processing can be reduced as compared to the case where a substantially circular area is extracted from the entire image.

Further, in another aspect, in the above-described head detecting device, the marker is a marker having a specific shape.

By using a marker having a specific shape, such a head detecting device can reduce erroneous detection in the marker detecting unit.

Then, a head detecting method according to another aspect of the present invention includes an image acquisition step of acquiring an image of a monitored person who is a monitoring target from above the monitored person, and an acquisition step in the image acquiring step. Based on the image, the marker detection step of detecting a predetermined marker, from the remaining area excluding the area having the marker detected in the marker detection step from the image acquired in the image acquisition step, a substantially circular shape From the circular area extracted in the circular area extraction step, the circular area extraction step of extracting the area as a circular area, the area of a predetermined reflectance or less for infrared light as a low reflectance area A low reflectance region extracting step of extracting, and a head selecting step of selecting the head region based on the low reflectance region extracted in the low reflectance region extracting step to detect the head, the marker is only a possible identification by the infrared light, and wherein the reflectance to the infrared light is beyond a predetermined reflectance.
Further, a head detecting method according to another aspect of the present invention includes an image acquisition step of acquiring an image of a monitored person who is a monitoring target from above the monitored person, and an acquisition step in the image acquiring step. Based on the image, the marker detection step of detecting a predetermined marker, from the remaining area excluding the area having the marker detected in the marker detection step from the image acquired in the image acquisition step, infrared light With respect to the low reflectance region extraction step of extracting a region having a predetermined reflectance or less as a low reflectance region, from the low reflectance region extracted in the low reflectance region extraction step, a substantially circular area is circled. A circular area extracting step of extracting as a shape area, and a head selecting step of detecting the head by selecting an area of the head based on the circular area extracted in the circular area extracting step, The marker can be identified only by the infrared light, and the reflectance of the infrared light exceeds the predetermined reflectance.

In such a head detecting method, the head is detected not only in a substantially circular shape but also in consideration of the reflectance with respect to infrared light. Therefore, the head of the monitored person is detected based on the image of the monitored person from above. It can be detected more accurately.

Further, a monitored person monitoring apparatus according to another aspect of the present invention includes a head detecting unit that detects a monitored person as a monitoring target from an image captured from above the monitored person, and a head detecting unit, An action detection unit that detects a predetermined action of the monitored person based on the head of the monitored person detected by the head detection unit, and a notification that notifies the predetermined action detected by the action detection unit to the outside. And a head detecting unit including any one of the above head detecting devices.

Since such a person-to-be-monitored device detects the head using any one of the head detecting devices described above, the head of the person to be monitored can be more accurately detected based on the image of the person being monitored from above. As a result, the predetermined behavior of the person to be monitored can be detected more accurately.

The head detecting apparatus, the head detecting method, and the monitored person monitoring apparatus according to the present invention can detect the monitored person's head more accurately based on the image of the monitored person taken from above.

It is a figure which shows the structure of the to-be-monitored person monitoring system in embodiment. It is a figure which shows the structure of the sensor apparatus in the to-be-monitored person monitoring system of 1st Embodiment. It is a figure which shows the mode of arrangement|positioning of the sensor apparatus in the to-be-monitored person monitoring system of embodiment. It is a flowchart which shows operation|movement of the 1st aspect of the sensor apparatus in the to-be-monitored person monitoring system of 1st Embodiment. It is a figure for demonstrating an example of the image acquired by the sensor apparatus in the to-be-monitored person monitoring system of 1st Embodiment. It is a figure which shows the design of a futon. It is a flowchart which shows operation|movement of the 2nd aspect of the sensor apparatus in the to-be-monitored person monitoring system of 1st Embodiment. It is a figure which shows the structure of the sensor apparatus in the to-be-monitored person monitoring system of 2nd Embodiment. It is a flowchart which shows operation|movement of the 1st aspect of the sensor apparatus in the to-be-monitored person monitoring system of 2nd Embodiment. It is a flowchart which shows operation|movement of the 2nd aspect of the sensor apparatus in the to-be-monitored person monitoring system of 2nd Embodiment.

An embodiment of the present invention will be described below with reference to the drawings. In addition, in each of the drawings, the components denoted by the same reference numerals indicate the same components, and the description thereof will be appropriately omitted. In the present specification, reference numerals without suffixes are used for generic names, and reference numerals with suffixes are used when referring to individual configurations.

The person-to-be-monitored device includes a behavior detector that detects a preset predetermined behavior of a monitored person, and a notification unit that externally notifies the predetermined behavior detected by the behavior detector. And with. Then, the monitored person monitoring device further comprises a head detecting section for detecting the head of the monitored person from an image taken from above the monitored person, and the action detecting section, as one aspect, A predetermined action in the monitored person is detected based on the head of the monitored person detected by the head detecting unit. Such a person-to-be-monitored device may be realized by being integrally configured as one device, or may be realized by a plurality of devices as a system. Then, when the monitored person monitoring device is realized by a plurality of devices, the action detection unit may be mounted on any of the plurality of devices. As an example, an embodiment of the monitored person monitoring apparatus will be described here in the case where the monitored person monitoring apparatus is realized by a plurality of devices as a system. Even when the monitored person monitoring device is integrally configured as one device, the monitored person monitoring device can be configured as in the following description. In addition, as an example, a case will be described here in which the behavior detection unit is mounted on the sensor device SU described later together with the head detection unit and the notification unit. However, other devices in this system, for example, described later. Also in the case of being mounted on the management server device SV, the fixed terminal device SP, or the mobile terminal device TA, the monitored person monitoring device can be configured as in the following description.

(First embodiment)
FIG. 1 is a diagram showing a configuration of a monitored person monitoring system according to the embodiment. FIG. 2 is a diagram showing a configuration of a sensor device in the monitored person monitoring system of the first embodiment. FIG. 3 is a diagram showing how the sensor device is arranged in the monitored person monitoring system of the embodiment.

The monitored person monitoring system MSa in the first embodiment of the example in which the monitored person monitoring device is realized as a system is a monitored person (watched person) to be monitored (should be watched) (monitored person). Ob (Ob-1 to Ob-4) detects a predetermined action set in advance and monitors the monitored person Ob. For example, as shown in FIG. 1, one or a plurality of sensor devices are provided. SUa (SUa-1 to SUa-4), a management server device SV, a fixed terminal device SP, and one or more mobile terminal devices TA (TA-1, TA-2) are provided, which are wired or Wirelessly, communication is connected via a network (network, communication line) NW such as a LAN (Local Area Network), a telephone network, and a data communication network. The network NW may be equipped with repeaters such as repeaters, bridges, routers, and cross-connects that relay communication signals. In the example illustrated in FIG. 1, the plurality of sensor devices SUa-1 to SUa-4, the management server device SV, the fixed terminal device SP, and the plurality of mobile terminal devices TA-1 and TA-2 are wireless including an access point AP. A LAN (for example, a LAN according to the IEEE 802.11 standard) NW is communicably connected to each other.

The monitored person monitoring system MSa is arranged at an appropriate place according to the monitored person Ob. The person to be monitored (person to be watched) Ob is, for example, a person who needs nursing care due to illness or injury, a person who needs nursing care due to deterioration of physical ability, a single person living alone, and the like. In particular, from the viewpoint of enabling early detection and early action, the monitored person Ob may be a person who needs to be detected when a predetermined inconvenient event such as an abnormal state occurs in the person. preferable. Therefore, the monitored person monitoring system MSa is preferably installed in a building such as a hospital, a welfare facility for the aged, and a dwelling unit according to the type of the monitored person Ob. In the example shown in FIG. 1, the monitored-person monitoring system MS is arranged in a building of a care facility including a plurality of living rooms RM in which a plurality of monitored persons Ob live and a plurality of rooms such as a nurse station.

The sensor device SUa has a communication function of communicating with other devices SV, SP, and TA via the network NW, and is a device that detects the monitored person Ob and transmits the detection result to the management server device SV. Such a sensor device SUa includes, for example, as shown in FIG. 2, a sensor unit 1, a sound input/output unit 2, a control processing unit 3, a communication interface unit (communication IF unit) 4, and a storage unit 5. Equipped with.

The sensor unit 1 is a device that is connected to the control processing unit 3 and detects, under the control of the control processing unit 3, various preset amounts of the monitored person Ob. The predetermined amounts are appropriately determined according to predetermined actions to be detected by the monitored person Ob. In the present embodiment, the predetermined behaviors are waking up, leaving the bed, falling, and microscopic movement abnormality of the monitored person Ob. In order to detect these, the sensor unit 1 includes, for example, a Doppler sensor 11 and a camera 12.

The Doppler sensor 11 is a body motion sensor that transmits a transmission wave, receives a reflection wave of the transmission wave reflected by an object, and outputs a Doppler signal of a Doppler frequency component based on the transmission wave and the reflection wave. , And outputs the Doppler signal to the control processing unit 3. The transmission wave may be an ultrasonic wave, a microwave, or the like, but is a microwave in the present embodiment. Since the microwaves can pass through the clothes and be reflected on the body surface of the monitored person Ob, the movement of the body surface can be detected even when the monitored person Ob is wearing clothes, which is preferable.

The camera 12 is a device that is connected to the control processing unit 3 and generates an image (image data) under the control of the control processing unit 3. The camera 12 is arranged so as to be able to monitor the space (location space, room RM of the installation location in the example shown in FIG. 1) where the monitored person Ob to be monitored is scheduled to reside, and the location space is the aforementioned location space. Is imaged from above as an imaging target, an image (image data) of the bird's-eye view of the imaging target is generated, and the image of the imaging target is output to the control processing unit 3.

In the present embodiment, as shown in FIG. 3, since there is a high probability that the entire monitored person Ob can be imaged, the camera 12 causes the monitored person Ob to detect the monitored person Ob in the bedding BT such as a bed lying on the monitored person Ob. The sensor device SU is arranged so that the imaging target can be imaged from directly above a preset head planned position (usually, a pillow disposition position) where the head is supposed to be located. The sensor device SU obtains the Doppler signal measured from above the person Ob to be monitored by the Doppler sensor 11 of the sensor unit 1, and the camera 12 of the sensor unit 1 monitors the person Ob to be monitored. An image captured from above, preferably an image captured from immediately above the planned head position is acquired. As will be described later with reference to FIG. 5, a pillow PI is placed on the bedding BT, a futon BD including a pattern PT is hung, and a trash can WB and a washbasin BA are provided in the living room RM of the monitored person Ob. Are shown, but they are not shown in FIG.

Such a camera 12 may be a device that generates an image of visible light, but in the present embodiment, it is a device that generates an image of infrared light so that the monitored person Ob can be monitored even in a relatively dark place. is there. Such a camera 12 is, for example, in the present embodiment, an imaging optical system that forms an infrared optical image of an imaging target on a predetermined imaging surface, and a light receiving surface is arranged so as to coincide with the imaging surface. And an image sensor that converts an infrared optical image of the imaging target into an electrical signal, and image data that is data representing an infrared image of the imaging target by performing image processing on the output of the image sensor. It is a digital infrared camera including an image processing unit that generates the image. In the present embodiment, the imaging optical system of the camera 12 is preferably a wide-angle optical system (a so-called wide-angle lens (including a fisheye lens)) having an angle of view capable of imaging the entire living room RM in which the camera 12 is arranged.

The sound input/output unit 2 is a circuit that is connected to the control processing unit 3 and that acquires an external sound and inputs the external sound to the sensor device SU. According to the control of the control processing unit 3, the sound input/output unit 2 responds to an electric signal representing the sound. It is a circuit for generating and outputting sound. The sound input/output unit 2 includes, for example, a microphone that converts acoustic vibration of sound into an electric signal, a speaker that converts electric signal of sound into the acoustic vibration of sound, and the like. The sound input/output unit 2 outputs an electric signal representing an external sound to the control processing unit 3, and also converts the electric signal input from the control processing unit 3 into acoustic vibration of sound and outputs the acoustic vibration.

The communication IF unit 4 is a communication circuit that is connected to the control processing unit 3 and performs communication under the control of the control processing unit 3. The communication IF unit 4 generates a communication signal containing the data to be transferred, which is input from the control processing unit 3, according to the communication protocol used in the network NW of the monitored person monitoring system MSa, and generates the generated communication signal. It is transmitted to other devices SV, SP, TA via the network NW. The communication IF unit 4 receives communication signals from other devices SV, SP, TA via the network NW, extracts data from the received communication signals, and a format in which the control processing unit 3 can process the extracted data. Data and output to the control processing unit 3. The communication IF unit 4 further uses, for example, a Bluetooth (registered trademark) standard, an IrDA (Infrared Data Association) standard, a USB (Universal Serial Bus) standard, and the like to input and output data to and from an external device. An interface circuit for performing the above may be provided.

The storage unit 5 is a circuit which is connected to the control processing unit 3 and stores various predetermined programs and various predetermined data under the control of the control processing unit 3. The various predetermined programs include, for example, a control processing program such as a monitoring processing program that executes information processing regarding monitoring of the monitored person Ob. The monitoring processing program includes a head detection processing program that detects the head of the monitored person Ob based on the output of the sensor unit 1, and detects a predetermined action of the monitored person Ob based on the output of the sensor unit 1. An action detection processing program, a notification processing program that notifies the predetermined action detected by the action detection program to the outside, and a moving image captured by the camera 12 is streamed to a fixed terminal device SP or a mobile terminal device TA that requests the moving image. A streaming processing program to be distributed and a nurse call processing program for making a voice call with the fixed terminal device SP or the mobile terminal device TA by using the sound input/output unit 2 and the like are included. Then, the head detection processing program is based on a moving body extraction program that extracts a moving body region as a human body region of the monitored person Ob from the image acquired by the camera 12 of the sensor unit 1, based on the moving body region extracted by the moving body extraction program. A circular area extraction program for extracting a substantially circular area as a circular area, and based on the moving body area extracted by the moving body extraction program, an area having a predetermined reflectance or less for infrared light has a low reflectance. A low reflectance region extraction program to extract as a region, and a head region is selected based on the circular region extracted by the circular region extraction program and the low reflectance region extracted by the low reflectance region extraction program. A head selection program for detecting the head is included. As one aspect, the behavior detection processing program detects a predetermined behavior of the monitored person Ob based on the head of the monitored person Ob detected by the head detection processing program. The various kinds of predetermined data include data necessary for executing these programs and data necessary for monitoring the monitored person Ob. The storage unit 5 includes, for example, a ROM (Read Only Memory) which is a non-volatile storage element, and an EEPROM (Electrically Erasable Programmable Read Only Memory) which is a rewritable non-volatile storage element. The storage unit 5 includes a RAM (Random Access Memory) that serves as a working memory of the so-called control processing unit 3 that stores data and the like generated during execution of the predetermined program.

The control processing unit 3 controls each unit of the sensor device SUa in accordance with the function of each unit, the sensor unit 1 detects a preset various amount in the monitored person Ob, and the detected predetermined number. It is a circuit for detecting and notifying a predetermined behavior of the monitored person Ob based on various amounts. The control processing unit 3 includes, for example, a CPU (Central Processing Unit) and its peripheral circuits. The control processing unit 3 causes the control unit 31, the head detection processing unit 32, the action detection processing unit 33, the notification processing unit 34, the streaming processing unit 35, and the nurse call processing unit 36 to be executed by executing the control processing program. Be functionally equipped.

The control unit 31 controls each unit of the sensor device SUa according to the function of each unit, and controls the entire control of the sensor device SU.

The head detection processing unit 32 detects the head of the monitored person Ob based on the output of the sensor unit 1. More specifically, the head detection processing unit 32 detects the head of the monitored person Ob based on the image captured by the camera 12 of the sensor unit 1 from above the monitored person Ob. For this purpose, the head detection processing unit 32 functionally includes a moving body extraction unit 321, a circular region extraction unit 322, a low reflectance region extraction unit 323, and a head selection unit 324.

The moving body extraction unit 321 extracts a moving body region as a human body region of the monitored person Ob from the image acquired by the camera 12 of the sensor unit 1 by using a method such as a background difference method or an interframe difference method. In the background subtraction method, a background image is obtained in advance and stored in the storage unit 5 as one of the various kinds of predetermined data in advance, and whether or not there is a moving object is detected from the difference image between the image generated by the camera 12 and the background image. Is determined, and if there is a moving body as a result of this determination, the area of this moving body is set as the moving body area. In the frame difference method, the presence/absence of a moving object is determined from the difference image between the image of the current frame and the image of the past frame (for example, the previous frame) generated by the camera 12, and as a result of this determination, the moving object is detected. If there is, the moving body area is set as the moving body area. The moving body extraction unit 321 notifies the extracted moving body region to the circular region extraction unit 322 in the operation of the first mode described later, and notifies the low reflectance region extraction unit 323 in the operation of the second mode described later. ..

The circular area extraction unit 322 extracts a substantially circular area as a circular area based on the image acquired by the camera 12 of the sensor unit 1. In the image picked up from above, the head appears in a substantially circular shape, and therefore by extracting the circular area, a head candidate area (head candidate area) is extracted. For example, the circular area extracting unit 322 extracts the circular area from the image acquired by the camera 12 of the sensor unit 1 by using the Hough transform for extracting the circular shape. Further, for example, a circular shape pattern corresponding to the shape pattern of the head is prepared in advance and stored in the storage unit 5 as one of the various kinds of predetermined data, and the circular area extraction unit 322 uses the storage unit. 5, the circular shape pattern stored in advance in 5 is searched by using pattern matching from the image acquired by the camera 12 of the sensor unit 1, and the area matching the circular shape pattern is set as the circular shape area. Extract. More specifically, in the operation of the first aspect, the circular area extracting unit 322 extracts a circular area from the moving object area extracted by the moving object extracting unit 321, for example, by the Hough transform method or the pattern matching method. The extracted circular area is notified to the low reflectance area extraction unit 323. Further, in the operation of the second aspect, the circular area extracting unit 322 uses, for example, the Hough transform method or the pattern matching method from the low reflectance area extracted by the low reflectance area extracting unit 323 as described later. The circular area is extracted by and the extracted circular area is notified to the head selecting unit 324.

The low reflectance region extraction unit 323 extracts a region having a predetermined reflectance or less with respect to infrared light as a low reflectance region based on the image acquired by the camera 12 of the sensor unit 1. Since the head has a relatively low reflectance to infrared light, the head candidate area is extracted by extracting the low reflectance area. Since the head has a low reflectance of, for example, 9%, 10%, and 11% with respect to infrared light, the threshold is set to, for example, 50%, preferably 30%, and more preferably 10%. The area extraction unit 323 extracts an area equal to or less than the threshold value from the image acquired by the camera 12 of the sensor unit 1 as a low reflectance area. More specifically, in the operation of the first aspect, the low reflectance region extraction unit 323 extracts a region equal to or less than the threshold value as the low reflectance region from the circular region extracted by the circular region extraction unit 322, The head selection unit 324 is notified of the extracted low reflectance region. Further, in the operation of the second aspect, the low reflectance region extraction unit 323 extracts a region below the threshold value as a low reflectance region from the moving body region extracted by the moving body extraction unit 321, and the extracted low reflectance ratio The area is notified to the circular area extraction unit 322.

The head selecting unit 324 selects the head region based on the circular region extracted by the circular region extracting unit 322 and the low reflectance region extracted by the low reflectance region extracting unit 323, and the head region is selected. Is to detect. More specifically, in the operation of the first aspect, the head selecting unit 324 detects the head by selecting the head region based on the low reflectance region extracted by the low reflectance region extracting unit 323. Then, the detected head (head region) is notified to the action detection processing unit 33. In the present embodiment, the head selecting unit 324 causes the low reflectance region extracting unit 323 to extract the low reflectance region until the number of low reflectance regions becomes one by changing the default threshold value by a predetermined value. One low reflectance region is selected as the head (head region) and the head is detected. In the operation of the second aspect, the head selecting unit 324 selects the head region based on the circular area extracted by the circular area extracting unit 322, detects the head, and detects the detected head. The part (head region) is notified to the action detection processing unit 33. In the present embodiment, the head selection unit 324 changes the default threshold value by a predetermined value until the number of circular regions extracted by the circular region extraction unit 322 becomes one, and thus the low reflectance region extraction unit 323. The low-reflectance area is extracted, and this one circular area is selected as the head (head area) to detect the head.

The action detection processing unit 33 detects a predetermined action set in advance in the monitored person Ob based on the output of the sensor unit 1. In the present embodiment, as described above, the predetermined action is the waking up, leaving the bed, falling, and slight body movement abnormality of the monitored person Ob, and the action detection processing unit 33 determines whether the predetermined action is based on the output of the sensor unit 1. Waking up, leaving the bed, falling, and fine movement abnormality in the observer Ob are detected as detection results, and the detection result is notified to the notification processing unit 34. For example, the behavior detection processing unit 33 determines the posture (for example, standing position, sitting position, and recumbent position) of the monitored person Ob from the height (size) of the head (head region) detected by the head detection processing unit 32. The position of the detected head is detected, and whether the user is getting up, leaving the bed, or falling is determined based on the detected and detected posture and position of the monitored person Ob. For example, when the height (size) of the head (head region) is a height (size) corresponding to the bedding BT and the position of the head (head region) is in the bedding BT. In particular, the behavior detection processing unit 33 can determine that the monitored person Ob is lying down on the bedding BT, that is, sleeping. Further, for example, when the height (size) of the head (head region) is a height (size) corresponding to a sitting position and the position of the head (head region) is in the bedding BT, The action detection processing unit 33 can determine that the monitored person Ob has woken up. In addition, for example, when the height (size) of the head (head region) is a height (size) corresponding to standing, and the position of the head (head region) is outside the bedding BT. In particular, the behavior detection processing unit 33 can determine that the monitored person Ob has left the bed. Further, for example, when the height (size) of the head (head region) is a height (size) corresponding to the floor, and the position of the head (head region) is outside the bedding BT, The action detection processing unit 33 can determine that the monitored person Ob has fallen. The area of the bedding BT on the image is previously stored in the storage unit 5 as one of the various kinds of predetermined data. The height of the head (head region) is obtained from the size of the head (head region) (for example, horizontally long, vertically long, or area) because the image is acquired from above the monitored person Ob. be able to. Further, for example, the action detection processing unit 33 detects the body movement of the chest (up and down movement of the chest) associated with the breathing movement of the monitored person Ob by the Doppler sensor 11 of the sensor unit 1, and the disturbance of the cycle in the body movement of the chest. When the amplitude of the body movement of the chest that is less than or equal to a preset threshold value is detected, it is determined that the fine body movement is abnormal.

The notification processing unit 34 notifies the outside of the predetermined action detected by the action detection processing unit 33 (in the present embodiment, getting up, leaving the bed, falling down, and abnormal body movements). More specifically, the notification processing unit 34 includes information indicating the detected predetermined action (state, situation) (detection action information (in the present embodiment, one of wake-up, leaving the bed, falling, and abnormal body movement or (Information indicating a plurality)), identifier information for identifying and identifying the monitored person Ob in which the predetermined action is detected (identifier for identifying and identifying the sensor device SUa detecting the monitored person Ob) Information) and a communication signal (surveillance information communication signal) accommodating the image used for detecting the predetermined action and the like are generated and transmitted to the management server SV by the communication IF unit 4.

When there is a request for distribution of a moving image from the fixed terminal device SP or the mobile terminal device TA via the network NW and the communication IF unit 4, the streaming processing unit 35 requests the fixed terminal device SP or the mobile terminal device. A moving image (for example, a live moving image) generated by the camera 12 of the sensor unit 1 is distributed to the TA by streaming reproduction via the communication IF unit 4 and the network NW.

When the nurse call processing unit 36 receives an input operation by a nurse call push button switch (not shown) that receives a nurse call from the monitored person Ob, the nurse call processing unit 36 transmits the fixed terminal device SP or the fixed terminal device SP via the communication IF unit 4 and the network NW. This enables a voice call with the mobile terminal device TA.

In FIG. 1, four first to fourth sensor devices SUa-1 to SUa-4 are shown as an example, and the first sensor device SUa-1 is Mr. A who is one of the monitored persons Ob. The second sensor device SUa-2 is arranged in a living room RM-1 (not shown) of Ob-1 and is arranged in a living room RM-2 (not shown) of Mr. B Ob-2 who is one of the monitored persons Ob. The third sensor device SUa-3 is installed in the room RM-3 (not shown) of Mr. C. Ob-3, who is one of the monitored persons Ob, and the fourth sensor device SUa-4, It is arranged in the room RM-4 (not shown) of Mr. D Ob-4 who is one of the monitored persons Ob.

In the present embodiment, the camera 12 corresponds to an example of an image acquisition unit, and the head detection processing unit 32 corresponds to an example of a head detection device. That is, the sensor device SUa includes a head detecting device.

The management server device SV has a communication function of communicating with other devices SUa, SP, TA via the network NW, and receives the detection result of the monitored person Ob and the image of the monitored person Ob from the sensor device SUa. It is a device that manages information (monitoring information) about monitoring the monitored person Ob. When the management server device SV receives the detection result of the monitored person Ob and the image of the monitored person Ob from the sensor device SUa, the management server device SV stores (records) the monitoring information about the monitoring of the monitored person Ob, and A communication signal (monitoring information communication signal) accommodating the monitoring information regarding the monitoring of the monitor Ob is transmitted to the fixed terminal device SP and the mobile terminal device TA. Further, the management server device SV provides the client with data in response to a request from the client (the fixed terminal device SP, the mobile terminal device TA, etc. in this embodiment). 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 of communicating with other devices SUa, SV, TA via the network NW, a display function of displaying predetermined information, an input function of inputting predetermined instructions and data, and the like. A user interface of the monitored person monitoring system MS by inputting a predetermined instruction or data to be given to the management server device SV or the mobile terminal device TA, displaying a detection result or an image obtained by the sensor device SUa, and the like. A device that functions as a (UI). Such a fixed terminal device SP can be configured by, for example, a computer with a communication function.

The mobile terminal device TA performs a communication function of communicating with other devices SV, SP, SUa via the network NW, a display function of displaying predetermined information, an input function of inputting predetermined instructions and data, and a voice call. It is equipped with a call function to perform, and inputs predetermined instructions and data to be given to the management server device SV and the sensor device SUa, and displays the detection results and images obtained by the sensor device SUa by the notification from the management server device SV. It is a device that receives and displays the monitoring information regarding the monitoring of the person Ob to be monitored by, for example. Such a mobile terminal device TA can be configured by a portable communication terminal device such as a so-called tablet computer, smartphone, or mobile phone.

Next, the operation of this embodiment will be described. In the monitored person monitoring system MSa having such a configuration, each of the devices SUa, SV, SP, and TA, when the power is turned on, executes necessary initialization of each unit and starts its operation. Further, in the sensor device SUa, the control processing unit 3 causes the control processing unit 3 to execute a control processing program, a head detection processing unit 32, an action detection processing unit 33, a notification processing unit 34, a streaming processing unit 35, and a nurse. The call processing unit 36 is functionally configured, and the head detection processing unit 32 is functionally configured with a moving body extraction unit 321, a circular region extraction unit 322, a low reflectance region extraction unit 323, and a head selection unit 324. To be done.

Then, the monitored person monitoring system MSa having the above-mentioned configuration monitors each monitored person Ob by the following operation. The sensor device SUa samples the output of the Doppler sensor 11 of the sensor unit 1 at a predetermined sampling period and acquires an image with the camera 12, and the action detection processing unit 33 performs this sampling and the acquired output of the Doppler sensor 11 and the camera. The predetermined behavior (state, situation) of the monitored person Ob is determined based on the 12 images, and as a result of this determination, the predetermined behavior of the monitored person Ob set in advance (for example, wake-up in the present embodiment, When the notification processing unit 34 determines that the person is out of bed, falls, and abnormalities of microscopic movements), the notification processing unit 34 determines the determination result information indicating the determination result and the image data of the still image of the monitored person Ob. A communication signal (monitoring information communication signal) accommodating monitoring information such as is transmitted to the management server device SV via the network NW. The operation of detecting the head (head detection operation) for detecting getting up, leaving the bed, and falling will be described in detail later.

When the management server device SV receives the monitoring information communication signal from the sensor device SUa via the network NW, the management server device SV stores the monitoring information such as the determination result information and the still image data contained in the monitoring information communication signal in its storage unit. Memorize (record) in. Then, the management server device SV transmits a monitoring information communication signal accommodating the determination result information and the monitoring information such as the image data of the still image to the terminal devices (the fixed terminal device SP and the mobile terminal device TA in this embodiment). .. As a result, the state (situation) of the monitored person Ob is notified to the monitoring person such as a nurse or a caregiver via the terminal devices SP and TA.

When the fixed terminal device SP and the mobile terminal device TA receive the monitoring information communication signal from the management server device SV via the network NW, the fixed terminal device SP and the mobile terminal device TA display the monitoring information contained in the monitoring information communication signal. By such an operation, the monitored person monitoring system MS detects each monitored person Ob by the sensor device SUa, the management server device SV, the fixed terminal device SP, and the mobile terminal device TA, and roughly detects each monitored person Ob. Ob is being monitored.

Next, the head detecting operation in the monitored person monitoring system MSa will be described. FIG. 4 is a flowchart showing the operation of the first aspect of the sensor device in the monitored person monitoring system of the first embodiment. FIG. 5 is a diagram for explaining an example of an image acquired by the sensor device in the monitored person monitoring system of the first embodiment. FIG. 6 is a diagram showing a design of a futon. FIG. 7 is a flowchart showing the operation of the second aspect of the sensor device in the monitored person monitoring system of the first embodiment. The sensor device SUa according to the present embodiment detects the head (head region) by, for example, the operation of the first mode shown in FIG. 4, and also detects the head (head by the operation of the second mode shown in FIG. 7, for example. Area) is detected. Hereinafter, the operation of the first aspect will be described first, and then the operation of the second aspect will be described.

First, the operation of the first aspect will be described. The sensor device SUa operates as follows each time the output of the Doppler sensor 11 of the sensor unit 1 is sampled and the image is acquired by the camera 12 at each sampling timing, whereby the head of the monitored person Ob ( The head region) is detected to detect a predetermined action in the monitored person Ob.

In FIG. 4, first, the control processing unit 3 acquires a Doppler signal from the Doppler sensor 11 of the sensor unit 1 and acquires an image (an image for one frame) from the camera 12 of the sensor unit 1 (S11). The image shown in FIG. 5, for example, is acquired by the camera 12. In the image shown in FIG. 5 of this example, not only the monitored person Ob composed of the trunk BD and the substantially circular head HD, but also the bedding BT, the substantially circular pillow PI on the bedding BT, and the bedding BT are hung. The futon BD, the substantially circular trash can WB, and the substantially circular washbasin BA are shown in the figure. The futon BD has a circular pattern PT, and the circular pattern PT is reflected in the image. In the case where the head HD is detected only by the process of extracting the substantially circular area in the image shown in FIG. 5, not only the head HD is detected but also the pillow PI, the pattern PT, and the trash box WB. Also, the washbasin BA may be erroneously detected as the head HD. The pattern PT of the futon BD may be erroneously detected not only as the circular shape shown in FIG. 5 but also as shown in FIG. 6 as the head HD. In FIG. 6, an octagon (a typical example of a polygon), a substantially circular shape surrounded by V-shaped notches, a substantially circular shape surrounded by eight triangles radially (a shape imitating the sun), Three substantially circular shapes (three shapes imitating a flower pattern), triangles and quadrangles that are radially surrounded by a plurality of petals are illustrated. The shape of the triangle or the quadrangle is distorted due to the distortion of the futon BD, and thus may be erroneously detected as a substantially circular shape. In order to reduce such erroneous detection, in the present embodiment, the image is processed as follows. Note that the reflectance of the pillow PI, the pattern PT, the trash can WB, and the washbasin BA with respect to infrared light is generally higher (greater) than the reflectance of infrared light with respect to the head, depending on its material and the like.

Returning to FIG. 4, next, the control processing unit 3 uses the moving body extraction unit 321 of the head detection processing unit 32 to perform a method such as a background difference method or an interframe difference method from the image acquired by the camera 12. By using it, a moving body region extraction process is executed to extract a moving body region as a human body region of the monitored person Ob, and it is determined whether or not the moving body region has been extracted (S12). As a result of this determination, if the moving body region is not extracted (No), the control processing unit 3 terminates the processing at this timing, while if the moving body region is extracted (Yes), The control processing unit 3 notifies the circular region extraction unit 322 of the moving body region extracted by the moving body extraction unit 321 and executes the next process S13.

In this processing S13, the control processing unit 3 uses, for example, a Hough transform or a pattern matching method from the moving body region extracted by the moving body extraction unit 321 by the circular region extraction unit 322 of the head detection processing unit 32. In step S21, a circular area extracting process for extracting a substantially circular area (circular area) is executed to determine whether or not the circular area is extracted. As a result of this determination, if the circular area is not extracted (No), the control processing unit 3 ends the processing at this timing, while if the circular area is extracted (Yes). The control processing unit 3 notifies the circular area extracted by the circular area extracting unit 322 from the circular area extracting unit 322 to the low reflectance area extracting unit 323 and the head selecting unit 324, and the next processing is performed. Execute S14.

In this processing S14, the control processing unit 3 determines whether the head selection unit 324 of the head detection processing unit 32 has a plurality of circular areas extracted by the circular area extraction unit 322. As a result of this determination, when there are not a plurality of circular areas, that is, when the number of circular areas is one (No), the control processing unit 3 causes the head selecting unit 324 to perform the process S13. The extracted circular region is selected as the head (head region), and the head (head region) selected by the head selection unit 324 is transferred from the head detection processing unit 32 to the action detection processing unit 33. It is notified and the following process S15 is performed. On the other hand, as a result of the determination, when the circular region is plural (Yes), the control processing unit 3 includes a head (head region) in the circular regions extracted in the process S13. If an object other than the above is also extracted, the following process S17 is executed.

In this processing S17, the control processing unit 3 causes the low reflectance region extraction unit 323 of the head detection processing unit 32 to extract the circular region extracted by the circular region extraction unit 322 in the processing S13 from the circular region equal to or less than the threshold value. Is executed as a low reflectance area, and the low reflectance area extraction processing is executed, and the next processing S18 is executed.

In this processing S18, the control processing unit 3 determines whether the head selection unit 324 of the head detection processing unit 32 has one low reflectance region extracted by the low reflectance region extraction unit 323. As a result of this determination, when the number of the low reflectance region is one (Yes), the control processing unit 3 causes the head selecting unit 324 to determine that the low reflectance region extracted in the process S17 is the head ( Head region), and the head detection processing unit 32 notifies the action detection processing unit 33 of the head (head region) selected by the head selection unit 324, and the next process S15 is executed. .. On the other hand, as a result of the determination, when the low reflectance region is not one, that is, when the low reflectance regions are plural (No), the control processing unit 3 selects the plural extracted in the processing S17. It is assumed that an object that is not a head (head area) is also extracted in the low reflectance area of the above, and the head selecting unit 324 determines a predetermined threshold value (for example, 50%, 30%, 10%, etc.). The threshold value is reset by subtracting a value (for example, 0.5% or 0.2%) (S19), and the process returns to the process S17. Therefore, the control processing unit 3 causes the head selection unit 324 to change the default threshold value by a predetermined value, thereby performing the low reflectance region extraction processing by the low reflectance region extraction unit 323 in the processing S17. Therefore, steps S17 to S19 are repeated until the number of low reflectance regions is one.

For example, in the image shown in FIG. 5 described above, not only the head HD, but also the head HD is not performed by the above-described processing S12 and processing S13 due to the displacement of the pillow PI or the futon BD and the movement of the dustbin WB or the washbasin BA. , Pillow PI, pattern PT, trash can WB, and washbasin BA are also extracted as circular areas. If the pattern PT is erroneously detected as the head (head region), if the futon BD slips off, it is erroneously detected as the fall of the monitored person Ob. However, in the present embodiment, the processing S17 to the processing S19 are executed on the plurality of circular areas through the execution of the processing S14. Here, the pillow PI, the pattern PT, the trash can WB, and the washbasin BA have a red reflectance at the head with respect to infrared light due to their materials (for example, cloth, metal, metal coating, plastic, and rattan). Since the reflectance is substantially higher (larger) than the reflectance with respect to external light, it is removed from the low reflectance area by performing the processing S17 to S19, and only the head HD remains as the low reflectance area. By thus considering the reflectance with respect to infrared light, the head HD can be detected more accurately.

Returning to FIG. 4, in process S15, the head (head region) is detected by each of the processes S11 to S14 and S17 to S19 described above, so the control processing unit 3 causes the action detection processing unit 33 to detect the sensor. Based on the output of the unit 1, an action detection process of detecting a preset predetermined action in the monitored person Ob is executed to determine whether or not the predetermined action is detected. More specifically, the behavior detection processing unit 33 determines, as one aspect of the behavior detection processing, from the height (size) of the head (head region) detected by the head detection processing unit 32, the monitored person Ob. Posture (for example, standing position, sitting position, and recumbent position) is detected, and the detected position of the head is detected. Based on these determinations and the detected posture and position of the monitored person Ob, the wake-up, bed leaving, and fall are detected. Determine another. As another mode of the action detection process, the action detection processing unit 33 detects the body movement of the chest (up and down movement of the chest) associated with the breathing action of the monitored person Ob by the Doppler sensor 11 of the sensor unit 1, and The presence/absence of body movement abnormality is determined. As a result of this determination, when the predetermined action is not detected (No), the control processing unit 3 ends the process at this timing, while the predetermined action (in the present embodiment, wakes up, When at least one of leaving the bed, falling, and anomalous body movement is detected (Yes), the control processing unit 3 notifies the notification processing unit 34 of the predetermined action detected in step S15, The following process S16 is executed.

In this processing S16, when the behavior detection processing unit 33 notifies the predetermined behavior of the monitored person Ob, the notification processing unit 34 notifies the management server device SV of the fact by the above-described monitoring information communication signal, The process at this timing ends.

Next, the operation of the second aspect will be described. The sensor device SUa operates as follows each time the output of the Doppler sensor 11 of the sensor unit 1 is sampled and the image is acquired by the camera 12 at each sampling timing, whereby the head of the monitored person Ob ( The head region) is detected to detect a predetermined action in the monitored person Ob.

In FIG. 7, first, the control processing unit 3 acquires a Doppler signal from the Doppler sensor 11 of the sensor unit 1 and acquires an image (an image of one frame) from the camera 12 of the sensor unit 1 as in the above-described process S11. It is acquired (S21).

Next, the control processing unit 3 executes the moving body region extraction processing by the moving body extraction unit 321 of the head detection processing unit 32 and determines whether or not the moving body region is extracted, as in the above-described processing S12. Yes (S22). As a result of this determination, if the moving body region is not extracted (No), the control processing unit 3 terminates the processing at this timing, while if the moving body region is extracted (Yes), The control processing unit 3 notifies the moving body extraction unit 321 of the moving body region extracted by the moving body extraction unit 321 to the low reflectance region extraction unit 323, and executes the next process S23.

In this processing S23, the control processing unit 3 causes the low-reflectance area extraction unit 323 of the head detection processing unit 32 to perform low reflection of the area below the threshold value from the moving body area extracted by the moving body extraction unit 321 in the processing S22. Low reflectance region extraction processing for extracting as a reflectance region is performed, the low reflectance region extracted by the low reflectance region extraction unit 323 is notified from the low reflectance region extraction unit 323 to the circular region extraction unit 322, and then The processing S24 is executed.

In this processing S24, the control processing unit 3 causes the circular region extraction unit 322 of the head detection processing unit 32 to extract, for example, Hough transform or pattern matching from the low reflectance region extracted by the low reflectance region extraction unit 323. By using the method described above, a circular area extraction process for extracting a substantially circular area (circular area) is executed to determine whether or not the circular area has been extracted. As a result of this determination, if the circular area is not extracted (No), the control processing unit 3 ends the processing at this timing, while if the circular area is extracted (Yes). First, the control processing unit 3 notifies the head selecting unit 324 of the circular area extracted by the circular area extracting unit 322 from the circular area extracting unit 322, and executes the next process S25.

In this processing S25, the control processing unit 3 determines by the head selecting unit 324 of the head detection processing unit 32 whether or not there is one circular area extracted by the circular area extracting unit 322. As a result of this determination, when the number of the circular areas is one (Yes), the control processing unit 3 causes the head selecting unit 324 to determine that the circular area extracted in the processing S24 is the head (the head). Region), the head detection processing unit 32 notifies the action detection processing unit 33 of the head (head region) selected by the head selection unit 324, and the next process S26 is executed. On the other hand, as a result of the determination, when the number of the circular areas is not one, that is, when the number of the circular areas is plural (No), the control processing unit 3 causes the plurality of the plurality of the circular areas extracted in the processing S24. It is assumed that an object that is not the head (head area) is also extracted in the circular area, and the head selecting unit 324 sets a predetermined value (for example, 50%, 30%, or 10%) from a default threshold value (for example, 50%, 30%, or 10%). The threshold value is reset by subtracting (0.5%, 0.2%, etc.) (S28), and the process returns to the process S23. Therefore, the control processing unit 3 causes the head selecting unit 324 to change from the default threshold value by a predetermined value, so that the low reflectance region extracting process by the low reflectance region extracting unit 323 in process S23 causes the low reflectance region to be reduced. The processes S23 to S25 and S28 are repeated until the number of circular regions is one.

On the other hand, in the process S26, the head (head region) is detected by the processes S21 to S25 and S28 described above, and thus the control processing unit 3 executes the action detection process as in the process S15 described above. Then, it is determined whether or not the predetermined action is detected. As a result of this determination, when the predetermined action is not detected (No), the control processing unit 3 ends the process at this timing, while the predetermined action (in the present embodiment, wakes up, When at least one of leaving the bed, falling down, and microscopic movement abnormality) is detected (Yes), the control processing unit 3 notifies the notification processing unit 34 of the predetermined action detected in step S26, The following process S27 is executed.

In this processing S27, when the behavior detection processing unit 33 notifies the predetermined behavior of the monitored person Ob, the notification processing unit 34 notifies the fact by the above-described monitoring information communication signal, as in the above-described processing S16. The management server device SV is notified, and the processing at this timing ends.

As described above, the monitored person monitoring system MSa, which is an example of the monitored person, and the sensor device SUa, which uses the head detecting device and the head detecting method, are not only substantially circular but also infrared. Since the head HD is detected in consideration of the reflectance with respect to light, the head HD of the monitored person Ob can be detected more accurately based on the image of the monitored person Ob taken from above. As a result, the monitored person monitoring system MSa and the sensor device SUa can more accurately detect the predetermined behavior of the monitored person Ob.

In addition, the monitored person monitoring system MSa and the sensor device SUa narrow down the circular areas extracted by the circular area extracting unit 322 as candidates for the head area in the operation of the above-described first aspect, and select from the narrowed candidates. Since the head HD is detected in consideration of the reflectance with respect to infrared light, it is possible to simply erroneously detect an object having a low reflectance as compared with the case of extracting the low reflectance region from the entire image acquired by the camera 12. It can be reduced.

Further, the monitored person monitoring system MSa and the sensor device SUa narrow down the low reflectance region extracted by the low reflectance region extraction unit 323 as a candidate for the head region in the operation of the above-described second aspect, and narrows down this. Since the head HD is detected in consideration of the substantially circular shape from the candidates, the amount of information processing can be reduced as compared with the case where the substantially circular circular area is extracted from the entire image acquired by the camera 12.

In addition, in the above-described embodiment, in order to further reduce erroneous detection of a head that is not the head, a predetermined marker may be added to the head that is not the head. In this case, the head detection processing unit 32 of the sensor device SUa, which is an example of the head detection device, is acquired by the camera 12 of the sensor unit 1 that is an example of an image acquisition unit, as indicated by a broken line in FIG. A marker detecting unit 325 that detects a predetermined marker based on the image is functionally further provided, and the head selecting unit 324 uses the circular region extracted by the circular region extracting unit 322 and the low reflectance region extracting unit 323. The head region is selected based on the extracted low reflectance region and the marker detected by the marker detection unit 325 to detect the head. Since such a sensor device SUa further considers the marker, the head of the monitored person Ob can be detected with higher accuracy.

More specifically, the head selection unit 324 selects the marker detected by the marker detection unit 325 from the circular region extracted by the circular region extraction unit 322 and the low reflectance region extracted by the low reflectance region extraction unit 323. An area of the head is selected based on the remaining circular area excluding the area to be held and the low reflectance area, and the head is detected. In this case, for example, in the above-described process S12, for each of the remaining moving body regions obtained by removing the region having the marker detected by the marker detection unit 325 from the moving body region extracted by the moving body extraction unit 321, the following respective processes described above are performed. S13 to S19 are executed. Further, for example, in the above-described process S13, the remaining circular-shaped region obtained by removing the region having the marker detected by the marker detection unit 325 from the circular-shaped region extracted by the circular-shaped region extraction unit 322 is described above. The respective processes S14 to S19 are executed. Further, for example, in the above-described process S17, with respect to the remaining low reflectance region excluding the region having the marker detected by the marker detection unit 325 from the low reflectance region extracted by the low reflectance region extraction unit 323, The respective processes S15 to S19 described above are executed. In addition, for example, in the above-described processing S22, for each of the remaining moving body areas obtained by removing the area having the marker detected by the marker detection unit 325 from the moving body area extracted by the moving body extraction unit 321, the following respective processing S23 to S28 is executed. Further, for example, in the processing S23 described above, from the low reflectance region extracted by the low reflectance region extraction unit 323, with respect to the remaining low reflectance region excluding the region having the marker detected by the marker detection unit 325, The respective processes S23 to S28 described above are executed. Further, for example, in the above-described process S24, the remaining circular-shaped region obtained by removing the region having the marker detected by the marker detection unit 325 from the circular-shaped region extracted by the circular-shaped region extraction unit 322 is described below. The respective processes S23 to S28 are executed. Such a sensor device SUa removes the circular area and the low reflectance area having the marker by adding a marker to the head which is not the head and thus the circular area extraction unit. The circular region extracted in 322 and the low reflectance region extracted by the low reflectance region extraction unit 323 can be excluded from the above-mentioned non-head portion, and the head of the monitored person Ob can be detected more accurately.

Such a marker is preferably a marker having a specific shape. For example, a marker having, for example, a rectangular shape or an arc shape is attached to the edge of the trash can WB or the edge of the bedding BT such as a bed. Such a sensor device SUa can reduce erroneous detection by the marker detection unit 325 by using a marker having a specific shape. Also preferably, the marker is a marker that can be identified only by infrared light. The marker that can be identified only by the infrared light is preferably a material that reflects infrared light with a reflectance (for example, 50% or more) higher than the reflectance of the head with respect to infrared light, the material. A seal formed of (for example, a metal seal or a wood seal), a pigment that reflects infrared light with a reflectance (for example, 50% or more) higher than the reflectance of the head with respect to infrared light (infrared reflective pigment). ) And a combination of one or more of the predetermined shape formed by the difference in the density of the weave of the cloth. For example, the futon BD or the pillow PI is made of the above-mentioned material that reflects infrared light with high reflectance, so that the futon BD or the pillow PI is provided with a marker (the futon BD itself or the pillow PI itself serves as a marker). ). Further, for example, since natural materials such as cotton and linen and chemical fiber materials such as polyester have different reflectances to infrared light, a futon BD or pillow PI made of a natural material (or a chemical fiber material) has a chemical fiber By sewing in a thread of a material (or a natural material), a marker is given to the futon BD or the pillow PI. Further, for example, since the reflectance to infrared light differs depending on the density of the woven fabric, the futon BD or the pillow PI made of the coarse woven fabric (or the dense woven fabric) has a dense woven fabric (or a predetermined shape). A marker is given to the futon BD or the pillow PI by sewing in a coarsely woven material. Such a sensor device SUa can reduce erroneous detection by the marker detection unit 325 by using a marker that can be identified only by infrared light. Since the marker cannot be seen, the sensor device SU, when used in the monitored person monitoring system MSa, does not cause the monitored person Ob to recognize the presence of the marker and does not give a sense of discomfort.

Next, another embodiment will be described.
(Second embodiment)
FIG. 8 is a diagram showing the configuration of the sensor device in the monitored person monitoring system of the second embodiment.

The monitored person monitoring system MSb in the second embodiment, which is an example of the monitored person monitoring apparatus realized as a system, is the same as the monitored person monitoring system MSa in the first embodiment. In order to monitor the monitored person Ob by detecting a preset predetermined action in a monitored person (monitoring target person) Ob (Ob-1 to Ob-4) which is a target (monitoring target), For example, one or a plurality of sensor devices SUb (SUb-1 to SUb-4), a management server device SV, a fixed terminal device SP, and one or a plurality of mobile terminal devices TA (TA-1, TA-2). Equipped with. That is, the monitored person monitoring system MSb in the second embodiment is the same as the monitored person monitoring system MSa in the first embodiment except that the sensor device SUa is replaced by the sensor device SUb. Therefore, the description of the management server device SV, the fixed terminal device SP, and the mobile terminal device TA is omitted.

Like the sensor device SUa, the sensor device SUb has a communication function of communicating with other devices SV, SP, TA via the network NW, detects the monitored person Ob, and sends the detection result to the management server device SV. It is a device for transmitting. Such a sensor device SUb includes, for example, as shown in FIG. 8, a sensor unit 1, a sound input/output unit 2, a control processing unit 6, a communication interface unit (communication IF unit) 4, and a storage unit 7. Equipped with. That is, the sensor device SUb is similar to the sensor device SUa except that the control processing unit 3 is replaced by the control processing unit 6 and the storage unit 5 is replaced by the storage unit 7. Therefore, the description of the sensor unit 1, the sound input/output unit 2, and the communication IF unit 4 is omitted.

The storage unit 7 is a circuit which is connected to the control processing unit 6 and stores various predetermined programs and various predetermined data under the control of the control processing unit 6. The various predetermined programs include, for example, a control processing program such as a monitoring processing program that executes information processing regarding monitoring of the monitored person Ob. The monitoring processing program includes a head detection processing program that detects the head of the monitored person Ob based on the output of the sensor unit 1, and detects a predetermined action of the monitored person Ob based on the output of the sensor unit 1. An action detection processing program, a notification processing program that notifies the predetermined action detected by the action detection program to the outside, and a moving image captured by the camera 12 is streamed to a fixed terminal device SP or a mobile terminal device TA that requests the moving image. A streaming processing program to be distributed and a nurse call processing program for making a voice call with the fixed terminal device SP or the mobile terminal device TA by using the sound input/output unit 2 and the like are included. Then, the head detection processing program is based on a moving body extraction program that extracts a moving body region as a human body region of the monitored person Ob from the image acquired by the camera 12 of the sensor unit 1, based on the moving body region extracted by the moving body extraction program. A circular area extraction program for extracting a substantially circular area as a circular area, a marker detection program for detecting a predetermined marker based on the moving body area extracted by the moving body extraction program, and the circular shape area extraction A head selection program or the like for selecting a head region based on the circular region extracted by the program and the marker extracted by the marker detection program to detect the head is included. As one aspect, the behavior detection processing program detects a predetermined behavior of the monitored person Ob based on the head of the monitored person Ob detected by the head detection processing program. The various kinds of predetermined data include data necessary for executing these programs and data necessary for monitoring the monitored person Ob. The storage unit 7 includes, for example, a ROM that is a nonvolatile storage element, an EEPROM that is a rewritable nonvolatile storage element, and the like. The storage unit 7 includes a RAM or the like that serves as a working memory of the so-called control processing unit 3 that stores data and the like generated during execution of the predetermined program.

The control processing unit 6 controls each unit of the sensor device SUb in accordance with the function of each unit, the sensor unit 1 detects a predetermined amount set in the monitored person Ob, and the detected predetermined amount. It is a circuit for detecting and notifying a predetermined behavior of the monitored person Ob based on various amounts. The control processing unit 6 includes, for example, a CPU and its peripheral circuits. The control processing unit 6 causes the control unit 61, the head detection processing unit 62, the action detection processing unit 63, the notification processing unit 64, the streaming processing unit 65, and the nurse call processing unit 66 to be executed by executing the control processing program. Be functionally equipped. The control unit 61, the behavior detection processing unit 63, the notification processing unit 64, the streaming processing unit 65, and the nurse call processing unit 66 in the control processing unit 6 are respectively the control unit 31 and the behavior in the control processing unit 3 of the first embodiment. The detection processing unit 33, the notification processing unit 34, the streaming processing unit 35, and the nurse call processing unit 36 are the same as those of the detection processing unit 33, the description thereof will be omitted.

The head detection processing unit 62, like the head detection processing unit 32, detects the head of the monitored person Ob based on the output of the sensor unit 1. More specifically, the head detection processing unit 62 detects the head of the monitored person Ob based on the image captured by the camera 12 of the sensor unit 1 from above the monitored person Ob. For this purpose, the head detection processing unit 62 functionally includes a moving body extraction unit 621, a circular area extraction unit 632, a marker detection unit 623, and a head selection unit 624.

Similar to the moving body extracting unit 321, the body movement extracting unit 621 uses the image obtained by the camera 12 of the sensor unit 1 as a human body region of the monitored person Ob by using a method such as a background difference method or an interframe difference method. The moving body area is extracted. The moving body extraction unit 621 notifies the extracted moving body region to the circular area extraction unit 622 in the operation of the first mode described later, and notifies the marker detection unit 623 in the operation of the second mode described later.

The circular area extraction unit 622, similar to the circular area extraction unit 322, extracts a substantially circular area as a circular area based on the image acquired by the camera 12 of the sensor unit 1. More specifically, in the operation of the first aspect, the circular area extraction unit 622 extracts the circular area from the moving body area extracted by the moving body extraction unit 621 by, for example, the Hough transform method or the pattern matching method. The extracted circular area is notified to the marker detection unit 623. Further, in the operation of the second aspect, the circular area extraction unit 322 uses, for example, the Hough transform method or the pattern matching from the remaining body motion area excluding the marker area detected by the marker detection unit 623 as described later. The circular area is extracted by the method described above and the extracted circular area is notified to the head selecting unit 624.

The marker detection unit 623 detects a predetermined marker based on the image acquired by the camera 12 of the sensor unit 1. Similar to the above, the predetermined marker is given to the one that is close to the head that is not the head in order to further reduce the false detection of the one that is close to the head that is not the head, and is preferably a specific shape. And a marker that can be identified only by infrared light. More specifically, in the operation of the first aspect, the marker detection unit 623 detects the predetermined marker from the circular area extracted by the circular area extraction unit 622 and extracts it by the circular area extraction unit 622. The head selecting unit 624 is notified of the remaining circular area excluding the circular area having the detected marker from the circular area. Further, in the operation of the second aspect, the marker detection unit 623 detects the predetermined marker from the moving body region extracted by the moving body extraction unit 621, and has the detected marker from the moving body region extracted by the moving body extraction unit 621. The remaining body movement area excluding the body movement area is notified to the circular area extraction unit 622.

The head selecting unit 624 detects the head by selecting a region of the head based on the circular region extracted by the circular region extracting unit 622 and the predetermined marker extracted by the marker detecting unit 623. Is. More specifically, in the operation of the first aspect, the head selection unit 624 selects the head region based on the marker detected by the marker detection unit 623, detects the head, and detects the detected head. The part (head region) is notified to the action detection processing unit 63. In the operation of the second aspect, the head selecting unit 624 selects the head region based on the circular area extracted by the circular area extracting unit 622, detects the head, and detects the detected head. The part (head region) is notified to the action detection processing unit 63.

In the monitored person monitoring system MSb having such a configuration, each of the devices SUb, SV, SP, and TA, when the power is turned on, initializes necessary parts and starts operating. Further, in the sensor device SUb, by executing the control processing program, the control processing unit 6 has the control unit 61, the head detection processing unit 62, the action detection processing unit 63, the notification processing unit 64, the streaming processing unit 65, and the nurse. The call processing unit 66 is functionally configured, and the head detection processing unit 62 is functionally configured with a moving body extraction unit 621, a circular region extraction unit 622, a low reflectance region extraction unit 623, and a head selection unit 624. To be done. The monitored person monitoring system MSb having the above-described configuration operates in the same manner as the monitored person monitoring system MSa described above, except that the sensor device SUb operates as described below, and therefore description thereof will be omitted.

Next, the head detecting operation in the monitored person monitoring system MSb will be described. FIG. 9 is a flowchart showing the operation of the first aspect of the sensor device in the monitored person monitoring system of the second embodiment. FIG. 10 is a flowchart showing the operation of the second aspect of the sensor device in the monitored person monitoring system of the second embodiment. The sensor device SUb in the present embodiment detects the head (head region) by, for example, the operation of the first mode shown in FIG. 9, and also detects the head (head by the operation of the second mode shown in FIG. 10, for example. Area) is detected. Hereinafter, the operation of the first aspect will be described first, and then the operation of the second aspect will be described.

First, the operation of the first aspect will be described. The sensor device SUb operates as follows each time the output of the Doppler sensor 11 of the sensor unit 1 is sampled and the image is acquired by the camera 12 at each sampling timing, whereby the head of the monitored person Ob ( The head region) is detected to detect a predetermined action in the monitored person Ob.

In FIG. 9, first, the control processing unit 6 acquires a Doppler signal from the Doppler sensor 11 of the sensor unit 1 and acquires an image (an image for one frame) from the camera 12 of the sensor unit 1 as in the above-described process S11. It is acquired (S31).

Next, the control processing unit 6 executes the moving body region extraction processing by the moving body extraction unit 621 of the head detection processing unit 62 and determines whether or not the moving body region has been extracted, as in the above-described processing S12. Yes (S32). As a result of this determination, if the moving body region is not extracted (No), the control processing unit 6 ends the process at this timing, while if the moving body region is extracted (Yes), The control processing unit 6 notifies the circular region extracting unit 622 of the moving body region extracted by the moving body extracting unit 621, and executes the next process S33.

In this processing S33, the control processing unit 6 uses a method such as Hough transform or pattern matching from the moving body region extracted by the moving body extraction unit 321 by the circular shape region extraction unit 622 of the head detection processing unit 62. In step S21, a circular area extracting process for extracting a substantially circular area (circular area) is executed to determine whether the circular area has been extracted. As a result of this determination, when the circular area is not extracted (No), the control processing unit 6 ends the processing at this timing, while when the circular area is extracted (Yes). Then, the control processing unit 6 notifies the marker detection unit 623 and the head selection unit 624 of the circular area extracted by the circular area extraction unit 622 from the circular area extraction unit 622, and executes the next processing S34. To do.

In this processing S34, the control processing unit 6 determines whether or not there are a plurality of circular areas extracted by the circular area extraction unit 622 by the head selection unit 624 of the head detection processing unit 62. As a result of this determination, when there are not a plurality of circular areas, that is, when the number of circular areas is one (No), the control processing unit 6 causes the head selecting unit 624 to perform the processing in S33. The extracted circular region is selected as the head (head region), and the head (head region) selected by the head selection unit 624 is transferred from the head detection processing unit 62 to the action detection processing unit 63. It is notified and the following process S35 is performed. On the other hand, as a result of the determination, when there are a plurality of circular areas (Yes), the control processing unit 6 sets the head (head area) in the plurality of circular areas extracted in the process S33. If an object other than the above is also extracted, the following process S37 is executed.

In this processing S37, the control processing unit 6 causes the marker detection unit 623 of the head detection processing unit 62 to detect a predetermined marker from the circular area extracted by the circular area extraction unit 622, and the circular area extraction unit The head-shaped selecting unit 624 is notified of the remaining circular-shaped region excluding the circular-shaped region having the detected marker from the circular-shaped region extracted in 622, and the head-selecting unit 624 removes the residual circular-shaped region by the marker detecting unit 623. The circular area is selected as the head area, the head is detected, the detected head (head area) is notified to the action detection processing unit 63, and the next processing S35 is executed. The control processing unit 6 may notify the behavior detection processing unit 63 from the marker detection unit 623 of the remaining circular area removed by the marker detection unit 623 as a head region.

In this process S35, the head (head region) is detected by each of the processes S31 to S34 and S37 described above, and thus the control processing unit 6 causes the action detection processing unit 63 to perform the same operation as in the process S15 described above. Based on the output of the sensor unit 1, an action detection process of detecting a preset predetermined action in the monitored person Ob is executed to determine whether or not the predetermined action is detected. As a result of this determination, when the predetermined action is not detected (No), the control processing unit 6 ends the process at this timing, while the predetermined action (in the present embodiment, wakes up, When at least one of leaving the bed, falling, and anomalous body movement is detected (Yes), the control processing unit 6 notifies the notification processing unit 64 of the predetermined action detected in step S35, The following process S36 is executed.

In this processing S36, when the behavior detection processing unit 63 notifies the predetermined behavior of the monitored person Ob, the notification processing unit 64 notifies the management server device SV of that fact by the above-mentioned monitoring information communication signal, The process at this timing ends.

Next, the operation of the second aspect will be described. The sensor device SUb operates as follows each time the output of the Doppler sensor 11 of the sensor unit 1 is sampled and the image is acquired by the camera 12 at each sampling timing, whereby the head of the monitored person Ob ( The head region) is detected to detect a predetermined action in the monitored person Ob.

In FIG. 10, first, the control processing unit 6 acquires a Doppler signal from the Doppler sensor 11 of the sensor unit 1 and acquires an image (an image for one frame) from the camera 12 of the sensor unit 1 as in the above-described process S11. It is acquired (S41).

Next, the control processing unit 6 executes the moving body region extraction processing by the moving body extraction unit 621 of the head detection processing unit 62 and determines whether or not the moving body region has been extracted, as in the above-described processing S12. (S42). As a result of this determination, if the moving body region is not extracted (No), the control processing unit 6 ends the process at this timing, while if the moving body region is extracted (Yes), The control processing unit 6 notifies the marker detection unit 623 from the moving body extraction unit 621 of the moving body region extracted by the moving body extraction unit 621, and executes the next process S43.

In this processing S43, the control processing unit 6 causes the marker detection unit 623 of the head detection processing unit 62 to detect a predetermined marker from the body movement region extracted by the body movement extraction unit 621, and the body movement extraction unit 621 The remaining body movement area excluding the body movement area having the detected marker from the extracted body movement area is notified to the circular area extraction unit 622, and the next process S44 is executed.

In this processing S44, the control processing unit 6 causes the circular area extraction unit 622 of the head detection processing unit 62 to extract, for example, a Hough from the remaining body movement area excluding the body movement area having the marker by the marker detection unit 623. A circular area extraction process for extracting a substantially circular area (circular area) by using a method such as conversion or pattern matching is executed to determine whether or not the circular area is extracted. As a result of this determination, when the circular area is not extracted (No), the control processing unit 6 ends the processing at this timing, while when the circular area is extracted (Yes). In addition, the control processing unit 6 notifies the circular area extracted by the circular area extracting unit 622 from the circular area extracting unit 622 to the head selecting unit 624, and the head selecting unit 624 causes the circular area extracting unit 624 to detect the circular area. The circular area extracted by 622 is selected as the area of the head, the head is detected, the detected head (head area) is notified to the action detection processing unit 63, and the next processing S45 is executed. To do. The control processing unit 6 may notify the action detection processing unit 63 from the circular area extracting unit 622 of the circular area extracted by the circular area extracting unit 622 as the head area.

In this process S45, the head (head region) is detected by each of the processes S41 to S44 described above, so that the control processing unit 6 causes the action detection processing unit 63 to detect the sensor unit as in the case of the process S15 described above. Based on the output of 1, the behavior detection process for detecting a preset predetermined behavior in the monitored person Ob is executed to determine whether or not the predetermined behavior is detected. As a result of this determination, when the predetermined action is not detected (No), the control processing unit 6 ends the process at this timing, while the predetermined action (in the present embodiment, wakes up, When at least one of leaving the bed, falling down, and anomalous body movement is detected (Yes), the control processing unit 6 notifies the notification processing unit 64 of the predetermined action detected in step S45, The next process S46 is executed.

In this processing S46, when the behavior detection processing unit 63 notifies the predetermined behavior of the monitored person Ob, the notification processing unit 64 notifies the management server device SV of that fact by the above-mentioned monitoring information communication signal, The process at this timing ends.

As described above, the monitored person monitoring system MSb, which is an example of the monitored person monitoring device, and the sensor device SUb of the example using the head detecting device and the head detecting method, not only has a substantially circular shape but also a marker. Since the head HD is detected in consideration, the head HD of the monitored person Ob can be detected more accurately based on the image of the monitored person Ob taken from above. As a result, the monitored person monitoring system MSb and the sensor device SUb can more accurately detect the predetermined behavior of the monitored person Ob.

Further, the monitored person monitoring system MSb and the sensor device SUb in the operation of the first aspect described above narrow down the circular area extracted by the circular area extraction unit 622 as a head area candidate, and from this narrowed-down candidate, By removing the circular area having the marker, the circular area extracted by the circular area extraction unit 622 can be removed from the circular area, and the head HD of the monitored person Ob can be more accurately detected. Can be detected.

Further, the monitored person monitoring system MSb and the sensor device SUb remove the body movement area having the marker from the body movement area extracted by the body movement extraction unit 621 in the operation of the above-described second aspect, thereby removing the body movement area. Since the head HD is detected by narrowing down and considering the substantially circular shape from the narrowed body movement area, the amount of information processing is larger than that in the case of extracting the substantially circular circular area from the entire image acquired by the camera 12. Can be reduced.

Further, in the above-described embodiments, when the circular area is detected within the area of the bedding BT from the idea that it is safe on the bedding BT, the circular area is processed by the processing S15, the processing S26, and the processing S26. It may be excluded from the targets of the action detection processing in each of S35 and processing S45.

In addition, in the above-described embodiments, the sensor devices SUa and SUb include the action detection unit and the notification unit, but the action detection unit and the notification unit may be included in the management server device SV. The fixed terminal device SP may be provided, or the mobile terminal device TA may be provided. In such a case, a communication interface or the like that receives and acquires a communication signal containing an image and a Doppler signal captured from above the monitored person Ob via the network NW from the sensor devices SUa and SUb is an example of the image acquisition unit. It also corresponds to an example of a part of the distance measuring unit.

In order to represent the present invention, the present invention has been described above appropriately and sufficiently through the embodiments with reference to the drawings, but those skilled in the art can easily modify and/or improve the embodiments. It should be recognized that this is possible. Therefore, unless a modification or improvement carried out by a person skilled in the art is at a level that departs from the scope of rights of the claims recited in the claims, the modification or the improvement is covered by the scope of claims of the claim. Is understood to be included in.

Ob (Ob-1 to Ob-4) Monitored person NS (NS-1, NS-2) Monitored person (user)
MSa, MSb Monitored person monitoring system SUa, SUb Sensor device SV Management server device SP Fixed terminal device TA Mobile terminal device 1 Sensor unit 3, 6 Control processing unit 4 Communication interface unit (communication IF unit)
5, 7 Storage unit 11 Doppler sensor 12 Camera (an example of image acquisition unit)
31, 61 Control unit 32, 62 Head detection processing unit 33, 63 Behavior detection processing unit 34, 64 Notification processing unit 321, 621 Moving body extraction unit 322, 622 Circular region extraction unit 323 Low reflectance region extraction unit 324, 624 Head selection unit 325, 623 Marker detection unit

Claims (6)

An image acquisition unit that acquires an image of a monitored person who is a monitoring target from above the monitored person,
Based on the image acquired by the image acquisition unit, a marker detection unit for detecting a predetermined marker,
From the remaining region excluding the region having the marker detected by the marker detecting unit from the image acquired by the image acquisition unit, a circular region extraction unit for extracting a substantially circular area as the circular region,
From the circular region extracted by the circular region extraction unit, a low reflectance region extraction unit that extracts a region having a predetermined reflectance or less for infrared light as a low reflectance region,
E Bei a head selection unit for detecting the head by selecting an area of the head on the basis of the low reflectance area extracted in the previous SL low reflectance region extraction unit,
Before SL marker, the only a distinguishable with infrared light, a head detecting apparatus characterized by reflectance to the infrared light is beyond a predetermined reflectance. An image acquisition unit that acquires an image of a monitored person who is a monitoring target from above the monitored person,
Based on the image acquired by the image acquisition unit, a marker detection unit for detecting a predetermined marker,
From the residual region excluding the region having the marker detected by the marker detection unit from the image acquired by the image acquisition unit, a region having a predetermined reflectance or less for infrared light is extracted as a low reflectance region. A low reflectance region extraction unit,
From the low reflectance region extracted by the low reflectance region extracting unit, a circular region extracting unit that extracts a substantially circular region as a circular region,
A head selection unit that detects a head region by selecting a head region based on the circular region extracted by the circular region extraction unit,
The marker is the only a distinguishable with infrared light, the head portion detection apparatus you wherein the reflectance to the infrared light is beyond a predetermined reflectance. The marker head detecting apparatus according to any one of claims 1 to 2, characterized in that a marker having a particular shape. An image acquisition step of acquiring an image of a monitored person who is a monitoring target from above the monitored person,
Based on the image acquired in the image acquisition step, a marker detection step of detecting a predetermined marker,
From the remaining area excluding the area having the marker detected in the marker detection step from the image acquired in the image acquisition step, a circular area extraction step of extracting a substantially circular area as a circular area,
From the circular area extracted in the circular area extraction step, a low reflectance area extraction step of extracting a region having a predetermined reflectance or less for infrared light as a low reflectance area,
A head selecting step of detecting the head by selecting a head area based on the low reflectance area extracted in the low reflectance area extracting step,
The marker is distinguishable only by the infrared light, and the reflectance for the infrared light exceeds the predetermined reflectance.
A head detection method characterized by: An image acquisition step of acquiring an image of a monitored person who is a monitoring target from above the monitored person,
Based on the image acquired in the image acquisition step, a marker detection step of detecting a predetermined marker,
From the remaining area excluding the area having the marker detected in the marker detection step from the image acquired in the image acquisition step, an area having a predetermined reflectance or less for infrared light is extracted as a low reflectance area. Low reflectance region extraction step,
From the low reflectance area extracted in the low reflectance area extraction step, a circular area extraction step of extracting a substantially circular area as a circular area,
A head selecting step of detecting the head by selecting an area of the head based on the circular area extracted in the circular area extracting step ,
Before SL marker, only a identifiable by the infrared light, a head detecting method characterized by reflectance to the infrared light is beyond a predetermined reflectance. A monitored person as a monitoring target, a head detection unit that detects a head from an image captured from above the monitored person,
An action detection unit that detects a predetermined action in the monitored person based on the monitored person's head detected by the head detection unit,
A notification unit for notifying the outside of the predetermined action detected by the action detection unit,
The said head detection part contains the head detection apparatus of any one of Claim 1 thru|or 3 , The to-be-monitored person monitoring apparatus characterized by the above-mentioned.

Images