JP2015138427A - monitor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a monitor capable of being easily installed so as to image an optimal place for watching.SOLUTION: A monitor comprises: an image part; a video storage part for storing video data in the imaging part; a movement history detection storage part for detecting a position of a monitor object from the video data in the imaging part, and storing it as history information in which the monitor object moved; an imaging place determination part for comparing video data which was imaged past in the video storage part and video data which is being imaged by the imaging part now, and determining the place where the imaging is performed now; and an installation guiding part for searching the movement history information of the monitor object which was detected and stored past at the place determined by the imaging place determination part from the movement history detection storage part, detecting a high frequency present place where the monitor object was present by high frequency from the searched movement history information, and guiding an imaging direction to a direction where the high frequency present place is a center of a screen of the imaging part.

Description

  The present invention relates to a monitoring device.

  Currently, the birthrate and aging of the population are rapidly increasing in Japan, and care and care for the elderly will become a major social problem. In a method in which a caregiver always watches and cares for a cared person, a long-time restraint operation is imposed on the caregiver. Currently, there is an urgent need to develop a monitoring system that can reduce the burden on caregivers because of the shortage of caregivers and the need to reduce the cost of caregivers.

  A system that watches over caregivers such as the elderly is required to monitor the caregiver's behavior and promptly notify the caregiver if a situation such as a fall that could cause a physical hazard occurs. It is done. This monitoring system is expected to utilize a technique for photographing a cared person with a camera and detecting an abnormal situation from the photographed image, and its development and system deployment are actively performed.

  For example, in Patent Document 1 below, in a camera that captures a cared person and outputs it as a video signal in a nursing facility such as a hospital, a nursing home, or a nursing home, the luminance and saturation of the video signal from the camera change over a certain time. If not, a motion stop detection device that determines that an abnormal situation has occurred in the care recipient and issues an alarm is disclosed.

  In Patent Document 2 below, an image of an elderly person is acquired by a camera, the contour of the target person is extracted from the image, and the movement and state are determined by comparing the data stored in the system with the extracted contour. An automatic monitoring method is disclosed in which an automatic determination is made and when an abnormal situation occurs, the information and image data are communicated to a monitoring center or relatives.

  Furthermore, there is an overwhelming shortage of care facilities that house caregivers both now and in the future. As a form of future care, a home helper visits the caregiver's home to provide care. Nursing care is expected to become mainstream. Also in this home care, the above-mentioned monitoring and monitoring technology of the cared person by the camera is effective for reducing the burden of home helper work. However, unlike a care facility, home care is difficult to set up at all times because the camera is placed at the home of the care recipient. Furthermore, the installation of a large surveillance camera is likely to cause mental distress that is always watched by the care recipient.

  From this point of view, a home helper for home care can be carried with the caregiver at home and can be easily placed in an inconspicuous place in the caregiver's room, so that the home helper can reach There is a growing demand for a small watch camera that can casually watch the cared person when he is not. For example, in the following Patent Document 3, a portable surveillance camera that can be installed without a restriction of a connection cord is disclosed. This mobile surveillance camera compresses and encodes a captured video and transmits it to a monitor using a wireless line to display the video. Thereby, since this portable surveillance camera can be installed freely without restrictions on installation conditions, it is easy to use and can be used for a monitoring system or the like.

JP 2003-85671 A JP 2002-44645 A JP-A-6-319142

  With the above-mentioned small watching camera, it is feasible for the home helper to bring it at home care visit and place it in the care recipient's room to photograph the care recipient. Furthermore, by analyzing the captured video, it is possible to detect the care receiver's fall, and to monitor the home helper's portable device via a wireless line or the like when an abnormal situation occurs. However, when using such a small watching camera that is portable and can be easily installed, there are the following problems.

  There are many small monitoring cameras that omit a video display unit such as a display from the viewpoint of portability and power consumption, and it is not possible to easily check a captured video. Therefore, when the home helper places a small network camera in the room, it is difficult to know what kind of place is being photographed, and there is a possibility that the place intended by the home helper cannot be photographed.

  From the viewpoint of watching a cared person, it is desirable to install a watch camera so that the cared person can be photographed as much as possible on the shooting screen, and to be able to photograph a place with the highest risk for the cared person as much as possible. It is desirable to install. Furthermore, considering notifying the caregiver of information that the cared person has fallen, it is necessary to set so that the fallen state can be photographed on the screen.

  It is difficult to install a camera so that the optimal location can be photographed from the viewpoint of watching such care recipients, and it is difficult even with a camera equipped with a display. Improvement of home helper operations in home care is expected to expand in the future. Therefore, it can be said that the realization of a monitoring camera that can be easily installed so that the home helper can shoot an optimal place for watching is a major issue to be solved immediately.

  In view of the above-described problems, an object of the present invention is to provide a technique that can be installed so that anyone can easily photograph an optimum place for watching.

  According to an aspect of the present invention, an imaging unit, a video storage unit that stores video data of the imaging unit, a position of a monitoring target watching person is detected from the video data of the imaging unit, and the monitoring target monitoring target is detected. The movement history detection storage unit that stores the history information moved by the user, the video data captured in the past stored in the video storage unit, and the video data currently captured by the imaging unit are compared, The movement history information of the monitoring target watching target detected and stored in the past at the shooting location determined by the shooting location determination unit is determined from the movement history detection storage unit. Search and select, detect from the movement history information searched and selected a high-frequency presence location where the monitoring target person was present, and shoot in the direction where the high-frequency presence location becomes the screen center of the imaging unit Direction An installation guide portion guiding, monitoring devices watching camera comprising: a is provided with.

  According to the present invention, it is possible to photograph a place suitable for monitoring.

It is a figure which shows the example of an external appearance structure of the watching camera which concerns on the 1st Embodiment of this invention. It is a functional block diagram which shows the example of 1 structure of the watching camera of this embodiment. It is a figure explaining the photography place determination process in this implementation. It is a figure which shows the example of 1 structure of the preserve | saved data. It is a functional block diagram which shows one structural example of an imaging | photography place determination part. It is a flowchart figure explaining the imaging | photography place determination part in this embodiment. It is a figure explaining the movement history information in this embodiment. It is a functional block diagram which shows the example of 1 structure of an installation guidance part. It is a flowchart figure explaining the installation guidance process in this embodiment. It is a flowchart figure explaining operation | movement of the monitoring apparatus of this embodiment. It is a figure which shows the flow of a process in the installation guidance part which concerns on the 2nd Embodiment of this invention. It is a figure explaining the installation guidance process of this embodiment. It is a flowchart figure explaining the installation guidance process in this embodiment. It is a figure explaining another example of the installation guidance process in this embodiment. It is a three-view figure which shows the external appearance of the watching camera of the 3rd Embodiment of this invention. It is a functional block diagram which shows the example of 1 structure of the watching camera of this embodiment.

  Hereinafter, a monitoring technique according to an embodiment of the present invention will be described in detail with reference to the drawings. As an example of a monitoring device, a camera that takes an image of a subject and watches the situation will be described as an example, and a monitoring camera used in a system that provides care and care for elderly people will be described as an example.

(First embodiment)
A first embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a diagram illustrating an example of an overview configuration of the watching camera 1 according to the present embodiment, and FIG. 2 is a functional block diagram illustrating the configuration example.

  As shown in FIG. 1, a watching camera 1 according to the present embodiment has an imaging unit 2 that captures a monitoring target (hereinafter referred to as a “watching target person”) that is a moving subject to be monitored, and imaging. The camera case 4 which accommodates the part 2, and four induction | division LED3 which guides the imaging | photography direction distribute | arranged to the left and right upper and lower sides of the camera case 4 are provided. The camera case 4 is connected to an installation stand 5 via a hinge 6 so that the user can manually adjust the direction in which the imaging unit 2 captures an image.

  As shown in FIG. 2, the watching camera 1 includes an image capturing unit 2 that captures a person to be watched, a video storage unit 21 that stores video data captured by the image capturing unit 2, and the video data of the image capturing unit 2. A movement history detection storage unit 22 that detects the position and stores it as history information that the person to watch over has moved, video data captured in the past stored in the video storage unit 21, and a video currently captured by the imaging unit 2 The shooting location determination unit 23 that compares the data with the shooting location to determine the shooting location, and the movement history information of the watching target that has been detected and stored in the past at the shooting location determined by the shooting location determination unit 23. An installation guidance unit 24 that guides the shooting direction so that the position (location) where the person to be watched has stayed for the longest time is an easy-to-see position such as the center of the screen based on the retrieved movement history information , Four induction LED3 provided in example different directions to light under the control of the location induction unit 24, and a. Furthermore, it has the control part (CPU) 7 which controls the whole, and database DB (memory) 8 which preserve | saves data. The arrangement of the guide LED 3 is not limited to the arrangement shown in FIG. 1 as long as the direction can be indicated.

Hereinafter, each functional block will be described in detail.
The imaging unit 2 forms an image of light from a subject on an imaging element with a photographing lens, and photoelectrically converts the formed image with an imaging element such as a CMOS image sensor and outputs it as video data. Note that the imaging lens used in the present embodiment is preferably focused in a wide range, and for example, a pan focus lens is preferably used. In addition, it is desirable that the image sensor used in this embodiment is an image sensor with a high dynamic range so that it can capture images from a dark place in a room where illumination does not reach to a bright place near the window.

  The video storage unit 21 stores the video data captured by the imaging unit 2 in a storage device (for example, DB 8) such as a flash memory. The video data is stored by embedding time information when the image is taken, for example, as Exif information (a standard for embedding conditions at the time of shooting in an image). In addition, in consideration of a shooting location determination process described later, it is desirable to store a video in which only a background that does not include the person to be watched is shot. In the present embodiment, for example, video data in a time zone in which a watching target person is not detected is stored using a movement history detection storage unit 22 described later.

  In addition, regarding the number of video data to be stored, it is sufficient to store at least one image while the shooting location does not change. In the present embodiment, the movement history detection storage unit 22 determines that there is no person to watch after the camera installation is completed. Save the first frame that was recorded. However, the storage processing of the video storage unit 21 is not limited to this, and the video may be stored for each shooting location by detecting that the shooting location has been changed. The change of the shooting location can be detected by detecting whether the shot image has changed greatly as a whole. Further, a vibration sensor, an acceleration sensor, or the like may be mounted in the case 4 so that a signal detected when the camera is moved is sent to the control unit (CPU) 7 to detect a change in the shooting location. .

  The movement history detection / storage unit 22 performs face detection processing on the video data captured by the imaging unit 2, watches the center point of the face area, and calculates the position information of the target person. The face detection process scans a search window (for example, a determination area such as 8 pixels × 8 pixels) from the upper left of the input video data, and has an area having a feature point that can be recognized as a face for each area of the search window Determine if there is any. As facial feature points, feature points called facial organs such as facial contours, eyes, nose and mouth are used to detect their positional relationship. Various algorithms such as the Viola-Jones method have been proposed as the face detection method, but in the present embodiment, they can be used without being limited to a specific algorithm.

  Position detection of the person being watched over by this face detection processing is executed at a predetermined time interval (for example, every 3 seconds), and the output result is saved in time series in the form of coordinates (X value, Y value) of the shooting screen. The FIG. 4 is a diagram illustrating an example of stored data. As illustrated in FIG. 4, the stored data includes a subject ID that identifies a subject, a feature point, position coordinates (X, Y), And shooting time t. By analyzing this data, it is possible to grasp the movement of the watching target person during the shooting period.

  The shooting location determination unit 23 compares the video data captured in the past stored in the video storage unit 21 with the video data currently captured by the imaging unit 2, and the location currently captured is It is determined whether or not it has been taken. The comparison determination method will be described with reference to FIG.

  In FIG. 3, reference numeral 31 denotes an image currently taken by the imaging unit 2, and reference numeral 32 denotes a collection of images taken in the past stored in the video storage unit 21. As shown in FIG. 3, the shooting location determination unit 23 uses the center region 33 of the current shot image 31 as a template and performs pattern matching while moving the image in the past shot image 32 in the vertical and horizontal directions. If a past video 34 that matches the current photographed image 31 is found from the result of this pattern matching, a shift amount 36 is calculated as to how much the matching template position 35 is shifted from the center of the screen. As a result, the shooting location determination unit 23 determines whether the current shooting location has been shot in the past, and when shooting, shooting time information embedded and stored in the matched past video 34, A deviation amount 36 from the current shooting direction is output to the installation guiding unit 24.

FIG. 5 is a functional block diagram illustrating a configuration example of the shooting location determination unit 23. As shown in FIG. 5, the shooting location determination unit 23 includes a template creation unit 23-1, an image reading unit 23-2, a pattern match determination unit 23-3, a deviation amount calculation unit 23-4, and an output unit. 23-5.
The operation of the shooting location determination unit 23 will be described in detail with reference to the flowchart shown in FIG.

  First, the template creation unit 23-1 creates a template for the central portion indicated by reference numeral 33 in FIG. 3 from the current shot video shot by the imaging unit 2 (step S01). Subsequently, the image reading unit 23-2 reads images in the order from the latest shooting time from the past shot images stored in the video storage unit 21 (step S02). The pattern match determination unit 23-3 performs pattern matching on the read past captured image and the current captured image (step S03), and if they match, the shift amount calculation unit 23-4 calculates the shift amount. (Step S04), the output unit 23-5 outputs the photographing time information and the deviation amount data to the installation guiding unit 24 (Step S05), and the process is terminated. When not matching, it returns to step S02 and repeats a matching process (step S06). If there is no matching image even if the matching process is completed for all the images in the video storage unit 21, it is output that it is the first shooting location that has not been shot in the past (step S07), and the processing is terminated. .

  In order to reduce the pattern matching processing amount of the shooting location determination unit 23, a reduction unit for reducing the images 31 and 32 to be compared may be provided, or the movement of the template 33 that can be placed in the past shooting image 32 is 1 Changes may be made such that rough movement is performed in units of several pixels, not in units of pixels, and matching is performed only with green (G value) or luminance (Y value) instead of RGB color images. Furthermore, instead of template matching, for example, feature point-based matching processing such as SIFT (Scale-Invariant Feature Transform) may be used.

  Furthermore, when a watching camera is installed in the same place as the last taken place, it is also possible to reduce the processing amount of pattern matching by transmitting the information to the installation guiding unit 24. Specifically, when the same location installation button (not shown) is mounted on the camera case 4 and the watching camera is installed at the same location as the last taken location, the user presses the same location installation confirmation button and Tell. When the same location installation button is pressed, the installation guide unit 24 does not match all the past captured videos 32 stored in the video storage unit 21, but only matches the most recently stored video, Only the deviation amount 36 is calculated.

  Next, the configuration and processing of the installation guiding unit 24 will be described with reference to FIGS. FIG. 7 is a diagram in which each data of the movement history information selected from the movement history detection storage unit 22 is plotted with black dots on the coordinates of the imaging screen 41. The position of the black spot indicates the position where the watching target person was present. In the example of FIG. 7, it can be seen that the watching target person was the longest in the range of the dotted circle 42. From the viewpoint of watching, it is desirable to install the watching camera so that the position where the person to be watched stays longest (high frequency existence position) is the center of the shooting screen. The installation guiding unit 24 performs this guiding process according to the procedure shown in FIG.

  FIG. 8 is a functional block diagram illustrating a configuration example of the installation guide unit 24. As illustrated in FIG. 8, the installation guide unit 24 includes a movement history selection unit 24-1, a highest (highest) frequent value coordinate calculation unit 24-2, a target movement amount calculation unit 24-3, and a movement direction notification control. Section 24-4, camera movement amount calculation section 24-5, adjustment necessity determination section 24-6, and adjustment direction notification control section 24-7.

  As shown in FIG. 9, in the installation guide unit 24, first, based on the time information input from the shooting location determination unit 23, the movement history of the watching target person when the movement history selection unit 24-1 has shot in the past. Information is selected from the movement history detection storage unit 22 (step S11). Subsequently, in order to identify the place 42 where the person being watched over has been longest, the mode value coordinate calculation unit 24-2 calculates the mode coordinates of each movement history information (step S12). As shown in FIG. 7, the mode coordinates are calculated by dividing the photographing screen 41 into blocks, counting the movement history (number of black spots) existing in each block, and determining the center point of the block 43 with the largest count. It can be calculated as the most frequent coordinate. The method of calculating the most frequent coordinates is not limited to this, and can be calculated by, for example, cluster analysis. Since the mode coordinate calculated in step S12 is a coordinate at the camera position taken in the past, it is corrected by the deviation amount 36 from the current shooting direction input from the shooting location determination unit 23, and the current camera position is corrected. Calculate the most frequent coordinates at. Further, the target movement amount calculation unit 24-3 calculates a difference between the calculated most frequent coordinate and the screen center coordinate and stores it as a target movement amount (step S13). Subsequently, the movement direction notification control unit 24-4 notifies the user of the movement direction in which the most frequent coordinates are the center of the screen with the guidance LED 3 (step S14). Specifically, the lighting of the two guide LEDs 3 arranged side by side, which is an adjustment guide in the horizontal direction from the positive / negative of the X coordinate of the target movement amount calculated in step S13, is controlled to adjust the positive / negative of the Y coordinate in the vertical direction. The lighting of the two guidance LEDs 3 arranged in the vertical direction as guidance is controlled. After that, the camera movement amount calculation unit 24-5 calculates the camera movement amount by matching processing to determine how much the camera has moved from the first captured image after a predetermined time (step S15). The adjustment necessity determination unit 24-6 compares the calculated camera movement amount with the target movement amount stored in step S13, and determines that further adjustment is necessary if the difference between the movement amount and the target movement is equal to or greater than a predetermined value. (Yes), it returns to step S14, and adjustment direction alerting | reporting control part 24-7 notifies an adjustment direction to a user with guidance LED (step S16). If the difference between the movement amount and the target movement is equal to or less than the predetermined value (No in step S16), all the guidance LEDs are turned off (step S17), and the guidance processing flow is ended (End). If the subject cannot be found even after guidance, or if the subject photographed by guidance is in an abnormal state, the notification unit may perform notification.

  The overall operation of the watching camera of this embodiment will be described with reference to the flowchart of FIG. After the watching camera is turned on, the shooting location determination unit 23 determines whether the location currently being shot has been shot in the past (step S21). As a result of the determination, if the past shooting has been performed, the process proceeds to the process of the installation guide unit 24 in step S23, and if the previous shooting has not been performed, the process proceeds to the process of the movement history detection storage unit 22 in step S24 (step S22). In step S23, the user adjusts the camera installation according to the lighting of the guidance LED controlled by the installation guidance unit 24. After the guidance processing flow of the installation guidance unit 24 is completed, that is, after all guidance LEDs are turned off, the process proceeds to step S24. In step S24, the movement history of the watching target person is stored at a predetermined interval in the movement history detection storage unit 22 until the power of the camera body is turned off (Yes in step S25 and End). In addition, the process which preserve | saves the image | video of the time zone when a to-be-photographed object is not detected to the image | video preservation | save part 21 is also performed in step S24.

  The processing flow described in FIG. 9 explains the installation method of the watching camera, which is a feature of the present invention, and naturally also performs the action detection of the watching target and the notification result of the detection result, which are the basic functions of the watching camera. Is done. For example, the movement history of the watching target person detected by the movement history detection storage unit 22 in step S14 is monitored, and when there is no movement of the watching target person or an excessively large movement is detected for a long time, the caregiver is detected. The process of notifying can be easily added using the configuration of the present embodiment, and is preferably executed.

  With the above configuration, when the home helper for home care is carried and installed at the time of visit, the shooting position direction is guided so that the most suitable place for watching can be shot using the movement history information of the watching target person so far Can be realized.

(Second Embodiment)
Next, a second embodiment of the present invention will be described in detail with reference to FIGS. The second embodiment is different from the first embodiment in a method of calculating a target movement amount from movement history information in the installation guide unit 24, and about the same function as in the first embodiment. Will not be described.

  FIG. 11 is a diagram showing a flow of processing in the installation guiding unit 24 according to the present embodiment, and the graph (A) in FIG. 12 has the Y-axis coordinates of the movement history information indicating vertical movement as the vertical axis. The horizontal axis is plotted by the detection time, and FIG. 12B shows an example of the movement of the subject indicated by the movement history. Reference numerals 71, 72, and 73 in the graph indicate places where the vertical change is large, and it can be understood that the subject is moving up and down at this place. For example, the places shown by reference numerals 71 and 72 move down greatly, and then move upward by the same movement amount after a certain period of time. it is conceivable that. Moreover, since the place shown by the code | symbol 73 is moving upwards in steps, it is thought that the place which has a level | step difference as shown by the code | symbol 75 is moving. From the viewpoint of watching, such a sitting / stand-up movement or moving to a place with a step is accompanied by a risk of falling or the like, so special attention must be paid.

  In order to be able to photograph this place, the installation guiding unit 24 detects places (71, 72, 73) having a large vertical change from the graph of FIG. Take control.

  First, from the amount of deviation between the current shooting direction calculated by the shooting location determination unit 23 and the shooting direction when the graph of FIG. Is calculated (step S31 in FIG. 11). As a result of the calculation, a target movement amount for moving the camera in a direction in which 74 and 75 can be photographed is calculated (step S32). The target moving amount will be described with reference to FIG. 12. When the screen currently being shot is 76, the target screen is in a state of 77 where 74 and 75 locations can be shot, and the target moving amount is indicated by an arrow of 78. It will be shown. Similar to the processing flow (steps S14, S15, and S16) described in FIG. 9 of the first embodiment, the installation guiding unit 24 moves in the right direction, which is the direction indicated by the arrow 78, until the target image 77 can be captured. The guidance LED 3 is turned on to guide the user's camera position adjustment (step S33). By this guidance processing, it is possible to realize a watching camera that can guide the shooting position and direction so that a place where there is a risk of falling can be shot from the viewpoint of watching.

  Next, another method for calculating the target movement amount from the movement history information in the installation guiding unit 24 will be described with reference to FIGS. 13 and 14. The code | symbol 81 shown in FIG. 14 shows the state in which the watching target person fell down. When such a situation occurs, it is necessary for the watching camera to take a picture of the person being watched over and to notify the caregiver together with the image. For this reason, it is desirable that the watching camera be installed as downward as possible in consideration of the movement of the subject. In order to guide the installation, the installation guiding unit 24 detects the uppermost coordinate 82 from the selected movement history information (step S41), and calculates the target movement amount so that the coordinate 82 is at the top of the screen. (Step S42). The target movement amount will be described with reference to FIG. 14. When the screen currently being photographed is 76, the target image is 77 in which the coordinates 82 can be photographed at the top of the screen, and the target movement amount is indicated by an arrow of 78. It will be shown. Similar to the processing flow (steps S14, S15, and S16) described in FIG. 9 of the first embodiment, the installation guiding unit 24 moves downward in the direction indicated by the arrow 78 until the target image 77 can be captured. The guidance LED 3 is turned on to guide the user's camera position adjustment (step S43). By this guidance processing, it is possible to realize a watching camera that can guide the photographing position and direction so that a state in which a situation such as a fall has occurred can be photographed.

(Third embodiment)
Below, the 3rd Embodiment of this invention is described with reference to FIG. 15, FIG. In addition, about the part of the same function as 1st and 2nd embodiment, description is abbreviate | omitted using the same code | symbol.

  FIG. 15 is a three-view diagram illustrating an external configuration example of the watching camera according to the present embodiment. The difference from the first and second embodiments is that the installation stand 5 and the camera case 4 of FIG. 1 are connected via a vertical rotation mechanism 91 and a horizontal rotation mechanism 92. The vertical rotation mechanism 91 and the horizontal rotation mechanism 92 are provided with small motors 93 and 94, respectively, so that the camera case 4 can be rotated as indicated by reference numerals 95 and 96.

  FIG. 16 is a functional block diagram illustrating a configuration example of the watching camera according to the present embodiment. The difference from the first and second embodiments is that a control signal from the installation guiding unit 24 is input to the small motors 93 and 94 of the vertical rotation mechanism 91 and the horizontal rotation mechanism 92 instead of the induction LED 3. . Specifically, the small motor 94 of the horizontal rotation mechanism 92 is controlled from the positive / negative of the X coordinate of the target movement amount, and the rotation of the small motor 93 of the vertical rotation mechanism 91 is controlled from the positive / negative of the Y coordinate.

  Therefore, in the present embodiment, the installation guide 24 can automatically adjust the shooting direction by rotating the small motors 93 and 94 according to the target movement amount.

  With the above configuration, the installation guide unit 24 automatically adjusts the shooting direction by rotating the small motors 93 and 94 according to the target movement amount, so that the place to be shot can be automatically shot from the viewpoint of watching. The monitoring camera that changes the shooting direction can be realized.

Hereinafter, a specific use scene example of the watching camera described in the present embodiment will be described.
First, a home helper for home care brings a watch camera in the company and visits the caregiver's house. When visiting a caregiver's house, a watch camera is installed in the caregiver's room. The installation place is preferably a place such as a TV stand where the room can be seen well.
When the watching camera is turned on after the installation, the LED, which is an installation guidance process, starts blinking, and the watching operation is started by adjusting the shooting direction of the watching camera according to the instruction.
Alternatively, in the watching camera described in the third embodiment, the shooting direction can be automatically adjusted.
Thereafter, the watching camera recognizes the caregiver, and when an emergency such as a fall occurs, it notifies a portable terminal such as a smart phone carried by the home helper. At the end of the nursing time, the home helper takes a watch camera and stores it in the company.

  As described above, according to the present embodiment, the home helper for home care can be easily installed so that an optimum place for watching can be photographed even when the home helper is carried during the visit. Furthermore, it can be installed so that it is possible to take pictures of places where there is a risk of falls that should be watched over and situations where an emergency such as a fall has occurred.

  The processing and control described above can be implemented by software processing by CPU (Central Processing Unit) or GPU (Graphics Processing Unit), ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Hardware) by FPGA (Field Programmable Hardware processing). it can.

  Further, in the above-described embodiment, the configuration and the like illustrated in the accompanying drawings are not limited to these, and can be appropriately changed within a range in which the effect of the present invention is exhibited. In addition, various modifications can be made without departing from the scope of the object of the present invention.

  Each component of the present invention can be arbitrarily selected, and an invention having a selected configuration is also included in the present invention.

  In addition, a program for realizing the functions described in the present embodiment is recorded on a computer-readable recording medium, and the program recorded on the recording medium is read into a computer system and executed to execute processing of each unit. May be performed. The “computer system” here includes an OS and hardware such as peripheral devices.

Further, the “computer system” includes a homepage providing environment (or display environment) if a WWW system is used.
The “computer-readable recording medium” refers to a storage device such as a flexible medium, a magneto-optical disk, a portable medium such as a ROM and a CD-ROM, and a hard disk incorporated in a computer system. Furthermore, the “computer-readable recording medium” dynamically holds a program for a short time like a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line. In this case, a volatile memory in a computer system serving as a server or a client in that case, and a program that holds a program for a certain period of time are also included. The program may be a program for realizing a part of the above-described functions, or may be a program that can realize the above-described functions in combination with a program already recorded in a computer system. At least a part of the functions may be realized by hardware such as an integrated circuit.

(Appendix)
(1)
An imaging unit;
A video storage unit for storing video data of the imaging unit;
A movement history detection storage unit that detects the position of the monitoring target from the video data of the imaging unit and stores it as history information of the movement of the monitoring target;
A shooting location determination unit that compares the video data captured in the past stored in the video storage unit with the video data currently captured by the imaging unit, and determines the location currently being captured,
The movement history information of the monitoring target detected and stored in the past at the shooting location determined by the shooting location determination unit is searched from the movement history detection storage unit, and the monitoring target exists from the searched movement history information. A monitoring apparatus comprising: an installation guiding unit that detects a high-frequency existence part having a high frequency and guides a photographing direction in a direction in which the high-frequency existence part becomes a screen center of the imaging unit.
According to the above monitoring device, for example, when a home helper for home care is carried and installed at the time of visit by an installation guidance operation using the movement history information of the cared person, an optimum place for watching is taken. It can be installed as easily as possible.
(2)
The installation guide part is
(1) wherein a vertical movement location having a large vertical movement amount is detected from the movement history information of the monitoring target, and the imaging direction is guided in a direction in which the vertical movement location can be imaged by the imaging unit. Monitoring device.
Since the person to be monitored sits / rises and moves to a place with a step involves a risk of falling or the like, it is necessary to pay special attention, so these actions can be detected effectively. By detecting the vertical movement location of the person being watched over from the movement history information, it is possible to set up a place where there is a risk of falling that needs to be watched. By detecting the movement range of the person being watched over from the movement history information, even if an emergency such as a fall occurs, it can be installed so that the state can be photographed.
(3)
The installation guide part is
The monitoring apparatus according to (1), wherein an upper movement range is detected from the movement history information of the monitoring target, and the shooting direction is guided in a direction in which the movement range can be shot by the imaging unit.
(4)
The monitoring apparatus according to any one of (1) to (3), further including a reduction unit that reduces an image to be compared in pattern matching of the shooting location determination unit.
It is possible to reduce the pattern matching processing amount of the shooting location determination unit.
(5)
The monitoring apparatus according to any one of (1) to (4), further comprising a photographing direction adjustment mechanism that automatically adjusts a photographing direction under the control of the installation guide unit.
The shooting direction can be automatically changed so that the most suitable place for watching can be shot. Since the photographing direction can be automatically changed appropriately, monitoring can be performed easily.
(6)
Further, in the above (1) to (5), when the subject cannot be photographed even after the guidance, an informing unit for informing the abnormality may be provided.
(7)
A movement history detection storing step for detecting the position of the monitoring target from the captured video data and storing it as history information of the movement of the monitoring target;
A shooting location determination step that compares the previously captured video data stored in the video storage step with the currently captured video data to determine the current shooting location;
The movement history information of the monitoring target detected and stored in the past at the shooting location determined in the shooting location determination step is searched from the data stored in the movement history detection storage step, and the monitoring target is searched from the searched movement history information. A high-frequency existence location where the frequency is high, and an installation guidance step for guiding the shooting direction in a direction in which the high-frequency existence location becomes the center of the screen of the video data. Method.
(8)
A program for causing a computer to execute the monitoring method according to (7) above.

  The present invention is applicable to a monitoring device.

DESCRIPTION OF SYMBOLS 1 ... Watching camera, 2 ... Imaging part, 3 ... Guidance LED, 4 ... Camera case, 5 ... Installation stand, 21 ... Image | video storage part, 22 ... Movement history detection storage part, 23 ... Shooting place determination part, 24 ... Installation Guide unit 31... Currently captured image, 32... Collection of previously captured images, 33... Template central region, 34... Past image matching current captured image, 36. Shooting screen, 42: Location where the subject is the longest, 43: Block with the largest number of counts, 71, 72, 73 ... Location with a large vertical change, 74 ... Location where to sit and stand up, 75 ... Step, 76 ... Shooting screen, 77 ... Adjustment target screen, 78... Target movement amount, 81... The state where the person to be watched over has fallen, 82... The movement history coordinate located at the top, 91 ... Vertical rotation mechanism, 92 ... Horizontal rotation mechanism, 93, 94.

Claims (5)

An imaging unit;
A video storage unit for storing video data of the imaging unit;
A movement history detection storage unit that detects the position of the monitoring target from the video data of the imaging unit and stores it as history information of the movement of the monitoring target;
A shooting location determination unit that compares the video data captured in the past stored in the video storage unit with the video data currently captured by the imaging unit, and determines the location currently being captured,
The movement history information of the monitoring target detected and stored in the past at the shooting location determined by the shooting location determination unit is searched from the movement history detection storage unit, and the monitoring target exists from the searched movement history information. A monitoring apparatus comprising: an installation guiding unit that detects a high-frequency existence part having a high frequency and guides a photographing direction in a direction in which the high-frequency existence part becomes a screen center of the imaging unit. The installation guide part is
2. The vertical movement point having a large vertical movement amount is detected from the movement history information of the monitoring target, and the vertical movement point guides a shooting direction in a direction in which the imaging unit can shoot. Monitoring device. The installation guide part is
The monitoring apparatus according to claim 1, wherein an upper moving range is detected from the movement history information of the monitoring target, and the shooting direction is guided in a direction in which the moving range can be shot by the imaging unit.   The monitoring apparatus according to any one of claims 1 to 3, further comprising a reduction unit that reduces an image to be compared in pattern matching of the shooting location determination unit.   The monitoring apparatus according to any one of claims 1 to 4, further comprising a shooting direction adjustment mechanism that automatically adjusts a shooting direction under the control of the installation guide unit.

Images