JP3747459B2 - Human body detection device - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a human body detection device that has an imaging device and issues a warning to another person at a remote location when an abnormality occurs due to detection of a human body motion.
[0002]
[Prior art]
Conventionally, for example, as shown in Japanese Patent Application No. 2001-146744, a human body sensor is attached to a wall surface of a bathroom or the like, a monitoring area is imaged at predetermined time intervals, and the captured images are continuously stored and stored as image data. The image data of this time and the current image are compared, and the difference between the image data is captured to determine whether the bather is moving. More specifically, two consecutive images captured by the imaging device are compared, the difference is captured, the amount of motion is calculated, and the difference is generated by the movement of the person. Then, the stop of the movement is detected as “no movement amount” due to the rest of the person thereafter. When the stoppage of the bather's movement is detected, the alarm unit installed in a place other than the bathroom is notified of the alarm by voice, an image, etc., and the bather's safety is monitored.
[0003]
[Problems to be solved by the invention]
However, in the human body detection device as described above, when the human body detection device is installed above the water surface part and illuminated by a lighting device, particularly in the case of a bathroom, it is reflected on the surface of the bathtub. Due to the fluctuation of the reflected light of the electric light, a difference occurs in the pixel data on the captured image that changes with time, and it is detected as the amount of movement. There was a problem of detection and false alarms. In addition, even if the bather leaves the bathroom, the pixel data on the captured image that changes with time due to the wave of the bathtub hot water surface will cause a difference, which will be detected as the amount of movement, and will be erroneously detected as human movement. Therefore, there was a problem of erroneously detecting that there was a person in the bathroom even though there was no person.
[0004]
Therefore, in view of the above problems, the present invention allows the human body detection sensor to detect the movement of the reflected light of the electric lamp reflected on the hot water surface of the bathtub and the water surface as the amount of movement, and the movement of the person can be detected as usual. It is an object of the present invention to provide a human body detection device that can detect a stable movement of a human body.
[0005]
[Means for Solving the Problems]
In order to solve the above-described problem, the human body detection device of the present invention is an imaging device that images a monitoring region at predetermined time intervals A human body detecting sensor, an infrared sensor provided in the same case body in addition to the human body detecting sensor, and a bathroom when the human body detecting sensor detects a person within a certain time after the infrared sensor detects the human body and is turned on. It is determined that a person has entered the room, Previous image data computing means for computing data of the previous image captured by the imaging device, current image data computing means for computing data of the current image captured by the imaging device, data of the previous image, and current image A motion amount calculating means for calculating the difference between the data of the two, a motion determining means for determining the presence / absence of a human body motion by the motion amount calculating means, An area dividing means for dividing the detection area into a plurality of areas; In what consists of Said Before judging the presence or absence of movement of the human body by the movement amount calculation means, Of the divided areas, in the bathtub area A first feature is that replacement means for specifying a pixel position having protruding pixel data and replacing the pixel data with another pixel data is provided.
According to the first feature, before entering the motion amount calculation, only the protruding pixel data is replaced with another pixel data, and then the motion amount calculation is performed to determine the presence or absence of the movement of the human body. Thus, abnormal pixel data such as reflected light from the bath surface of the bathtub can be excluded, and erroneous detection can be prevented without detecting fluctuation due to reflected light as the amount of movement. In addition, since only the protruding pixel data is to be replaced with another data, it is possible to detect normal movement and stop of the human body with high sensitivity without reducing the amount of movement.
[0006]
In addition, the human body detection device of the present invention is an imaging device that captures an image of a monitoring area at predetermined time intervals. A human body detection sensor, an infrared sensor provided in the same case body in addition to the human body detection sensor, and after the infrared sensor detects and turns on the human body, the human body detection sensor is Detects that a person is entering the bathroom, and even if the human body detection sensor does not detect a person in the washroom, if a person is detected in the bathtub, it is determined that a person is entering the bathroom. And said Previous image data computing means for computing data of the previous image captured by the imaging device, current image data computing means for computing data of the current image captured by the imaging device, data of the previous image, and current image A motion amount calculating means for calculating the difference between the data of the two, a motion determining means for determining the presence / absence of a human body motion by the motion amount calculating means, An area dividing means for dividing the detection area into a plurality of areas In what consists of Before determining the presence / absence of the movement of the human body by the movement amount calculation means, in the bathtub area among the divided areas Surrounding pixel data difference value computing means for computing the difference value of pixel data between each pixel and its surrounding pixels, and evaluation determining means for judging whether or not the value computed by the surrounding pixel data difference value computing means is equal to or greater than an evaluation value The second feature is that replacement means is provided for replacing pixel data determined to be equal to or higher than the evaluation value by the evaluation determination means with a predetermined value.
According to the second feature, in addition to the above feature, the pixel position of the protruding pixel data can be specified by grasping the difference from the pixel data in the eight surrounding directions. It is possible to quickly identify large pixel data that is different from the above. In particular, it becomes easy to specify pixel data of reflected light on the bathtub hot water surface and water surface, and it becomes possible to quickly perform replacement correction of pixel data. In addition, the human body detection device of the present invention is an imaging device that captures an image of a monitoring area at predetermined time intervals. A human body detection sensor, an infrared sensor provided in the same case body in addition to the human body detection sensor, and after the infrared sensor detects and turns on the human body, the human body detection sensor is Detects that a person is entering the bathroom, and even if the human body detection sensor does not detect a person in the washroom, if a person is detected in the bathtub, it is determined that a person is entering the bathroom. And said Previous image data computing means for computing data of the previous image captured by the imaging device, current image data computing means for computing data of the current image captured by the imaging device, data of the previous image, and current image A motion amount calculating means for calculating the difference between the data of the two, a motion determining means for determining the presence / absence of a human body motion by the motion amount calculating means, An area dividing means for dividing the detection area into a plurality of areas In what consists of Before determining the presence / absence of the movement of the human body by the movement amount calculation means, in the bathtub area among the divided areas Average pixel data calculation means for calculating an average value of all pixel data, and an average value calculated by the average pixel data calculation means Each pixel data in the bathtub area Comparison determination means for determining pixel data having a difference of a certain value or more, and pixel data determined by the comparison determination means to be a certain value or more In the bathtub area A third feature is that replacement means for replacing the average value is provided.
According to the third feature, by replacing the protruding data with, for example, the average pixel data of the bathtub area, the protruding large pixel data can be eliminated and corrected according to the surrounding environment, and the detection of the amount of movement at a later time is normal. Thus, it is possible to detect the stop of movement of a person as usual.
[0007]
In addition, the human body detection device of the present invention is an imaging device that captures an image of a monitoring area at predetermined time intervals. A human body detection sensor, an infrared sensor provided in the same case body in addition to the human body detection sensor, and after the infrared sensor detects and turns on the human body, the human body detection sensor is Detects that a person is entering the bathroom, and even if the human body detection sensor does not detect a person in the washroom, if a person is detected in the bathtub, it is determined that a person is entering the bathroom. And said Previous image data computing means for computing data of the previous image captured by the imaging device, current image data computing means for computing data of the current image captured by the imaging device, data of the previous image, and current image A motion amount calculating means for calculating the difference between the data of the two, a motion determining means for determining the presence / absence of a human body motion by the motion amount calculating means, An area dividing means for dividing the detection area into a plurality of areas In what consists of Before determining the presence / absence of the movement of the human body by the movement amount calculation means, in the bathtub area among the divided areas Average pixel data calculation means for calculating an average value of all pixel data, and an average value calculated by the average pixel data calculation means Each pixel data in the bathtub area Comparison determination means for determining pixel data having a difference of a certain value or more, and pixel data determined by the comparison determination means to be a certain value or more Bathtub area A fourth feature is that replacement means for replacing the lowest value is provided.
According to the fourth feature, by replacing the protruding data with the lowest pixel data of the bathtub area, the protruding large pixel data can be eliminated and corrected according to the surrounding environment, and the detection of the movement amount at a later time can be normally performed. In this way, it is possible to detect stoppage of human movement as usual.
[0008]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is an overall configuration diagram showing an embodiment of the present invention. FIG. 2 is a block diagram of an electric circuit showing an embodiment of the present invention. FIG. 3 is a circuit diagram showing a configuration of an image core circuit constituting one pixel of the image detection unit of the human body detection sensor. FIG. 4 is an explanatory diagram showing the relationship between the imaging range of the sensor, the detection range, and the detection region. FIG. 5 is a control flowchart showing an embodiment of the present invention. FIG. 6 is an overhead view of the bathroom as seen from the human body detection sensor according to the embodiment of the present invention. FIG. 7 is an explanatory diagram of a pixel and peripheral pixels according to an embodiment. FIG. 8 is a block diagram of the control device and the imaging device. FIG. 9 is an explanatory diagram showing the contents of the control device. 10A is a diagram showing the current image and the previous image of the object moved to the lower right, FIG. 10B is a diagram showing the brightness of the previous image for each pixel, and FIG. 10C is the brightness of the current image. It is a figure shown for every pixel. FIG. 11 is a diagram showing a difference image showing a change in light and dark at the pixel corresponding to the boundary of the image. FIG. 12 is an electric circuit block diagram showing an embodiment, and FIG. 13 is a flowchart showing the embodiment. FIG. 14 is a flowchart showing an embodiment. FIG. 15 is a flowchart showing another embodiment.
[0009]
FIG. 1 shows an outline of an embodiment of the present invention, and a bathtub 2 and a washroom 3 are provided inside a bathroom 1. Reference numeral 4 denotes an entrance to the bathroom 1. Reference numeral 5 denotes a human body detection device, which will be described in detail later, but is attached to the upper part of the inner wall surface of the bathroom 1.
Specifically, it is attached to the upper position of the bathroom wall surface facing the bathroom wall surface in contact with the longitudinal direction of the bathtub 2. Connected to the hot water device 40 are a bath remote controller 60 installed in the bathroom for operating the hot water device 40 from a remote location and a kitchen remote controller 70 installed in the kitchen. A lighting device 71 such as an electric lamp is attached to the wall or ceiling of the bathroom 1.
And although the human body detection apparatus 5 is attached to the wall surface of the bathroom 1 in this embodiment, you may attach to the ceiling surface of the bathroom 1 not only in this example.
The human body detection device 5 includes an imaging device incorporating an artificial retina chip, and a human body detection sensor 51 that images and processes the movement of the human body in the bathroom 1 and an infrared sensor 52 that detects a human body by thermal detection using infrared rays. Consists of.
The installation of the human body detection device 5 is not limited to a bathroom, and may be a sealed space such as a toilet, a washroom, a sauna room, an indoor pool.
[0010]
A bath remote controller 60 for remotely operating the hot water device 40 is installed in the bathroom 1, and a kitchen remote controller 70 for remotely operating the hot water device 40 is installed in the kitchen.
Here, the hot water device 40 is a device for heating water such as hot water in the bathtub, and specifically includes a bath with a hot water heater, a heater with a hot water heater, a hot water heater, a hot water heater, and the like. Yes.
The hot water apparatus may be one that uses not only gas as fuel but also petroleum.
Regarding the connection of the hot water device 40, the remote controllers 60 and 70, and the human body detection sensor 51, in FIG. 1, the hot water device 40 and the kitchen remote controller 70 are first connected by the cable 41, and then the kitchen remote controller 70 and The bath remote controller 60 is connected by a cable 41, and the bath remote controller 60 and the human body detection sensor 51 are connected by a cable 41.
The remote controls 60 and 70 for controlling the water heater and the like have a display unit such as a liquid crystal display panel for notifying that there is a bather in the bathroom 1, and the human body detection device 5 detects the bather. When the detection signal is output, the display unit may display lighting or the like.
The display unit is not limited to the above, and if there is no movement of the bather for a certain period of time, it is assumed that the user is sleeping or falls down in the bathtub. If the response is not within a predetermined time, the kitchen remote controller 70 may alert the other person such as a family by an alarm sound or voice.
In addition, when the human body detection device is installed in the toilet, a notification unit may be provided in a remote controller or the like that remotely operates the hot water toilet seat.
Further, when the human body detection device is installed in the washroom, a notification means may be provided in a device for remotely operating the hot water temperature of the hot water supply curan in the washroom or the remote controller of the bathroom heater.
[0011]
And the heat exchanger and the burner are incorporated in the inside of the hot water apparatus 40, and the various sensors for control are provided.
A hot water drop-in pipe 46 is connected to the bathtub 2 from the hot water device 40. In addition, power for operating the human body detection device 5 is introduced from a power plug 47 of the hot water device 40, and is stepped down and supplied through a transformer (not shown) of the controller 42 of the hot water device 40.
[0012]
FIG. 2 shows a specific configuration of a human body detection device 5 including a human body detection sensor 51 using an artificial retina chip and an infrared sensor 52.
The human body detection sensor 51 includes an imaging device 6 that images a monitoring area, and a control device 7 that controls the imaging device 6 and determines processing information.
The control device 7 and the external remote controllers 60 and 70 are configured to transmit and receive by a communication unit 53 such as a communication IC described later.
In addition to the human body detection sensor 51, an infrared sensor 52 is provided in the same case body, the control device 7 is shared, and mutual compensation for monitoring when the bathroom 1 is dark is performed.
[0013]
The image pickup unit 8 of the image pickup apparatus 6 includes an image detection unit 9 having 128 vertical pixels × 128 horizontal pixels, an imaging lens 10, a scanner 11, a multiplexer 12, and a scanner drive control unit 13. Each pixel of the image detection unit 9 is expressed by 256 monochrome gradations “256 gradations of level 0 (black) to 255 (white)”.
[0014]
In the imaging unit 8, the image in the bathroom is imaged on the image detection unit 9 by the imaging lens 10. The scanner 11 is driven and controlled by a scanner drive control unit 13, and the scanner drive control unit 13 controls each pixel column of the image detection unit 9 so as to sequentially enter a light receiving state (on state) at regular intervals. .
The photocurrents simultaneously output from the pixels in one column in the light receiving state are combined into a single electric signal as a plurality of electric signals by the multiplexer 12, amplified by the amplifier 14, and then output as an analog voltage. Conversion from analog data to digital data is performed by the control device 7.
[0015]
Each pixel of the image detection unit 9 is constituted by a pixel core circuit 17 as shown in FIG. The pixel core circuit 17 includes a light receiving element 18, a charge storage circuit 19, and a sensitivity variable circuit 20. A sensitivity variable terminal 21 and a reset terminal 22 are connected to the scanner 11, and a photocurrent output terminal 23 is connected to the multiplexer 12. ing.
[0016]
In FIG. 2, the gain adjustment unit 16 checks the image average value (image brightness) in the image output unit 15, and adjusts the gain of the imaging device 6 by the amplifier 14 if the image average value is out of an appropriate range. At the same time, the scanner drive control unit 13 adjusts the accumulation time of the image detection unit 9 to adjust the light so that an image with appropriate brightness can be obtained.
[0017]
In the imaging device 6 using the artificial retina chip, the average gradation value of the image is a gradation (256 gradations from 0 gradation (black) to 255 gradations (white)) in all pixels constituting the image detection unit 9. The average value is represented by a value of 0-255.
This average image value is determined by the gain of the amplifier 14 and the image accumulation time of the image detector 9.
Here, the gain corresponds to the aperture of the camera, and the image accumulation time corresponds to the shutter speed of the camera. Therefore, if an appropriate image gradation average value of the image pickup device 6 is to be obtained, the image accumulation time may be adjusted by fixing the gain to an appropriate gain. Alternatively, an appropriate image accumulation time may be fixed and the gain adjusted.
[0018]
In FIG. 2, at least the image detection unit 9, the scanner 11, the scanner driving unit 13, and the gain adjustment unit 16 that perform imaging are configured by one chip. This chip is called an artificial retina chip.
Further, a control device 7 is provided on the substrate at the back surface position of the chip, and the control device 7 is composed of a microcomputer, and a detection region for performing detection processing by the human body detection sensor 51 is provided in a plurality of regions. The area dividing means 24 and the like for dividing the area into software are incorporated as software.
[0019]
Specifically, as shown in FIG. 4, the point table 25 for processing the image information input to the control device 7 is divided into a plurality of areas.
That is, the imaging capability range that can be detected by the human body detection sensor 51 (corresponding to the entire point table 25) is first divided into a detection area 26 that requires image processing and a non-detection area 27 that does not perform image processing.
That is, the entire imaging capability range is not set as the detection area.
Thus, a part of the detection processing area where detection processing can be performed is used as a sensor detection area for actually detecting and processing, thereby limiting the image processing range and speeding up the image processing.
[0020]
Further, the detection area 26 is divided into three areas, that is, an entrance area 29, a wash area 30 and a bathtub area 31, as shown in FIG. 4. Here, the entrance area 29 refers to an area located in the vicinity of the entrance door to the bathroom in the bathroom. The wash area 30 mainly refers to the area of the floor where the head and body are washed, and the bathtub area 31 refers to the area where the bathtub is located. Image information is sequentially input to the control device 7 for each of the divided areas as described above, and processing such as detection and calculation is performed for each area and the entire divided area.
[0021]
The imaging lens 10, the imaging device 6, and the control device 7 constituting the human body detection sensor 51 are housed in one case together with the infrared sensor 52 and attached to a wall surface or the like as a human body sensor set. The attachment position may be set so that the entire bathroom 1 including the entrance 4 to the bathroom is within the viewing angle as a monitoring area.
[0022]
Then, the detection output of the imaging device 6 and the detection output of the infrared sensor 52 are respectively input to the determination unit 32. Based on the output from the imaging device 6 and the output from the infrared sensor, the determination means 32 comprehensively determines the presence / absence of a bather in the bathroom and the movement of the bather.
[0023]
The image detected by the artificial retina is subjected to image processing as follows.
The control device 7 that controls and processes the image receives image information from all the pixels constituting the image detection unit 9 at predetermined time intervals. When the image information is received at predetermined time intervals, the control device 7 processes the image information and determines the information. 32, the movement of the bather is determined.
[0024]
Next, an image processing method for extracting a human motion from an image captured by the imaging device 6 will be described.
When receiving image information every predetermined time, the control device 7 constituted by a microcomputer analyzes the bather's movement from the image information according to a predetermined analysis algorithm, and monitors the bather's movement.
[0025]
Specifically, it is assumed that an image (bright image) P of a square object has moved from position P1 to position P2 as shown in FIG. At this time, if the bright pixel is represented by the symbol B and the dark pixel is represented by the symbol D, the previous image is represented by FIG. 10B, and the current image is represented by FIG. 10C. The before and after images are temporarily stored by the image storage means in the control device 7. Images captured continuously are sequentially updated so that the latest images are always stored. Then, the two images are compared for each divided region by a motion amount calculating means 81 for calculating a motion amount provided in the control device 7, and the previous image for each pixel (x, y) in each region. Difference (movement amount) between the received light amount Pp (x, y) of p and the received light amount Pn (x, y) of the current image n
D (x, y) = Pn (x, y) -Pp (x, y)
And the calculation result can be obtained as a difference image as shown in FIG.
[0026]
In the difference image of FIG. 11, a pixel having a positive difference D (x, y) is represented by a + symbol, a negative pixel is represented by a − symbol, and a pixel having a zero D (x, y) is represented by a 0 symbol. Yes. By capturing the sum of such differences, it can be determined for each region whether or not there is a motion, and this determination is performed by the motion determination means 82 provided in the control device 7. If there is no motion amount, it is determined that there is no motion, and if there is a motion amount, it is determined that there is motion.
[0027]
As shown in FIG. 8, various operations and determination means are programmed as software in the control device 7 composed of a microcomputer. The surrounding pixel data difference value calculation means 76 calculates a difference value of pixel data between each pixel in each region and its surrounding pixels for one captured image. Specifically, as shown in FIG. 7, for example, the difference between the pixel data T and the pixel data T in each of the eight directions of the surrounding pixels A, B, C, D, E, H, G, H I try to take it. Further, the difference may be squared and weighted. Furthermore, the square of the difference may be added for the 8 pixels.
[0028]
The evaluation determination unit 77 determines whether the value calculated by the surrounding pixel data difference value calculation unit 76 is equal to or greater than a predetermined evaluation value. What is necessary is just to make the evaluation value determine the value corresponding to the data by water surface reflected light. For example, it is determined by measuring reflected light in a standard bathroom by experiment and setting an optimal value from the pixel data.
[0029]
The replacement unit 78 is a unit that replaces the pixel data determined by the evaluation determination unit 77 to be equal to or higher than the evaluation value with a predetermined value. The predetermined value may be set to an image gradation having an optimum value by an experiment or the like.
The previous image data calculation means 79 calculates the image of each area of the previous image captured at a predetermined time interval by the imaging device 6 described above as image gradation data for each pixel. A set of each pixel data becomes image data. The current image data calculation means 80 calculates an image for each region of the current image captured at a predetermined time interval by the imaging device 6 described above as image gradation data for each pixel. 81 is a motion amount calculation means for calculating the motion amount described above. Reference numeral 82 denotes motion determination means for determining that there is motion when the detection output from the motion amount calculation means 81 is equal to or greater than a threshold value.
[0030]
The control flow will be described with reference to FIG.
In FIG. 13, first, an image of one detection area that is imaged at a predetermined time interval by the imaging device 6 is taken into the control device 7 (step S11). The detection area is preferably a bathtub area. Next, the surrounding pixel data difference value calculation means 76 calculates the difference value between the surrounding image data of each pixel in the region and searches for a pixel having a difference (step S12). Then, whether or not the difference value is equal to or greater than a certain evaluation value is determined by the evaluation determination means 77 (step S13). If the difference value is equal to or greater than the evaluation value (Yes in step S13), it is determined that there is an image of reflected light (H) (step S14), and the replacement unit 78 sets all pixel data equal to or greater than the evaluation value to a predetermined value. The value is replaced with a value (step S16).
[0031]
Thus, before the calculation of the motion amount, the pixel position having the protruding image data is specified, and this pixel data is replaced with another predetermined pixel data. Thereby, abnormal pixel data such as the reflected light (H) of the bathtub surface is excluded, and erroneous detection can be prevented without detecting the fluctuation due to the reflected light (H) as the amount of movement. In addition, by replacing only the protruding pixel data with other data, it is possible to detect normal determination of movement and stop of the human body without reducing the amount of movement.
[0032]
This replacement is performed instantaneously and does not affect the calculation of the motion amount at a later time. Then, the image corrected by the replacement is rewritten with image data having no movement, and the image is continuously captured by the image data calculation means 79 and the current image data calculation means 80. The difference between the previous image and the current image is calculated by the motion amount calculation means 81 (step S17, 18), and the motion amount is continuously calculated (step S19). If there is a certain amount of movement (Yes in step S20), it is determined that “there is movement” (step S21). Also. If there is no movement amount (in the case of No in step S20), it is determined that “no movement” (step S22).
[0033]
Next, determination of whether or not a person has entered the bathroom 1 will be described.
In FIG. 5, when a person begins to enter the bathroom 1, first, the infrared sensor 52 in a standby state detects a human body and is turned on (step S1), and a timer is set (step S2). If a person is detected in the washroom (step S3), it is determined that the person has entered the room (step S4).
[0034]
In this entrance determination, since the human body detection by the human body detection sensor 51 takes time for imaging and calculating the amount of motion, or the monitoring sensitivity is low when the bathroom 1 is dark, the infrared sensor 52 is used together. After the detection by the sensor 52, the human body detection sensor 51 detects the person together, thereby compensating for the weak point of the human body detection sensor 51 and ensuring the entrance into the room.
[0035]
Further, when the infrared sensor 52 is turned off even when leaving the bathroom 1 (in the case of no in step S5), and the human body detection sensor 51 does not detect the amount of movement (in the case of no in step S6). ) Is judged to have left the bathroom 1 (step S7).
If only the infrared sensor 52 remains at the entrance, it will turn off and it may be erroneously determined that the sensor has left. This is complemented by the use of sensors.
[0036]
Even when the human body detection sensor 51 does not detect a person in the washroom 3 (in the case of no in step S3), if the person is detected in the bathtub 2 (step S8), the infrared sensor 52 and the human body detection are detected within a predetermined time. When both the sensors 51 detect people (steps S9 and S10), it is determined that they are entering the room (step S4).
[0037]
Next, a control flow according to another embodiment of the present invention will be described.
[0038]
In FIG. 9, the description of the same numbered part as in FIG. 8 is omitted. The average pixel data calculation means 83 is a means for calculating the average value of all the pixel data in the bathtub area 31, specifically, the average value of the image gradation of each pixel in the bathtub area 31, and a value of 0 to 255 Is displayed. The comparison determination means 84 determines whether or not the difference between each pixel data in the region and the average value is a certain value or more. In the present embodiment, the replacement unit 85 is a unit that replaces all pixel data determined by the comparison determination unit 84 to be equal to or greater than a certain value with the average value.
[0039]
This control flow will be described with reference to FIG.
In FIG. 14, the image of one detection area imaged by the imaging device 6 at predetermined time intervals is taken into the control device 7 (step S23). Next, the average value of the pixel data of all the pixels in the bathtub area 31 is calculated by the average pixel data calculation means 83 (step S24). Next, it is determined by the comparison determination means 84 whether or not the difference between each pixel data in the bathtub region 31 and the average value is equal to or greater than a certain value (step S25).
[0040]
That is, the average value of the pixel data in the bathtub area 31 is compared with each pixel data, and it is determined that a pixel having a large difference is an image due to the reflected light (H) (step S26). The pixel data greater than a certain value is replaced with an average value by 85 (step S27). By using the average value, it is possible to correct the error with less error following the change of the surrounding environment.
[0041]
As described above, before the calculation of the motion amount, the pixel position having the protruding image data is specified, and this pixel data is replaced with another average pixel data. Thereby, abnormal pixel data such as the reflected light (H) of the bathtub surface is excluded, and erroneous detection can be prevented without detecting the fluctuation due to the reflected light (H) as the amount of movement. In addition, by replacing only the protruding pixel data with an average value of other data, it is possible to cope with the installation environment, and normal human body movement and stop determination can be detected with high sensitivity without reducing the amount of movement. .
[0042]
This replacement is performed instantaneously and does not affect the calculation of the motion amount at a later time. Then, the image corrected by the replacement is rewritten with the image data having no motion, and the motion amount calculation means 81 calculates the motion of the person by continuously rewriting the fluctuation of the water surface to the image data without motion.
[0043]
FIG. 12 shows still another embodiment. The difference from FIG. 9 is that the pixel data calculation means 86 for calculating the lowest pixel data by comparing the pixel data in the bathtub region 31 with each other. Is provided.
[0044]
Thereby, as shown in FIG. 15, the image of one detection area imaged by the imaging device 6 at predetermined time intervals is taken into the control device 7 (step S23). Next, the average value of the pixel data of all the pixels in the bathtub area 31 is calculated by the average pixel data calculation means 83 (step S24). Next, it is determined by the comparison determination means 84 whether or not the difference between each pixel data in the bathtub region 31 and the average value is equal to or greater than a certain value (step S25). Next, the lowest pixel data calculation means 86 calculates the lowest pixel data (step S28). Thereafter, the average value of the pixel data in the bathtub region is compared with each pixel data, and it is determined that the pixel having the large difference is an image due to the reflected light. Is replaced with the minimum value (step S29).
[0045]
Thereby, abnormal pixel data such as the reflected light (H) of the bathtub surface can be excluded, and erroneous detection can be prevented without detecting the fluctuation due to the reflected light (H) as the amount of movement. In addition, by replacing only the protruding pixel data with the lowest value of other data, it is possible to cope with the environment around the bathtub, and normal human body movement and stop determination can be detected with high sensitivity without reducing the amount of movement. it can.
[0046]
Next, when the entrance determination is made as described above, a human body stop detection flow is entered, and the monitoring device is imaged at predetermined time intervals by the imaging device 6 as described above, and the previous image and the current image are temporarily controlled. Store in device 7. Next, the motion amount calculation means 81 programmed in the control device 7 calculates the difference (motion amount) between the light reception amount of the previous image and the light reception amount of the current image for each pixel in each region.
These pieces of information are sent to the determination unit 32 of the control device 7 to determine whether or not the human body has stopped moving.
[0047]
In addition, embodiment mentioned above shows suitable embodiment of this invention, This invention is not limited to this, Various design changes are possible within the range.
For example, although the system bathroom has been described in the present embodiment, the present invention is not limited to this example, and can be installed in other existing bathrooms. Furthermore, it can be used not only in the bathroom but also in a toilet, a washroom, and the like.
[0048]
【The invention's effect】
As described above, the present invention excludes abnormal pixel data such as reflected light from the bath surface of the bathtub, and can prevent erroneous detection without detecting fluctuation due to the reflected light as the amount of movement. In addition, since only the protruding pixel data is to be replaced with another data, it is possible to detect normal movement and stop of the human body with high sensitivity without reducing the amount of movement.
In addition, the present invention makes it easy to specify pixel data of reflected light particularly on the bathtub hot water surface and water surface, and enables pixel data replacement correction to be performed quickly.
Furthermore, the present invention eliminates the large pixel data that protrudes, can be corrected according to the surrounding environment, and can detect the amount of movement at a later time normally, so that it is possible to detect stoppage of human movement as usual. .
[Brief description of the drawings]
FIG. 1 is an overall configuration diagram showing an embodiment of the present invention.
FIG. 2 is a block diagram of an electric circuit showing an embodiment of the present invention.
FIG. 3 is a circuit diagram showing a configuration of an image core circuit constituting one pixel of the image detection unit of the human body detection sensor.
FIG. 4 is an explanatory diagram illustrating a relationship between an imaging range of a sensor, a detection range, and a detection region.
FIG. 5 is a flowchart showing an embodiment of the present invention.
FIG. 6 is an overhead view of the bathroom as seen from the human body detection sensor.
FIG. 7 is an explanatory diagram showing a relationship between a pixel T and surrounding pixels.
FIG. 8 is a control block diagram of one embodiment of the present invention.
FIG. 9 is a control block diagram of another embodiment of the present invention.
10A is a diagram showing a current image and a previous image of an object moved toward the lower right, FIG. 10B is a diagram showing the brightness of the previous image for each pixel, and FIG. 10C is a current image. It is a figure which shows the contrast of an image for every pixel.
FIG. 11 is a diagram showing a difference image showing a change in light and dark at pixels corresponding to the boundary of the image.
FIG. 12 is an electric block diagram showing another embodiment.
FIG. 13 is a flowchart illustrating an example of control.
FIG. 14 is a flowchart illustrating an example of control.
FIG. 15 is a flowchart illustrating an example of control.
[Explanation of symbols]
1 bathroom
2 Bathtub
3 Washroom
4 doorway
5 Human body sensor
6 Imaging device
7 Control device
9 Image detector
15 Image output unit
17 Image Core Circuit
24 Area dividing means
26 Detection area
29 Entrance area
30 Washing area
31 Bathtub area
32 judgment means
40 Hot water equipment
41 cable
42 Controller
47 Power plug
51 Human body detection sensor
52 Infrared sensor
60 bath remote control
70 Kitchen remote control
76 Ambient pixel data difference value calculation means
77 Evaluation judging means
78 Replacement means
79 Previous image data calculation means
80 This time image data calculation means
81 Motion amount calculation means
82 Motion judging means
83 Mean pixel data calculation means
84 comparison judgment means
85 Replacement means
86 Minimum pixel data calculation means

Claims (4)

A human body detection sensor having an imaging device that images the monitoring area at predetermined time intervals, an infrared sensor provided in the same case body in addition to the human body detection sensor, and a predetermined time after the infrared sensor detects and turns on the human body When the human body detection sensor detects a person inside, it is determined that a person has entered the bathroom, and the previous image data calculation means for calculating the data of the previous image captured by the imaging device A current image data calculation means for calculating data of the current image captured by the imaging device, a motion amount calculation means for calculating a difference between the previous image data and the current image data, and the motion amount calculation means. and determining motion determination means whether the body movement, in those comprising a region dividing means for dividing the detection area into a plurality of regions, Yu body motion by said motion amount calculation means The before determining to identify pixel locations having pixel data which protrudes in a bathtub region of the divided regions human body detection device, characterized in that a replacement means for replacing the pixel data in different pixel data. A human body detection sensor having an imaging device that images the monitoring area at predetermined time intervals, an infrared sensor provided in the same case body in addition to the human body detection sensor, and a constant after the infrared sensor detects and turns on the human body If the human detection sensor detects a person in the washroom within the time, it is judged that a person has entered the bathroom, and even if the human detection sensor does not detect a person in the washroom, It is determined that a person has entered the room, and the previous image data calculation means for calculating the data of the previous image captured by the imaging device, and the current image captured by the imaging device Current image data calculation means for calculating data, motion amount calculation means for calculating the difference between the previous image data and the current image data, and presence or absence of human motion by the movement amount calculation means A motion determination means for determining, in a made from the region dividing means for dividing the detection area into a plurality of regions, before determining whether a human body motion by said motion amount calculating means, in a bathtub region of the divided regions Surrounding pixel data difference value computing means for computing the difference value of pixel data between each pixel and its surrounding pixels, and evaluation determining means for judging whether or not the value computed by the surrounding pixel data difference value computing means is equal to or greater than an evaluation value And a replacement means for replacing the pixel data determined to be equal to or higher than the evaluation value by the evaluation determination means with a predetermined value. A human body detection sensor having an imaging device that images the monitoring area at predetermined time intervals, an infrared sensor provided in the same case body in addition to the human body detection sensor, and a constant after the infrared sensor detects and turns on the human body If the human detection sensor detects a person in the washroom within the time, it is judged that a person has entered the bathroom, and even if the human detection sensor does not detect a person in the washroom, It is determined that a person has entered the room, and the previous image data calculation means for calculating the data of the previous image captured by the imaging device, and the current image captured by the imaging device Current image data calculation means for calculating data, motion amount calculation means for calculating the difference between the previous image data and the current image data, and presence or absence of human motion by the movement amount calculation means A motion determination means for determining, in a made from the region dividing means for dividing the detection area into a plurality of regions, before determining whether a human body motion by said motion amount calculating means, in a bathtub region of the divided regions Average pixel data calculation means for calculating an average value of all pixel data, and comparison determination means for determining pixel data in which the difference between the average value calculated by the average pixel data calculation means and each pixel data in the bathtub region is a certain value or more And a replacement unit that replaces the pixel data determined to be equal to or greater than a certain value by the comparison determination unit with an average value of the bathtub area . A human body detection sensor having an imaging device that images the monitoring area at predetermined time intervals, an infrared sensor provided in the same case body in addition to the human body detection sensor, and a constant after the infrared sensor detects and turns on the human body If the human detection sensor detects a person in the washroom within the time, it is judged that a person has entered the bathroom, and even if the human detection sensor does not detect a person in the washroom, It is determined that a person has entered the room, and the previous image data calculation means for calculating the data of the previous image captured by the imaging device, and the current image captured by the imaging device Current image data calculation means for calculating data, motion amount calculation means for calculating the difference between the previous image data and the current image data, and presence or absence of human motion by the movement amount calculation means A motion determination means for determining, in a made from the region dividing means for dividing the detection area into a plurality of regions, before determining whether a human body motion by said motion amount calculating means, in a bathtub region of the divided regions Average pixel data calculation means for calculating an average value of all pixel data, and comparison determination means for determining pixel data in which the difference between the average value calculated by the average pixel data calculation means and each pixel data in the bathtub region is a certain value or more And a replacement unit that replaces the pixel data determined to be equal to or greater than a certain value by the comparison determination unit with the lowest value in the bathtub region .

Images