JP2001283225A - In-space abnormality detector and in-space abnormality detecting method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an in-space abnormality detecting method and an in-space abnormality detector with higher detection precision by eliminating disturbance such as waves on the water. SOLUTION: A photographic area is divined into approximately 60 sections and a featured value (a integrated value or average value of image data) is calculated by every section from image data to be obtained. Then secular change for every section is calculated from extremely small number of pieces of section group information and whether the section is an active area or a still area is decided. On the other hand, a reference value (for example, an average value of luminance signals or color difference signals in the entire image pickup area) about image data in the entire or a part of image pickup area is periodically or aperiodically calculated. And a threshold is set based on the reference value (for example, 5% of the average value of luminance signals in the entire image pickup area is set as the threshold) and whether the section is in a still state or in an active state is decided. When fixed time elapses from a state that the number of sections decided to be in an active state is equal to or less than the prescribed value, the state is decided as an abnormal state.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method and an apparatus for detecting an abnormality in a space for detecting that an abnormal condition has occurred when a person falls down in a room such as a bathroom or a toilet.

[0002]

2. Description of the Related Art In a bathroom, the number of accidents in which a person taking a bath died during bathing has been increasing year by year, and the number of fatalities has been attracting more attention than the number of deaths due to traffic accidents.

[0003] The direct cause of this is that during bathing, heart failure, stroke or impaired consciousness occurs and drowns. However, although the cause of such a condition is being investigated, the change in the current lifestyle is also difficult to identify. Therefore, it is difficult to prevent accidents such as heart failure during bathing. However, even if symptoms cannot be prevented from occurring, the chances of surviving early detection are greatly increased.

Therefore, an image in the bathroom is detected, and in order to protect privacy, a very coarse image (about 100 to 5,000 pixels) that barely tells the presence of a bather is taken in, and the center of gravity of the bather is calculated. Then, the movement of the position of the center of gravity is detected, and the movement of the bather is detected. When this movement cannot be detected for a certain period of time, an abnormality is notified to the kitchen and notified, for example, in JP-A-11-101502. Has been described.

[0005]

However, moving objects other than people usually exist in the room.
For example, in a bathroom, there are fluctuations of hot water stored in a shower or a bathtub. JP-A-11-101502
In the detection method disclosed in Japanese Patent Application Laid-Open Publication No. H10-157, a coarse image is taken in and processed, but with such a degree of roughness, it has been difficult to clearly distinguish a person's movement from a disturbance such as a shower or fluctuation of the water surface. For this reason, there is a problem that, despite the fact that the bather has stopped moving, due to disturbance such as fluctuation of the water surface, the bather is erroneously detected as having a movement and cannot detect an abnormal state. In particular, whirlpools have been adopted in ordinary households, and the air bubbles caused by the whirlpools are factors in erroneous detection.

Further, for example, in a bathroom, when the daytime luminance level is compared with the nighttime luminance level, the difference is large, and it is extremely difficult to set a threshold value for determining whether or not a human is operating. There's a problem. Setting a threshold value is easy because a constant level of luminance signal can be obtained if the illumination is always on. However, it is not always possible to turn on the illumination when taking a bath in the morning. In addition, the color of the bathtub in the bathroom or the color of the washroom tile varies from household to household, and the color difference signals that can be obtained are also different. Therefore, it is difficult to set a threshold value when the in-space abnormality detection device is shipped. There was also. Further, it is difficult to request the setting of the threshold value from the contractor or the user at the time of installation.

[0007] In the bathroom, there are disturbance elements depending on the area. For example, in the bathtub area, the surface of the water fluctuates, bubbles generated by the jet and hot water poured from the caran, and showers exist near the washing place. On the other hand, there are areas where no disturbance is present, such as near the entrance. However, in the conventional in-space abnormality detection device, since the threshold value is constant in all areas, it is erroneously detected that a human is operating due to disturbance such as fluctuation of the water surface, and despite the fact that the human has fallen, There is a problem that an abnormality cannot be detected.

Further, the conventional in-space abnormality detecting apparatus monitors the static movement of a person, and detects an abnormality when a certain period of time has elapsed after the operation stopped. Therefore, if a person becomes stuck and cannot move due to heart failure or the like, an abnormal state can be detected.However, if the person is struggling, such as convulsions, it is erroneously determined to be operating and the abnormal state cannot be detected. There was a problem.

[0009] The structure of the bathroom in the home is various,
It is difficult to specify the bathroom area and height. Also,
Due to construction reasons, the in-space abnormality detection device may be mounted not only on the ceiling but also on the side wall.
In such a case, it is troublesome to measure and input the distance and the angle of view from the in-space abnormality detection device to the floor when the installer or the user attaches the in-space abnormality detection device.

The present invention has been made in view of such circumstances, and aims to automate and real-time the setting of a difficult-to-set threshold value, improve detection accuracy, and improve the privacy of bathers. An object of the present invention is to provide an in-space abnormality detection method and an in-space abnormality detection method that provide appropriate protection and remove disturbances such as fluctuations in the water surface, thereby achieving higher detection accuracy.

It is another object of the present invention to provide a method and apparatus for detecting an abnormality in a space which enables a threshold value to be set for each area, prevents erroneous detection, and has higher detection accuracy. It is in.

[0012] Another object of the present invention is to provide a more reliable method that can detect an abnormal condition not only when a bather or the like is stuck due to heart failure or the like, but also when struggling with convulsions or the like. It is an object of the present invention to provide a method for detecting abnormalities in a space and a device for detecting abnormalities in a space.

Still another object of the present invention is to reduce the burden on the contractor or user by automatically optimizing the setting of the in-space abnormality detecting device according to the type of bathroom in each home, and to improve the detection accuracy. And a space abnormality detection method.

[0014]

According to a first aspect of the present invention, there is provided a method for detecting an abnormality in a space, comprising: taking an image of a space; processing image data obtained by the imaging; and detecting an abnormality in the space. An imaging step for imaging the space;
Extracting image data for each pixel from the captured video, calculating a characteristic value related to the image data for each of a plurality of divided areas of the imaging region, and detecting a temporal change amount of the calculated characteristic value Performing a step of periodically or aperiodically calculating a reference value related to image data of a part or the whole area of the imaging area; and a threshold calculating a threshold based on the calculated reference value. A value calculating step, a state determining step of determining that the section is an operation section when the temporal change amount is equal to or greater than the calculated threshold, and a state in which the number of sections determined to be the operation section is equal to or less than a predetermined number of sections. Determining that an abnormal state has occurred if the time has elapsed.

In the space abnormality detecting method according to a second aspect, the threshold value calculating step calculates a different threshold value for each section.

In the space abnormality detecting method according to a third aspect of the present invention, there is provided an operation history detecting step of detecting a time at which an operation section is determined in the state determination step and a position of the operation section corresponding to the time, And an operation history accumulation step of accumulating the position of the operation section corresponding to the time, and a correlation value between the operation section position with respect to the time accumulated in the operation history accumulation step and the operation section position with respect to the time detected in the operation history detection step And a step of judging a second abnormal state when the calculated correlation value is equal to or more than a predetermined value.

In the space abnormality detecting method according to a fourth aspect, prior to the imaging step, a step of measuring a distance from an imaging position to a subject, and a step of determining an angle of view according to the measured distance are further included. It is characterized by having.

A space abnormality detecting apparatus according to a fifth aspect of the present invention is a space abnormality detecting apparatus which takes an image of a space, processes image data obtained by the imaging, and detects an abnormality in the space. Image data extracting means for extracting image data for each pixel from a video, characteristic value calculating means for calculating a characteristic value related to the image data for each of a plurality of sections into which the imaging region is divided, and calculation by the characteristic value calculating means A temporal change amount detecting means for detecting a temporal change amount of the obtained characteristic value, and a reference value calculation for periodically or non-periodically calculating a reference value relating to image data of a part or all of the imaging region Means, a threshold value calculating means for calculating a threshold value based on the reference value calculated by the reference value calculating means, and a temporal change amount detected by the temporal change amount detecting means is calculated by the threshold value calculating means. By A state judging means for judging the section as an operation section if the calculated value is equal to or more than the calculated threshold value; Abnormal state determining means for determining a state.

In the space abnormality detecting apparatus according to a sixth aspect, the threshold value calculating means is configured to calculate a different threshold value for each section.

The space abnormality detecting apparatus according to a seventh aspect of the present invention is an operation history detecting means for detecting a time at which the state judging means judges an operation section and a position of the operation section corresponding to the time. Operation history data storage means for storing the time detected by the detection means and the position of the operation section corresponding to the time; an operation section position with respect to the time stored by the operation history data storage means; and a time detected by the operation history detection means A correlation value calculating means for calculating a correlation value with respect to the operation section position with respect to the second section; and a second abnormal state determining means for determining a second abnormal state when the correlation value calculated by the correlation value calculating means is equal to or more than a predetermined value. It is further characterized by being provided.

According to an eighth aspect of the present invention, there is provided a space abnormality detecting apparatus for measuring a distance from an image pickup position to a subject before taking an image of a space, and an angle of view corresponding to the distance measured by the distance measure. And an angle of view determining means for determining the angle of view.

In the first invention and the fifth invention, the imaging area is divided into about 60 sections, and characteristic values (for example, integrated values or average values of image data) are obtained for each section from the obtained image data. calculate. Then, the amount of change with time for each section is calculated from this extremely small section group information, and it is determined whether the section is an operating section or a stationary section. On the other hand, a reference value (for example, an average value of a luminance signal or a color difference signal of the entire imaging region) for the image data of the entire or partial imaging region serving as a reference value is calculated periodically or aperiodically. Then, a threshold value is set based on the reference value (for example, 5% of the average luminance signal value of the entire imaging region is set as the threshold value), and it is determined whether the section is in a stationary state or an operating state. Then, when a state in which the number of sections determined to be an operation section is equal to or less than a predetermined value has elapsed for a predetermined time, an abnormal state is determined. Therefore, even if there is a luminance or color change in the room, it is possible to detect it with high accuracy, and to provide a more accurate abnormality detection method and apparatus in a space by preventing disturbance such as fluctuation of the water surface. can do.

In the second and sixth aspects of the invention, for example, in the case of a bathroom, the threshold value is set to a high value near the bathtub (area) in order to prevent disturbance such as bubbles. On the other hand, the threshold value is set to a low value in the vicinity of the entrance since there is no disturbance such as a shower while the bather enters and exits, and it is necessary to determine the start or end of detection. As described above, since the threshold value can be changed for each section, precise detection is performed for each area, and as a result, the detection accuracy is improved, and a more accurate in-space abnormality detection method and an in-space abnormality detection method are provided. An apparatus can be provided.

According to the third and seventh aspects of the present invention, the operation history of the bather is detected by storing the time at which the section is determined to be an operation section and the section position in association with the time. Then, the detection results are sequentially stored in the database. Then, the operation history data stored in the database is compared with the behavior history of the bather to obtain a correlation value. When the correlation value is equal to or more than a predetermined value, that is, when the bather performs an unusual action (for example, the operation history of moving to the bathtub area after operating for a certain period of time in the washing area under normal conditions is stored in the database. If accumulated, this bathing will continue to operate in the washing area forever,
In other words, when struggling is struggling), it is determined to be an abnormal state, so that a highly versatile in-space abnormality detection method and an in-space abnormality detection apparatus that can cope with various abnormal states can be provided.

In the fourth and eighth inventions, the distance from the imaging section to the floor is measured by an infrared distance measuring device or the like. When the distance is short, the angle of view of the imaging unit is large, and when the distance is long, the angle of view of the imaging unit is small.
The angle-of-view data of the imaging unit with respect to the distance measurement distance is stored in advance, and an appropriate angle of view of the imaging unit is determined according to the result of the distance measurement. Therefore, since an appropriate detection area can be set according to the type of each room or the mounting position of the imaging unit of the in-space abnormality detection device, the detection accuracy can be improved and the burden on the installer and the user can be reduced. can do.

[0026]

DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below in detail with reference to the drawings showing the embodiments.

Embodiment 1 FIG. 1 is an explanatory diagram for explaining an example of use of a space abnormality detecting device 9 according to the present invention. In the figure, 1 is a bathroom, 2 is a dressing room, 3 is a corridor, and 4 is a kitchen. A door 5 is provided on the wall 1a between the bathroom 1 and the dressing room 2 so as to be openable and closable. When the door 5 is opened, a person enters the bathroom 1 from the dressing room 2 or enters the bathroom 1.
From the room to the dressing room 2. Further, an illumination switch 6 for turning on the illumination in the bathroom 1 is disposed at a position adjacent to the door 5 on the side of the dressing room 2 on the wall 1a. The lighting switch 6 is operated by a person when entering the bathroom 1 to turn on the lighting 7.
Is turned on, and the light 7 is turned off by operating when leaving the bathroom 1.

Reference numeral 8 denotes an image pickup unit, such as a CCD, for picking up an image of the interior of the bathroom 1, and reference numeral 9 denotes a space abnormality detection device for detecting an abnormal state based on the image of the image pickup unit 8. Reference numeral 10 denotes a first alarm device disposed in the bathroom 1 to issue an alarm to a bather entering the bathroom 1 based on the detection result of the in-space abnormality detection device 9.
Reference numeral 11 denotes a second alarm device disposed in, for example, the kitchen 4 to warn a person outside the bathroom 1 of an abnormal state in the bathroom 1 based on a detection result of the in-space abnormality detection device 9.

FIG. 2 shows a space abnormality detecting device 9 according to the present invention.
FIG. 3 is a block diagram showing the configuration of FIG. In the figure, reference numeral 91 denotes a pre-processing unit for A / D-converting the video imaged by the imaging unit 8 via a CDS (correlated double sampling circuit) and an AGC (automatic gain control circuit). Reference numeral 92 denotes a YC separation unit that separates the video processed by the pre-processing unit 91 into YC. The section-by-section characteristic calculation circuit 94 obtains a characteristic value for each section from one field of image data (for example, a luminance signal or a color difference signal) output from the YC separation section 92 in accordance with an instruction from a microcomputer 93. (For example, the integrated value or average value of the luminance signal or color difference signal of each pixel included in the section) is calculated. 93a is an internal timer of the microcomputer 93. Further, the timing control section 95 controls the timing of transferring data from each section to the next section, and outputs the data. The number of sections on one screen is 30 or more and 99 or less,
More preferably, it is 60 or more and 70 or less. in this way,
Approximately 60 sections are provided, and the integrated value or average value of the luminance signal or the color difference signal is obtained for each section. If the number of sections is too small, the resolution is reduced, so that human motion is detected. It becomes difficult, on the other hand, if the number of sections is too large, the resolution will be high, and as a result, it will be determined that the human is still moving due to fluctuation of the water surface due to bubbles or disturbance such as shower etc. is there.

FIG. 3 is a flowchart showing the processing procedure of the microcomputer 93. First, a characteristic value (for example, a luminance signal or a color difference signal) from one field of image data output from the section-specific characteristic calculation circuit 94 is stored in a RAM (not shown) (step S31). The sampling period of the characteristic value is about one second, and one field (1/6
The processing is performed by taking in the characteristic value for 0 second). The sampling cycle may be changed depending on the section.

In the present embodiment, processing is performed by taking in characteristic values from one field of image data. However, in order to prevent the influence of flicker, characteristics from image data of a plurality of fields (for example, three or more fields) are taken. The processing may be performed by taking in a value. That is, since the frequency of the illumination 7 in the bathroom 1 does not match the frequency of the NTSC signal, it is affected by flicker. This is because the influence of such flicker can be reduced to some extent by taking characteristic values from image data for a plurality of fields.

Further, when characteristic values from image data for an odd number of fields (for example, three fields) are fetched, the NTSC signal performs interlaced scanning. Therefore, if the field to be sampled is shifted after one second, the luminance signal and the color difference signal are obtained. The level fluctuates. For example, in the case of three fields, the sum of the luminance of the odd field, the even field, and the odd field is slightly different from the sum of the even field, the odd field, and the even field after one second. In order to prevent this variation, it is preferable to perform processing by taking in characteristic values from image data of even fields (multiples of 2 fields) as much as possible.

Therefore, in order to prevent the above-mentioned inconvenience, it is preferable to store the characteristic values for each section of a multiple field of 6 in a RAM (not shown) for each sampling period of 1 second before processing. However, in order to fundamentally prevent flicker, the shutter speed is set to 1/100 second, or the master clock (not shown) of the image pickup unit 8 is genlocked to light 7.
May be completely synchronized with the data reading frequency of the imaging unit 8.

Next, in step S31, characteristic values from the image data stored in the RAM (not shown) are read out for each section (step S32). Then, a process of determining a threshold value as a criterion for judging the movement of a person present in the section is performed (step S33). The processing in step S33 will be described later. In step S34, step S3
The temporal change in the characteristic value read in step 2 is detected for each section. The detection of the amount of change with time for each section takes, for example, the difference between the average luminance value one second before and the average luminance value after one second. Alternatively, the change rate of the average luminance value one second after the average luminance value one second before is calculated. Then, it is determined whether the temporal change amount, that is, the difference value (absolute value of the difference) or the change rate is equal to or more than a predetermined threshold value (step S35). If it is determined that the value is equal to or more than the threshold value (Yes in step S35),
It is determined that the section is an operation section (step S3).
6). On the other hand, when it is determined that the distance is equal to or smaller than the threshold value (No in step S35), it is determined that the section is a stationary section (step S37). In addition, the movement of the image of the door area 5 is detected to detect entry into and exit from the bathroom 1, the operation of the in-space abnormality detection device 9 is started when entry is detected, and the space is detected when exit is detected. The operation of the internal abnormality detection device 9 may be in a standby state. Instead of the lighting switch 6, an operation may be added such that the lighting 7 in the bathroom 1 is turned on when it is detected that the room has been entered, and the lighting 7 in the bathroom 1 is turned off when it is detected that the room has been left.

In step S38, the number of operation sections is counted, and it is determined whether or not the total is equal to or less than a predetermined value (for example, 3 or less). When the total sum of the operation sections is equal to or smaller than the predetermined value (Yes in step S38), it is determined that the bather is stationary, and the internal timer 93a of the microcomputer 93 is operated to count time (step S310). When the internal timer 93a operates, it keeps measuring the time until there is a reset request. Then, it is determined whether the timer operation time has passed a predetermined time (step S311). When it is determined that the predetermined time (for example, one minute) has elapsed (Yes in step S311), it is determined that some abnormality has occurred, and an alarm signal is transmitted to the first alarm device 10 or the second alarm device 11. Processing is performed (step S312). On the other hand, if the predetermined time has not yet elapsed (No in step S311), the measurement is restarted (the process proceeds to step S31) because there is a possibility that the bathtub is simply immersed in the bathtub. When it is determined in step S38 that the total sum of the operation sections is equal to or more than the predetermined value (N in step S38)
o) The bather determines that it is operating and the internal timer 93a
Is reset (step S39), and the measurement is restarted again (moving to step S31). Step S3
In step 8, the number of times that the total sum of the operation sections is determined to be equal to or less than the predetermined value is counted. Transmission processing may be performed. For example, if it is determined that the operation is performed only three times a minute, an alarm is issued.

FIG. 4 is a flowchart showing a processing procedure of the threshold value determining step S33. First, a reference value related to the imaging data of the entire imaging region, for example, an average value (reference value) of the luminance signal or the color difference signal of the entire imaging region, that is, an average value of the characteristic values of all the partitions in step S32 is calculated (step S41). ). Note that the average of a specific section (for example, a section near an entrance where a bather always passes) may be obtained instead of the average of the entire imaging area. Next, several% (for example, 5%) of the average value (reference value) obtained in step S41 is determined as a threshold value (step S42). Thus, when the indoor reference value is low (when the lighting 7 is off), the threshold value is also low. On the other hand, when the indoor reference value is high (when the lighting 7 is on), the threshold value is high. Therefore, even when the room is dark, human motion can be detected, and when the room is bright, the threshold value is increased, so that the influence of disturbance such as fluctuation of the water surface can be reduced. Note that the cycle of calculating the reference value may be performed each time image data is captured (step S31), or may be performed aperiodically. Note that the threshold value may be a fixed set value instead of several percent of the average value. Further, according to the magnitude of the reference value, when the reference value is low (when it is dark), it may be a fixed set value, and when the reference value is high (when it is bright), it may be several% of the average value. Furthermore, an average value may be obtained for each section instead of several percent of the entire screen, and several percent of this average value may be used as a threshold value for each section.

FIG. 5 is a flowchart showing the procedure of the alarm processing step S312. If it is determined in step S311 that the predetermined time has elapsed (Yes in step S311), a process for operating the first alarm 10 in the room is performed (step S51). Then, it is determined whether or not the time counted by the internal timer 93a has passed the second predetermined time (step S52). If it is determined that the second predetermined time has not elapsed (No in step S52), the process shifts to step S31 in the main routine to start detection again. Here, the reason for notifying only the inside of the room first is that the bather may only fall asleep, so that the bather is first alerted. The sound in the room may be changed stepwise according to the timer time. For example,
At first, make the birds sing or melody, and if it still does not work, output a voice message such as "Are you OK?"

On the other hand, if it is determined that the second predetermined time has passed (Yes in step S52), the second outdoor
A process for operating the alarm 11 is performed (step S53).
Thereby, when an abnormal state such as unconsciousness occurs in the bathroom, an emergency notification can be made to the outside. The second alarm 11 may be installed in a security company or a fire department (not shown) other than at home. In this case, the microcomputer 9
Reference numeral 3 performs a process of transmitting a signal for activating the second alarm 11 to a security company or the like through a wired or wireless telephone line (not shown).

Embodiment 2 FIG. 6 is a plan view of the bathroom 1. In the figure, 13 is a bathtub, and 12a is a currant for pouring hot water into the bathtub 13. Reference numeral 14 denotes a washing place, and 12b denotes a shower provided in the washing place. In the figure, areas surrounded by dotted lines are a door area 5, a callan area 12a, a shower area 12b, a bathtub area 13, and a washing area 14, respectively.
It is.

FIG. 7 is a block diagram showing a configuration of a space abnormality detecting device 9 according to the second embodiment of the present invention. The area information storage unit 15 which is a storage device such as a hard disk device is connected to the microcomputer 93. The microcomputer 93
Is connected to the input unit 16 and the area information storage unit 1
5 can be rewritten. The area information storage unit 15 stores a threshold value and the like of each area.

FIG. 8 is a flowchart showing a procedure for calculating a different threshold value for each section. This processing performs the following processing in place of the processing of step S42 in FIG. Instead of step S42, a process of determining a different threshold value for each section, that is, for each area composed of a plurality of sections is performed (step S81). Area information storage unit 1
5 stores threshold information for each area. For example, the bathtub area 13 stores a slightly higher threshold value of 5% of a reference value in order to prevent disturbance such as bubbles. On the other hand, in the door area 5, since the bather enters and leaves the bath, it is necessary to determine the start or end of detection with high accuracy. Further, since there is no disturbance such as a shower, the threshold value is 2% of the reference value.
And a value lower than the bathtub area 13 are stored. In step S81, the area information storage unit 15 and step S4
The threshold value for each section is determined based on the reference value calculated in step 1, that is, the threshold value is determined for each area composed of a plurality of sections.

The second embodiment is configured as described above, and other configurations and operations are the same as those of the first embodiment. Corresponding portions are allotted with the same reference numerals, and description thereof is not repeated. Omitted.

Third Embodiment FIG. 9 is a block diagram showing a configuration of an in-space abnormality detecting device 9 according to a third embodiment of the present invention. The operation history data storage unit 17 which is a storage device such as a hard disk device is connected to the microcomputer 93. The input unit 16 is connected to the microcomputer 93, and the contents of the operation history data storage unit 17 can be rewritten. The operation history is stored in the operation history data storage unit 17 every time a bather enters the room. It is to be noted that a plurality of operation histories may be accumulated separately by dividing the storage area. Reference numeral 18 denotes a RAM for temporarily storing processing data of the microcomputer 93.

FIG. 10 is a schematic diagram in which the bathroom is divided into a plurality of sections. In the figure, the imaging area is divided into 24 sections for easy explanation.

FIG. 11 is a flowchart showing a processing procedure for determining the second abnormal state. This processing is performed in step S3
After the respective sections are distinguished from the operating section or the stationary section in step 6 and step S37, the following processing is performed. First, a process of detecting a time at which an operation section is determined and a position of the operation section corresponding to the time is performed, and the detection result is temporarily stored in the RAM 18 (step S111).
For example, at time 10 seconds, the operation sections are stored as “1” and “2”. Then, every time sampling is performed, the operation history is
The data is sequentially stored in the AM 18 (step S111). next,
The data stored in the RAM 18 is stored in the operation history data storage unit 17 (Step S112). The operation history data storage unit 17 has already stored the past operation history data, and accumulates the data sequentially each time new operation history data is obtained. A plurality of storage areas may be provided to accumulate operation history data for a plurality of persons.

Then, the operation history data temporarily stored in the RAM 18 and the operation history data stored in the operation history data storage unit 17 are compared to calculate a correlation value (step S113). Specifically, the correlation value between the position information newly obtained at each time and the accumulated position information (for example, since the sections “1” and “19” are three sections apart, the correlation value is “3”). ). Then, it is determined whether or not the sum of the correlation values is within a predetermined correlation value range within a predetermined time (for example, 10 minutes) (step S11).
4). That is, if the operation history is the same as the accumulated operation history, a small correlation value is calculated. On the other hand, when the movement is different from the normal movement, the correlation value increases. If the accumulated correlation value is equal to or greater than the predetermined value within the predetermined time (Yes in step S114), it is determined that the state is different from the normal state (for example, a state in which the patient is struggling due to convulsions or the like) and the first alarm device 10 is activated. Then, a process of transmitting an alarm signal to the same is performed (step S115). Since the alarm method is the same as the above-described method, the description thereof is omitted (steps S51 to S5).
3). On the other hand, when the correlation value is equal to or less than the predetermined value per predetermined time (No in step S114), the operation is not different from the normal operation, and the process shifts to step S39.

The third embodiment has the above configuration, and the other configurations and operations are the same as those of the first and second embodiments. Corresponding portions are denoted by the same reference numerals. A detailed description thereof will be omitted.

Fourth Embodiment FIG. 12 is a block diagram showing a configuration of a space abnormality detection device 9 according to a fourth embodiment of the present invention. In the figure, reference numeral 20 denotes, for example, an infrared distance measuring device that irradiates an infrared ray to a floor, receives a reflected infrared ray at a light receiving section, and measures a time from irradiation to reception of the infrared ray to measure a distance to the floor. It is a distance measuring unit. Note that the distance to the floor may be obtained by using the autofocus function of the imaging unit 8. The measured distance data is output to the microcomputer 93. The microcomputer 93 determines the angle of view and controls the angle of view of the imaging unit 8. Reference numeral 19 connected to the microcomputer 93 is a storage device such as a hard disk, which is an angle-of-view data storage unit that stores angle-of-view data corresponding to the distance from the imaging unit 8 to the floor. The angle-of-view data in the angle-of-view data storage unit 19 can be rewritten by the input unit 16.

FIG. 13 is a flowchart showing the procedure of the angle-of-view determination processing. This processing performs the following processing before capturing an image of the inside of the space. First, the distance from the imaging unit 8 to the floor is measured by the distance measurement unit 20 or the imaging unit 8 (step S131). Next, the microcomputer 93 stores the angle-of-view data storage unit 1
9, the angle of view of the imaging unit 8 with respect to the distance is determined (step S132). If the distance from the imaging unit 8 to the floor surface is large (for example, 4 m), it is better to reduce the angle of view (for example, 30 degrees), while if the distance is short (for example, 2 degrees).
m) The angle of view is preferably large (for example, 60 degrees). The angle-of-view data storage unit 19 stores an appropriate angle of view of the imaging unit 8 in which the entire imaging area 8 can be imaged by the imaging unit 8 in accordance with the distance from the imaging unit 8 to the floor. Then, a process of controlling the angle of view of the imaging unit 8 according to the obtained angle of view is performed (step S133).

The fourth embodiment has the above-described configuration, and the other configurations and operations are the same as those of the first to third embodiments. Corresponding portions are denoted by the same reference numerals. A detailed description thereof will be omitted.

In the above-described embodiment, the description has been given of the case of detecting an abnormal state in the bathroom. However, the in-space abnormality detecting device 9 of the present invention is not limited to this. It can be used as a sensor that replaces the on / off switch of lighting in bedrooms, baths, toilets, etc., and can be used as a monitoring device for intruder warnings in homes, factories, etc., as well as contamination of water purifiers and drainage devices. Alternatively, the present invention can be used as a contamination detection device, a behavior detection sensor for small animals such as pets, and as an interface sensor for motion input of an amusement device.

[0052]

As described above, in the first and fifth aspects of the present invention, the imaging area is divided into about 60 sections, and characteristic values (for example, integrated values of the image data) are obtained for each section from the obtained image data. Or average value). Then, from this extremely small number of section group information, the amount of change with time for each section is calculated,
It is determined whether the section is an operating section or a stationary section. On the other hand, a reference value (for example, an average value of a luminance signal or a color difference signal of the entire imaging region) which is a reference value for image data of the entire imaging region or a partial region is calculated periodically or aperiodically. Then, a threshold value is set based on the reference value (for example, 5% of the average luminance signal value of the entire imaging region is set as the threshold value), and it is determined whether the section is in a stationary state or an operating state.
Then, when a state in which the number of sections determined to be an operation section is equal to or less than a predetermined value has passed for a predetermined time, an abnormal state is determined. Therefore, even if there is a luminance or color change in the room, it is possible to detect it with high accuracy, and to provide a more accurate abnormality detection method and apparatus in a space by preventing disturbance such as fluctuation of the water surface. can do.

In the second invention and the sixth invention,
For example, in the case of a bathroom, the threshold value is set to a high value near the bathtub (area) in order to prevent disturbance such as bubbles. On the other hand, the threshold value is set to a low value in the vicinity of the entrance since there is no disturbance such as a shower while the bather enters and exits, and it is necessary to determine the start or end of detection. As described above, since the threshold value can be changed for each section, precise detection is performed for each area, and as a result, the detection accuracy is improved, and a more accurate in-space abnormality detection method and an in-space abnormality detection method are provided. An apparatus can be provided.

Further, in the third invention and the seventh invention,
The operation history of the bather is detected by storing the time determined as the operation section and the section position in association with the time. Then, the detection results are sequentially stored in the database. And
The correlation value is obtained by comparing the operation history data stored in the database with the behavior history of the bather. When the correlation value is equal to or more than a predetermined value, that is, when the bather performs an unusual action (for example, the operation history of moving to the bathtub area after operating for a certain period of time in the washing area under normal conditions is stored in the database. If it is accumulated, it will continue to operate in the washroom area forever in this bath, that is, if you are struggling), it is determined that it is an abnormal state, so it is possible to respond to various abnormal conditions A highly versatile space abnormality detection method and space abnormality detection device that can be provided.

Further, in the fourth and eighth inventions, the distance from the imaging section to the floor is measured by an infrared distance measuring device or the like. The angle-of-view data of the imaging unit corresponding to the distance to be measured is stored in advance, such as increasing the angle of view of the imaging unit for a short distance and decreasing the angle of view of the imaging unit for a long distance. An appropriate angle of view of the imaging unit is determined according to the result of the distance. Therefore, since an appropriate detection area can be set according to the type of each room or the mounting position of the imaging unit of the in-space abnormality detection device, the detection accuracy can be improved and the burden on the installer and the user can be reduced. can do.

[Brief description of the drawings]

FIG. 1 is an explanatory diagram illustrating an example of use of a space abnormality detection device according to the present invention.

FIG. 2 is a block diagram showing a configuration of a space abnormality detection device according to the present invention.

FIG. 3 is a flowchart illustrating a processing procedure of a microcomputer.

FIG. 4 is a flowchart illustrating a processing procedure for determining a threshold value.

FIG. 5 is a flowchart illustrating a procedure of an alarm process.

FIG. 6 is a plan view of a bathroom.

FIG. 7 is a block diagram showing a configuration of a space abnormality detection device according to Embodiment 2 of the present invention.

FIG. 8 is a flowchart illustrating a procedure of a process of calculating a different threshold value for each section.

FIG. 9 is a block diagram showing a configuration of a space abnormality detection device according to Embodiment 3 of the present invention.

FIG. 10 is a schematic diagram in which a bathroom is divided into a plurality of sections.

FIG. 11 is a flowchart illustrating a processing procedure for determining a second abnormal state.

FIG. 12 is a block diagram showing a configuration of a space abnormality detection device according to Embodiment 4 of the present invention.

FIG. 13 is a flowchart illustrating a procedure of an angle of view determination process.

[Description of Signs] 8 Imaging unit 9 In-space abnormality detection device 17 Operation history data storage unit 20 Distance measurement unit 91 Preprocessing unit 92 YC separation unit 93 Microcomputer 93a Internal timer 94 Section-specific characteristic calculation circuit

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) G08B 25/00 510 G08B 25/00 510M 25/04 25/04 K (72) Inventor Toshiya Iinuma Moriguchi, Osaka Sanyo Electric Co., Ltd. 2-5-2-5, Keihan-Hondori-shi, Sanyo (72) Inventor Kenji Koyamada 2-5-5-Keihanhondori, Moriguchi-shi, Osaka Sanyo Electric Co., Ltd. (72) Hiroya Nishimoto, inventor 1st Sanyo-cho, Daito-shi, Osaka Sanyo Electronics Co., Ltd. (72) Inventor Koji Tanaka 1st Sanyo-cho, Daito-shi, Osaka Sanyo Electronics Co., Ltd. F-term (reference) 5B057 AA20 BA02 CA01 CA08 CA12 CB01 CB08 CB12 CC02 CH09 CH18 DA08 DA15 DB02 DB06 DB09 DC01 DC32 5C086 AA22 BA04 CA28 CB36 DA01 DA08 DA33 EA13 EA40 EA45 FA02 5C087 AA02 AA03 AA32 AA42 BB03 BB74 DD03 DD49 EE08 EE18 GG GG19 GG31 GG35 GG83 5L096 AA13 BA02 CA04 DA03 FA01 FA32 GA09 GA19 GA26 HA02

Claims (8)

[Claims] 1. An in-space abnormality detection method for capturing an image of a space, processing image data obtained by the imaging, and detecting an abnormality in the space, comprising: an imaging step of imaging the space; Extracting the image data, calculating the characteristic value related to the image data for each of the divided sections of the imaging region, detecting the temporal change amount of the calculated characteristic value, Periodically or aperiodically calculating a reference value related to image data of a part or all of the region, a threshold value calculating step of calculating a threshold value based on the calculated reference value, If the change over time is equal to or greater than the calculated threshold, a state determination step of determining the section as an operation section; and a state in which the number of sections determined to be an operation section is equal to or less than a predetermined number of sections for a predetermined time. Space anomaly detection method if spent, characterized in that it comprises a step of determining an abnormal state. 2. The space abnormality detecting method according to claim 1, wherein the threshold value calculating step calculates a different threshold value for each section. 3. An operation history detecting step of detecting a time determined as an operation section in the state determination step and a position of the operation section corresponding to the time, and a detected time and a position of the operation section corresponding to the detected time An operation history accumulating step of accumulating the data, a step of calculating a correlation value between the operation section position with respect to the time accumulated in the operation history accumulation step and the operation section position with respect to the time detected in the operation history detection step, and a calculated correlation value. Determining a second abnormal state when is greater than or equal to a predetermined value. 3. The method according to claim 1, further comprising: 4. The method according to claim 1, further comprising a step of measuring a distance from an imaging position to a subject, and a step of determining an angle of view according to the measured distance, prior to the imaging step. 3. The method for detecting an abnormality in a space according to item 3. 5. An in-space abnormality detecting apparatus for capturing an image of a space and processing image data obtained by the imaging to detect an abnormality in the space, wherein image data for each pixel is extracted from a video image of the space. Image data extracting means; characteristic value calculating means for calculating a characteristic value related to the image data for each of a plurality of sections into which the imaging region is divided; detecting a temporal change amount of the characteristic value calculated by the characteristic value calculating means Time-dependent change amount detection means, reference value calculation means for periodically or non-periodically calculating a reference value relating to image data of a part or all of the imaging region, and calculation by the reference value calculation means Threshold value calculating means for calculating a threshold value based on the obtained reference value; and a case where a temporal change amount detected by the temporal change amount detecting means is equal to or larger than the threshold value calculated by the threshold value calculating means. Means for judging the section as an operating section; and abnormal state judging means for judging an abnormal state when a state in which the number of sections determined to be the operating section by the state determining means is equal to or less than a predetermined number of times has elapsed for a predetermined time. A space abnormality detection device, comprising: 6. The space abnormality detecting apparatus according to claim 5, wherein said threshold value calculating means calculates a different threshold value for each section. 7. An operation history detecting means for detecting a time determined as an operation section by the state determining means and a position of the operation section corresponding to the time, and a time detected by the operation history detecting means and the time. Operation history data accumulation means for accumulating the position of the corresponding operation section; calculating a correlation value between the operation section position for the time accumulated by the operation history data accumulation means and the operation section position for the time detected by the operation history detection means. 6. The apparatus according to claim 5, further comprising: a correlation value calculating unit that performs a second abnormal state determination process when the correlation value calculated by the correlation value calculating unit is equal to or more than a predetermined value. Or the in-space abnormality detecting device according to 6. 8. A distance measuring means for measuring a distance from an image capturing position to a subject before capturing an image in a space, and an angle of view determining means for determining an angle of view according to the distance measured by the distance measuring means. 6. The method according to claim 5, wherein
8. The abnormality detection apparatus in a space according to any one of items 7 to 7.