JP2008299515A - Device automatic stop system and program to be executed in device automatic stop system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a device automatic stop system which accurately stops operation of an indoor device to secure high safety and also can give a consideration to an environment. <P>SOLUTION: This is the device automatic stop system connected to the indoor device via a communication circuit. The device automatic stop system is provided with: an imaging means for imaging the inside of a room; a change mode data acquisition means which acquires the change mode data which shows a change mode of a video from the video data showing the video of length of predetermined time obtained by imaging by the imaging means; a decision means to decide whether the video has changed by a predetermined amount or more based on a change mode data acquired by the change mode data acquisition means; a timekeeping means to perform timekeeping; and an automatic stop means for performing processing to stop operation of the device when the timekeeping means measure the time of a first predetermined period after the decision means has decided that there is a change in the video at the latest. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

The present invention relates to an apparatus automatic stop system and a program executed in the apparatus automatic stop system.

Conventionally, when leaving a room, the user turns off the power of devices such as a heating device, an air conditioner, a lighting device, and a television receiver. Some of these devices have a so-called “forget to turn off” function that automatically turns off the power if the user does not operate the response button or the like when the preset time or the preset time has elapsed even if the user does not turn off the power. There is something. On the other hand, there is a technique for detecting a person from an image captured by a camera (see, for example, Patent Documents 1 to 5).

JP 2002-352239 A JP 2003-6757 A JP 2004-295416 A Japanese Patent No. 3562491 JP 2005-78445 A

In particular, many devices that can cause a fire, such as heating equipment, are equipped with a function to forget to turn them off. It is. However, the conventional forgetting to erase function is executed at a certain time or at a certain time regardless of whether or not a person exists. If the forgetting function is activated 3 hours after the start of operation, and the person leaves the room after 1 hour has passed), the operation will continue until the forgetting to turn off function is executed, and its safety is low. There was a problem such as. In addition, even if there is a person, when sleeping or the like, there is a problem that even if the driving is continued for a long time and a fire occurs, even the life of the person will be jeopardized. On the other hand, if the time interval at which the forgetting to turn off function is narrowed, the operation is immediately stopped, which is inconvenient. In addition, there is a problem that it is not preferable to keep a device that is not used by anyone from the viewpoint of environmental problems even if the device has a low risk of fire or the like.
In addition, Patent Documents 1 to 5 do not disclose that the operation of an apparatus in a room is stopped by an image captured by a camera.

The present invention has been made in view of the above-described problems, and an object of the present invention is to automatically stop the operation of a device in a room to ensure high safety and consider the environment. An object of the present invention is to provide a program to be executed in a stop system and an apparatus automatic stop system.

In order to solve the above-described problems, the present invention provides the following.
(1) A device automatic stop system connected to a device provided in a room via a communication line,
Imaging means for imaging the room;
Change mode data acquisition means for acquiring change mode data indicating a video change mode from video data indicating a video of a predetermined length of time obtained by imaging by the imaging unit;
Determination means for determining whether or not the video has changed by a predetermined amount or more based on the change aspect data acquired by the change aspect data acquisition means;
A time measuring means for measuring time;
And a stop means for performing a process for stopping the operation of the apparatus when the time measuring means has timed the first predetermined period since it was determined that the video was last changed. A device automatic stop system characterized by

According to the invention of (1), the change mode data indicating the change mode of the video is acquired from the video data captured by the imaging means (for example, the monitor camera), and a predetermined amount is added to the video based on the change mode data. It is determined whether or not the above change has occurred. Then, when it is determined that there has been a change in the video at the end, when the first predetermined period is counted, a process for stopping the operation of the apparatus connected to the room and provided in the room (for example, Processing for outputting a stop signal to the device, processing for stopping the supply of power to the device, and the like). That is, when it is assumed that there is a change in the image due to, for example, a person moving in the room and the person is present in the room, the operation of the apparatus is not stopped and the first change is made after the change in the image last. If it is assumed that there is no change in the indoor image even after the predetermined period has passed and no person is present in the room, the operation of the apparatus is stopped.
In this way, when the person is assumed not to be present in the room, the operation of the apparatus is stopped, so that it is possible to reduce the risk of the occurrence of a fire due to the operation in the state where there is no person, It is possible to suppress wasteful energy consumption due to operation of a device that is not used by anyone, and to consider the environment.
In addition, since the operation of the apparatus is stopped when there is no change in the video for the first predetermined period, it is not necessary to operate the forgetting to turn off button or the like at regular time intervals or at certain time intervals. It can be reduced and is highly convenient.

Furthermore, the present invention provides the following.
(2) The device automatic stop system according to (1) above,
Warning means for performing a process for giving a warning when the timing means counts a second predetermined period shorter than the first predetermined period after the determination means determines that the video has changed last; ,
A release input means for inputting a warning release;
And a resetting means for resetting the timekeeping by the timekeeping means when a warning canceling input is received from the release input means by the time the first predetermined period elapses.

According to the invention of (2), when the second predetermined period shorter than the first predetermined period is counted after it is determined that the video has changed last, a process for giving a warning is performed. 1 When the warning is canceled before the predetermined period elapses, the time is reset. Therefore, for example, if there is no change in the image due to sleeping etc. (no human action), a warning can be given, and if there is no response, the release input cannot be made, Even if a person exists, high safety can be ensured by stopping the operation of the apparatus. As described above, normally, as long as there is a human action, no warning is given, but only when there is no change in the video by a predetermined amount during the second predetermined period, Can be avoided as much as possible, and high safety can be ensured. In addition, when there is a cancel input, the time count is reset and the apparatus can be operated continuously.

Furthermore, the present invention provides the following.
(3) The device automatic stop system according to (1) or (2) above,
Face data acquisition means for acquiring face data indicating the characteristics of a person's face from image data obtained by imaging by the imaging means;
Storage means for storing specific face data indicating facial features of a specific person;
Based on the face data acquired by the face data acquisition means and the specific face data stored in the storage means, it is determined whether the face data acquired by the face data acquisition means satisfies a predetermined condition. An authentication means,
The stop means performs processing for stopping the operation of the device when the authentication means determines that the face data acquired by the face data acquisition means does not satisfy the predetermined condition. To do.

According to the invention of (3), acquisition is performed based on face data acquired from image data obtained by imaging a room and specific face data indicating the characteristics of a face of a specific person stored in advance. When it is determined that the face data thus satisfied does not satisfy a predetermined condition, a process for stopping the operation of the apparatus is performed. Therefore, for example, by storing only the faces of parents as specific face data, the operation of the apparatus can be stopped when there are only children in the room. Thus, even when there is a change in the video, if there is no specific person in the room, the operation of the apparatus can be stopped to ensure higher safety.

Furthermore, the present invention provides the following.
(4) A device automatic stop system connected to a device provided in a room via a communication line,
Imaging means for imaging the room;
Change mode data acquisition means for acquiring change mode data indicating a video change mode from video data indicating a video of a predetermined length of time obtained by imaging by the imaging unit;
Determination means for determining whether or not the video has changed by a predetermined amount or more based on the change aspect data acquired by the change aspect data acquisition means;
A time measuring means for measuring time;
A stop means for performing a process for stopping the operation of the apparatus when the time counting means has timed the first predetermined period after the determination means has determined that the video has changed last; Face data acquisition means for acquiring face data indicating the characteristics of a person's face from image data obtained by imaging;
Storage means for storing face data indicating the characteristics of the face of a specific person;
Based on the face data acquired by the face data acquisition means and the specific face data stored in the storage means, it is determined whether the face data acquired by the face data acquisition means satisfies a predetermined condition. Authentication means;
A deusable unit that performs a process for making the device unusable when the authentication unit determines that the face data acquired by the face data acquiring unit does not satisfy the predetermined condition;
An enabling means for performing processing for enabling use of the device when the authentication means determines that the face data acquired by the face data acquisition means satisfies the predetermined condition. A device automatic stop system characterized by that.

According to the invention of (4), the change mode data indicating the change mode of the video is obtained from the video data captured by the imaging means, and whether or not the video has changed by a predetermined amount or more based on the change mode data. Determine whether. Then, when it is determined that there has been a change in the video at the end, when the first predetermined period is counted, a process for stopping the operation of the apparatus connected to the room and provided in the room (for example, Processing for outputting a stop signal to the device, processing for stopping the supply of power to the device, and the like). That is, when it is assumed that there is a change in the image due to, for example, a person moving in the room and the person is present in the room, the operation of the apparatus is not stopped and the first change is made after the change in the image last. If it is assumed that there is no change in the indoor image even after the predetermined period has passed and no person is present in the room, the operation of the apparatus is stopped.
In this way, when the person is assumed not to be present in the room, the operation of the apparatus is stopped, so that it is possible to reduce the risk of the occurrence of a fire due to the operation in the state where there is no person, It is possible to suppress wasteful energy consumption due to operation of a device that is not used by anyone, and to consider the environment.
In addition, since the operation of the apparatus is stopped when there is no change in the video for the first predetermined period, it is not necessary to operate the forgetting to turn off button or the like at regular time intervals or at certain time intervals. It can be reduced and is highly convenient.

In addition, the acquired face data is predetermined based on the face data acquired from the image data obtained by imaging the room and the specific face data indicating the characteristics of the face of a specific person stored in advance. When it is determined that the above condition is not satisfied, processing is performed to disable the use of the device. When it is determined that the predetermined condition is satisfied, processing is performed to enable the use of the device. Do. Therefore, since the apparatus can be used only when a specific person exists in the room, for example, when only a child exists in the room, the apparatus can be used to prevent injury.

Furthermore, the present invention provides the following.
(5) A program that is executed in an apparatus automatic stop system that includes an imaging unit for imaging a room,
A change mode data acquisition step of acquiring change mode data indicating a change mode of a video from video data indicating a video of a predetermined length of time obtained by imaging by the imaging unit;
A determination step of determining whether or not there has been a change of a predetermined amount or more based on the acquired change mode data;
A timing step for timing the time;
And a stop step for performing a process for stopping the operation of the device when the time counted by the timing step has counted the first predetermined period since it was determined that there was a change in the video at the end. A program characterized by that.

According to the invention of (5), the change mode data indicating the change mode of the video is acquired from the video data captured by the imaging means, and whether or not the video has changed by a predetermined amount or more based on the change mode data. Determine whether. Then, when it is determined that the video has changed last time and the first predetermined period is counted, processing is performed to stop the operation of the device connected through the communication line and provided in the room. That is, when it is assumed that there is a change in the image due to, for example, a person moving in the room and the person is present in the room, the operation of the apparatus is not stopped and the first change is made after the change in the image last. If it is assumed that there is no change in the indoor image even after the predetermined period has passed and no person is present in the room, the operation of the apparatus is stopped.
In this way, when the person is assumed not to be present in the room, the operation of the apparatus is stopped, so that it is possible to reduce the risk of the occurrence of a fire due to the operation in the state where there is no person, It is possible to suppress wasteful energy consumption due to operation of a device that is not used by anyone, and to consider the environment.
In addition, since the operation of the apparatus is stopped when there is no change in the video for the first predetermined period, it is not necessary to operate the forgetting to turn off button or the like at regular time intervals or at certain time intervals. It can be reduced and is highly convenient.

According to the present invention, it is possible to accurately stop the operation of a device in a room to ensure high safety and consider the environment.

FIG. 1 is a diagram showing an outline of an apparatus automatic stop system according to the present embodiment.
The apparatus automatic stop system 90 includes a processing terminal 10, a monitor camera 50, a monitor camera 51, a speaker 52, and a confirmation button 53, and is installed indoors. The processing terminal 10 can transmit and receive signals (data) wirelessly with the monitor camera 50, the monitor camera 51, the speaker 52, and the confirmation button 53.

The room is also equipped with home appliances (hereinafter also referred to as each device) such as an air conditioner 54 (hereinafter also referred to as an air conditioner 54), a stove 55, and an electric pot 56, and wirelessly connected to the processing terminal 10. Signals (data) can be transmitted and received.

The monitor camera 50 and the monitor camera 51 transmit video data obtained by imaging the room to the processing terminal 10. The monitor camera 50 is installed so that the entire room is viewed from above the room. The video data obtained by the monitor camera 50 is converted into optical flow data by the processing terminal 10, and it is determined whether or not a person exists in the room by analyzing the optical flow data. The optical flow will be described in detail later.

The speaker 52 outputs a warning sound and a warning message according to the data received from the processing terminal 10. Specifically, when a warning signal transmitted from the processing terminal 10 is received when it is determined by the processing terminal 10 that there is no person in the room for five minutes or longer, a warning sound or warning message indicating that fact is output.

The confirmation button 53 is used to input a warning cancellation. When there is an input, the confirmation button 53 transmits a signal to the processing terminal 10. As a result, a warning stop signal for stopping the warning is transmitted from the processing terminal 10 to the speaker 52, and output of a warning sound or the like from the speaker 52 is stopped. On the other hand, if the warning stop signal is not transmitted from the confirmation button 53 even after one minute has passed since the output of the warning sound or the like, the processing terminal 10 sends to the air conditioner 54, the stove 55, and the electric pot 56 (each device). In response to this, an operation stop signal is transmitted. When receiving the operation stop signal, each device stops its operation. The confirmation button 53 corresponds to a cancellation input unit of the present invention.

Moreover, the monitor camera 51 is installed so that the entrance direction of a room may be imaged in the position of predetermined | prescribed height (for example, 1m60cm) (refer FIG. 2). When a person enters the room, the monitor camera 51 can capture the face of the person from the front. In the processing terminal 10, it is determined from the video data obtained by the monitor camera 51 whether or not a face is imaged. If it is determined that a face is imaged, the person of the face is a specific person. It is determined whether or not. When it is determined that the user is a specific person, a use permission signal for enabling use is transmitted from the processing terminal 10 to each device. Thus, each device can be used. Specifically, if the power button of the air conditioner 54 is operated, the power is turned on, if the power button of the stove 55 is operated, the power is turned on, and if the pouring button of the electric pot 56 is operated, You will be able to pour hot water. On the other hand, when a certain period (60 minutes in the present embodiment) has elapsed since the face of a specific person was last recognized from the video data obtained by the monitor camera 51, the processing terminal 10 sends each device to each device. A disable signal is transmitted to disable use. This makes each device unusable. Specifically, even if the power button of the air conditioner 54 is operated, the power is not turned on, and the power is not turned on even if the power button of the stove 55 is operated, and the pouring button of the electric pot 56 is operated. Even then, you will not be able to pour hot water.

As described above, according to the apparatus automatic stop system 90, when there is a possibility that no person exists in the room, a warning sound or the like is output, and when the confirmation button 53 is not operated, no person exists in the room. As a result, by stopping the operation of each device, it is possible to reduce the risk of a fire due to the operation of each device in the absence of a person and to operate a device that no one uses It is possible to suppress wasteful energy consumption due to the environment and to consider the environment.
In addition, since each device can be used only when a specific person is present in the room, for example, a person who is unfamiliar with the use of each device uses each device, such as when only a child exists in the room. By doing so, it is possible to prevent injury.

In the present embodiment, a case where the processing terminal 10, the monitor camera 50, the monitor camera 51, the speaker 52, the confirmation button 53, and each device (the air conditioner 54, the stove 55, and the electric pot 56) perform data transmission and reception wirelessly will be described. However, the present invention is not limited to this example, and transmission and reception may be performed by wire. That is, the communication line in the present invention includes wired and wireless transmission paths.

The air conditioner 54, the stove 55, and the electric pot 56 correspond to the apparatus in the present invention. The apparatus in the present invention is not particularly limited as long as it can be installed indoors, and is a television receiver, a television broadcast recording / reproducing device, a stereo, a telephone, an electric appliance such as a lighting fixture, a gas, and the like. Examples include gas appliances such as heating equipment, hot water heaters, gas cookers, water supply equipment (equipment related to water supply from a faucet), and the like.
In addition, the room is not particularly limited, and examples thereof include a room in a general house, a facility (for example, a research facility or a facility in a company) in which only a certain person is permitted to enter, a school facility, and the like. .

FIGS. 2A and 2B are diagrams for explaining an optical flow obtained by imaging the room shown in FIG.
The diagram on the left side of FIG. 2A is a diagram showing the interior of the room taken by the monitor camera 50 shown in FIG.
In the image obtained by the monitor camera 50, a monitor camera 51, a speaker 52, a confirmation button 53, an air conditioner 54, a stove 55, an electric kettle 56 and other furniture (for example, a bed) are displayed. In addition, the person 60 is shown in this image. In FIG. 2A, other than the person 60, anything that moves the position is not shown.

The diagram on the right side of FIG. 2A shows the optical flow when the room is in the state of the diagram on the left side of FIG.
An optical flow is a velocity vector between pixels in an image. As a method of calculating the optical flow, first, a pixel block composed of a plurality of pixels is set in advance in the first image. Next, this pixel block is detected in the second image following the first image. Then, the movement of each pixel block in the two images is detected. Thereby, the optical flow of the object in the imaging region of the monitor camera 50 can be calculated. The pixel block and its setting will be described later with reference to FIG.

The monitor camera 50 transmits image data to the processing terminal 10 every second. Then, the processing terminal 10 calculates an optical flow every second from each transmitted image data. In the diagram on the right side of FIG. 2A, the optical flow is not obtained. This indicates that there was no movement in the room from one second ago to the present.

The diagram on the left side of FIG. 2 (b) is a diagram showing the interior of the room one second after the state of the diagram on the right side of FIG. 2 (a), and the diagram on the right side of FIG. It is a figure which shows an optical flow when it is in the state of the figure on the left side of 2 (b).
The left diagram of FIG. 2B is the same as the left diagram of FIG. 2A except that the person 60 has moved to the right from the state of the left diagram of FIG.
In the diagram on the right side of FIG. 2B, an optical flow indicating that each pixel block P (P1 to P6) on which the body portion of the person 60 is displayed has been moved to the right side is obtained. This is because each pixel block P has moved to the right from one second ago (the state in the left diagram in FIG. 2A) to the present (the state in the left diagram in FIG. 2B). Show.
In the present embodiment, a case will be described in which the “video of a predetermined time length” of the present invention is a video of 1 second, and an optical flow is calculated every second. However, in the present invention, the length of video time for calculating the optical flow is not limited to this example. Alternatively, a video having a predetermined time length may be divided into a plurality of time lengths, and an optical flow may be calculated for each time. In this case, the obtained data indicating a plurality of optical flows may be set as one optical flow data.
In this embodiment, a case where the processing terminal 10 calculates an optical flow from each image data transmitted every second will be described. However, the present invention is not limited to this example, and an image transmitted is transmitted. The optical flow may be calculated from a part of the data (for example, image data every 5 seconds of transmitted image data).

3A and 3B are diagrams for explaining pixel blocks.
Image data output from the monitor camera 50 is temporarily stored in the SDRAM 26. The image data is composed of a plurality of raster data (data indicated by dots). Each pixel block P shown in FIGS. 2A, 2B, and 3A includes a plurality of adjacent dots ( In the present embodiment, the gradation of 2 × 2 dots (see FIG. 3B) is an average value.
In this embodiment, the monitor camera 50 is fixed, and images the interior of the room from the upper side to the lower diagonal direction at a constant magnification. Therefore, the size of the image shown on the monitor camera 50 does not change greatly due to the movement of the person. Therefore, the size of the object displayed in each pixel block is almost constant. In the present embodiment, the area of six pixel blocks corresponds to the area of the image of the trunk portion of a person (average person). Therefore, in this embodiment, when the object displayed in the area of 2 × 3 pixel block or more moves as a whole, it is determined that the person has moved (the video has changed by a predetermined amount or more). Yes. As a result, for example, even if something smaller than the human torso (for example, an animal that is smaller than a person such as a cat or dog) moves, it can be assumed that the person does not exist in the room.

In the present embodiment, “the image has changed by a predetermined amount or more” means that the object displayed in the area of 2 × 3 pixel block or more has moved as a whole, and the predetermined area or more as the predetermined amount. If the movement is detected, the amount of movement is not limited.
However, in the present invention, for example, if there is a movement of 5 cm or more per second, it may be determined that there has been a change, such as determining that there has been a change, such as determining that there has been a change.

FIG. 4 is a block diagram showing the internal configuration of the processing terminal.
The processing terminal 10 includes a CPU 12, a ROM 14, a RAM 16, and a hard disk 18.
The ROM 14 is a nonvolatile memory, and stores a program executed by the CPU 12 (a program corresponding to a program executed in the apparatus automatic stop system of the present invention), data used when the CPU 12 performs processing, and the like. Yes. The RAM 16 is a volatile memory, and temporarily stores data corresponding to the processing result of the CPU 12 and the like. The hard disk 18 stores specific face data indicating the face characteristics of a specific person. The hard disk 18 functions as storage means for storing specific face data. The specific face data is obtained and registered in advance by the monitor camera 51, and is data indicating a face graph described later. The specific face data may be registered after being obtained by another device outside the device automatic stop system 90.

Connected to the CPU 12 is an image processing unit including an image recognition LSI 24, SDRAM 26, and EEPROM 28, and a clock circuit 22. Further, a monitor camera 50, a monitor camera 51, a speaker 52, and a confirmation button 53 are connected to the CPU 12 via the wireless communication unit 20. The monitor camera 50 and the monitor camera 51 capture an image of the room, and transmit image data obtained by the imaging to the CPU 12 via the wireless communication unit 20. The monitor camera 50 and the monitor camera 51 function as imaging means. The speaker 52 outputs a warning sound and a warning message based on the warning signal received from the CPU 12 via the wireless communication unit 20. The confirmation button 53 outputs a warning stop request signal wirelessly when operated by a person. When the CPU 12 receives the warning stop request signal, the CPU 12 transmits a warning stop signal to the speaker 52. When the speaker 52 receives the warning stop signal, the speaker 52 stops outputting the warning sound and the warning message. The clock circuit 22 is for measuring the elapsed time t and the elapsed time T. The clock circuit 22 functions as a time measuring means.

The image processing unit calculates an optical flow from the image data received from the monitor camera 50, and acquires the optical flow data. The optical flow data corresponds to the change mode data in the present invention.

Further, the image processing unit recognizes feature points from the image data output from the monitor camera 51 to acquire a face graph (face data), and specific face data indicating a face of a specific person stored in the hard disk 18 To determine whether or not. When executing this processing, the image processing unit functions as an authentication unit that determines whether or not the face graph (face data) acquired from the image data matches the specific face data stored in the hard disk 18. Note that in this specification, face data and specific face data coincide with each other when the values of face data and specific face data quantified by a predetermined process are within a predetermined range (high similarity). Including.

The image processing unit includes an image recognition LSI 24, SDRAM 26, and EEPROM 28. Although not shown, the image recognition LSI 24 includes, for example, a module including a coprocessor that can process a plurality of data in parallel for one instruction, a DRAM, a DMA controller, and an affine conversion module. In the SDRAM 26, the image data output from the monitor camera 51 is temporarily stored. The EEPROM 28 stores a face recognition program, a filter and a pattern for recognizing feature points, and the like.

The image processing unit performs the following processing to recognize the player's face.
When the image data output from the monitor camera 51 is stored in the SDRAM 26, the image recognition LSI 28 sets a threshold value and performs a binarization process for separating the image data into a bright area and a dark area based on the threshold value. Do. Examples of the process for setting the threshold include a mode method, a p-tile method, and a discriminant analysis binarization method. Next, a separability filter is applied to each pixel included in the dark region, and the separability is calculated by changing the radius of the separability filter. Subsequently, the local maximum point of the degree of separation is extracted as a feature point candidate. At this time, the feature point candidate corresponds to a dark region where all or part of the outer edge shape is close to a perfect circle or an ellipse. Specifically, the nose, mouth end, eyes, eye corners, eyebrows, background noise, and the like are included. Next, pattern matching using the subspace method is performed, and feature points are identified from the feature point candidates based on the positions and shapes of the feature point candidates. Next, the position and size of the face region are normalized by two-dimensional affine transformation based on the feature points, and a graph (face graph) connecting the feature points is created (see FIG. 8). Then, it is determined whether or not the face graph matches face data (face graph) indicating the face of the specific person stored in advance in the hard disk 18.

An air conditioner 54, a stove 55, and an electric pot 56 are connected to the wireless communication unit 20. The CPU 12 can transmit / receive signals to / from these devices, and transmits, for example, an operation stop signal, a use permission signal, a disabling signal to each device.

FIG. 5 is a flowchart showing a warning process executed in the processing terminal shown in FIG.
When the warning process is started, the processing terminal 10 starts counting the elapsed time t (minutes) by the clock circuit 22 under the control of the CPU 12. The process in which the time is counted by the clock circuit 22 corresponds to a time measuring step.

First, the CPU 12 receives image data (video data) transmitted every second from the monitor camera 50, and acquires optical flow data from the video data (step S10). When executing the process of step S10, the CPU 12 functions as a change mode data acquisition means for acquiring optical flow data. Moreover, the process of step S10 is corresponded to a change mode data acquisition step.

Next, in step S12, the CPU 12 determines whether or not there is a change in the video, that is, whether or not an optical flow exists. When determining that there is a change in the video, the CPU 12 determines whether or not the video has changed in a predetermined area or more, that is, all of a predetermined number of adjacent pixel blocks (2 × 3 pixel blocks or more in this embodiment). In step S14, it is determined whether or not an optical flow exists. When executing the process of step S14, the CPU 12 functions as a determination unit. Further, the process of step S14 corresponds to a determination step.

If it is determined in step S12 that the video has not changed, or if it is determined in step S14 that there is no optical flow in all the predetermined number of adjacent pixel blocks, the CPU 12 determines that the elapsed time t is 5 minutes or more. Judge whether there is. When determining that the elapsed time t is 5 minutes or more, the CPU 12 transmits a warning signal to the speaker 52 (step S20), and moves the process to step S22. As a result, a warning sound and a warning message are output from the speaker 52. When executing the process of step S20, the CPU 12 functions as a warning means. On the other hand, if it is determined that the elapsed time t is not 5 minutes or longer, this subroutine is terminated.

In step S22, the CPU 12 determines whether or not the warning stop request signal output from the confirmation button 53 has been received within one minute after the warning signal is transmitted. When determining that the warning stop request signal is received within one minute from the transmission of the warning signal, the CPU 12 transmits a warning stop signal to the speaker 52 (step S24). As a result, the output of the warning sound and warning message from the speaker 52 is stopped. On the other hand, if it is determined that the warning stop request signal has not been received within one minute from the transmission of the warning signal, an operation stop signal is transmitted to each device (step S26), and this subroutine is terminated. As a result, the operation of each device is stopped. When executing the process of step S26, the CPU 12 functions as a stopping means. Moreover, the process of step S26 is corresponded to a stop step.

When it is determined in step S14 that an optical flow is present in all the adjacent pixel blocks of a predetermined number or more, or after the processing in step S24, the CPU 12 sets the elapsed time t to t = 0 (step S16), and this subroutine. Exit. When executing the process of step S16, the CPU 12 functions as a reset means.

FIG. 6 is a flowchart showing face recognition processing executed in the processing terminal shown in FIG.
This subroutine is a process performed in the image processing unit 28.
When the face recognition process is started, the processing terminal 10 starts measuring the elapsed time T (minutes) by the clock circuit 22 under the control of the CPU 12.
First, image data is received from the monitor camera 51 (step S30). The received image data is stored in the SDRAM 26. The image recognition LSI 28 uses binarization processing on the image data, and separates the image data into a bright region and a dark region (step S31). When face image data is included in the image data, the bright region includes a portion corresponding to the skin of the face, particularly a flat portion. On the other hand, the dark region includes other parts of the face.

Next, the image recognition LSI 28 applies a separability filter to each pixel in the dark region, calculates the separability by changing the radius of the separability filter (step S32), and determines the local maximum point of separability. Is extracted as a feature point candidate (step S33). Subsequently, the image recognition LSI 28 determines whether or not a feature point candidate exists in the image data (step S34). In step S34, it may be determined that there are no feature point candidates when there are a predetermined number or less of feature point candidates. If it is determined that no feature point candidate exists, this subroutine is terminated.

If it is determined that a feature point candidate exists, the image recognition LSI 28 performs a process of recognizing the feature point by pattern matching using the subspace method (step S35).

Next, the image recognition LSI 28 determines whether or not a feature point exists in the image data (step S36). In step S36, when the number of feature points is equal to or less than a predetermined number, it may be determined that no feature points exist. If it is determined that there is no feature point in the image data, this subroutine is terminated. When it is determined that the feature points exist in the image data, the image recognition LSI 28 normalizes the position and size of the face area by two-dimensional affine transformation with the feature points as a reference, and connects the feature points. A graph (face data) is generated, and the process proceeds to step S38. When executing the processing of step S30 to step S37, the image recognition LSI 28 functions as a face data acquisition unit.

In step S38, the image recognition LSI 28 determines whether or not the face graph generated in step S37 matches the face data (face graph) of a specific person stored in the hard disk 18 in advance. It is determined whether or not the person imaged at 51 is a specific person. When executing the processing of step S38, the image recognition LSI 28 functions as an authentication means. If it is determined in step S38 that the person is a specific person, a use permission signal is transmitted to each device (step S39), and after T = 0, this subroutine is terminated. Each device that has received the use permission signal executes processing that enables use. When executing the processing of step S39, the image recognition LSI 28 functions as enabling means.

On the other hand, when it is determined in step S38 that the person is not a specific person, it is determined whether or not the elapsed time T (minutes) is 60 minutes or more (step S40). When it is determined that the elapsed time T is 60 minutes or more, the image recognition LSI 28 transmits an operation stop signal to each device (step S41). Thus, the operation of each device that has received this is stopped.
Next, the image recognition LSI 28 transmits a disable signal to each device (step S42). Each device that receives this cannot use it. When executing the processing of step S42, the image recognition LSI 28 functions as a non-use means.
If it is determined in step S40 that the elapsed time T (minutes) is not 60 minutes or more, or after the process of step S42, this subroutine is terminated.

The face recognition process shown in FIG. 6 will be described with reference to FIGS.
FIG. 7A is a diagram schematically illustrating image data obtained by imaging with the monitor camera 51, and FIG. 7B is a diagram schematically illustrating image data in which feature points are recognized. c) is a diagram schematically showing image data in which face image data is recognized. FIG. 8 is a diagram showing a graph (face graph) connecting feature points.

People 60 came into chamber and is picked up by the monitor camera 51, a monitor camera 51, the image data I ₁ shown in FIG. 7 (a) is transmitted, is input to the image processing unit (step S30).

Processing in steps S31~S33 the image data I ₁ shown in FIG. 7 (a) feature point candidates are extracted by is performed, identifying the feature point C from the feature point candidates by the processing of step S35 is performed Then, it becomes as shown in FIG. In the figure, the feature point C is indicated by a white circle.

When the process of step S37 to the image data I ₁ shown in FIG. 7 (b) is performed, a face graph shown in FIG. 8 is obtained.
In step S38, it is determined whether or not the face graph matches the face data (face graph) of a specific person stored in the hard disk 18 in advance.

As described above, according to the apparatus automatic stop system 90 and the program executed in the apparatus automatic stop system 90, the optical flow data is acquired from the video data captured by the monitor camera 50, and the video is generated based on the optical flow data. It is determined whether or not there has been a change of a predetermined amount or more. Then, when 6 minutes (first predetermined period) has been counted since it was determined that there was a change in the last video, the air conditioner 54 stove 55 and the electric pot 56 (device) that are connected wirelessly and are provided indoors The process to stop the operation is performed. That is, if there is a change in the image due to, for example, a person moving in the room, and it is assumed that a person is present in the room, the operation of the device is not stopped, and 6 minutes have passed since the last change in the image. If it is assumed that there is no change in the room image even after elapse of time and no person is present in the room, the operation of the apparatus is stopped.
In this way, when the person is assumed not to be present in the room, the operation of the apparatus is stopped, so that it is possible to reduce the risk of the occurrence of a fire due to the operation in the state where there is no person, It is possible to suppress wasteful energy consumption due to operation of a device that is not used by anyone, and to consider the environment.
In addition, since the operation of the apparatus is stopped when there is no change in the video for 6 minutes, it is not necessary to operate the forgetting to turn off button or the like at regular time intervals or at regular time intervals, thereby reducing the number of times that a person performs the operation. Can be convenient.

In addition, when 5 minutes (second predetermined period shorter than the first predetermined period) has been counted since the last determination that the video has changed, a process for giving a warning is performed, and 6 minutes (first If a warning cancellation input is received before the predetermined period), the time measurement is reset. Therefore, for example, if there is no change in the image due to sleeping etc. (no human action), a warning can be given, and if there is no response, the release input cannot be made, Even if a person exists, high safety can be ensured by stopping the operation of the apparatus. As described above, normally, as long as there is a human action, a warning is not given, but a release input is requested only when there is no change in video for a predetermined amount of 5 minutes, thereby making the operation complicated. In addition to avoiding as much as possible, high safety can be ensured. In addition, when there is a cancel input, the time count is reset and the apparatus can be operated continuously.

In addition, the acquired face data is a specific face based on face data acquired from image data obtained by imaging the room and specific face data indicating the characteristics of a face of a specific person stored in advance. If the data does not match, a process for stopping the operation of the apparatus is performed. Therefore, for example, by storing only the faces of parents as specific face data, the operation of the apparatus can be stopped when there are only children in the room. Thus, even when there is a change in the video, if there is no specific person in the room, the operation of the apparatus can be stopped to ensure higher safety.
Further, when the acquired face data does not match the specific face data based on the face data acquired from the image data obtained by imaging the room and the specific face data stored in advance, the device When the acquired face data matches the specific face data, a process for enabling the use of the apparatus is performed. Therefore, since the apparatus can be used only when a specific person exists in the room, for example, when only a child exists in the room, the apparatus can be used to prevent injury.

In this embodiment, the case where it is determined whether or not there is a change in the image using the optical flow has been described. However, in the present invention, the image itself is changed by detecting the movement of a person or an object from the image data. However, the present invention is not limited to this example. As a method for detecting the movement of a person or an object from video data, a conventionally well-known technique can be adopted. For example, it is assumed that a person wears a marker and the movement of the marker is detected. it can. When using a marker, it is preferable to arrange the imaging means so as to stretch around the room. This is because it is possible to prevent the marker from being hidden by the orientation of the person's body or the location of the room, and to reliably detect the movement. Further, an infrared camera may be used as the imaging means, and a marker that reflects or emits infrared light may be used.
Furthermore, in the present invention, a magnetic field is generated in a room by a transmitter, a person wears a magnetic sensor as a marker, the direction and intensity of the magnetic field existing in the room are detected, and the direction and intensity of the obtained magnetic field are The movement of the sensor may be detected.

In the present embodiment, a case where a warning signal for outputting a warning sound or the like is transmitted to the speaker 52 has been described. However, the processing for performing a warning in the present invention is not limited to this example, and, for example, means for emitting light (For example, a warning lamp) may be provided, and a signal for emitting light may be transmitted to the light emitting means.

In the present embodiment, the case where the warning is stopped when the signal is received from the confirmation button 53 has been described. However, the present invention is not limited to this example, and the warning is given when the video is changed after the warning is performed. May be canceled.

In this embodiment, when it is determined that the face data obtained by imaging with the monitor camera 51 does not match the specific face data, and the elapsed time T (minutes) is 60 minutes or more, it is used for each device. Although the case where the disable signal is transmitted has been described, the present invention is not limited to this example. For example, face data is acquired every 5 minutes, and the acquired face data matches the specific face data. If not, a signal for making the device unusable may be output.

The embodiment of the present invention has been described above, but only specific examples are illustrated, and the present invention is not particularly limited. The specific configuration of each unit and the like can be appropriately changed. The effects described in the embodiments of the present invention are only the most preferable effects resulting from the present invention, and the effects of the present invention are limited to those described in the embodiments of the present invention. is not.

It is a figure which shows the outline of the apparatus automatic stop system which concerns on this embodiment. (A), (b) is a figure for demonstrating the optical flow obtained by imaging the room | chamber interior shown in FIG. (A), (b) is a figure for demonstrating a pixel block. It is a block diagram which shows the internal structure of a processing terminal. It is a flowchart which shows the warning process performed in the processing terminal shown in FIG. It is a flowchart which shows the face recognition process performed in the processing terminal shown in FIG. (A) is a figure which shows typically the image data obtained by imaging with a monitor camera, (b) is a figure which shows the image data by which the feature point was recognized typically, (c). It is a figure which shows typically the image data by which face image data was recognized. It is a figure for demonstrating a face graph.

Explanation of symbols

10 processing terminal 12 CPU
14 ROM
16 RAM
18 Hard Disk 20 Wireless Communication Unit 22 Clock Circuit 24 Image Recognition LSI
26 SDRAM
28 EEROM
50, 51 Monitor camera 52 Speaker 53 Confirm button 54 Air conditioner 55 Stove 56 Electric pot 60 Person 90 Device automatic stop system

Claims (5)

A device automatic stop system connected to a device provided in a room via a communication line,
Imaging means for imaging the room;
Change mode data acquisition means for acquiring change mode data indicating a video change mode from video data indicating a video of a predetermined length of time obtained by imaging by the imaging unit;
Determination means for determining whether or not the video has changed by a predetermined amount or more based on the change aspect data acquired by the change aspect data acquisition means;
A timing means for timing the period;
And a stop means for outputting a signal for stopping the operation of the apparatus when the time measuring means has timed the first predetermined period since it was determined that the video was last changed. A device automatic stop system characterized by that. Warning means for performing a process for giving a warning when the timing means counts a second predetermined period shorter than the first predetermined period after the determination means determines that the video has changed last; ,
A release input means for inputting a warning release;
2. The apparatus according to claim 1, further comprising: a reset unit that resets the time count by the time measuring unit when a warning cancel input is received from the cancel input unit before the first predetermined period elapses. Automatic device stop system. Face data acquisition means for acquiring face data indicating the characteristics of a person's face from image data obtained by being imaged by the imaging means;
Storage means for storing specific face data indicating facial features of a specific person;
Based on the face data acquired by the face data acquisition means and the specific face data stored in the storage means, it is determined whether the face data acquired by the face data acquisition means satisfies a predetermined condition. An authentication means,
The stop means outputs a signal for causing the apparatus to stop the operation when the authentication means determines that the face data acquired by the face data acquisition means does not satisfy the predetermined condition. The apparatus automatic stop system according to claim 1 or 2, characterized by the above. A device automatic stop system connected to a device provided in a room via a communication line,
Imaging means for imaging the room;
Change mode data acquisition means for acquiring change mode data indicating a video change mode from video data indicating a video of a predetermined length of time obtained by imaging by the imaging unit;
Determination means for determining whether or not the video has changed by a predetermined amount or more based on the change aspect data acquired by the change aspect data acquisition means;
A timing means for timing the period;
A stop means for performing a process for stopping the operation of the apparatus when the time measuring means has timed the first predetermined period since the determination means determined that the video was last changed, and the imaging means; Face data acquisition means for acquiring face data indicating the characteristics of a person's face from image data obtained by imaging;
Storage means for storing face data indicating the characteristics of the face of a specific person;
Based on the face data acquired by the face data acquisition means and the specific face data stored in the storage means, it is determined whether the face data acquired by the face data acquisition means satisfies a predetermined condition. Authentication means;
A deusable unit that outputs a signal for making the device unusable when the authentication unit determines that the face data acquired by the face data acquiring unit does not satisfy the predetermined condition; ,
Enabling means for outputting a signal for enabling use of the device when the authentication means determines that the face data acquired by the face data acquisition means satisfies the predetermined condition. A device automatic stop system characterized by that. A program executed in an apparatus automatic stop system provided with an imaging means for imaging a room,
A change mode data acquisition step of acquiring change mode data indicating a video change mode from video data indicating a video of a predetermined length of time obtained by imaging by the imaging means;
A determination step of determining whether or not there has been a change of a predetermined amount or more based on the acquired change mode data;
A timing step for timing the period;
A stop step of outputting a signal for stopping the operation of the device when the time counted by the timing step has counted the first predetermined period since it was determined that the video was changed last A program characterized by comprising.

Images