JPH07271482A - Computer system - Google Patents

Abstract

PURPOSE:To heighten an added value by easily attaining the prevention of burning of a CRT, etc., and power saving control by obtaining scrupulous human-machine interface by effectively using an image fetched from a camera in a computer system combined with the camera. CONSTITUTION:Video information from a camera means 1 connected to a computer means 2 is inputted to an image processing means 3. The image processing means 3 recognizes the ambient status(whether a person approaches or separates from a system, or the person faces toward the front of the system, etc.) of the computer system based on inputted video information. A recognized result is outputted to a system control means 4. The system control means 4 performs control for the connection/disconnection of the power source of a power source part 2i and a display part 2f in the computer means 2, etc.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a computer system such as a personal computer or a workstation, and more particularly to a computer system combined with a camera for photographing an operator. The computer system of the present invention is also applicable to home information terminals such as HA systems and portable information terminals.

[0002]

2. Description of the Related Art In a conventional computer system combined with a camera, an image from the camera is captured and mainly used for a video conference, a video telephone, or reading characters and figures.

Recently, in order to prevent CRT burn-in, a geometric pattern is displayed on the screen when there is no signal input from an input device such as a keyboard or a mouse for a certain time as seen in AfterDerk. It is known to let it move.

[0004]

In the computer system combined with the conventional camera, as described above, the input image from the camera is used as an image in a video conference or a videophone, and characters or figures are read. Was mainly used for.

Also, in the environmental control of the computer system, the ON / OFF control by the timer is only performed.

As described above, the conventional system has not been satisfactory to the operator in environmental control and security.

The present invention was devised in view of the above circumstances, and it is intended to enhance added value by effectively utilizing an image captured from a camera in a computer system combined with the camera. Has an aim.

[0008]

[Means for Solving the Problems]

(1) A computer system according to a first aspect of the present invention is a computer means including a CPU, a power supply section, a display section, etc., a camera means for capturing a subject, and a subject image input from the camera means. Image processing means for recognizing the surroundings of the computer system,
System control means for turning on / off the power of the computer system according to the recognition result of the image processing means.

(2) A computer system according to a second aspect of the present invention is the computer system according to the first aspect, wherein the image processing means recognizes the face of the person and determines that the person has left the front surface of the computer system. The system control means shuts off the power supply or sleeps, and the system control means automatically starts up the system when it is determined that the user has approached the front of the computer system and is seated.

(3) A computer system according to a third aspect of the present invention is the computer system according to the first or second aspect, wherein the system control means has a timer, and the power is shut off after a person leaves the timer. It is characterized in that the time until it is set can be set.

[0011]

[Action]

(1) In the computer system according to claim 1,
The peripheral condition of the computer system is recognized based on the subject image obtained from the camera means, and the power is turned on / off according to the recognition result, that is, whether the operator is sitting or away from the seat. A detailed human
You can get a machine interface and easily C
It is possible to prevent burning such as RT and control power saving.

(2) In the computer system according to the second aspect, it is determined whether or not the operator is actually working toward the computer system by recognizing the face of the operator. When the operator is completely away from the computer system, or when the operator is not away from the system but is not facing the system, it is determined that the operator is not working, and the power is shut down or the sleep state is set. When the operator approaches the computer system and faces the system, it is determined that the operator is working and the system is automatically started. Therefore, even if there is no input from an input device such as a keyboard or mouse for a certain period of time, as long as the operator's face is detected, there is no unexpected power cutoff or sleep state. To provide a flexible environment for

(3) In the computer system according to the third aspect, the operator sets the time from when the operator leaves the computer system until when the power is actually cut off, for example, when the operator leaves the system. You can keep the application running with.

[0014]

Embodiments of a computer system according to the present invention will be described below in detail with reference to the drawings. Each of the embodiments described below has a built-in camera,
The TR may be attached externally.

[First Embodiment] The first embodiment is claim 1
FIG. 1 is a block diagram showing an electrical configuration of the computer system according to the embodiment.

In the camera means 1, the image pickup device 1b converts an optical image captured by the lens 1a into an electric signal. The pre-processing unit 1e samples and holds the output signal from the image sensor 1b, performs automatic gain correction, performs analog-digital conversion, and converts digital data in pixel units. The digital video signal processing unit 1f generates a luminance signal and a color difference signal based on the digital data output from the preprocessing unit 1e, performs white balance processing, gamma correction processing, etc., and converts the luminance signal and the color difference signal into digital signals. Output.

The color difference signal at this time is output as an R-Y / B-Y dot-sequential color difference signal.

The image pickup device driving section 1c generates a drive timing pulse for controlling the image pickup device 1b, a video signal synchronizing pulse, a video signal processing pulse and the like. The camera microcomputer 1d controls the image pickup device driving section 1c, the preprocessing section 1e, the digital video signal processing section 1f, etc., and realizes the operation of the camera means 1.

The computer means 2 comprises a CPU 2a and a RAM
2b, ROM 2c, peripheral circuit section 2 such as hard disk
e, a power supply unit 2i for supplying power to the computer, an input / output circuit unit 2 for interfacing with the outside of the computer
h, a display control unit 2g for controlling graphic display, and a display unit 2f for displaying a graphic signal output from the display control unit 2g. The display control unit 2g receives the video signal from the camera unit 1 and processes it.
The display unit 2f is synthesized with the graphic signal generated in a.
It is also possible to display in.

The image processing means 3 performs image processing such as human body detection, face recognition, and motion feature extraction based on the luminance signal output from the camera means 1. In this example, the processing is performed using the luminance signal, but if the recognition is performed using the color difference signal, the accuracy becomes higher.

The system control means 4 realizes control of the power supply section 2i, the display section 2f, etc. of the computer means 2 based on the data output from the image processing means 3.

With the above structure, the camera means 1 used as an image capturing device is combined with the image processing means 3 and the system control means 4 so that the image processing means 3 can use the video signal obtained from the camera means 1. The environment around the computer system is recognized and detected, the operating condition of the computer means 2 is determined from the recognition and detection result, and the control content is output to the system control means 4. Based on the output contents, the system control means 4 optimally controls the turning on / off of the power supply of the computer means 2. Since the power is turned on and off depending on whether the operator is seated or away from the seat, a fine-grained human-machine interface can be obtained.
It is possible to easily prevent burning of T etc. and control power saving.

[Second Embodiment] This second embodiment is claimed in claim 2.
2 is a block diagram of the image processing means 3.

The luminance data of the nth frame output from the camera means 1 is converted into binary data by the binarization processing unit 3a. The binarized n-th frame binary data is stored in the frame memory 3f through the difference detection unit 3b.
The difference detection unit 3b compares the binary data of the nth frame already stored in the frame memory 3f with the binary data of the (n + 1) th frame to be input next, and determines whether there is a motion between the frames. Detect whether or not. This operation is sequentially executed. The difference detecting unit 3b is for determining whether or not the input image has a motion. If there is movement, it is determined that there is a person (operator), and if there is no movement, it is determined that there is no person. When it is determined that there is no movement, the information that there is no person is output to the person recognition unit 3d.

Then, the above difference detection operation is continued.

When the difference detecting unit 3b determines that there is a motion, the image data in the frame memory 3f is used as the face detecting unit 3b.
c, output to the body detection unit 3e. The binary image data output from the difference detection unit 3b is input to the face detection unit 3c. The face detecting section 3c scans in the X-axis direction and the Y-axis direction at a predetermined timing, as shown in FIG. First,
First, the Y coordinate of the pixel in which the difference appears is recognized as the crown Yt. As the scanning progresses, pixels corresponding to the image of the face moving with respect to the static background image appear after this coordinate. However, when scanning from the left in FIG. 3, the pixel is located at the leftmost X coordinate position. The appearing pixel is recognized as the head left coordinate Xl. Similarly, the pixel appearing at the rightmost X coordinate position in the process of continuing scanning is recognized as the right head coordinate Xr.

Regarding the lower coordinates of the face, since the visitor's torso image appears continuously, the coordinates of the X axis (Xl,
The Y coordinate Yu under the head of the lower face is calculated from the distance data of Y1) and the face length Fl statistically obtained. That is, Xc = (Xr-Xl) / 2 + Xl Yc = (Yu-Yt) / 2 + Yt Yu = Yt + Fl By the above calculation, 4 of the most prominent part of the face is calculated.
The coordinates of the points can be determined. The coordinates of the above 4 points are the top Pt
(Xc, Yt), head left Pl (Xl, Yl), head right Pr
(Xr, Yr) and below-the-head Pu (Xc, Yu). The area surrounded by these four points is set as the face area, and the face area coordinates and the image signal are stored in the memory. Based on the stored face area coordinates and the image signal, the features of the eyes, nose, and mouth are extracted to recognize the face. Regarding this screen extraction, Japanese Patent Application No. 5-177 filed by the applicant of the present application
No. 720 (TV intercom device), Japanese Patent Application No. 5-15
No. 3933 (image processing apparatus), Japanese Patent Application No. 5-268608
No. (image format conversion device).
The fact that the face is detected by these processes is output to the system control means 4.

Next, the body detecting section 3e detects the body based on the data output from the difference detecting section 3b and the face coordinates output from the face detecting section 3c. As shown in FIG. 4, the projection processing is performed in the X-axis direction and the Y-axis direction from the input image data to calculate the projection data of the person.
The body portion is extracted from the projection data and the face coordinate data output from the face detecting unit 3c. That is, the parietal coordinates Yt and the subordinate coordinates Y of the Y-axis coordinates detected by the face detecting unit 3c.
The range of u is the projected Y-axis face, and the range of the X-axis coordinate head left coordinate Xl and the head right coordinate Xr is the projected X-axis face. Then, it is determined that the part having an area having movement following the face on the projected X-axis and Y-axis is the body. This determination result is output to the person recognition unit 3d.

When the person recognizing unit 3d recognizes from the face detecting unit 3c and the body detecting unit 3e that both the face and the body exist, it determines that the person (operator) is working toward the computer system. And outputs data indicating that there is a person to the system control means 4. The person recognition unit 3d determines whether or not the user is actually working toward the computer system.

Based on the data output from the person recognizing section 3d, the system control means 4 grasps the state of whether the person is away from the computer system or sits in front of the computer system, and considers the operating state of the computer system. The power supply unit 2i is controlled to turn on / off the computer system. Similarly, the power of the display unit 2f is turned on or off. At this time, when the operator leaves the computer system, the power is cut off, and when the operator sits in front of the computer system, the power is turned on. It is also possible to combine these operations. The system may be put into a sleep state instead of power-off.

As long as the operator faces his or her face toward the computer system, even if the input from the input device such as the keyboard or the mouse does not occur for a certain period of time, the power is not cut off or the sleep state is not unexpectedly reached. ,
An environment that is more flexible for the operator can be set.

[Third Embodiment] This third embodiment is claimed in claim 3.
FIG. 5 is a block diagram of the system control means 4 of the embodiment.

The timer 5a is a counter which receives a signal from the image processing means 3 that the operator has left the front of the computer system and counts the timer. When the preset time is counted, an event signal is output from the power control unit 5a.
output to b. The count setting of the timer 5a is executed from the computer means 2 through the input / output circuit section 2h.
Further, the counting operation is started by checking the operation status flag of the computer means 2 input from the input / output circuit section 2h. For example, if the application program is in the execution state, the busy flag is set to prevent the timer operation from being executed. As a result, the power control unit 5
Since the event signal is not output to b, the power cutoff operation and the sleep operation are not executed.

Then, in response to the event signal output from the timer 5a (information that the operator recognizes that the operator has moved away from the front of the computer system), the power source of the power source unit 2i or the display unit 2f is shut off. There are two modes for shutting off the power supply unit 2i: a mode for shutting off the power of the entire system and a mode for shutting off the power of a part that does not affect the operation of the system, which can be set and used.

According to this embodiment, it is possible to set the time from when the operator leaves the computer system until the power is cut off. For example, there is a method of using the application such that the computer system is kept away from the user, and it is possible to set a more flexible environment for the operator.

[Fourth Embodiment] FIG. 6 is a block diagram of the system control means 4 of the fourth embodiment.

The switch section 6a judges the situation from the signal from the image processing means 3, the signal for enabling / disenabling the power cutoff inputted from the input / output circuit section 2h, and the signal showing the operating situation of the computer system, and controls the power source. Event information indicating whether or not the power is cut off is sent to the unit 6b. When the enable signal is sent from the input / output circuit unit 2h of the computer unit 2, the switch unit 6a is turned on, and the power control unit 6b outputs a signal from the image processing unit 3 that the operator has left the computer system. In response to this signal, the power supply control unit 6b executes the power supply cutoff operation.

When a disenable signal is sent from the input / output circuit section 2h of the computer means 2, the switch section 6a is turned off, and even if the operator from the image processing means 3 receives a signal that the operator has left the computer system. ,
No event signal is output to the power supply controller 6b. Therefore, the power cutoff operation is not executed.

[Fifth Embodiment] FIG. 7 is a block diagram of the image processing means 3 and the system control means 4 of the fifth embodiment.

The binarization processing section 3a, the difference detection section 3b, the frame memory 3f, and the face detection section 3c, which are the constituent elements of the image processing means 3, are the same as those in the second embodiment, and therefore their explanations are omitted.

The system control means 4 includes a face cutting section 7
d, a frame memory 7e, an image memory 7a, a face file memory 7c, and a screen comparison unit 7b. The face cutout unit 7d cuts out the face from the image stored in the frame memory 7e based on the image coordinates surrounding the face input from the face detection unit 3c. That is, the coordinates surrounding the face output from the face detection unit 3c, the top Pt
(Xc, Yt), head left Pl (Xl, Yl), head right Pr
From (Xr, Yr) and below-the-head Pu (Xc, Yu), the coordinates of four points surrounding the face are obtained. The coordinates of these four points are P1 (X
l, Yt), P2 (Xr, Yt), P3 (Xl, Y
u) and P4 (Xr, Yu). By accessing the address of the frame memory 7e by these coordinates, P1, P
The face image data surrounded by 2, P3 and P4 is output.
FIG. 8 shows a cutout image. The frame memory 7e is a temporary storage memory for the processing of the face cutout unit 7d.

The image memory 7a is a memory for temporarily storing the facial image output from the facial clipping unit 7d, and is used for comparing the facial images. The face file memory 7c is a memory in which the face image of the operator is registered in advance. The screen comparison unit 7b performs comparison and comparison between the face image cut out in the image memory 7a, which is the face image of the operator sitting in front of the computer system, and the face image registered in advance in the face file memory 7c. is there.

The flow of this processing will be described below. First,
The image data input from the camera means 1 is binarized by the binarization processing unit 3a, and the difference detection unit 3b and the face cutout unit 7 are processed.
Binarized image data is input to d. The difference detection unit 3b detects the difference and outputs the difference result to the face detection unit 3c. The face detection unit 3c detects only the face and calculates the coordinates of the face area. The calculation result is output to the face cutout unit 7d.

First, a face file for each operator is created. For this, only the face data of the face portion is cut out from the image data stored in the frame memory 7e from the coordinate data of the face output from the face detection unit 3c and registered in the face file memory 7c. At the same time when the face data is registered, the image name and the identification number are also stored by the operation from the computer means 2. This operation is repeated as many times as necessary to sequentially register the facial images of each operator. This operation is performed in advance.

Next, when the operator sits in front of the computer system, the image data is input from the camera means 1 and binarized by the binarization processing unit 3a, and the binary data is binarized by the difference detection unit 3b and the face cutout unit 7d. The converted image data is input. The difference detection unit 3b performs difference processing, the face detection unit 3c generates data surrounding the face, and outputs the data to the face cutout unit 7d. The face cutout unit 7d cuts out only the face image data from the image data stored in the frame memory 7e and outputs it to the image memory 7a. Here, the face image data in the image memory 7a and the face file memory 7c registered in advance are stored.
The screen comparison unit 7b executes the comparison and collation processing with and searches the image for the name and the identification number.

This search result is given to the CPU 2a via the input / output circuit section 2h of the computer means 2 and the system bus. The CPU 2a recognizes the registered name and identification number and automatically sets the operating environment according to the person sitting in front of the computer system. Therefore, it is possible to detect who is the operator sitting in front of the computer system. As a result, for example, an erroneous operation such as erasing the data of another operator by mistake is eliminated, and the security of the computer system can be enhanced.

[Sixth Embodiment] FIG. 9 is a block diagram of the image processing means 3 and the system control means 4 of the sixth embodiment.

The binarization processing section 3a, the difference detection section 3b, the frame memory 3f, and the face detection section 3c, which are the constituent elements of the image processing means 3, are the same as those in the second embodiment, and therefore their explanations are omitted.

The system control means 4 includes a face cutting section 7
d, frame memory 7e, image memory 7a, screen comparison unit 7b, binarized image memory 9a, image frame memory 9b
And an image output unit 9c.

The binarized image memory 9a stores the binarized and cut-out face image, and stores the binarized face image data of the operator who is operating the computer system. Even when the operator leaves, the face image data is retained as it is.

The image frame memory 9b stores image data at the same timing as the image data stored in the binarized image memory 9a. The image data of the image frame memory 9b is not the binary face image data stored, but the gradation data input from the camera means 1. The image output unit 9c is the image frame memory 9
The image data of b is displayed by the display controller 2g of the computer means 2.
Output to. The control of the output of this image data is determined by the output signal from the screen comparison unit 7b.

In the screen comparison section 7b, the image memory 7a and the binarized image memory 9a are collated with each other, and if they are similar to each other, a signal permitting the output of the image data is outputted to the image output section 9c. Thereby, the image data can be output from the image output unit 9c to the display control unit 2g of the computer means 2.

As described above, first, the face image data of the operator is stored in the binarized image memory 9a while operating the computer system. When the operator recognizes that the user has left, the face image data in the binarized image memory 9a is held as it is. Next, when another operator sits in front of the computer system, the image data is input from the camera means 1 to the binarization processing unit 3a. The image data binarized by the binarization processing unit 3a is input to the face cutout unit 7d, the face is cut out, and stored in the image memory 7a. Then, the comparison processing of the face image data already stored in the binarized image memory 9a and the cut-out face image data of the image memory 7a is performed by the screen comparison unit 7b, and when it is determined that they are not the same person, the input / output circuit unit 2h The signal is output to the image output unit 9c. In response to this, the image output unit 9c outputs the image data to the display control unit 2g, and the input / output circuit unit 2h outputs the CPU data.
The image data from the image output unit 9c is controlled to be displayed on 2a. As a result, when another operator sits in front of the computer system, the image of the person who has been operating and has left is displayed on the display unit 2f. As a result, erroneous operations such as erasing data of other operators by mistake are eliminated, and the security of the computer system can be enhanced.

[Seventh Embodiment] FIG. 10 is a block diagram of the image processing means 3 of the seventh embodiment.

The binarization processing unit 3a, the difference detection unit 3b, the frame memory 3f, the face detection unit 3c, the body detection unit 3e, and the person recognition unit 3d, which are the components of the image processing means 3, are the same as those in the second embodiment. Therefore, the description is omitted.

In this embodiment, the image processing means 3 further comprises a face width detecting section 10a and a body width detecting section 10b. The face width detection unit 10a detects the lateral width of the face, and the body width detection unit 10b detects the width of the body.

The face width detecting section 10a obtains the face width by calculating the difference between the right head coordinates and the left head coordinates shown in FIG. The face width HW is along the X-axis direction, and HW = head right coordinate−head left coordinate = Xr−X1.

The body width detection unit 10b obtains the width of the body by taking the difference between the left and right coordinates of the body shown in FIG. The body width DH is DH = Dr-Dl.

Both the face width and the body width are statistically calculated in advance and stored as data, and a close data value is determined to determine whether or not the user is sitting at the computer system. Based on this result, the person recognition unit 3d determines whether or not there is an operator, and controls the computer system.

According to the present embodiment, the operator and the surrounding person are distinguished based on the face width and the body width, and the computer system reacts to the operator, but to the surrounding person. Can be unresponsive. Therefore, the power saving effect is further enhanced.

[0061]

【The invention's effect】

(1) According to the computer system of claim 1, the power is turned on / off according to the recognition result of the peripheral condition of the computer system, that is, whether the operator is seated or away from the computer. A human-machine interface can be obtained, and it is possible to easily realize burning prevention and power saving control of a CRT or the like.

(2) According to the computer system of claim 2, even if there is no input from an input device such as a keyboard or a mouse for a certain period of time, as long as the face of the operator is detected, it is unexpected. It is possible to set a flexible environment for the operator without shutting off the power or going to sleep.

(3) According to the computer system of claim 3, by setting the time from the time when the computer system is left until the time when the power is cut off, it is more flexible for the operator to keep the application running. You can set an environment.

[Brief description of drawings]

FIG. 1 is a block diagram showing an electrical configuration of a computer system according to a first embodiment of the present invention.

FIG. 2 is a block diagram of image processing means in a computer system according to a second embodiment of the present invention.

FIG. 3 is a coordinate diagram of a face.

FIG. 4 is a projection view of a person.

FIG. 5 is a block diagram of system control means in a computer system according to a third embodiment of the present invention.

FIG. 6 is a block diagram of system control means in a computer system according to a fourth embodiment of the present invention.

FIG. 7 is a block diagram of image processing means and system control means in a computer system according to a fifth embodiment of the present invention.

FIG. 8 is an image diagram of an image memory.

FIG. 9 is a block diagram of image processing means and system control means in a computer system according to a sixth embodiment of the present invention.

FIG. 10 is a block diagram of image processing means in a computer system according to a seventh embodiment of the present invention.

[Explanation of symbols]

 1 ... Camera means 2 ... Computer means 2a ... CPU 2f ... Display section 2g ... Display control section 2h ... Input / output circuit section 2i ... Power supply section 3 ... Image processing means 3a ... Binarization processing section 3b ... Difference detection section 3c ... Face detection unit 3d ... Person recognition unit 3e ... Body detection unit 4 ... System control means 5a ... Timer 5b ... Power supply control unit 7a ... Image memory 7b ... Screen comparison unit 7c ... Face file memory 7d ... Face cutout unit 9a ... Binary image memory 9b ... Image frame memory 9c ... Image output unit 10a ... Face width detection unit 10b ... Body width detection unit

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁶ Identification code Internal reference number FI Technical indication H04N 7/14

Claims (3)

[Claims] 1. A computer means composed of a CPU, a power supply section, a display section, etc., a camera means for picking up an image of a subject, and a subject image input from the camera means for processing to recognize the surroundings of the computer system. And a system control means for turning on / off the power of the computer system according to the recognition result of the image processing means. 2. The image processing means recognizes a person's face, and when it is determined that the person has moved away from the front surface of the computer system, the system control means shuts off the power or sleeps, and approaches the front surface of the computer system to sit down. 2. The computer system according to claim 1, wherein the system control means automatically starts up the system when it is determined to be. 3. The system control means has a timer, and the timer is configured to be able to set the time from the time when the person leaves until the power is cut off. Computer system.