JPH0659040A - Image forming device - Google Patents

Abstract

PURPOSE:To improve the accuracy and speed of recognition by previously recognizing a stationary obstruction, and recognizing whether a body except the recognized stationary obstruction is a person using a device or not. CONSTITUTION:After predeterminate time from a time of turning on an electric source, a sensor is actuated, and a spot where some body is detected is recognized and remembered as the existing place of a solid body, namely an obstruction. A distance sensor 6 is actuated on a sampling signal given by a control section 11 to measure a distance to the body. A parameter extracting section 8 extractingly computes feature parameters required for the recognition and various judgements of the body decided as responded object on distance data to each body, and sends them to a recognizing-judging section 9 and writes them in a memory 13. The judging section 9 receives the parameter and judges about the body being a responded object. For example, judgement is given to whether the body being the responded object is a user for a image forming device or not and, whether the using of the device is finished or not.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image forming apparatus, and more particularly to an image forming apparatus which recognizes whether or not a person approaching the image forming apparatus is a user and controls the operation of the apparatus based on the recognition result. It relates to the device.

[0002]

2. Description of the Related Art In recent years, in order to improve the convenience of users, automation of devices has been increasingly attempted. In particular, the field of interest in the present invention is to detect a user who approaches the device by providing the device with a sensor for detecting an object in the vicinity of the device,
This is a field in which automation of the equipment is desired to be enhanced. The technology in this field includes, for example, an automatic door that automatically detects the approach of a person and opens and closes the door, and a cash dispenser of a bank that detects the approach of a person and automatically turns on / off the operation display unit (LCD). It has been put to practical use as such. Further, in the image forming apparatus, automatic power ON / OFF,
It is applied to automatic preheating function.

The automatic power ON / OFF function is used when an image forming apparatus such as a copying machine is provided with a sensor for detecting the presence or absence of an object (human body) on the front surface of the apparatus and when the human body is not detected (when not in use). Is a function of turning off the power and turning on the power when the human body is being detected (in use).

In the image forming apparatus such as a copying machine, the automatic preheating function is provided with a sensor for detecting the presence or absence of an object (human body) in front of the apparatus, and when the human body is not detected (when not in use), an operation display is displayed. The fixing temperature of the fixing means (roller having a built-in heater) for fixing the image information (toner image) transferred onto the sheet while the display of the unit (LCD) is turned off is lower than that when the human body is detected. This is a function of setting the temperature (preheating state), turning on the display of the operation display unit while detecting the human body (in use), and setting the fixing temperature to a predetermined temperature at which the fixing operation is possible.

Thus, the conventional power ON / OFF and preheat activation / cancellation had to be executed by manual input. In recent years, however, an apparatus for automatically combining the sensors as described above has appeared. (Japanese Patent Laid-Open No. 63-26
1270).

[0006]

However, the conventional device described above has the following problems. Since the sensor is configured to detect the presence of an object facing the device, even a non-user can recognize the user as long as he walks in front of the device, turn on the power switch, or preheat. Will be canceled. If the sensitivity of the sensor is set weak to avoid this problem, the user recognizes the user for the first time when standing in front of the device, so control such as releasing the preheating state is delayed, and the user eventually There was a problem of operating the switch.

[0007]

In order to solve the above-mentioned problems, the present invention detects the distance from a device to an object in the vicinity of the device and a detection signal from the detection device. An image forming apparatus having a recognition unit that recognizes whether or not an object is a person who uses the device, at least at a timing before the detected object reaches the device, wherein the recognition unit detects the detection by the detection unit. The static obstruction object is recognized from the signal, whether or not a person who uses the apparatus is recognized for objects other than the static obstruction object, and the operation of the apparatus is controlled based on the recognition result.

[0008]

The present invention has the following structure in order to solve the above problems. (1) Based on a detection means for detecting the distance from the device to an object in the vicinity of the device and a detection signal from the detection means, at least the detected object is a person who uses the device. In an image forming apparatus having a recognition unit for recognizing at a timing before reaching the device, and a control unit for controlling the operation of the device according to a recognition result of the recognition unit, the recognition unit is configured to detect from the detection unit in advance. Recognizing a stationary obstacle on the basis of the detection signal of, and recognizing whether or not a person is using the apparatus for an object other than the recognized stationary obstacle, and further (2)
The recognition of the stationary obstacle is performed by the detection data detected after a predetermined time has passed since the power is turned on, or
(3) The stationary obstacle is recognized based on the detection data detected at every predetermined timing after the power is turned on, and the memory is updated each time it is recognized, or (4) the stationary obstacle is recognized. Is performed by detection data detected when not in use, and is stored and updated each time it is recognized, or (5) has a timer to recognize the stationary obstacle,
It is performed by the detection data detected in the non-use time zone set in the timer, and it is stored and updated every time it is recognized, or (6) it has a calendar, and the stationary obstacle is recognized by the It is carried out according to the detection data detected on the holiday set in the calendar, and is stored and updated every time it is recognized, or (7) it has an initial condition setting switch, and the stationary obstacle is recognized in the initial stage. It is performed by the detection data detected when the setting switch is turned on.
It is characterized in that it is stored and updated each time it is recognized.

[0009]

The present invention is based on a detection signal from the detection means for detecting the distance from the device to an object in the vicinity of the device, at least whether the detected object is a person who uses the device or not. In the image forming apparatus, which recognizes the timing before reaching the apparatus and controls the apparatus to greatly improve the operational convenience, whether or not the person uses the apparatus for an object other than a stationary object By recognizing whether or not, the recognition accuracy of the recognition means is significantly improved.

Device Outline FIG. 1 is a block diagram for explaining a configuration concept when an automatic response system is applied to an OA device. The automatic response system includes a sensor unit 2 composed of one or more sensors.
A recognition determination device 3 and a service providing device 4, which are mounted on various OA devices 1 to realize an automatic response function, and which are suitable regardless of the active action of the user of the OA device 1. It responds and provides various services.

The sensor unit 2 is mounted on the surface or inside of the OA device 1 in order to generate various data for recognizing an object (for example, a human being approaching) that automatically responds, and recognizes the obtained data. Send to device 3. The types of sensors, the mounting positions, and the number of sensors are the parameters to be detected from the data from the sensors, the direction to be detected (for example, the direction in which the operation panel is facing = the OA device front direction), and the size of the object to be responded to. (Width, height), detection accuracy (resolution, detection interval) and the like.

FIG. 2 is a diagram showing an example of mounting a sensor section composed of a plurality of distance sensors 6 in an image forming apparatus 5 which is a copying machine, a facsimile machine or a laser beam printer. FIG. Overall perspective view of device, (b)
The figure is a plan view. In the example of FIG. 2, the object to be responded to is a human (operable person), the data obtained by measurement is the distance from the image forming apparatus 5 to the object to be measured, and the directions to be measured are the front and side surfaces of the apparatus 5. . In addition to these, in order to obtain the direction of the object to be measured, the distance is measured in a plurality of directions by a distance sensor having a relatively sharp directivity. In this type of sensor, for example, infrared light is emitted from the light emitting unit in the target direction and the distance is measured by measuring the amount of reflected light at the receiving end, and ultrasonic waves of a certain frequency are transmitted from the transmitter. However, there is one in which the reflected wave is received by a wave receiver and the distance is measured by the phase difference.

In the example of FIG. 2, a plurality of sensors are mounted in order to obtain high resolution in a relatively short detection period, and the distance sensors are operated in parallel to perform measurement. Each sensor emits light little by little (at intervals of 10 degrees) to obtain the direction of the measured object.
It is implemented by shifting the direction of transmission / reception / reception. Also, since vertical data (height, etc.) is not required, the directions of light emission / transmission / light reception / reception are developed and mounted only on the horizontal plane. In addition to the distance sensor, an image input device using a CCD, for example, can be considered as the configuration of the sensor unit. In this case, the image data taken in from the image input device is sent to the recognition determination device.

The recognition determination device 3 is built in or attached to the OA equipment 1 and makes a recognition determination based on the data sent from the sensor unit 2. For example, as in the example shown in FIG. 2, from a distance to an object and its direction data, a stationary object and a moving object as a response target are recognized, and an object (human) as a response target recognizes an OA device. Determine behavior such as whether or not to use (or whether or not to use). In addition, for a device that has a sensor unit composed of an image input device and uses image data, the characteristics of the responding target object (human) are extracted, the individual is identified based on the extracted characteristics, and the individual ID (eg name,
Number, etc.) and sends the generated judgment data to the service providing device.

The service providing device 4 has a function of driving each part of the OA equipment 1, and embodies services by various automatic responses. For example, when there is a response target object approaching the OA device 1 and the determination data indicating that the object uses the OA device is sent, the preheating mode is automatically released, or conversely, the use end is determined. When data is sent, this is a service that automatically transitions to the residual heat mode. In addition, regarding the device in which the personal ID is sent as data, the operation unit is optimized for each user (key / layout change, instruction screen switching,
Etc.) to provide an environment that is easier to use. This service providing device may be provided with dedicated hardware, but it is also possible to substitute the function in software by the central processing unit of the OA equipment.

Recognition Judgment Device Outline of Recognition Judgment Device FIG. 3 is a block diagram showing the basic configuration of the recognition judgment device.
The operation of each part will be described. Note that the OA device in which the automatic response system is installed is an image forming apparatus, and the sensor unit that sends data to the recognition and determination apparatus has a configuration in which a plurality of distance sensors with strong directivity emit light as shown in FIG. -Reception / light reception-The following explanation will be made assuming that the direction of reception is expanded and mounted on a horizontal plane. The recognition determination device 3 includes a sensor driving unit 7, a parameter extraction unit 8, a recognition determination unit 9, and a post-processing unit 1.
0, control unit 11, input / output management unit 12, storage device 13, data line 14, control line 15, and external I / F (interface) line 16.

The sensor drive unit 7 drives the distance sensor 6 and receives measured distance data. Control unit 1
Based on the sampling signal from 1, each distance sensor 6 is driven and the distance to the object is measured. Then, the measurement result data is sent to the parameter extraction unit 8. The parameter extraction unit 8 extracts and calculates, from the measured distance data, the characteristic amount parameters required for recognition and various determinations of the response target object from the distance data to each object. The generated parameter and its additional information are sent to the recognition determination unit 9 and written in the storage device 13 as appropriate.
It is read from other blocks as needed.

The recognition determining unit 9 makes a determination regarding the object to be responded to by the request signal from the control unit 11. The parameters generated by the parameter extraction unit 8 are received directly or via the storage device 13, and, for example, whether or not the response target object is a user of the image forming apparatus (“use” or “do not use the image forming apparatus”). Whether or not the use of the image forming apparatus is completed (“in use” or “used”),
And so on.

The post-processing section 10 collects the judgment results and arranges them in a format for final output to the outside. For example, the process is performed in this block when there are multiple objects to be responded to. The control unit 11 controls the entire recognition determination device. Communication is performed with the outside (image forming apparatus) via the input / output management unit 12, and control is performed by sending a control signal to each block.

The input / output management unit 12 controls the interface with the outside (image forming apparatus) through the external I / F line 16. It also functions as a buffer for synchronizing with the outside. The input / output signals include the post-processing unit 10
In addition to the determination data generated in step 1 and sent to the service providing device, control signals such as various requests and timing signals between the recognition determination device and the image forming device are also included.

The storage device 13 is composed of a RAM for storing the dirty data generated in each block as necessary, and a ROM for storing the programs and data required to move each block. Data reading / writing is performed. Data line 14
Is used for transmitting each data. The control line 15 is used for transmitting control signals. The external I / F line 16 is used for transmitting control signals and data for interfacing with the outside (image forming apparatus).

Sensor drive unit The sensor drive unit 7 has a period T from the control unit 11 via the control line 15 (T must be a period sufficiently shorter than the moving speed of the object to be recognized as a response target). The distance sensor 6 mounted on the image forming apparatus is driven according to the sent sampling signal. The distance sensors are driven simultaneously (in parallel), and the distance is measured once in one sampling cycle (time interval T). The measurement data is converted into a digital data from analog data in the sensor drive unit 7, and a parameter can be identified by a method (for example, a sensor identification number is added to each data) that can identify which data is measured. It is sent to the extraction unit 8.

Parameter Extraction Unit The parameter extraction unit 8 extracts parameters required for recognition from the distance data sent from the sensor drive unit 7. As shown in FIG. 4, the distance sensors are arranged at intervals of 10 degrees with the center of the image forming apparatus 5 as the center (however, for the tenth to nineteenth positions, ◯ 10, ◯ 11,
It is mounted so that the measurement is performed in 19 directions (denoted as ◯ 19) (however, the measurement is performed only in the measuring direction and the front direction of the image forming apparatus, and the rear surface is not considered here). , The measurement of the distance to the object is repeated at the time interval T at the same time. Each arrow in FIG. 4 indicates the direction of light emission / transmission / light reception / reception of the sensor.

The parameter extraction unit performs the following processing at time intervals T (every time measurement is performed). Position Detection (1) Storage of Measurement Results Now, as shown in FIG. 4, the image forming apparatus 5 is installed in a place where there is a stationary object 17 such as a wall in one of the forward direction and the lateral direction. It is assumed that the maximum distance at which the distance sensor can measure the distance to the object is Rmax.
In addition to the measurable distance of the distance sensor itself, this measurable distance is such that the gap between the measurable directions (the range in which measurement is not performed) is sufficiently smaller than the size of the response target object (human). It is such a range. In the example of FIG. 4, 19
There is some stationary object (in this case, a wall, hereinafter referred to as an obstacle) 17 within the measurable distance of the distance sensor with respect to the direction indicated by the white letters among the measurement directions of. The parameter extraction unit 8 stores the distance data together with the measurement direction (distance sensor number) in the storage device (memory) 13 for each measurement. An example of the distance data written in the storage device 13 in the case of FIG. 4 is schematically shown in FIG. Here, in FIG. 5, r _d represents the measurement result (distance to the object) in the direction d, and the ∞ symbol indicates that there was no object closer than the object was not measured (Rmax)). It is shown that. The parameter extraction unit 8 writes the measurement result in a predetermined address in the storage device 13 every time the measurement is performed at the time interval T.

(2) Update of environmental information An object (= obstacle: wall, for example, which is within the measurable range of the distance sensor and does not actively work on the image forming apparatus 5)
Position information of desks, chairs, etc.) will be called environmental information. The parameter extraction unit 8 distinguishes these objects from those that may actively act on the image forming apparatus 5 (= moving objects: for example, humans, etc., hereinafter referred to as target objects). First, the environment information in the storage device 5 is referred to. The environmental information is conceptually in the form of a table of distances in each direction shown in FIG. 5, and indicates at which distance an obstacle exists in each direction. The environmental information is obtained by selecting the maximum distance measured in each direction in the image forming apparatus 5 for a period (for example, after the power is turned on) sufficiently longer than the period in which the target object is active in the measurable range of the distance sensor. Created. If the maximum distance in the direction d measured in the above period is _rd max,
Environmental information is conceptually shown as in FIG. Time interval T
The distance rd measured in each direction each time
And the environment information rdmax are compared, if, if Naritate the relationship of r _d> r _d max, replacing the environmental information in r _d. In this way, environmental information is created after a sufficiently long time has elapsed. For example, in the image forming apparatus installed in the environment as shown in FIG. 4, after a sufficiently long time (it is enough if there is no moving object such as a human within the measurement range of the distance sensor). The environmental information of is as shown in FIG. However, r _d represents the distance to the obstacle in the direction d in the case of FIG.

(3) Object Detection After updating the environment information, the parameter extraction unit 8 detects an object by the following method. For example, the state at time t0 is as shown in FIG.
Think of when you are approaching. FIG. 9 shows distance data in the case of FIG. 8 written in the storage device by the procedure of (1). However, r _dt is the distance to the object in the direction d at time t. The parameter extraction unit 8 creates the storage device 5 based on this distance data and the procedure of (2).
The target object is detected by comparing it with the environmental information stored in it. Specifically, for example, the difference between the distance written in the environmental information and the distance data is calculated for each direction. FIG. 10 shows the result of taking the difference between the environmental information and the distance data in the case of FIG. According to FIG. 10, there is a difference between the distance data and the environmental information regarding the direction, and the target object 18 is recognized in the direction according to this (environment ≠ distance data). Now, considering a polar coordinate system in which the center of the image forming apparatus is the origin and the direction of 010 is the angle θ = 0, the position of the target object 18 in the example of FIG. 8 is (r _5t0 , 50 °). expressed. When an object is recognized,
The position (distance and direction) is written in a predetermined position in the storage device 13.

Incidentally, as the moving object 18 approaches the image forming apparatus, the same object may be measured by a plurality of distance sensors. In this case, the position is calculated by the following method. In the example of FIG. 11, the same object is measured by the sensor in the directions of and, and according to the above means, two positions (r ₆ , θ ₆ (= 40 °)) and (r ₇ ,
θ ₇ (= 30 °)) is detected. Therefore, when two or more positions are detected, the distances between them are calculated, and all the distances are set to a predetermined value Lmin (where Lmin is an object to be responded (= human). Each point which is smaller than the value of) and whose detection directions are adjacent to each other is grouped as one position. If there are two points, they will be grouped in the middle point and
If the number of points is equal to or more than the point, the points are combined into the position of the center of gravity to generate one position. In the example of FIG. 11, the distance l between the two points detected is

[0028]

[Equation 1]

When l <Lmin, the two points are combined into one and the midpoint is newly adopted as the position.
When the number of points is 3 or more, as shown in FIG.
3 only when <Lmin and l2 <Lmin and l3 <Lmin
The points are collected, and the center of gravity G of the three points is adopted as the position of the target object and written in the storage device.

Object Tracking (1) Tracking of One Object Once the target object is recognized within the measurable range of the distance sensor, the target object is tracked. For example, the target object 18 shown in the example of FIG. 8 is displayed at time t1 (= t0 + T) in FIG.
If it moves as shown in 3, the object position (r _6t1 , 40 °) is detected by the method described above. Here, if the position information of the target object one measurement interval time before (time T before) is stored in the storage device 13, the moving speed v and the moving direction φ are calculated. As for the target object 18 shown in the example of FIG. 13, the position information calculated in the example of FIG. 8 has already been stored in the storage device 13, so the moving speed v and the moving direction φ are calculated.

The calculation method will be described below with reference to FIGS. 8 and 13. The moving distance of the target object 18 from time t0 to t1 is l _t1 , the average speed is v _t1 , the line connecting the coordinate origin (center of the image forming apparatus) and the position of the target object 18 at time t0, and at time t0. If the angle formed by the line connecting the position of the target object 18 and the position of the target object 18 at time t1 (moving direction) is defined as φ _t1 , the amount represented by each parameter is as shown in FIG. In FIG. 14, l _t1 is

[0032]

[Equation 2]

It becomes The moving speed v and the moving direction φ calculated by Expression 3, Expression 5, and Expression 6 are written in the storage device 13 together with the position (r, θ) calculated previously. By repeating the above operation at time intervals t,
In the storage device 13, position information r, θ, and if
If there is position information measured before, the moving speed v and the moving direction φ are sequentially stored as the trajectory information of the object at time intervals t. The trajectory information of the object 18 is stored in the storage device 13 in a data format such as a list or a ring buffer, but it can be conceptually considered as a table. Target object 18 after time T (= t2) in FIG.
FIG. 15 shows the movement of the robot, after a further time T (= t
FIG. 16 shows the movement of the object in 3), and a conceptual diagram of the trajectory information obtained when the object moves as shown in FIGS. 8, 13, 15, and 16 between times t0 and t3. Are shown in FIG. 17, respectively.

(2) Tracking of a plurality of objects When there are a plurality of target objects within the measurement range of the distance sensor 6, a plurality of locus information is generated for each target object in the storage device and tracking is performed. For example, consider a case where two target objects, a target object A and a target object B, exist as shown in FIG. Two pieces of trajectory information are generated for the target object A and the target object B in the storage device. FIG.
In the state of, as the position of the target object A, (r ₆ , θ ₆ (= 4
0)), as the position of the target object B (r ₁₂ , θ ₁₂ (=-
20 °)) is detected and the trajectory information of each is written. FIG. 19 shows a state after one sampling period (time interval T) from the state of FIG. Position 1 (r ₇ , θ ₇ (= 30 °)) and position 2 by object detection
Two positions of (r ₁₁ , θ ₁₁ (= -10 °)) are detected. As a possibility, as shown in FIG. 20, the target object A
There are two possible cases, ie, where is moved to position 1 and target object B is moved to position 2 (case A), or target object A is moved to position 2 and target object B is moved to position 1 (case B), respectively. Which locus information to write each position is determined by the following method.

Moving direction in each of the above two cases
φ and velocity v are calculated according to equations 5 and 6. If
Let φ be the moving direction of the target object A calculated for A._A2, Move
V is the velocity_A2, The moving direction of the target object B is φ_B4,Moving Speed
V_B4, And of the target object A calculated for case B
Φ_Ab, Moving speed v_Ab, How to move the target object B
Direction_Bb, Moving speed v_BbAnd In addition, 1 sample
State before the switching cycle (time interval T) (in the state of FIG. 18
The moving direction of the target object A is φ_Apre, Moving speed v _Apre,versus
Let φ be the moving direction of elephant object B_BpreThen, the transfer of the target object A
Change in moving direction δφ_A, Amount of change in moving speed δv_A,Object
Amount of change in the moving direction of body B δφ_B, Change the moving speed by δ
v_BIs

[0036]

[Equation 3]

It is expressed as follows. Here, defined by Equation 9 below variation e _i about the target object i, further case is defined by equation 10 below the total variation En for n.

[0038]

[Equation 4]

However, α and β are change amounts δ in the moving direction.
It is a constant for weighting φ _i and the moving speed change amount δv _i . As the combination of the target object and the detection position, the combination of the target object and the detection position in the case where the total change amount is the smallest is adopted. The total change amounts E _a and E _b of case A and case B are

[0040]

[Equation 5]

Since E _a <E _b , the combination of the target object and the detection position for case A is adopted,
In the trajectory information of the target object A, the position 1 (r ₇ , θ ₇ (= 30
)), The moving direction φ _Aa , the moving speed v _Aa , and the locus information of the target object B includes the position 2 (r ₁₁ , θ ₁₁ (= -10).
°)), the moving direction φ _Ba , and the moving speed v _Ba are written.

Similarly, in all cases where three or more target objects exist within the measurement range of the distance sensor, combinations of target objects and detection positions are created,
Data to be written in the trajectory information is determined by calculating the total change amount E in each case. When the target object whose total change amount E cannot be calculated is included, for example, the moving distance 1
Is performed so that the target object and the detection position are associated with each other so as to minimize (corresponding the detection positions of the close objects to each other as compared with one sampling period (time interval T) before).

When a plurality of target objects overlap with each other when viewed from the image forming apparatus as in the case of the target object A and the target object B in FIG. 21 (exist in the same sensor measurement direction),
The number of detected target objects temporarily decreases. In such a case, tracking is performed as described below to generate trajectory information. In the example of FIG. 21, the object is detected in the direction of and the position (r ₉ , θ ₉ (= 10 °)) is obtained. Here, the target object A one sampling cycle (time interval T) before
And the position of the target object B respectively (r _Apre , θ _Apre )
And (r _Bpre , θ _Bpre ), and as shown in FIG. 22, the moving direction and the moving speed when it is considered that the target object A and the target object B respectively reach the detected position are φ _A , Given v _A and φ _B , v _B , from Equation 5 and Equation 6,

[0044]

[Equation 6]

It becomes Further, the moving directions and moving speeds of the target objects A and B one sampling period (time interval T) before are φ _Apre , v _Apre and φ _Bpre , v _Bpre.
Then, the respective variation amounts e _A and e _B are given by

[0046]

[Equation 7]

It becomes Assuming that the detected position is the position of the target object with the smaller change amount, in the case of the example in FIG. 22, since e _B <e _A , the detected position is the trajectory information of the target object B. Written. In this case, with respect to the target object A whose position is not determined, the writing of the trajectory information is suspended, and when the position is determined, the trajectory information is written backward from the time. For example, if the position of the target object A is determined to be (r _Apost , θ _Apost ) after one sampling period (time interval T), then the position between the two points (r _Apre , θ _Apre ) and (r _Apost , θ _Apost ) The point is assigned to the reserved position (r _A , θ _A ). Similarly, when the position is determined after n sampling cycles (time interval nT), points that internally divide the two points into n are assigned to the reserved positions and written in the trajectory information.

The same applies when three or more target objects exist within the measurement range of the distance sensor and the target objects overlap with each other when viewed from the image forming apparatus (exist in the same sensor measurement direction). Then, the change amount e is calculated for each target object, and the changes are compared to obtain the correspondence between the target object and the detected position.

Generation of Recognition Judgment Trigger The distance r to the approaching target object 17 is a certain value Lmi.
When the number becomes equal to or less than n, the parameter extraction unit 8 sends a recognition determination trigger to the control unit 11 to perform the distance determination regarding the target object 17. When a plurality of target objects are present within the measurement range, this operation is activated each time the distance r to any one of the target objects falls below a certain value Lmin. The recognition determination trigger is converted into a recognition determination request signal by the control unit 11 and sent to the recognition determination unit 9. Similarly, when the target object using the image forming apparatus moves away, the distance r to the target object becomes
When the value becomes equal to or more than a certain value Lmin, the parameter extraction unit 8 sends a recognition determination trigger to the control unit 11 to make a recognition determination regarding the target object. The same applies when a plurality of target objects are present within the measurement range. FIG. 23 shows how the judgment recognition trigger is generated.

The value of Lmin is usually set to a distance at which the recognition judgment device has to output the recognition judgment result (= whether the target object acts on the image forming device, for example) to the service providing device. This distance is appropriately determined according to the type of service provided by the output result from the recognition and determination device, the time required for the service, the moving speed of the target object, and the like. The value of Lmax is appropriately set to a distance within the maximum distance measured by the distance sensor (Rmax in FIG. 4). After outputting the recognition judgment trigger, the data related to the trajectory information of the target object for which the recognition determination needs to be performed (the address in the storage device where the trajectory information is stored, the size of the trajectory data, and whether the target object is approaching. The data required for access to the trajectory information by the recognition determination unit, such as whether or not the user has moved away, is sent to the recognition determination unit 9.

Recognition Judgment Unit The recognition judgment unit 9 makes a judgment regarding the object to be responded to in response to a request from the control unit 11. After receiving the recognition determination request signal from the control unit 11, data relating to the trajectory information of the target object for which the recognition determination needs to be performed from the parameter extraction unit 8 (the address in the storage device 13 where the trajectory information is stored, the trajectory data, and the like). , The size of the target object, whether the target object is approaching or moving away, and the like), which are necessary for accessing the trajectory information) are received from the parameter extracting unit 8. Then, by accessing the trajectory information of the target object that needs to be recognized and determined in the storage device 13 and performing a predetermined process, for example, when the target object approaches, the user of the image forming apparatus is identified. Whether or not ("use" or "not use" of the image forming apparatus), whether or not the use of the image forming apparatus has ended ("in use" or "finished") when going away. Etc., and outputs the result to the post-processing unit 10. Among the recognition determination processes, some examples of the process for determining whether the image forming apparatus is “used” or “not used” when the target object approaches will be described below.

Preprocessing In order to make a recognition judgment regarding the target object, the recognition judgment section 9 generates some parameters from the trajectory information. One or more reference distances are provided within the measurement range of the distance sensor. For example, as shown in FIG. 24, n reference distances (where L0 <L1 <L2 <... L (n-1)) of distances L0, L1, L2, ..., L (n-1) from the center of the image forming apparatus. Shall be established). Here, the reference distance of the closest distance L0 from the image forming apparatus is Lmin.
(Distance at which the recognition judgment trigger is generated by the parameter extraction unit). The locus information at the reference distance Lm is time t _Lm , distance r _Lm (= Lm), direction θ _Lm , moving speed v _Lm , moving direction φ _Lm, and distance L (m−
1) and Lm, the change amount of the moving speed is Δv _Lm (= v _Lm
-V _L ( _m-1 )), the amount of change in the moving direction is Δ _Lm (= φ _{Lm −} φ _L
( _m-1 )), and parameters are generated for each distance (however, the change amount Δv _L0 of the moving speed and the change amount Δφ _{0 of the} moving direction at the distance L0 are excluded). The parameters generated for each distance are conceptually shown in FIG. The generated parameters are processed so that they can be used in the next stage. For example, it is divided into groups according to the value range and converted into the group number, or normalization processing for a certain value range is performed.

Recognition / Decision Processing Among the methods for performing recognition / decision using the parameters generated in the preprocessing stage, a method using a neural network will be described below. For example, the following neural network 21 for determining whether the target object "uses" or "does not use" the image forming apparatus is prepared. FIG. 26 shows a schematic diagram of a recognition judgment neural network 21 by a hierarchical neural network composed of three layers of an input layer 22, an intermediate layer 23 and an output layer 24.
The input layer 22 corresponds to each input parameter, and the output layer 24 corresponds to each determination (in this case, "use" and "not use"). The neural network used here is trained by a predetermined method (for example, back propagation) using the characteristic pattern collected in advance by experiment as teacher data. That is, it is assumed that each parameter is input and the object to be learned at that time is to "use" or "not use" the image forming apparatus.

In the recognition judgment processing, the parameters generated from the trajectory information by the control signal from the control unit are input to the neural network for recognition judgment, and most of the output layers 24 of the neural network at that time are input. The result corresponding to the unit that strongly ignites (the output value is the largest) is output to the post-processing unit 10 as the recognition determination result. With the same specifications, a neural network for determining whether the target object is “in use” or “used” of the image forming apparatus is prepared, and the recognition determination result is output to the post-processing unit 10.

Post-Processing Section The post-processing section 10 collects the recognition judgment results and arranges them in a format for final output to the outside, and then, if necessary, the control section 11
After notifying the change of state to the input / output management unit 12, the recognition determination data is sent. For example, consider a case where a plurality of target objects exist in the measurement range of the distance sensor as shown in FIG. In the case of the example of (a), the target object B who is trying to use the image forming apparatus newly comes to the place where the target object A is already using the image forming apparatus. in this case,
A recognition determination trigger is generated when the target object B approaches the distance Lmin from the image forming apparatus, and the recognition determining unit 9 determines that the target object B "uses" the image forming apparatus. Is this determination masked? If it is not held, a problem occurs that the service for the target object B is started even though the target object A is in use. On the other hand, as in the case of the example of (b), it is assumed that the target object A, which is the previous user, has left while the target object B is using the image forming apparatus. In this case, a recognition determination trigger is generated when the target object A approaches the distance Lmax from the image forming apparatus, and the recognition determining unit 9 determines that the target object A has “used up” in the image forming apparatus. If the target object B is not masked or held, the service is started even though the target object B is in use (transition to residual heat mode, auto reset, etc.). If necessary, the post-processing unit 10 fetches external (image forming apparatus) information (for example, whether or not copying is in progress) through the control unit 11, and masks or suspends the determination regarding a plurality of target objects. Only when it is necessary to change the state, the recognition determination data is sent to the input / output management unit 12.

Control Unit The control unit 11 controls the entire recognition / judgment device. The main control contents are as follows.

(1) Timing Processing of Each Block Data of each block (sensor drive unit 7, parameter extraction unit 8, recognition determination unit 9, post-processing unit 10, input / output management unit 12) in the recognition determination device Performs synchronous processing for delivery. For example, when data is transferred from a certain block A to a certain block B, first, a data transmission request is issued from the block A to the control unit 11. The control unit 11 sends a data reception request signal from the block A to the block B, confirms that the reception preparation of the block B is completed, and then sends the data transmission request signal to the block A. In block A, after receiving the data transmission request signal from the control unit 11, data transfer is started.

(2) Request processing of each block Requests sent from each block in the recognition / judgment apparatus (for example, recognition judgment trigger generated in the parameter extraction unit, recovery request for error generated in each block,
Etc.) is performed.

(3) Storage device access management Arbitration is performed so that a plurality of blocks do not access the storage device at the same time (read / write does not collide). Each block in the recognition / judgment device can be accessed only when the storage device is accessed and the access right is requested from the control unit.

(4) Control of interface with the outside The clock signal and the reset signal from the outside (image forming apparatus) are received through the input / output management unit 12, and the synchronization processing between the outside and each block in the recognition and determination apparatus is performed. Also,
External information (the state of the image forming apparatus, for example, “in operation / not operating”, information on the operation panel, etc.) is taken in, and information necessary for recognition determination is transferred to the corresponding blocks.

The input / output management unit 12 receives various requests from the outside.
And receive the request through the.
For example, when the trajectory information of the target object is requested from the outside,
This corresponds to processing such as reading trajectory information from a predetermined area in the storage device and outputting it through the input / output management unit 12. Further, a request to the outside (for example, displaying an error on the operation panel, etc.) when an error or the like occurs in the recognition determination device is also generated by the control unit 11, and the input / output management unit 12 is generated.
Is output to the outside through.

Input / Output Management Unit The input / output management unit 12 controls the interface with the outside (image forming apparatus) through the external I / F line 16.
It also functions as a buffer for synchronizing with the outside, and each input / output data / signal is latched by the input / output management unit 12 to be synchronized. The input / output signals include control data such as various requests and timing signals between the recognition / determination device and the outside, in addition to the determination data regarding the target object generated by the post-processing unit 10 and sent to the service providing device. included.

Storage Device The storage device 13 stores a RAM for storing the data generated in each block as needed, and a ROM for storing the programs and data required to operate each block.
Read / write data by each block
Writing is done.

Service Providing Device Service Providing Device Outline The service providing device 4 has a function of driving each part of the OA equipment, receives various judgment results generated by the recognition judging device 3, and provides a service by an automatic response corresponding to the judgment results. Embody. Further, if necessary, the recognition determination unit is requested to provide more detailed information regarding the target object. The service providing device 4 is a conceptual device, and there are several possible ways of implementing it. In particular, it is preferable to implement such a method for a service that does not stipulate that dedicated hardware is prepared and can substitute functions by software by a central processing unit of an OA device.

Service for People When a response target object (person) approaches the OA device and the judgment data indicating that the object uses the OA device is sent, the following service is executed. To do. (1) AI (Artificial Intelligence) residual heat function (2) AI automatic power switching function (3) AI pressure plate automatic opening and closing function (4) AI automatic interrupt function (5) Height variable function

Further, when a person who is using the OA equipment ends the operation and leaves the OA equipment, and the judgment data indicating that the use is completed is sent, the following service is executed. (1) AI residual heat function (2) AI automatic power supply switching function (3) AI pressure plate automatic opening / closing function (4) AI automatic interrupt function (5) AI automatic reset function (6) AI original / copy forget check function

Service for Individual The following service is executed for an apparatus having a response object (person) approaching the OA device and sending the ID of the individual as data. (1) Operation panel AI automatic setting function (2) AI guidance function (3) Management function (4) AI automatic interrupt function (5) AI automatic reset function (6) Message message function

Next, user recognition / personal recognition based on image data will be described. User recognition In the above-mentioned automatic response system, an example using a distance sensor such as an infrared sensor was given as a sensor. Next, based on the information such as the body and face orientation when the target object (person) approaches, which is obtained by processing the image data, not the distance information, is that person the "user"? ,
A method of recognizing / determining whether the user is a “passer” will be described. The configuration example in which a distance sensor is used in FIG. 1, the implementation example in FIG. 2, the basic configuration of the recognition determination device in FIG. . However, the distance sensor 2
It needs to be a sensor for inputting some image data using a CCD, a MOS, an image pickup tube, or the like. The parameter extraction unit 8 in FIG. 3 extracts necessary information from image data or the like by image processing or the like.

Now, let us consider the operation of an approaching person to use the image forming apparatus 5 such as a copying machine to which the present recognition and determination apparatus is attached. In particular, when there is no obstacle, it can be considered that a person usually walks straight to the device he / she wants to use. In other words, approach the device you want to use with your body straight. In addition, even if you cannot come in a straight line due to some obstacle, etc., if you can see the device at least several times as long as you can reach the target device by the time it comes close to the position of the target device, You can think. In other words, the face of the device desired to be used faces straight again and again. It is possible to determine whether the target person is a "user" or a simple "passerby" by storing such behaviors of human beings as a rule as rules and extracting / determining these behaviors by image processing or the like. To do.

Hereinafter, a simple example of a concrete method of judgment will be described with reference to FIG. First, it must be judged whether or not a person is photographed in the photographed image data (step 1). This can be achieved, for example, by holding image data in which no one is reflected and taking the difference from the image data taken. In other words, by deleting the background portion from the image data that is currently captured, the remaining portion is a moving object that is not the background,
In other words, it can be seen that the target person.

Next, the orientation of the body or face must be detected in the image data of the target person (step
2). Even if it says detection, it is enough to judge whether or not it is facing here. As a very simple example, the user may be judged if the body or face of the photographed person is facing this direction. However, it is usually difficult to judge just because you were only looking at me once. In other words, this is not enough accuracy. Therefore,
For example, a counter may be provided, and the number of times that it is observed that the user has turned to this side may be stored in the counter, and it may be determined that the user is the user when the number of times of observation is preset. .

Further, the orientation may be numerically observed by the number of angles or the like instead of yes / no, and the observation may be performed, and the determination may be made based on the data string. In this case, the data string pattern of the "user" may be stored in advance and the judgment may be made by referring to the stored table, or an appropriate weighting parameter may be added with time and direction as parameters. It may be judged by the evaluation function, or the behavior pattern of the "user" may be described by a natural language rule (for example, if the user turns here many times in a short time, the user is the one.), It may be judged by fuzzy reasoning, or the behavior pattern of the "user" may be stored in advance in the neural network, and the observed data string may be input to the neural network to output whether or not the user is the "user". May be.

The configuration for carrying out this recognition processing is basically the same as that described above, but the distance sensor 2 in FIG. 1 is replaced by an image input sensor such as a CCD. In addition, the image data obtained by photographing the approaching target object (target person) is processed by the parameter extraction unit 8 in FIG. The feature amount (data / information) to be extracted here is the orientation of the face or body of the target person described above. Further, in the recognition determining unit 9, the table reference described above,
Judgment processing is performed by an evaluation function, fuzzy inference, neural network, etc.

Individual Recognition Recognizing that a target object that is a person is a specific individual is called personal identification. Individual recognition can be divided into two larger recognitions. One is the recognition of identifying an individual who has been registered in advance (identified individual identification), and the other is not to register the individual in particular, but for the target person observed at a certain point. , The same person is recognized (the same person is sequentially identified).
In the above-described automatic response system, an example in which a distance sensor is provided to measure the position of the target object as a sensor is shown, and an infrared or ultrasonic sensor has been described as a specific example thereof. Here, an example relating to individual recognition of the target person is shown. In this case, a specific example of the sensor is a CCD.
An example in which image data is processed after the image is input by, for example, will be mainly described.

In this case, the recognition judgment device 3 shown in FIG.
In the above, personal recognition is performed, and the distance sensor 2 is a sensor that can input image data, and the basic configuration is not changed at all. In the following, one image input sensor will be described as an example for simplification of description, but a plurality of sensors may be provided as shown in FIGS. 1 and 2. In addition,
Even if an image input device such as a CCD is used as a sensor, it is possible to observe the position up to the target object described in the above-mentioned automatic response system without any problem by using the current image processing technology ([“robot ] Bit special edition, pp
711/724, July 1976], ["Stereoscopic vision", Journal of the Robotics Society of Japan, Vol. 1, pp30 / 35, 1983], etc.). That is, the image input sensor is just one specific example of the distance sensor, and for example, in order to obtain the position of the target object from the image data captured by one fixed sensor, the image of the position of the foot of the target person is used. Data coordinates may be extracted and mapped to real world coordinate data. If there are multiple sensors, the position of the target object can be observed by applying the triangulation principle (stereoscopic method). Therefore, even if the sensor is changed from the infrared sensor or the like to the image sensor, not only the above-described processing is possible but also the sensor is useful in the individual recognition described below.

Existing Individual-Specific Identification The processing method for the already-identified individual identification for identifying the already registered individual from the image data will be described.
Discrimination technology has existed for a long time and has been put to practical use, for example, in character recognition. The same technique / principle can be applied to the already-identified personal identification. To explain the principle briefly, prepare a dictionary that describes the characteristics of something to be specified in advance, extract the characteristics of the observed input data, compare with each content of the dictionary, and find the best match. What is present is identified. In addition to such a discriminant approach, a table reference method, an evaluation function method, a confidence factor calculation method, a fuzzy inference method, a neural network method, etc. are also known.

As the data for identifying an individual, the information about the individual, that is, the feature that must be registered in advance, may be any feature obtained by image processing or the like, but it must be good for identifying the individual. I have to. For example, height, weight (volume), sex, size or shape of body or face, presence or absence of eyeglasses, etc. may be considered. The height can be obtained by converting the number of pixels from the head to the toes into the actual length from the image data. This is easy to convert because the distance to the target object should be known. Finding the head and toes can be realized by ordinary image processing techniques such as binarization and filtering and knowledge engineering. The sex can be determined by obtaining the shape of the hair, the covering, the presence or absence of makeup, and the like by image processing. Facial features are often used and are often used to identify individuals based on image data. For example, relations between parts, shapes of individual parts, and the like such as the degree of separation of eyes, the shape of eyes, and the contour of a jaw are often used.

By the individual recognition of this already-identified individual identification,
It is possible to improve the operability of the user and to save the management of the device. For example, when this personal recognition device is attached to an image forming device such as a copying machine,
The operation panel AI automatic setting function, AI guidance function, and AI automatic interrupt can be realized.

Sequential Person Discrimination Next, as described above, rather than registering an individual in advance, it is the recognition of whether or not the target person observed at a certain time point is the same person. Discrimination of the same person will be described. This is to store the characteristics of the target person observed at a certain point in time, determine whether they match the characteristics of the target person observed at another point, and determine whether they are the same person / You do not need to register in advance information that includes the characteristics of the individual you want to identify as a dictionary.For example, if someone does not artificially input the name of the observed person into the device, you can understand it. No information can be obtained. The method for sequentially identifying the same person is basically not much different from the method in the already identified individual identification. In the personal identification, based on the observed / extracted features, this was compared with the features of each individual, which was described in the dictionary in advance. The difference is that it compares the observed features. In the same person determination, the characteristics of the target person observed at a certain time are stored as a dictionary and used when comparing with the characteristics of the person observed later, but only the immediately preceding observed object is stored in the dictionary. Alternatively, it may be possible to store a plurality of items.

By making it possible to sequentially identify the same person, it is possible to know that the user of the apparatus has changed, for example, and it is possible to distinguish "in use / end of use" at that point. When a person is identified as the same person, it can be recognized as "in use" within a certain period of time, and when a person who is not the same person comes in, the previous person is recognized as finished using it. it can. If the apparatus is, for example, a copying machine, it is possible to automatically reset each parameter (AI auto reset function) to prevent the next erroneous operation by the user. Even if the AI automatic interrupt function cannot be specified for each individual, this recognition can be performed. Also,
The sensor for sequentially observing the characteristics in the same person discrimination is not limited to the CCD. For example, anything that can measure the characteristics of a person such as a color sensor, a weight scale, and a sound sensor may be used. Further, although there is a sensor which can be individually discriminated such as the image input sensor such as the CCD described above, it is possible to discriminate with higher accuracy by using a combination of sensors which are difficult to discriminate by themselves. .
The configuration in this case is only required to connect these sensors in parallel with the distance sensor 2 shown in FIG.

Processing method of recognition judgment parameter: Predetermined measurement condition detection area initial condition setting method A person approaching is a person who has come to operate a system (apparatus) attached to the present recognition apparatus. It is desirable to recognize and memorize the surrounding situation in order to make the determination early or more surely depending on the situation where the system is set when deciding whether the person is a passing person. As used herein, the term "situation" refers to the location of obstacles such as surrounding walls, for example. For example, when the system is installed at the far end of a dead-end corridor, the person who approaches the system is considered to be the person who uses the system in most cases. here,
Described is a method of automatically recognizing a situation where a system is installed at the far end of a dead-end corridor. The information to be detected is a fixed object, such as a wall, which is a blocking / obstacle for a human to walk. Find these objects at a certain time. For this purpose, for example, a service person or a user who installs the system to which the recognition device is attached can directly input to the system by some method.
It is troublesome to set it again. Here, the method of automatically recognizing these is described.

In order to recognize data (area data) such as an obstacle which is an initial condition in a measurable detection area by the sensor described in the above-mentioned recognition device, the following (a), (b) , (C) can be considered. (A) Area data is stored from the detection value detected after a lapse of a predetermined time after the power is turned on (blocking obstacle data based on regular received / received data) A predetermined time from the time the power is turned on This is a method in which the sensor is activated later, and the place where any object is detected by the sensor is recognized as a fixed object (obstacle) and stored. Immediately after the power is turned on, the person who turned on the power is nearby and may recognize this as a fixed object. Therefore, the power is turned on, and after a while (for example, 1 minute), the sensor is activated, and the place where something is detected is recognized as a fixed object and stored.

As one of the embodiments, a case where the above-mentioned sensor sets the initial condition will be described. 1 and 2 show configurations of a system (the OA device 1 or the image forming apparatus 5) and a sensor 2 to which the present recognition device is attached. Here, the sensor is attached to the system in a plurality of directions. When the power of this system is turned on by the user, for example, the power of the recognition device is shared with the power of the system, and the timing of the power is easily known by some means. A timer is installed in the device or the like, and each sensor is activated after a predetermined time, for example, 1 minute, which has been set in a random manner, to perform a predetermined measurement. These sensors are
At least some object can measure in what direction and at what distance, for example, FIG. 4 and FIG.
In such a case, it is indicated by a combination of the direction and distance in which some object was observed, and at ~ 〇13, 〇15〜 ○ 19,
Recognize that there is an obstacle and memorize it.

(B) The area data is stored and updated at every predetermined timing from the detection value detected at every predetermined timing after the power is turned on. After the power is turned on, the sensor is activated at every predetermined time. This is a method of comparing the detection status of the sensor at the time of the previous measurement with the detection status of this time, recognizing where the fixed object is, and updating the memory. A fixed object should be detected in the same place no matter how many times it is detected by the sensor, unless a situation change due to a layout change or the like does not occur artificially. On the other hand, if it is not an obstacle originally, such as a person who happened to be nearby, it will be observed by the sensor at first, but will have already left there and will not be observed at the next measurement. So, for example,
This is a method in which the detection status is obtained from the sensor every 5 minutes, the past detection status is memorized, and the object always detected at the same place is recognized as a fixed object. The predetermined timing need not always be observed, that is, at the minimum interval.
However, if you just want to get the area data,
There is no particular need for constant observation, and measurements may be taken at some intervals. For example, if you always activate the sensor to make some judgment, divert it,
It is more reliable if the area data is updated at all times, but if there is no need for other observations at all times, it is more effective to save power if measurements are taken at certain intervals.

To implement this method, the past detection status must be stored at least once. However, a plurality of times may be stored, which increases the recognition accuracy but increases the cost. When the past detection status is stored only once, the stored previous detection status is, for example, θ = 15 degrees, distance = 3 m and θ = 8.
It is assumed that the position is 0 degrees and the distance is 2 m, and the detection status measured this time after a predetermined time is 30 degrees, 4 meters and 80 degrees, and 2 degrees.
If it is m, it is recognized / determined that there is some fixed object (obstacle) in the part of 80 degrees and 2 m detected at the same place. And the past detection status is 30 degrees and 4 m;
Store 80 degrees and 2 meters.

Also, in the case of storing the detection statuses of a plurality of times, the judgment may be made in substantially the same manner. For example, when storing the situation for 5 times, it is judged that a fixed object is surely present at a place detected at the same place three or more times in a row recently,
It is not continuous, but it is 4 in 6 detection situations including this measurement
It is judged that there are some obstacles in the places detected more than once. By doing so, it becomes possible to more accurately know whether or not it is an obstacle. As a result, in addition to things such as walls that are truly stationary objects, for example, a word processor, etc., is installed near the system equipped with this recognition device, and a person using the word processor can detect it with a sensor. In this case, that is, it is possible to deal with the case where it is originally a moving object, but temporarily becomes an obstacle to the system for some reason, and the correct installation environment, that is, the initial condition can be obtained.

(C) Storing area data from the detected value detected under a predetermined condition (area data storage update for each predetermined condition) The timing of recognizing the area data is performed only when the predetermined condition is satisfied. Is the way. The predetermined condition is
Basically, it means that there are no people around. The sensor itself may be activated at fixed or irregular intervals,
Whether or not the area data should be recognized is compared with a predetermined condition to be recognized and stored. The following four cases can be considered as the predetermined condition.

(I) When not in use Measurement / recognition is performed when the system associated with this recognition device is not in operation, that is, when no one is using it.
When the system is not operating, there are basically no people nearby. In other words, if the measurement is performed at that point, it may be determined that there is an obstacle at the location where something is detected.
In this case, one measurement may recognize a location detected at that time as an obstacle, or it may be measured several times and a plurality of locations detected may be an obstacle. .

(Ii) Night with no people: Timer In a normal office, there are no people at night. Therefore,
At this time, measurement / recognition is performed. If some kind of object is detected by activating the sensor with a timer or the like when there is no person such as at night, it is assumed that it is an obstacle such as a wall. Moreover, it is possible to more reliably determine that there is no person, not only by the timer but also by the brightness of the illumination. For example, as a specific time setting, it is possible to set it by default at 3 o'clock in the middle of the night, and to change it by the user.
It may be set in conjunction with an ON / OFF timer incorporated in the system for another purpose, at the time of OFF, immediately before being turned OFF, immediately after being automatically turned ON, or the like. In this case, at least one measurement is required, and the location detected at that time may be identified as an obstacle, or, as a precautionary measure, it may be repeated several times during an unattended night time. Measure
The place where a large number is detected may be an obstacle.

(Iii) Holiday: Weekly timer In a normal office, there are no people on holidays. Therefore, measurement / recognition is performed at this time. If an object is detected when a sensor is activated by a calendar (weekly timer) on a day when there is no person such as Sunday, it is assumed that it is an obstacle such as a wall. The specific time may be set on Sunday by default, and may be set by the user if desired. In this case, the measurement may be performed at least once, and the location detected at that time may be recognized as an obstacle. Good.

(Iv) Initial condition setting means ON Here, the means for setting the initial condition is closed to the user. For example, an operation button such as a "first condition setting button" is attached to the apparatus. By recognizing / setting the initial condition, a service person or a user / administrator etc. decides the layout etc. and explicitly presses this button when it is determined that the initial condition should be set. is there. However, immediately after pressing the button, the person who presses it is in front of the device, so like the self-timer often used for cameras etc., it is set in advance so that it will be set in a few seconds, and during that time. In addition, the button operator may ask the user to evacuate outside the detection range of the sensor. Further, an infrared remote controller or the like may be used so that the present means can be operated from a distant place.

[0092]

【The invention's effect】

Effect on configuration (1): In a device that recognizes whether or not a person approaching the device is a person who uses the device, a stationary obstacle is recognized in advance, and the device is recognized for an object other than the recognized stationary obstacle. Since it recognizes whether or not it is the person using it, it is possible to improve the accuracy and speed of recognition,
It is possible to improve operability. Effect on composition (2): In addition to the effect of composition (1),
Since a stationary obstacle is recognized based on the detection signal detected after a lapse of a predetermined time after the power is turned on, which is considered not to be present near the device, it is possible to perform accurate recognition and determine whether or not the user is a user. There is an effect that the accuracy of recognition can be improved. Effect on composition (3): In addition to the effect of composition (1),
Recognize stationary obstacles at every predetermined timing after turning on the power,
By updating the record every time it is recognized, even if there is a change in the layout of stationary obstacles, the accurate layout of the stationary obstacles can be recognized correspondingly. The effect is that accurate recognition can always be performed. Effect on configuration (4): In addition to the effect of configuration (1),
It recognizes stationary obstacles when not in use, that is, when there is no person in front of the device, which enables more accurate recognition of stationary obstacles, and recognizes whether or not the person approaching the device is the person who uses it. The effect is to improve the accuracy of. Effect on configuration (5): In addition to the effect of configuration (1),
The timer is used to recognize stationary obstacles at times when no one is likely to be present near the device, such as at night, so more accurate recognition of stationary obstacles is possible, and it is used by people who approach the device. This has the effect of increasing the accuracy of recognizing whether a person or not. Effect on configuration (6): In addition to the effect of configuration (1),
By using a calendar, stationary obstacles can be recognized when there are no people near the device, such as on holidays, so more accurate recognition of stationary obstacles can be performed, and it is used by people approaching the device. This has the effect of increasing the accuracy of recognizing whether a person or not. Effect on composition (7): In addition to the effect of composition (1),
When a person is not near the device, the initial condition setting switch is operated to recognize a stationary obstacle, which allows more accurate recognition of a stationary obstacle. This has the effect of increasing the accuracy of recognition. Furthermore, when the layout near the device is changed, by operating the initial condition setting switch, it is possible to always recognize the stationary obstacle corresponding to the new layout, and always recognize whether or not the user is an accurate user. The effect is that you can.

[Brief description of drawings]

FIG. 1 is a block diagram for explaining a configuration concept when an automatic response system is applied to an OA device.

FIG. 2 is a diagram illustrating an example in which a sensor is mounted on the image forming apparatus.

FIG. 3 is a block diagram showing a basic configuration of a recognition device.

FIG. 4 is a diagram showing a relationship between an image forming apparatus and an obstacle.

FIG. 5 is a diagram schematically showing distance data between an image forming apparatus and an obstacle.

FIG. 6 is a diagram showing an example of environment information for the image forming apparatus.

FIG. 7 is a diagram showing environment information in FIG.

FIG. 8 is a diagram showing a change state of environmental information.

9 is a diagram showing distance data in FIG.

FIG. 10 is a diagram showing a result of taking a difference between environmental information and distance data in the case of FIG. 9;

FIG. 11 is a diagram showing a change state of environmental information.

FIG. 12 is a detailed view of a main part of FIG.

FIG. 13 is a diagram showing a change state of environmental information.

FIG. 14 is a detailed view of a main part of FIG.

FIG. 15 is a diagram showing a change state of environmental information.

FIG. 16 is a diagram showing a change state of environmental information.

FIG. 17 is a diagram showing the concept of movement trajectory information of a target object.

FIG. 18 is a diagram showing a change state of environmental information.

FIG. 19 is a diagram showing a change state of environmental information.

FIG. 20 is a diagram showing a change state of environmental information.

FIG. 21 is a diagram showing a change state of environmental information.

FIG. 22 is a diagram showing a change state of environment information.

FIG. 23 is a diagram for explaining recognition determination for a target object.

FIG. 24 is a diagram for explaining an example of recognition determination when a target object approaches an image forming apparatus.

FIG. 25 is a diagram conceptually showing parameters generated for each distance in the example of FIG. 24.

FIG. 26 is a diagram showing an example of a hierarchical neural network.

FIG. 27 is a diagram for explaining an example when a plurality of target objects are present within the measurement range of the distance sensor.

FIG. 28 shows whether the target person is a user of the image forming apparatus,
It is a figure showing an example of how to judge whether or not.

[Explanation of symbols]

1 ... OA device, 2 ... Sensor unit, 3 ... Recognition determination device, 4 ...
Service providing device, 5 ... Image forming device, 6 ... Distance sensor, 7 ... Sensor drive unit, 8 ... Parameter extraction unit, 9 ... Recognition determination unit, 10 ... Post-processing unit, 11 ... Control unit, 12 ... Input / output management unit , 13 ... Storage device, 14 ... Data line, 15 ... Control line, 16 ... External I / F, 17 ... Obstacle, 18 ... Target object, 21 ... Hierarchical neural network, 22 ... Input layer, 23 ... Intermediate layer , 24 ... Output layer.

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Koji Ichinomiya 1-3-6 Nakamagome, Ota-ku, Tokyo Inside Ricoh Co., Ltd. (72) Inventor Eiichi Sasaki 1-3-6 Nakamagome, Ota-ku, Tokyo In Ricoh Co., Ltd. (72) Inventor Kazuhisa Otsubo 1-3-6 Nakamagome, Ota-ku, Tokyo Inside Ricoh Co., Ltd.

Claims (1)

[Claims] 1. A detection means for detecting a distance from a device to an object in the vicinity of the device, and at least detecting whether or not the detected object is a person who uses the device, based on a detection signal from the detection means. In an image forming apparatus having a recognition means for recognizing a generated object at a timing before reaching the apparatus, and a control means for controlling the operation of the apparatus according to a recognition result of the recognition means, An image forming apparatus, which recognizes a stationary obstacle based on a detection signal from a detection means, and recognizes whether or not a person who uses the apparatus is aware of an object other than the recognized stationary obstacle.