WO2012008288A1

WO2012008288A1 - Output controller

Info

Publication number: WO2012008288A1
Application number: PCT/JP2011/064622
Authority: WO
Inventors: 圭介淺利; 石井　洋平; 本郷　仁志; 長輝楊
Original assignee: 三洋電機株式会社
Priority date: 2010-07-13
Filing date: 2011-06-27
Publication date: 2012-01-19
Also published as: JP2012021669A

Abstract

Air conditioners (D_1 to D_6) are installed in the ceiling (HV1) of a room (RM1) and generate output toward the room (RM1). A plurality of sub-areas corresponding to each of the air conditioners (D_1 to D_6) are allocated in the room (RM1). A CPU detects one or two or more representative points corresponding to one or two or more people in the room (RM1), measures the distance from each of the one or two or more detected representative points to the boundary of a sub-area, and controls the output operations of the air conditioners (D_1 to D_6) in accordance with the measurement results.

Description

Output control device

The present invention relates to an output control device, and more particularly to an output control device that controls the output of the device by measuring the degree of congestion of a specific object.

An example of this type of device is disclosed in Patent Document 1. According to this background art, the camera is installed in an elevator hall or a car. The image output from the camera is divided into a plurality of blocks, and the occupancy rate of waiting customers or passengers is calculated for each block. The number of waiting customers or passengers is determined based on the calculated occupancy rate, and the determination result is transmitted to the elevator control device.

JP-A-6-92563

However, in the background art, the coordinate system that defines the imaging surface of the camera does not always match the coordinate system that defines the plane on which the waiting customer or passenger exists. Here, if the two coordinate systems are different, the calculation accuracy of the occupancy rate, and hence the accuracy of the elevator control, is lowered.

Therefore, a main object of the present invention is to provide an output control device capable of improving the accuracy of adaptive output control.

The motion detection device according to the present invention comprises: definition means for defining a plurality of subspaces respectively corresponding to a plurality of devices that generate output toward the space; one or more specific objects present in the space Detecting means for detecting one or more representative points respectively corresponding to each of the above; measuring the distance from each of the one or more representative points detected by the detecting means to the boundaries of a plurality of small spaces defined by the defining means And measuring means for controlling the output operations of the plurality of devices based on the measurement results of the measuring means.

Preferably, a camera for capturing a space is further provided, and the detection unit searches for one or more specific object images from the object scene image output from the camera, and the specific object image found by the search unit. A determination means for determining a representative point is included.

More preferably, the space is defined according to the XYZ coordinate system, and the camera has an imaging surface defined according to the UV coordinate system.

Preferably, the control unit assigns a different weighting factor to each of the plurality of small spaces according to the magnitude of the distance measured by the measuring unit, and the congestion of the specific object based on the weighting factor assigned by the assigning unit. Calculation means for calculating the degree for each small space, and adjustment means for adjusting the outputs of the plurality of devices based on the degree of congestion calculated by the calculation means.

More preferably, the total sum of the weighting coefficients assigned by the assigning means corresponding to each of the one or more representative points is common among the one or more representative points.

Preferably, the definition means reproduces a reference image representing a bird's-eye view of a plane defining the space, and accepting means for accepting a designation operation for designating a plurality of areas in contact with each other on the reference image reproduced by the reproduction means And definition processing means for defining a plurality of small spaces corresponding to the plurality of areas designated by the designation operation.

An output control device according to the present invention comprises: an object field image representing a space having an imaging surface defined along a UV coordinate system and having a plane defined along an XY coordinate system; A search means for searching for an image representing a specific object existing in the space from the object scene image output from the camera; a calibration parameter indicating a correspondence relationship between the UV coordinate system and the XY coordinate system and the search means Calculating means for calculating XY coordinates of a specific object with reference to an image; detecting a positional relationship between a plurality of devices generating an output toward a space and the specific object with reference to XY coordinates calculated by the calculating means Detecting means; and control means for controlling output operations of the plurality of devices with reference to the positional relationship detected by the detecting means.

The congestion degree measuring apparatus according to the present invention comprises the following: defining means for defining a plurality of small spaces forming a space; one or more representatives corresponding to one or more specific objects existing in the space, respectively. Detecting means for detecting points; measuring means for measuring the distance from each of one or more representative points detected by the detecting means to boundaries of a plurality of small spaces defined by the defining means; and defined by the defining means Calculating means for calculating the degree of congestion of the specific object in each of the plurality of small spaces based on the measurement result of the measuring means; and output means for outputting congestion degree information indicating the degree of congestion calculated by the calculating means.

An output control method according to the present invention is an output control method executed by a processor of an output control device, and includes the following: a plurality of small spaces respectively corresponding to a plurality of devices that generate output toward a space Defining step; detecting step of detecting one or more representative points respectively corresponding to one or more specific objects existing in space; defining from each of one or more representative points detected by the detecting step A measuring step for measuring distances to boundaries of the plurality of small spaces defined by the steps; and a control step for controlling output operations of the plurality of devices based on the measurement results of the measuring steps.

The output control method according to the present invention is an output control including a camera having an imaging surface defined along a UV coordinate system and outputting a scene image representing a space having a plane defined along an XY coordinate system. An output control method executed by a processor of the apparatus, comprising: a search step for searching an image representing a specific object existing in space from an object scene image output from a camera; UV coordinate system and XY A calculation step of calculating an XY coordinate of the specific object with reference to a calibration parameter indicating a correspondence relationship with the coordinate system and an image found by the search step; a plurality of devices that generate an output toward the space and the specific object A detection step for detecting the positional relationship with reference to the XY coordinates calculated by the calculating step; and a plurality of devices with reference to the positional relationship detected by the detection step. Control step of controlling the force action.

A congestion degree measuring method according to the present invention is a congestion degree measuring method executed by a processor of a congestion degree measuring apparatus, and includes the following steps: a defining step for defining a plurality of small spaces forming a space; A detecting step for detecting one or more representative points respectively corresponding to one or more specific objects to be detected; a plurality of small points defined by the defining step from each of the one or more representative points detected by the detecting step A measurement step for measuring the distance to the boundary of the space; a calculation step for calculating the degree of congestion of the specific object in each of the plurality of small spaces defined by the definition step; and a calculation step for calculating the degree of congestion based on the measurement result of the measurement step; An output step for outputting congestion degree information indicating the degree of congestion.

An output control system according to the present invention is an output control system including a plurality of devices that generate output toward a space and a control device that controls the plurality of devices, and the control device includes the following: a plurality of devices Defining means for defining a plurality of small spaces respectively corresponding to the above; detecting means for detecting one or more representative points respectively corresponding to one or more specific objects existing in the space; 1 or 2 detected by the detecting means Measuring means for measuring the distance from each of the two or more representative points to the boundaries of the plurality of small spaces defined by the defining means; and output control means for controlling the output operation of the plurality of devices based on the measurement results of the measuring means .

An output control system according to the present invention is directed to a camera that outputs an object scene image that represents a space having an imaging surface defined along a UV coordinate system and a plane defined along an XY coordinate system. Output control system comprising a plurality of devices that generate output and a control device that controls the plurality of devices based on the object scene image output from the camera, the control device comprising: Search means for searching for an image representing a specific object existing in the space from the output object scene image; referring to a calibration parameter indicating the correspondence between the UV coordinate system and the XY coordinate system and the image found by the search means Calculating means for calculating the XY coordinates of the specific object; detecting means for detecting the positional relationship between the plurality of devices and the specific object with reference to the XY coordinates calculated by the calculating means; and detecting by the detecting means Output control means for controlling the output operation of a plurality of devices with reference to the position relationship.

According to the present invention, the plurality of small spaces respectively correspond to the plurality of devices that generate output toward the space. The outputs of the plurality of devices are controlled with reference to the distances from the boundaries of the plurality of small spaces to the representative points of the specific objects existing in the space. As a result, the accuracy of adaptive control for the space can be improved.

According to the present invention, since the imaging surface of the camera is defined along the UV coordinate system, the position of the image representing the specific object existing in the space is also indicated by the UV coordinates. However, the UV coordinates are converted into XY coordinates (XY coordinate system: a coordinate system that defines a plane that divides space) with reference to the calibration parameters, and the positional relationship between a plurality of devices and specific objects is converted XY coordinates. Detected by reference. By controlling the output operations of the plurality of devices with reference to the positional relationship thus detected, adaptive output control with respect to the movement of the specific object can be realized with high accuracy.

According to the present invention, one or more specific objects exist in a space formed by a plurality of small spaces. The degree of congestion of the specific object in each small space is calculated based on the distance from the representative point of the specific object to the boundary of the small space. Thereby, the evaluation performance of the congestion degree is improved.

The above object, other objects, features, and advantages of the present invention will become more apparent from the following detailed description of embodiments with reference to the drawings.

(A) is a block diagram showing a basic configuration of one embodiment of the present invention, and (B) is a block diagram showing a basic configuration of another embodiment of the present invention. It is a block diagram which shows the structure of one Example of this invention. It is an illustration figure which shows an example of the installation state of the camera applied to the FIG. 2 Example. It is an illustration figure which shows an example of the camera image displayed on the monitor of FIG. 2 Example. It is an illustration figure which shows an example of the map image displayed on the monitor of FIG. 2 Example. It is an illustration figure which shows an example of a structure of the area register applied to the FIG. 2 Example. FIG. 3 is an illustrative view showing one example of a configuration of a representative point register applied to the embodiment in FIG. 2; It is an illustration figure which shows an example of a structure of the weighting amount register | resistor applied to the FIG. 2 Example. (A) is an illustration figure which shows an example of the allocation state of the divided area on a map image, (B) is an illustration figure which shows an example of the allocation state of the measurement area on a camera image. (A) is an illustration figure which shows an example of a camera image, (B) is an illustration figure which shows an example of a corresponding bird's-eye view image. (A) is an illustrative view showing a part of a weighting amount calculating operation, (B) is an illustrative view showing another part of the weighting amount calculating operation, and (C) is a weighting amount calculating operation. It is an illustration figure which shows a part of others. It is a flowchart which shows a part of operation | movement of CPU applied to the FIG. 2 Example. It is a flowchart which shows a part of other operation | movement of CPU applied to the FIG. 2 Example. FIG. 11 is a flowchart showing still another portion of behavior of the CPU applied to the embodiment in FIG. 2; FIG. 10 is a flowchart showing yet another portion of behavior of the CPU applied to the embodiment in FIG. 2; It is a flowchart which shows a part of other operation | movement of CPU applied to the FIG. 2 Example. FIG. 11 is a flowchart showing still another portion of behavior of the CPU applied to the embodiment in FIG. 2; It is a flowchart which shows a part of operation | movement of CPU applied to another Example. It is a flowchart which shows a part of operation | movement of CPU applied to another Example. It is an illustration figure which shows an example of the congestion degree information displayed on a monitor screen by the process shown in FIG. It is a flowchart which shows a part of operation | movement of CPU applied to another Example.

Referring to FIG. 1 (A), the output control device of one embodiment of the present invention is basically configured as follows. The defining means 1a defines a plurality of small spaces respectively corresponding to the plurality of

devices

5a, 5a,. The detection unit 2a detects one or more representative points corresponding to one or more specific objects existing in the space. The measuring means 3a measures the distance from each of one or more representative points detected by the detecting means 2a to the boundaries of a plurality of small spaces defined by the defining means. The control unit 4a controls the output operations of the plurality of devices based on the measurement result of the measurement unit 3a.

A plurality of small spaces respectively correspond to a plurality of

devices

5a, 5a,... That generate outputs toward the space. Further, the outputs of the plurality of

devices

5a, 5a,... Are controlled with reference to the distances from the boundaries of the plurality of small spaces to the representative points of specific objects existing in the space. As a result, the accuracy of adaptive control for the space can be improved.

Referring to FIG. 1 (B), the output control device of one embodiment of the present invention is basically configured as follows. The camera 1b has an imaging surface defined along the UV coordinate system, and outputs an object scene image representing a space having a plane defined along the XY coordinate system. The search means 2b searches for an image representing a specific object existing in the space from the object scene image output from the camera 1b. The calculation unit 3b calculates the XY coordinates of the specific object with reference to the calibration parameter indicating the correspondence between the UV coordinate system and the XY coordinate system and the image found by the search unit 2b. The detecting means 4b detects the positional relationship between the specific objects and the plurality of

devices

6b, 6b,... That generate outputs toward the space with reference to the XY coordinates calculated by the calculating means 3b. The control means 5b refers to the positional relationship detected by the detection means 4b and controls the output operations of the plurality of

devices

6b, 6b,.

Since the imaging surface of the camera 1b is defined along the UV coordinate system, the position of the image representing the specific object existing in the space is also indicated by the UV coordinates. However, the UV coordinates are converted into XY coordinates (XY coordinate system: a coordinate system that defines a plane partitioning the space) with reference to the calibration parameters, and the positional relationship between the plurality of

devices

6b, 6b,. It is detected with reference to the generated XY coordinates. By controlling the output operation of the plurality of

devices

6b, 6b,... With reference to the positional relationship thus detected, adaptive output control with respect to the movement of the specific object can be realized with high accuracy.

Referring to FIG. 1C, the defining means 1c defines a plurality of small spaces forming a space. The detection unit 2c detects one or more representative points corresponding to one or more specific objects existing in the space. The measuring means 3c measures the distance from each of one or more representative points detected by the detecting means 2c to the boundaries of a plurality of small spaces defined by the defining means 1c. The calculating unit 4c calculates the congestion degree of the specific object in each of the plurality of small spaces defined by the defining unit 1c based on the measurement result of the measuring unit 3c. The output unit 5c outputs congestion level information indicating the congestion level calculated by the calculation unit 4c.

Thus, one or more specific objects exist in a space formed by a plurality of small spaces. The degree of congestion of the specific object in each small space is calculated based on the distance from the representative point of the specific object to the boundary of the small space. Thereby, the evaluation performance of the congestion degree is improved.

Referring to FIG. 2, the air conditioning control device 10 of this embodiment includes a camera 12 that repeatedly outputs image data representing an object scene (three-dimensional space) captured on the imaging surface. The image data output from the camera 12 is captured by the image processing circuit 14 and subjected to camera image display processing by the CPU 14p. As a result, an image representing the object scene, that is, a camera image is displayed on the monitor 16.

Referring to FIG. 3, room RM1 is partitioned by floor surface FL1 and ceiling HV1 and four wall surfaces WL1 to WL4. The camera 12 is provided above the wall surface WL1, and captures the internal space of the room RM1 from obliquely above. Therefore, the camera image is displayed on the monitor screen as shown in FIG. As shown in FIGS. 3 and 4, the internal space of the room RM1 is defined by the X, Y, and Z axes that are orthogonal to each other, and the imaging surface of the camera 12 is defined by the U and V axes that are orthogonal to each other.

The air conditioners D_1 to D_6 are installed at a predetermined distance on the ceiling HV1. Each of the air conditioners D_1 to D_6 outputs air having a specified temperature with a specified air volume, and the temperature of the room RM1 is adjusted by the air thus output.

Note that a system constituted by the air conditioner 10 shown in FIG. 2 and the air conditioners D_1 to D_6 shown in FIG. 3 is defined as an “air conditioner control system”.

When the area setting mode is selected by operating the input device 18, the following processing is executed by the CPU 14p.

First, the map image shown in FIG. The map image corresponds to an image that schematically represents a bird's-eye view of the plane FL1. In the map image, marks M_1 to M_6 respectively representing air conditioners D_1 to D_6 are displayed corresponding to the positions of the air conditioners D_1 to D_6.

When the display of the map image is completed, the variable K is set to “1”. When the mark M_K is clicked by the mouse pointer provided in the input device 18, coordinates indicating the clicked position, that is, click coordinates are calculated. The calculated click coordinates are described in the area register 14r1 shown in FIG. 6 corresponding to the variable K, and the variable K is incremented thereafter. The click operation is accepted a total of six times corresponding to the marks M_1 to M_6, and thereby six click coordinates respectively corresponding to the marks M_1 to M_6 are set in the area register 14r1.

The map image is divided in the manner shown in FIG. 9A with the six click coordinates thus set as a reference. The boundary lines BL_1 to BL_3 are drawn on the map image so as to surround the marks M_1 to M_6. As a result, the divided areas MP_1 to MP_6 are allocated around the marks M_1 to M_6, and the internal space of the room RM1 is divided into a plurality of small spaces respectively corresponding to the divided areas MP_1 to MP_6. In the area register 14r1, a plurality of XY coordinates defining the divided area MP_K (K: 1 to 6) are described.

Subsequently, each of a plurality of XY coordinates that define the divided area MP_K is converted into UV coordinates according to Equation 1.

The calibration parameters P11 to P33 shown in Equation 1 correspond to a matrix for performing planar projective transformation between the XY coordinate system that defines the plane FL1 and the imaging plane of the camera 12, that is, the UV coordinate system that defines the camera image. Therefore, by applying the desired XY coordinates to Equation 1, the corresponding UV coordinates on the camera image are calculated. The plurality of UV coordinates thus converted are described in the area register 14r1 corresponding to the plurality of XY coordinates of the conversion source. The measurement area DT_K corresponding to the divided area MP_K is defined on the camera image in the manner shown in FIG. 9B.

When the congestion degree measurement mode is selected by operating the input device 18, the following processing is executed by the CPU 14p every time the measurement period arrives.

First, a person image is searched from a camera image by pattern matching. When one or more person images are found, the variable L is set to each of “1” to “Lmax” (Lmax: total number of person images found), and one or more person images found are found. The representative point of the L-th person image is determined as “RP_L”. The determined XY coordinates of the representative point RP_L are described in the representative point register 14r2 shown in FIG.

When the persons H1 to H3 exist in the room RM1 as shown in FIG. 10A, the representative point RP_1 is determined on the image representing the person H1, the representative point RP_2 is determined on the image representing the person H2, and A representative point RP_3 is determined on the image representing the person H3. The XY coordinates of the representative points RP_1 to RP_3 are distributed on the bird's-eye view image in the manner shown in FIG. 10B, and are described in the representative point register 14r2 corresponding to L = 1 to 3.

The variable L is again set to each of “1” to “Lmax”, and the divided area to which the Lth representative point belongs among the divided areas MP_1 to MP_6 is detected as the representative area. 10A to 10B, the divided area MP_2 is a representative area corresponding to the representative point RP_1, the divided area MP_5 is a representative area corresponding to the representative point RP_2, and the divided area MP_6 is a representative. This is a representative area corresponding to the point RP_3.

Subsequently, the variable M is set to each of “1” to “3”, and the distance from the representative point RP_L to the boundary line BL_M is measured. If the calculated distance is less than the threshold value TH, a divided area in contact with the representative area across the boundary line BL_M is detected as a peripheral area.

Referring to FIG. 11A, the distance from representative point RP_1 to boundary line BL_1 is less than threshold TH, and the distance from representative point RP_1 to each of boundary lines BL_2 and BL_3 is greater than or equal to threshold TH. Therefore, for the representative point RP_1, the divided area MP_5 is detected as a peripheral area.

Referring to FIG. 11B, the distance from representative point RP_2 to each of boundary lines BL_1 and BL_3 is less than threshold TH, and the distance from representative point RP_1 to boundary line BL_2 is greater than or equal to threshold TH. Therefore, for the representative point RP_2, the divided areas MP_2 and MP_6 are detected as peripheral areas.

Referring to FIG. 11C, the distance from representative point RP_3 to each of boundary lines BL_1 to BL_3 is equal to or greater than threshold value TH. Therefore, the peripheral area is not detected for the representative point RP_3.

If the total number of representative areas and surrounding areas is “N”, the weighting amount “1.0 / N” is distributed to the representative area and surrounding areas. Specifically, the weighting amount is described in the weighting amount register 14r3 shown in FIG. 8 corresponding to the representative area and the peripheral area. Therefore, if no peripheral area is detected, a weighting amount of “1.0” is assigned to the representative area. On the other hand, if even one peripheral area is detected, a weighting amount of less than “1.0” is evenly distributed to the representative area and the peripheral area.

In the example of FIGS. 11A to 11C, a weighting amount of “0.5” is assigned to each of the divided areas MP_2 and MP_5 with respect to the person H1, and a weighting amount of “0.33” is assigned to the person H2. Assigned to each of the divided areas MP_2, MP_5, and MP_6, and a weighting amount of “1.0” is assigned to the divided area MP_6 with respect to the person H3.

When the weighting amount is thus determined, the variable K is set to each of “1” to “6”, and the congestion degree CR_K is calculated. The degree of congestion CR_K corresponds to the sum of weighting amounts assigned to the divided areas MP_K. Therefore, in the example of FIGS. 11A to 11C, the congestion levels CR_2 and CR_5 indicate “0.83”, the congestion level CR_6 indicates “1.33”, and the congestion levels CR_1 and CR_3. And CR_4 indicates “0.0”.

The outputs of the air conditioners D1 to D6 are controlled based on the congestion levels CR_1 to CR_6 thus calculated. Specifically, the output of the air conditioner corresponding to the divided area with a high degree of congestion is increased, and the output of the air conditioner corresponding to the divided area with a low degree of congestion is reduced.

The CPU 14p executes a plurality of tasks including a main task shown in FIG. 12, an area setting task shown in FIGS. 13 to 14, and a congestion degree measuring task shown in FIGS. Note that control programs corresponding to these tasks are stored in the recording medium 20.

Referring to FIG. 12, camera image display processing is executed in step S1. As a result, a camera image is displayed on the monitor 16. In step S3, it is determined whether or not the current operation mode is the area setting mode, and in step S7, it is determined whether or not the current operation mode is the congestion degree measurement mode.

If “YES” in the step S3, an area setting task is activated in a step S5, and thereafter, the process proceeds to a step S15. If “YES” in the step S7, it is determined whether or not the divided areas MP_1 to MP_6 have been set in a step S9. If the determination result is YES, the congestion degree measurement task is started in step S11 and then the process proceeds to step S15. If the determination result is NO, the process directly proceeds to step S15. If both step S3 and S7 are NO, another process is executed in step S13, and then the process proceeds to step S15.

In step S15, it is repeatedly determined whether or not a mode change operation has been performed. When the determination result is updated from NO to YES, the activated task is terminated in step S17, and thereafter, the process returns to step S3.

Referring to FIG. 13, the map image is displayed on monitor 16 in step S21, and variable K is set to “1” in step S23. In step S25, it is determined whether or not a click operation for designating an area has been performed. If the determination result is updated from NO to YES, click coordinates are calculated in step S27. The calculated coordinates are described in the area register 14r1 corresponding to the variable K. In step S29, it is determined whether or not the variable K has reached “6”. If the determination result is NO, the variable K is incremented in step S31 and then the process returns to step S25. Proceed to S33.

In step S33, the map image is divided with reference to the click coordinates. As a result, six divided areas MP_1 to MP_6 are allocated on the map image. In step S35, boundary lines BL_1 to BL_3 partitioning the divided images MP_1 to MP_6 are drawn on the map image.

In step S37, the variable K is set to “1”, and in step S39, a plurality of XY coordinates defining the divided area MP_K are calculated. The calculated XY coordinates are described in the area register 14r1 corresponding to the variable K. In step S41, each of the plurality of XY coordinates that define the divided area MP_K is converted into UV coordinates according to Equation 1. The converted UV coordinates are described in the area register 14r1 corresponding to the variable K, whereby the measurement area DT_K corresponding to the divided area MP_K is assigned to the camera image.

In step S43, it is determined whether or not the variable K has reached “6”. If the determination result is NO, the variable K is incremented in step S45 and then the process returns to step S39. If the determination result is YES, the process ends.

Referring to FIG. 15, in step S51, it is determined whether or not the measurement cycle has arrived. When the determination result is updated from NO to YES, the process proceeds to step S53, and a person image is searched from the camera image by pattern matching. In step S55, it is determined whether one or more person images have been found. If the determination result is NO, the process returns to step S51, whereas if the determination result is YES, the process proceeds to step S57.

In step S57, the variable L is set to “1”. In step S59, the representative point of the Lth person image among the one or more found person images is determined as “RP_L”, and is determined in step S61. The XY coordinates of the representative point RP_L are calculated. The calculated XY coordinates are described in the representative point register 14r2 corresponding to the variable L. In step S63, it is determined whether or not the variable L has reached the maximum value Lmax (= total number of discovered human images). If the determination result is NO, the variable L is incremented in step S65, and the process returns to step S59. On the other hand, if a determination result is YES, it will progress to Step S67.

In step S67, the variable L is set to “1” again. In step S69, the divided area to which the representative point RP_L belongs among the divided areas MP_1 to MP_6 is detected as a representative area. In step S71, the variables M and N are set to “1”, in step S73, the distance from the representative point RP_L to the boundary line BL_M is measured, and in step S75, it is determined whether or not the calculated distance is less than the threshold value TH. Determine.

If the determination result is YES, the process proceeds to steps S81 through S77 to S79, and if the determination result is NO, the process proceeds to step S81 as it is. In step S77, a divided area in contact with the representative area across the boundary line BL_M is detected as a peripheral area. In step S79, the variable N is incremented.

In step S81, it is determined whether or not the variable M has reached the maximum value Mmax (= total number of found boundary lines). If the determination result is NO, the variable M is incremented in step S83, and the process returns to step S73. On the other hand, if a determination result is YES, it will progress to Step S85.

In step S85, the weighting amount (= 1.0) is divided by the value of the variable N, and the division value obtained thereby is distributed to the representative area and the peripheral area. Therefore, if no peripheral area is detected, a weighting amount of “1.0” is described in the weighting amount register 14r3 corresponding to the representative area. On the other hand, if even one peripheral area is detected, a weighting amount of “1.0 / N” is described in the weighting amount register 14r3 corresponding to the representative area and the peripheral area.

In step S87, it is determined whether or not the variable L has reached the maximum value Lmax. If the determination result is NO, the variable L is incremented in step S89 and then the process returns to step S69, while if the determination result is YES. Proceed to step S91. In step S91, the variable K is set to “1”, and in step S93, the degree of congestion CR_K is calculated. The degree of congestion CR_K corresponds to the sum of weighting amounts assigned to the divided areas MP_K.

In step S95, it is determined whether or not the variable K has reached "6". If the determination result is NO, the variable K is incremented in step S97 and the process returns to step S93. If the determination result is YES, step S95 is performed. Proceed to S99. In step S99, the outputs of the air conditioners D1 to D6 are controlled with reference to the congestion levels CR_1 to CR_6 calculated in step S93. Specifically, the output of the air conditioner corresponding to the divided area with a high degree of congestion is strengthened, and the output of the air conditioner corresponding to the divided area with a low degree of congestion is weakened.

As can be seen from the above description, the CPU 14p defines a plurality of divided areas MP_1 to MP_6 respectively corresponding to the plurality of air conditioners D_1 to D_6 that generate outputs toward the room RM1 (S21 to S45), and the room RM1. One or more representative points respectively corresponding to one or more existing persons are detected (S53, S57 to S65). The CPU 14p also measures the distance from each of the detected one or more representative points to the boundaries of the divided areas MP_1 to MP_6 (S67 to S73, S81 to S83, S87 to S89), and performs air conditioning based on the measurement result. The output operation of the devices D_1 to D_6 is controlled (S75 to S79, S85, S91 to S99).

The divided areas MP_1 to MP_6 respectively correspond to the air conditioners D_1 to D_6 that generate outputs toward the room RM1. The outputs of the air conditioners D_1 to D_6 are controlled with reference to the distance from the boundary between the divided areas MP_1 to MP_6 to the representative point of the person existing in the room RM1. Thereby, the accuracy of adaptive control for the room RM1 can be improved.

Further, when it is assumed that the operation of the air conditioners D_1 to D_6 is stopped and the power consumption is suppressed when the person is absent, the timing when the air conditioners D_1 to D_6 are not intended if the presence / absence determination of the person is wrong. This stops the comfort of the person existing in the room RM1. In this embodiment, since the degree of congestion is measured by searching for a person in the manner described above, it is possible to maintain the person's presence / absence discrimination accuracy and thus the comfort of the person present in the room RM1.

In this embodiment, in calculating the congestion levels CR_1 to CR_6, the distance from the representative point of the person image to each of the boundary lines BL_1 to BL_3 is measured. However, the degree of congestion CR_1 to CR_6 may be calculated by measuring the distance from the representative point of the person image to each of the air conditioners D_1 to D_6. In this case, preferably, steps S101 to S117 shown in FIG. 18 are executed instead of steps S69 to S85 shown in FIG.

In step S101, as in step S69, the divided area to which the representative point RP_L belongs is detected as a representative area. In step S103, the variable K is set to “1”, and in step S105, the distance from the representative point RP_L to the air conditioner D_K is measured as “DS_K”. In step S107, it is determined whether or not the variable K has reached “6”. If the determination result is NO, the variable K is incremented in step S109 and then the process returns to step S105. Proceed to S111. The positional relationship between the Lth person and the air conditioners D_1 to D_6 is clarified by the distances DS_1 to DS_6 thus measured.

In step S111, the variable K is set to “1” again. In step S113, the weighting amount W_K corresponding to the divided area MP_K is calculated according to Equation 2.
[Equation 2]
W_K = 1−f (D_K) / Σf (D_K)
However, f (D_K) = a_K * DS_K + b_K

In Equation 2, “a_K” and “b_K” are variables depending on the current output of the air conditioner D_K and the indoor environment. The function value f (D_K) is defined by the variables a_K and b_K and the distance DS_K. The weighting amount W_K is derived by subtracting from “1” the ratio of the function value f (D_K) to the sum of the function values f (D_1) to f (D_6) respectively corresponding to the air conditioners D_1 to D_6. The variables a_K and b_K are adjusted so that the sum of the weighting amounts W_1 to W_6 is “1.0”.

In step S115, it is determined whether or not the variable K has reached “6”. If the determination result is NO, the variable K is incremented in step S117 and then the process returns to step S113. Proceed to S87.

In this embodiment, the coordinates of the marks M_1 to M_6 are designated by clicking the mouse pointer. However, instead of this, the coordinate values of the marks M_1 to M_6 may be directly specified.

In this embodiment, it is assumed that the output of the air conditioner is adaptively controlled. However, instead of the output of the air conditioner or together with the output of the air conditioner, the output (that is, brightness) of the lighting device is adaptive. You may make it control to.

Furthermore, in this embodiment, planar projective transformation with reference to Equation 1 is assumed, but perspective projective transformation may be performed instead.

Further, in this embodiment, an image schematically representing a state in which the floor surface FL1 is bird's-eye view is adopted as the map image. However, the map image may be generated by performing bird's-eye conversion with reference to Equation 1 described above on the camera image.

Furthermore, in this embodiment, the outputs of the air conditioners D1 to D6 are controlled with reference to the congestion levels CR_1 to CR_6 calculated in step S93. However, instead of controlling the air conditioners D1 to D6 or along with the controls of the air conditioners D1 to D6, a process of displaying the congestion degree information on the monitor 16 may be executed. In this case, the process shown in FIG. 17 is partially corrected as shown in FIG.

Referring to FIG. 19, when the determination result in step S95 is updated from NO to YES, the current time is detected in step S121. In step S123, FIG. 20 shows the congestion degree information including the number of person images discovered by the search process in step S53, the congestion levels CR_1 to CR_6 calculated in step S93, and the current time detected in step S121. It is displayed on the monitor 16 in a manner. When the process of step S123 is completed, the process proceeds to step S99 or returns to step S51.

When the process of step S99 shown in FIG. 17 is omitted, the name of the device is changed from “air conditioning control device” to “congestion degree measuring device”. In the congestion level information shown in FIG. 20, the congestion level may be expressed as a percentage.

In this embodiment, one or more person images are searched from the camera image by pattern matching, and representative points are determined on each of the found person images (steps S53 to S59 in FIG. 15). reference). However, one or more motion images may be detected on the camera image, and the representative point may be determined on each detected motion image. In this case, the process shown in FIG. 15 is partially corrected as shown in FIG.

Referring to FIG. 21, when the determination result in step S51 is updated from NO to YES, the process proceeds to step S131, and one or more motion images are searched on the camera image. Specifically, a plurality of pixels indicating motion are detected by paying attention to an inter-frame difference, and the detected plurality of pixels are divided into successive pixel clusters. One segmented block corresponds to one motion image. An identification number starting from “1” is assigned to each motion image detected in this way. In step S55, it is determined whether or not at least one moving image has been found. If the determination result is NO, the process returns to step S51. If the determination result is YES, the variable L is set to “1” in step S57. . In the subsequent step S133, the representative point of the Lth motion image is determined as “RP_L”, and then the process proceeds to step S61.

Further, in this embodiment, an area setting mode and a congestion degree measurement mode are prepared. However, if an area defined by another device is registered in the register 14r1, the area setting mode is not necessary and further input is performed. The device 18 is also unnecessary.

Although the present invention has been described and illustrated in detail, it is clear that it has been used merely as an illustration and example and should not be construed as limiting, and the spirit and scope of the present invention are attached Limited only by the wording of the claims.

DESCRIPTION OF SYMBOLS 10 ... Air-conditioning control apparatus 12 ... Camera 14 ... Image processing circuit 14p ... CPU
16 ... monitor 18 ... input device

Claims

An output control device comprising:
Defining means for defining a plurality of small spaces respectively corresponding to a plurality of devices that generate output toward the space;
Detecting means for detecting one or more representative points respectively corresponding to one or more specific objects existing in the space;
Measuring means for measuring a distance from each of one or more representative points detected by the detecting means to boundaries of a plurality of small spaces defined by the defining means; and based on a measurement result of the measuring means, Control means for controlling output operations of a plurality of devices.
An output control device according to claim 1, further comprising a camera that captures the space,
The detecting means searches for one or more specific object images from the object scene image output from the camera, and determines the representative point on the specific object image found by the searching means. Including means.
An output control device according to claim 2, wherein the space is defined according to an XYZ coordinate system,
The camera has an imaging surface defined according to a UV coordinate system.
An output control device according to claim 1, wherein the control means assigns a weighting coefficient that differs according to the distance measured by the measurement means to each of the plurality of small spaces, the assignment means Calculating means for calculating the degree of congestion of the specific object for each small space on the basis of the weighting coefficient assigned by, and adjusting means for adjusting the outputs of the plurality of devices based on the degree of congestion calculated by the calculating means. Including.
The output control device according to claim 4, wherein the sum of the weighting coefficients assigned by the assigning means corresponding to each of the one or more representative points is common among the one or more representative points. .
The output control device according to claim 1, wherein the definition unit reproduces a reference image representing a state in which a plane defining the space is viewed from above, a designation operation for designating a plurality of areas in contact with each other. Receiving means for receiving the reference image reproduced by the means, and definition processing means for defining the plurality of small spaces corresponding to the plurality of areas designated by the designation operation.
An output control device comprising:
A camera having an imaging surface defined along the UV coordinate system and outputting a scene image representing a space having a plane defined along the XY coordinate system;
Search means for searching for an image representing a specific object existing in the space from an object scene image output from the camera;
Calculating means for calculating XY coordinates of the specific object with reference to a calibration parameter indicating a correspondence relationship between the UV coordinate system and the XY coordinate system and an image found by the search means;
Detecting means for detecting a positional relationship between the plurality of devices generating the output toward the space and the specific object with reference to XY coordinates calculated by the calculating means; and a positional relationship detected by the detecting means Control means for controlling an output operation of the plurality of devices with reference to.
Congestion level measuring device comprising:
Defining means for defining a plurality of small spaces forming the space;
Detecting means for detecting one or more representative points respectively corresponding to one or more specific objects existing in the space;
Measuring means for measuring a distance from each of one or more representative points detected by the detecting means to boundaries of a plurality of small spaces defined by the defining means;
Calculation means for calculating the degree of congestion of the specific object in each of the plurality of small spaces defined by the definition means; and congestion degree information indicating the degree of congestion calculated by the calculation means; Output means for outputting.
An output control method executed by a processor of an output control device, comprising:
A definition step for defining a plurality of small spaces respectively corresponding to a plurality of devices that generate output toward the space;
A detection step of detecting one or more representative points respectively corresponding to one or more specific objects existing in the space;
A measuring step of measuring a distance from each of one or more representative points detected by the detecting step to boundaries of a plurality of small spaces defined by the defining step; and based on a measurement result of the measuring step, A control step for controlling output operations of a plurality of devices.
Output executed by a processor of an output control device comprising a camera having an imaging surface defined along a UV coordinate system and outputting a scene image representing a space having a plane defined along an XY coordinate system A control method comprising:
A search step of searching for an image representing a specific object existing in the space from an object scene image output from the camera;
A calculation step of calculating an XY coordinate of the specific object with reference to a calibration parameter indicating a correspondence relationship between the UV coordinate system and the XY coordinate system and an image found by the search step;
Detecting a positional relationship between the specific object and a plurality of devices that generate outputs toward the space with reference to XY coordinates calculated by the calculating step; and a positional relationship detected by the detecting step A control step of controlling output operations of the plurality of devices with reference to
A congestion measurement method executed by a processor of a congestion measurement apparatus, comprising:
A definition step for defining a plurality of small spaces forming the space;
A detection step of detecting one or more representative points respectively corresponding to one or more specific objects existing in the space;
A measuring step of measuring a distance from each of the one or more representative points detected by the detecting step to boundaries of a plurality of small spaces defined by the defining step;
A calculation step of calculating a congestion degree of the specific object in each of a plurality of small spaces defined by the definition step based on a measurement result of the measurement step; and congestion degree information indicating the congestion degree calculated by the calculation step Output step to output.
An output control system comprising a plurality of devices for generating an output toward a space and a control device for controlling the plurality of devices, the control device comprising:
Defining means for defining a plurality of small spaces respectively corresponding to the plurality of devices;
Detecting means for detecting one or more representative points respectively corresponding to one or more specific objects existing in the space;
Measuring means for measuring a distance from each of one or more representative points detected by the detecting means to boundaries of a plurality of small spaces defined by the defining means; and based on a measurement result of the measuring means, Output control means for controlling output operations of a plurality of devices.
A camera having an imaging surface defined along a UV coordinate system, and outputting a scene image representing a space having a plane defined along an XY coordinate system; and a plurality of outputs generating output toward the space An output control system comprising an apparatus and a control device for controlling the plurality of devices based on an object scene image output from the camera, wherein the control device comprises:
Search means for searching for an image representing a specific object existing in the space from an object scene image output from the camera;
Calculating means for calculating XY coordinates of the specific object with reference to a calibration parameter indicating a correspondence relationship between the UV coordinate system and the XY coordinate system and an image found by the search means;
Detecting means for detecting a positional relationship between the plurality of devices and the specific object with reference to XY coordinates calculated by the calculating means; and referring to a positional relationship detected by the detecting means. Output control means for controlling the output operation.