Area setting device, area setting method, and area setting program

The area setting device improves the detection accuracy of light emitters in air conditioner indoor units by using air outlet detection to set a region of interest, addressing the challenges of camera orientation and position uncertainties in existing methods.

JP7584715B2Active Publication Date: 2024-11-15MITSUBISHI ELECTRIC CORP
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2024540599
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2022-09-05
Publication Date
2024-11-15
Estimated Expiration
2042-09-05

AI Technical Summary

Technical Problem

Existing methods for detecting light emitters in an air conditioner's indoor unit face challenges due to the difficulty in obtaining the position and orientation of the photographer or camera, leading to inaccurate detection of light emitting bodies.

Method used

An area setting device that includes an air outlet detection unit to detect air outlets from image data, setting a region of interest based on the detected air outlets, and using a machine learning model to accurately define the detection area for light emitters.

Benefits of technology

The device enables precise detection of light emitting bodies by narrowing the detection area, reducing false positives and enhancing the accuracy of identifying light emitters and their operation information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007584715000001
    Figure 0007584715000001
  • Figure 0007584715000002
    Figure 0007584715000002
  • Figure 0007584715000003
    Figure 0007584715000003
Patent Text Reader

Abstract

An image acquisition unit (21) acquires image data obtained by imaging an indoor unit of an air conditioner. A blowout port detection unit (22) provides the image data of the indoor unit acquired by the image acquisition unit (21) to an object detection model as an input, and detects a blowout port. A region setting unit (23) sets, from a detection region of the blowout port detected by the blowout port detection unit (22), a region of interest serving as an area for detecting an object to be detected, such as a light emitting body mounted on the indoor unit or an identification number displayed on the indoor unit.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to a detection technique for light-emitting bodies and the like in an indoor unit of an air conditioner. [Background technology]

[0002] The indoor unit of an air conditioner is equipped with an illuminant such as an LED. LED is an abbreviation for Light-Emitting Diode. By having a terminal such as a smartphone read the lighting or blinking of this illuminant, it is possible to transmit operation information of the air conditioner to the terminal. It is conceivable that the transmitted operation information can be used for maintenance of the air conditioner, for example.

[0003] Each of the multiple air outlets installed in the indoor unit of the air conditioner is assigned an identification number, which is displayed near each air outlet. By having a terminal such as a smartphone read this identification number, it is possible to operate the desired air outlet from the terminal.

[0004] As in these examples, it is effective to appropriately detect light-emitting bodies, etc. in the indoor unit of the air conditioner by the terminal. As a method of detecting light-emitting bodies, etc. by the terminal, a method of detecting light-emitting bodies, etc. from image data captured by an imaging device can be considered. However, in a method of detecting light-emitting bodies, etc. from image data, there is a possibility that an object having characteristics similar to a light-emitting body, etc., may be erroneously detected. Examples of objects having characteristics similar to a light-emitting body include the surface of a housing of an indoor unit illuminated by an illumination light, and the light-emitting body of a wireless device installed on a ceiling.

[0005] Patent Document 1 describes a technology for detecting traffic lights using an on-board camera. In Patent Document 1, the position and attitude of the vehicle and map information are used to set an area in which a traffic light is likely to appear within the image data obtained by the on-board camera. This aims to improve the accuracy of traffic light detection. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] International Publication No. 2017 / 009934 Summary of the Invention [Problem to be solved by the invention]

[0007] In Patent Document 1, by setting an area where a traffic light is likely to be captured, locations that have similar characteristics to a traffic light are eliminated, improving the accuracy of detecting the traffic light. However, when detecting a light-emitting object in an indoor unit of an air conditioner from image data, it is not easy to obtain the position and posture of the person taking the picture or the camera, and map information of the shooting location. Therefore, it is not realistic to use the technology described in Patent Document 1 to set an area where a light-emitting object or the like is likely to be captured. The present disclosure aims to enable highly accurate detection of light-emitting bodies and the like in an indoor unit of an air conditioner. [Means for solving the problem]

[0008] The area setting device according to the present disclosure comprises: an air outlet detection unit that detects an air outlet from image data obtained by capturing an image of an indoor unit of the air conditioner; an area setting unit that sets an attention area within a detection area of ​​the air outlet detected by the air outlet detection unit, the attention area being a range within which a detection target in the indoor unit is to be detected; Equipped with. Effect of the Invention

[0009] In the present disclosure, a region of interest is set from a detection region in which an air outlet of the indoor unit is detected, as a range within which a detection target in the indoor unit is detected. By setting the region of interest, it is possible to detect the detection target with high accuracy. In addition, the air outlet is larger in size and easier to detect than light-emitting bodies, etc. Therefore, it is relatively easy to set the attention surface area. [Brief description of the drawings]

[0010] [Figure 1] 1 is a configuration diagram of an area setting device 10 according to a first embodiment. [Diagram 2] FIG. 1 is an explanatory diagram of an indoor unit 50 of an air conditioner according to a first embodiment. [Diagram 3] 3 is a flowchart showing a process flow of the area setting device 10 according to the first embodiment. [Figure 4] FIG. 6 is an explanatory diagram of image data 61 according to the first embodiment. [Diagram 5] FIG. 4 is an explanatory diagram of a detection area 62 according to the first embodiment. [Figure 6] FIG. 4 is an explanatory diagram of a region setting process according to the first embodiment. [Figure 7] FIG. 4 is an explanatory diagram of a region setting process according to the first embodiment. [Figure 8] FIG. 4 is an explanatory diagram of a second method for setting a reference graphic 67 according to the first embodiment. [Figure 9] 6 is an explanatory diagram of a third method for setting a reference graphic 67 according to the first embodiment. FIG. [Figure 10] FIG. 13 is a configuration diagram of an area setting device 10 according to a first modified example. [Figure 11] FIG. 11 is a configuration diagram of an area setting device 10 according to a second embodiment. [Figure 12] 10 is a flowchart showing the flow of processing of the area setting device 10 according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Embodiment 1 ***Configuration Description*** The configuration of an area setting device 10 according to the first embodiment will be described with reference to FIG. The area setting device 10 is a computer. The area setting device 10 includes the following hardware components: a processor 11, a memory 12, a storage 13, and a communication interface 14. The processor 11 is connected to other hardware components via signal lines and controls the other hardware components.

[0012] The processor 11 is an IC that performs processing. IC is an abbreviation for Integrated Circuit. Specific examples of the processor 11 include a CPU, a DSP, and a GPU. CPU is an abbreviation for Central Processing Unit. DSP is an abbreviation for Digital Signal Processor. GPU is an abbreviation for Graphics Processing Unit.

[0013] The memory 12 is a storage device that temporarily stores data. Specific examples of the memory 12 include SRAM and DRAM. SRAM is an abbreviation for Static Random Access Memory. DRAM is an abbreviation for Dynamic Random Access Memory.

[0014] The storage 13 is a storage device that stores data. A specific example of the storage 13 is an HDD. HDD is an abbreviation for Hard Disk Drive. The storage 13 may also be a portable recording medium such as an SD (registered trademark) memory card, CompactFlash (registered trademark), NAND flash, a flexible disk, an optical disk, a compact disk, a Blu-ray (registered trademark) disk, or a DVD. SD is an abbreviation for Secure Digital. DVD is an abbreviation for Digital Versatile Disk.

[0015] The communication interface 14 is an interface for communicating with an external device. Specific examples of the communication interface 14 include Ethernet (registered trademark), USB, and HDMI (registered trademark) ports. USB is an abbreviation for Universal Serial Bus. HDMI is an abbreviation for High-Definition Multimedia Interface.

[0016] The region setting device 10 includes, as functional components, an image acquisition unit 21, an air outlet detection unit 22, and a region setting unit 23. The functions of the functional components of the region setting device 10 are realized by software. The storage 13 stores a program that realizes the function of each functional component of the area setting device 10. The program is loaded into the memory 12 by the processor 11 and executed by the processor 11. In this way, the function of each functional component of the area setting device 10 is realized.

[0017] 1 shows only one processor 11. However, there may be a plurality of processors 11, and the plurality of processors 11 may cooperate to execute programs that realize the respective functions.

[0018] ***Explanation of Operation*** The operation of the area setting device 10 according to the first embodiment will be described with reference to FIGS. The operation procedure of area setting device 10 according to embodiment 1 corresponds to the area setting method according to embodiment 1. Moreover, the program for realizing the operation of area setting device 10 according to embodiment 1 corresponds to the area setting program according to embodiment 1.

[0019] In the first embodiment, as shown in Fig. 2, the indoor unit 50 of the air conditioner is a four-way cassette type having air outlets 51 provided in four directions. The indoor unit 50 is rectangular, with an intake port 52 provided in the center. The indoor unit 50 has four air outlets 51 provided around the intake port 52, with the air outlet directions shifted by 90 degrees each. The light emitters 53 and the like are present in an area outside the intake port 52 other than the air outlets 51.

[0020] The flow of processing performed by the area setting device 10 according to the first embodiment will be described with reference to FIG. (Step S11: Image acquisition process) The image acquisition unit 21 acquires image data 61 obtained by capturing an image of the indoor unit 50 by an imaging device. Here, it is assumed that the image data 61 shown in Fig. 4 has been acquired. The image acquisition unit 21 writes the image data 61 to the memory 12.

[0021] (Step S12: Air outlet detection process) The air outlet detection unit 22 detects the air outlet 51 from the image data 61 acquired in step S11. Specifically, the air outlet detection unit 22 reads image data 61 from the memory 12. The air outlet detection unit 22 provides the image data 61 as an input to an object detection model. The object detection model is a machine learning model such as YOLO. YOLO stands for You Only Look Once. The object detection model detects the area of ​​the air outlet 51 reflected in the image data 61. The air outlet detection unit 22 acquires the area detected by the object detection model as a detection area 62. Here, the detection area is a rectangular area whose sides are parallel to the vertical or horizontal axis of the image data 61. In the first embodiment, the indoor unit 50 is a four-way cassette type. Therefore, as shown in Fig. 5, the air outlet detection unit 22 detects four air outlets 51 provided in four directions. That is, the detection area 62 of each of the four air outlets 51 is acquired.

[0022] The object detection model is generated by using as input a plurality of pieces of learning data that are generated by performing at least one of resizing, rotating, and adjusting brightness on each of a plurality of pieces of image data obtained by capturing images of the indoor unit 50. This makes it possible to appropriately detect the air outlet 51 even when image data 61 captured at various distances, directions, and lighting conditions is provided as input. Moreover, the object detection model is generated as learning data from a plurality of image data obtained by capturing images of the indoor unit 50 with different opening degrees of the air outlet 51. This makes it possible to appropriately detect the air outlet 51 even when the air outlet 51 is in a state with different opening degrees.

[0023] (Step S13: Area setting process) The area setting unit 23 sets an attention area 63, which is a range in which a detection target is to be detected in the image data 61, from the detection area 62 of the air outlet detected in step S12. A specific example of the detection target is the light-emitting body 53 or an identification number.

[0024] This will be described in detail with reference to FIG. 6 and FIG. The area setting unit 23 sets the detection area 62 of each of the four air outlets as the target detection area 62. As shown in Fig. 6, the area setting unit 23 sets the midpoint of a line segment connecting a start point 64 in the target detection area 62 with a nearby end point among end points 65 in the other detection areas 62 as the reference point 66. At this time, the area setting unit 23 sets a point on one short side in the target detection area 62 as the start point 64, and sets a point on the other short side in the other detection area 62 as the end point 65. 6, when the detection area 62 is viewed from the center of the air outlet 51, the inner end point of the left short side is set as a start point 64, and the inner end point of the right short side is set as an end point 65. Then, each start point 64 and the closest end point 65 are connected, and the midpoint is set as a reference point 66.

[0025] 7, the region setting unit 23 sets a reference figure 67 centered on a reference point 66. The reference figure 67 has a shape such as a rectangle or an ellipse. The region setting unit 23 then sets a range within the reference figure 67 as a region of interest 63. When setting the reference graphic 67, the area setting unit 23 sets the reference graphic 67 to a size corresponding to the size of the detection area 62 of the target air outlet 51. The area setting unit 23 also sets the reference graphic 67 to a shape corresponding to the positional relationship of the four detection areas 62. The area setting unit 23 also sets the reference graphic 67 rotated corresponding to the positional relationship of the four detection areas 62. The reason for changing the size and rotating the reference graphic 67 in this manner is that the way the indoor unit 50 is captured differs depending on the imaging distance and orientation. The imaging distance is the distance between the imaging device and the indoor unit 50. The size of the detection region 62 refers to the area of ​​the detection region 62 or the lengths of the long and short sides. Similarly, the size of the reference graphic 67 refers to the area of ​​the reference graphic 67 or the lengths of the long and short sides or the lengths of the long and short axes.

[0026] A method for setting the reference figure 67 will now be described in detail. <Setting method 1> The area setting unit 23 increases the size of the reference graphic 67 as the size of the detection area 62 increases. Specifically, the reference size of the detection area 62 and the standard size of the reference graphic 67 are determined in advance. The area setting unit 23 calculates the ratio of the size of the detected detection area 62 to the reference size. Then, the area setting unit 23 adjusts the size of the reference graphic 67 by multiplying the standard size of the reference graphic 67 by the calculated ratio.

[0027] <Setting method 2> The region setting unit 23 adjusts the shape of the reference figure 67 based on the positional relationship of the centers of the four detection regions 62. Specifically, a reference shape when the centers of the four air outlets 51 are connected is determined in advance. A possible reference shape is a square. This is because when an image of the indoor unit 50 is captured from directly below, connecting the centers of the four air outlets 51 forms a square. As shown in FIG. 8, the region setting unit 23 identifies a distortion of the shape connecting the centers of the four detected detection regions 62 with respect to the reference shape. The region setting unit 23 adjusts the shape of the reference figure 67 by distorting the reference figure 67 in the same way as the identified distortion. In Fig. 8, the shape connecting the centers of the four detection areas 62 is not a square but a rectangle that is squashed in the horizontal direction. Therefore, if the standard shape of the reference figure 67 is a square, the horizontal sides are adjusted to be shorter than the vertical sides. If the standard shape of the reference figure 67 is a circle, it is adjusted to an ellipse with a major axis in the vertical direction and a minor axis in the horizontal direction.

[0028] <Setting method 3> The region setting unit 23 sets a reference figure 67 rotated according to the positional relationship of the centers of the four detection regions 62. Specifically, a reference shape when the centers of the four air outlets 51 are connected is determined in advance. The reference shape may be a square whose sides are parallel to the long and short sides of the image data. As shown in FIG. 9, the region setting unit 23 specifies the rotation angle of the shape connecting the centers of the four detected detection regions 62 with respect to the reference shape. For example, the region setting unit 23 specifies the angle θ of the side with respect to the long side of the image data 61 to specify the rotation angle. The region setting unit 23 rotates the reference figure 67 by the specified rotation angle.

[0029] The attention area 63 set by the area setting unit 23 is output to an external device that detects the detection target. When the area setting device 10 has a function for detecting the detection target, the attention area 63 is output to the function for detecting the detection target.

[0030] ***Advantages of the First Embodiment*** As described above, the region setting device 10 according to the first embodiment sets the attention region 63 based on the detection region 62 of the air outlet 51. Here, in the indoor unit 50 of a four-cassette type air conditioner, the positional relationship between the air outlet 51 and the light-emitting body 53 to be detected and the like is generally fixed. In addition, the air outlet 51 is relatively large in size and easy to detect. Therefore, by setting the attention region 63 based on the detection region 62 of the air outlet 51, it is possible to set an appropriate attention region 63.

[0031] By setting the attention area 63, the area in which the detection target is detected is narrowed down. Therefore, it is possible to reduce the possibility of mistakenly detecting an object having characteristics similar to the detection target. As a result, it is possible to detect the detection target with high accuracy.

[0032] Assume that the detection target is a light-emitting body 53 such as an LED. In this case, the lighting or blinking of this light-emitting body 53 can be read by a terminal such as a smartphone, and operation information of the air conditioner can be transmitted to the terminal. It is conceivable that the transmitted operation information can be used for maintenance of the air conditioner. By the terminal detecting the light-emitting body 53 with high accuracy, it is possible to accurately grasp the operation information.

[0033] It is assumed that the detection target is the identification number of the air outlet 51. In this case, by having a terminal such as a smartphone read the identification number, it is possible to operate the desired air outlet 51 from the terminal. By having the terminal detect the identification number with high accuracy, it is possible to operate the correct air outlet 51.

[0034] ***Other configurations*** <Variation 1> In the first embodiment, each functional component is realized by software. However, as a first modification, each functional component may be realized by hardware. The following describes the first modification in terms of differences from the first embodiment.

[0035] The configuration of an area setting device 10 according to the first modification will be described with reference to FIG. When each functional component is realized by hardware, the area setting device 10 includes an electronic circuit 15 instead of the processor 11, the memory 12, and the storage 13. The electronic circuit 15 is a dedicated circuit for realizing the functions of each functional component, the memory 12, and the storage 13.

[0036] The electronic circuit 15 may be a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, a GA, an ASIC, or an FPGA. GA is an abbreviation for Gate Array. ASIC is an abbreviation for Application Specific Integrated Circuit. FPGA is an abbreviation for Field-Programmable Gate Array. Each functional component may be realized by one electronic circuit 15, or each functional component may be distributed across multiple electronic circuits 15.

[0037] <Variation 2> As a second modification, some of the functional components may be realized by hardware, and other functional components may be realized by software.

[0038] The processor 11, the memory 12, the storage 13, and the electronic circuit 15 are collectively referred to as a processing circuit. In other words, the functions of the respective functional components are realized by the processing circuit.

[0039] Embodiment 2 The second embodiment differs from the first embodiment in that the region setting device 10 detects the light-emitting body 53 that is the detection target. In the second embodiment, this difference will be described, and a description of the same points will be omitted.

[0040] ***Configuration Description*** The configuration of an area setting device 10 according to the second embodiment will be described with reference to FIG. 1 in that the region setting device 10 includes a light-emitting body detection unit 24 as a functional component. The function of the light-emitting body detection unit 24 is realized by software or hardware, like the other functional components.

[0041] ***Explanation of Operation*** The operation of the area setting device 10 according to the second embodiment will be described with reference to FIG. An operation procedure of area setting device 10 according to embodiment 2 corresponds to an area setting method according to embodiment 2. Moreover, a program for realizing the operation of area setting device 10 according to embodiment 2 corresponds to an area setting program according to embodiment 2.

[0042] The flow of processing performed by the area setting device 10 according to the second embodiment will be described with reference to FIG. The processing from step S21 to step S23 is the same as the processing from step S11 to step S13 in FIG.

[0043] (Step S24: Light-emitting body detection process) The light-emitting body detection unit 24 detects the light-emitting body 53 from the attention area 63 set in step S23. In the second embodiment, the light-emitting body 53 is the detection target. Specifically, (1) when detecting a light-emitting body 53 in a lit state, the light-emitting body detection unit 24 converts the image into the HSV color space. HSV is an abbreviation for Hue Saturation Value. The light-emitting body detection unit 24 extracts a group of pixels included in a range between a lower threshold and an upper threshold of the HSV pixel value as an object. (2) When detecting a light-emitting body 53 in a blinking state, the light-emitting body detection unit 24 converts each of a plurality of consecutive image data 61 into the HSV color space to generate converted data. The light-emitting body detection unit 24 finds the difference between the converted data of two temporally consecutive image data 61. The light-emitting body detection unit 24 extracts a group of pixels in which the difference is greater than a threshold as an object. Note that when detecting a light-emitting body 53 in a blinking state, the light-emitting body detection unit 24 may convert into the RGB color space or grayscale instead of the HSV color space. The light-emitting body detection unit 24 detects, from among the extracted objects, objects whose size is smaller than a reference size as light-emitting bodies 53. The size is a perimeter or an area. When multiple light-emitting bodies 53 are detected from the image data 61, the light-emitting body detection unit 24 detects the light-emitting body 53 whose center of gravity is located closest to the center of the attention area 63. When there are multiple light-emitting bodies 53, a specified number of light-emitting bodies 53 are detected in order from closest to the center of the attention area 63. Here, there are four attention areas 63. Close to the center of the attention area 63 means close to the center of any of the attention areas 63.

[0044] When it is desired to extract adjacent light-emitting bodies 53 as a single object, the light-emitting body detection unit 24 may perform a process of expanding pixels before extracting the object. Furthermore, when the position of the light-emitting body 53 is included in the detection area 62 of the air outlet 51, the light-emitting body detection unit 24 may determine that it is not the light-emitting body 53.

[0045] ***Effects of the second embodiment*** As described above, the region setting device 10 according to the second embodiment detects the light-emitting body 53, which is the detection target, from the attention region 63. This allows the region setting device 10 to acquire operation information, etc., of the air conditioner. The region setting device 10 may use the operation information to perform some kind of control, etc., or may output the operation information to an external device.

[0046] The area setting device 10 according to the second embodiment detects the light-emitting body 53 by using the size. When the light-emitting body 53 is an LED, the size of the light-emitting body 53 is relatively small. Therefore, by using the size, the light-emitting body 53 can be detected with high accuracy.

[0047] The area setting device 10 according to the second embodiment preferentially detects an object closer to the center position of the attention area 63 as the light-emitting object 53. This increases the possibility that only the appropriate light-emitting object 53 will be detected even if an object having characteristics similar to those of the light-emitting object 53 is present in the attention area 63.

[0048] In addition, the word "part" in the above description may be read as a "circuit," "step," "procedure," "processing," or "processing circuit."

[0049] The above describes the embodiments and modifications of the present disclosure. Some of these embodiments and modifications may be combined and implemented. Also, one or some of them may be partially implemented. Note that the present disclosure is not limited to the above embodiments and modifications, and various modifications are possible as necessary. [Explanation of symbols]

[0050] 10 area setting device, 11 processor, 12 memory, 13 storage, 14 communication interface, 15 electronic circuit, 21 image acquisition unit, 22 air outlet detection unit, 23 area setting unit, 24 light-emitting body detection unit, 50 indoor unit, 51 air outlet, 52 air intake, 53 light-emitting body, 61 image data, 62 detection area, 63 attention area, 64 start point, 65 end point, 66 reference point, 67 reference figure.

Claims

1. an air outlet detection unit that detects an air outlet from image data obtained by capturing an image of an indoor unit of the air conditioner; a region setting unit that sets a region of interest within the detection region of the air outlet detected by the air outlet detection unit, the region being a range within which a detection target is to be detected in the image data; An area setting device comprising:

2. The indoor unit is a four-way cassette type having air outlets in four directions, The air outlet detection unit detects four air outlets provided in the four directions, The area setting unit sets the attention area based on a point on a line segment connecting a start point in the target detection area with a nearby end point among end points in the other detection areas, with respect to the detection area of ​​each of the four air outlets. The area setting device according to claim 1 .

3. The region setting unit sets a reference figure with a point on the line segment as a center, and sets a range within the reference figure as the attention region. The area setting device according to claim 2 .

4. The area setting unit sets the reference figure having a size corresponding to the size of the detection area of ​​the target air outlet. The area setting device according to claim 3 .

5. The area setting unit sets the reference figure having a shape corresponding to a positional relationship of the detection areas of the four air outlets. The area setting device according to claim 3 .

6. The area setting unit sets the reference figure rotated in accordance with a positional relationship between the detection areas of the four air outlets. The area setting device according to claim 3 .

7. The detection area is rectangular, The area setting unit sets a point on one short side of the detection area of ​​the object as a start point and a point on the other short side of the other detection area as an end point. The area setting device according to claim 2 .

8. The air outlet detection unit detects the air outlet from image data of the indoor unit using an object detection model that is generated by inputting learning data generated by performing at least one of resizing, rotating, and adjusting brightness on image data of the indoor unit and that detects the air outlet using the object detection model that receives image data as input. The area setting device according to claim 1 .

9. The air outlet detection unit detects the air outlet from image data of an image of the indoor unit using an object detection model that is generated by inputting learning data that is a plurality of image data of the indoor unit in states where the air outlet is opened to different degrees, and detects the air outlet from the image data of the indoor unit using the object detection model that detects the air outlet by inputting the image data. The area setting device according to claim 1 .

10. The region setting device further comprises: a light-emitting body detection unit that detects a light-emitting body having a size smaller than a reference size from the region of interest set by the region setting unit; The area setting device according to claim 1 .

11. The light-emitting body detection unit detects a light-emitting body located near the center of the region of interest among light-emitting bodies whose size is smaller than the reference size. The area setting device according to claim 10.

12. The computer detects the air outlet from image data obtained by capturing an image of the indoor unit of the air conditioner, A region setting method in which a computer sets a region of interest within the detected detection region of the air outlet, the region being a range within which a detection target is to be detected in the image data.

13. An air outlet detection process for detecting an air outlet from image data obtained by capturing an image of an indoor unit of the air conditioner; a region setting process for setting a region of interest within the image data from the detection region of the air outlet detected by the air outlet detection process, the region being a range within which a detection target is to be detected; A region setting program that causes a computer to function as a region setting device that performs the above.

Citation Information

Patent Citations

  • Traffic light recognition device and traffic light recognition method

    WO2017009934A1

  • Air conditioning visualization system

    WO2017195286A1

  • Air conditioning system

    WO2018042621A1

  • Obstacle detection device, automatic braking device using obstacle detection device, obstacle detection method, and automatic braking method using obstacle detection method

    WO2019202627A1

  • Air-conditioning operation terminal, air-conditioning operation program, and air conditioning system

    WO2021240625A1