KR102603108B1 - System for measuring work surface daylight illuminance and method therof - Google Patents

Abstract

The present invention relates to a system and method for measuring daylight illuminance on a work surface, comprising: at least one lighting fixture installed on the ceiling or upper wall in a preset lighting space; a light-emitting face disposed on an upper part of a working surface located below the lighting device and including at least one diffusion surface that uniformly diffuses the main light regardless of the direction of inflow of the main light; a photographing unit installed at an upper portion of the lighting space and configured to photograph and provide an image of a work surface including the light-emitting face; and a lighting controller that receives a work surface image from the photographing unit, tracks the light emitting surface in the received work surface image, calculates the luminance value of the light emitting surface, and calculates the work surface illuminance using the calculated luminance value. It may be a system that includes

Description

System for measuring work surface daylight illuminance and method therof}

The present invention relates to a system and method for measuring work surface daylight illuminance that can be applied to a lighting control system that saves lighting energy by using daylight inflow.

The content described in this part simply provides background information on an embodiment of the present invention and does not constitute prior art.

As the issue of energy saving grows around the world, much research is being conducted to implement zero energy buildings. Among the various facilities consumed in buildings, the energy consumption of lighting varies depending on the characteristics of the building, but is approximately 20 to 25%. It occupies a large proportion.

Recently, a lot of research has been conducted to reduce lighting energy within buildings, and in particular, the development of a system that reduces lighting energy by using daylight into buildings is being developed. As Korea pursues a greenhouse gas reduction policy through zero-energy buildings, public buildings must function as zero-energy buildings from 2020, and private buildings must function as zero-energy buildings after 2025.

The target illuminance, which is the basic standard required in the indoor lighting environment, is maintained by the lighting equipment. To this end, lighting fixtures are placed at appropriate intervals to create conditions that can supply equal illumination throughout the space. It is known that lighting energy consumed indoors constitutes the highest proportion of the total energy consumed in commercial buildings.

A daylight dimming control system introduces daylight indoors and uses it in conjunction with lighting fixtures to save lighting energy.

FIG. 1 is a diagram illustrating a general optical sensor dimming control system, and FIG. 2 is a flow chart illustrating a dimming control method using the optical sensor dimming control system.

Referring to Figure 1, the optical sensor lighting control system is one of the systems that saves lighting energy by using the inflow of daylight into the building. The optical sensor 11 recognizes the amount of daylight flowing into the room and sets the target in the indoor space. This is a system that saves energy by adjusting the brightness of the lighting fixture 10 to match the illuminance. The optical sensor lighting control system must be able to predict the indoor work surface illuminance distribution through the amount of daylight sensed by the optical sensor 11 attached to the ceiling or lighting fixture 10.

Referring to FIG. 2, in the optical sensor lighting control system, the optical sensor 11 detects the amount of daylight flowing into the room (S1), and determines the daylight illuminance (or illuminance value) of the indoor work surface through the detected amount of daylight. After prediction, the required illuminance is calculated by comparing the target illuminance and daylight illuminance (S2, S3). The optical sensor dimming control system calculates the dimming level for the required illuminance (S4), and controls the brightness of the lighting to achieve the target illuminance based on the calculated dimming level to dim the lighting fixture 10 (S5).

This optical sensor lighting control system can save about 30 to 60% of the energy used for lighting, even considering the influence of various factors such as the orientation and shape of the space, the area, location and shape of the window, and the transmittance and reflectance of the glass. there is.

However, the existing optical sensor lighting control system minimizes the energy consumption of artificial lighting and ensures that the indoor work surface illuminance always maintains the set value regardless of changes in the amount of external sunlight, but the altitude of the sun that changes depending on the current season or time It is not possible to accurately predict the signal of the optical sensor under various daylight conditions due to skylight.

In addition, the light reflected from the work surface, rather than the actual illuminance of the work surface, is calculated through an optical sensor attached to the ceiling, so the accuracy of the work surface illuminance value is low, and the work surface illuminance value is accurately calculated through an optical sensor attached to the ceiling. In order to calculate it, a process of learning the work surface illuminance value measured in advance under various illuminance conditions based on machine learning is required.

FIG. 3 is a diagram illustrating the process of learning the work surface illuminance value using the optical sensor of FIG. 1, and FIG. 4 is a diagram illustrating the learning results derived through the learning process of FIG. 3.

As shown in FIGS. 3 and 4, in the existing optical sensor light control system, the first optical sensor 11a installed on the ceiling measures the illuminance value of the work surface directly below the first optical sensor 11a, and 2 The optical sensor 11b measures the illuminance value of the work surface directly below the second optical sensor 11b. At this time, in order to correct error values in the illuminance values of each work surface of the first and second optical sensors 11a and 11b, the first and second illuminance meters 12a and 12b are located on each work surface, respectively.

Therefore, as shown in FIG. 4, the optical sensor lighting control system includes first and second illuminance meters ( The predicted solar illuminance slope can be calculated by learning using the work surface illuminance value measured in 12a, 12b). However, this learning process has a problem in that it requires a large amount of learning data and a long learning time because the error value increases when calculating the illuminance of the work surface depending on the angle of incidence of sunlight, amount of solar radiation, weather, etc.

In order to solve the above-described problems, the present invention provides a work surface daylight illuminance measurement system and method for calculating the work surface illuminance by daylight influx in order to increase the accuracy of the light control system according to an embodiment of the present invention. There is a purpose to it.

However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means for achieving the above-described technical problem, a work surface daylight illuminance measurement system according to an embodiment of the present invention includes at least one lighting fixture installed on the ceiling or upper wall in a preset lighting space; a light-emitting face disposed on an upper part of a working surface located below the lighting device and including at least one diffusion surface that uniformly diffuses the main light regardless of the direction of inflow of the main light; a photographing unit installed at an upper portion of the lighting space and configured to photograph and provide an image of a work surface including the light-emitting face; and a lighting controller that receives a work surface image from the photographing unit, tracks the light emitting surface in the received work surface image, calculates the luminance value of the light emitting surface, and calculates the work surface illuminance using the calculated luminance value. It includes.

The light emitting face has perfect diffusion characteristics because the diffusion surface is finished with any one of white matte paint and barium sulfate (BaSO4) coating.

The lighting controller extracts the feature vector of the luminescent face from the work surface image using a pre-trained learning dataset, and uses an artificial intelligence-based image processing algorithm to recognize the luminous face based on the extracted feature vector. It is done.

The lighting controller receives a plurality of work surface images with different exposure times from the photographing unit and synthesizes the plurality of received work surface images to generate a high dynamic range (HDR) composite image.

The lighting controller calculates the luminance value of the light-emitting body for each pixel, averages luminance values within a preset upper range among the calculated luminance values for each pixel, sets it as a representative luminance value, and then performs an operation using the representative luminance value. The surface illuminance is calculated.

The method of measuring the daylight illuminance of a work surface according to an embodiment of the present invention is applied to a lighting control system and includes: a) uniformly spreading the daylight regardless of the direction of inflow of the daylight on the upper part of the work surface; Arranging a light emitting surface including at least one diffusion surface; b) taking and providing images of the work surface including the light-emitting face at preset time intervals using a photographing unit according to the influx of daylight; c) recognizing the light emitting surface in the work surface image and then extracting the R G B values of the light emitting surface for each pixel; and d) calculating the luminance value using the extracted RGB values for each pixel and calculating the work surface illuminance using the calculated luminance value.

The light emitting face has perfect diffusion characteristics because the diffusion surface is finished with any one of white matte paint and barium sulfate (BaSO4) coating.

Step c) is an artificial intelligence-based image processing algorithm that extracts the feature vector of the luminescent face from the work surface image using a pre-trained learning dataset and recognizes the luminous face based on the extracted feature vector. It is to be used.

In step d), the luminance values within a preset upper range among the luminance values for each pixel of the light-emitting face are averaged and set as a representative luminance value, and then the work surface illuminance is calculated using the representative luminance value.

Meanwhile, the method of measuring the daylight illuminance of a work surface according to another embodiment of the present invention is applied to a lighting control system and measures the daylight illuminance of a work surface, a) measuring the daylight illuminance of the work surface regardless of the direction of inflow of the daylight into the upper part of the work surface. Arranging a light emitting surface including at least one diffusion surface that diffuses uniformly; b) taking images of the work surface including the light-emitting face at preset time intervals using a photographing unit according to the influx of daylight, with different exposure times; c) generating a high dynamic range (HDR) composite image by compositing a plurality of work surface images with different exposure times captured by the photographing unit; d)) recognizing the light-emitting faceplate in the HDR composite image and then extracting the RGB values of the light-emitting body for each pixel; and e) calculating the luminance value using the extracted RGB values for each pixel and calculating the work surface illuminance using the calculated luminance value.

According to the above-described means of solving the problem of the present invention, the present invention improves the illuminance of the work surface by the influx of daylight by using a light-emitting faceplate with a fully diffused surface placed on the upper part of the work surface without a separate additional device for power supply and data transmission. Since it can be calculated, it has the effect of increasing the accuracy of the lighting control system without using an optical sensor.

The present invention can dim a lighting fixture by accurately calculating the illuminance of an indoor work surface using images taken of a luminous surface that is less likely to be obscured by documents or other obstacles compared to a small illuminance sensor.

Figure 1 is a diagram explaining a general optical sensor dimming control system.
Figure 2 is a flowchart explaining a dimming control method using an optical sensor dimming control system.
FIG. 3 is a diagram illustrating the process of learning the work surface illuminance value using the optical sensor of FIG. 1.
Figure 4 is a diagram explaining the learning results derived through the learning process of Figure 3.
Figure 5 is a diagram explaining a work surface daylight illuminance measurement system according to an embodiment of the present invention.
Figure 6 is a diagram explaining the configuration of a light-emitting face according to an embodiment of the present invention.
Figure 7 is a diagram illustrating the distribution of reflected power of a light-emitting face according to an embodiment of the present invention.
Figure 8 is a diagram explaining the configuration of a CNN applied to an artificial intelligence-based image processing algorithm of a lighting controller according to an embodiment of the present invention.
FIG. 9 is an example diagram illustrating an object tracking process using the artificial intelligence-based image processing algorithm of FIG. 8.
Figure 10 is a diagram illustrating a process for calculating a work surface illuminance conversion formula using a work surface daylight illuminance measurement system according to an embodiment of the present invention.
Figure 11 is a flowchart explaining a method of measuring daylight illuminance on a work surface according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this does not mean excluding other components unless specifically stated to the contrary, but may further include other components, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The following examples are detailed descriptions to aid understanding of the present invention and do not limit the scope of the present invention. Accordingly, inventions of the same scope and performing the same function as the present invention will also fall within the scope of rights of the present invention.

Additionally, each configuration, process, process, or method included in each embodiment of the present invention may be shared within the scope of not being technically contradictory to each other.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the attached drawings.

Figure 5 is a diagram explaining a work surface daylight illuminance measurement system according to an embodiment of the present invention, Figure 6 is a diagram explaining the configuration of a light-emitting face according to an embodiment of the present invention, and Figure 7 is a diagram of the present invention. This is a diagram explaining the distribution of reflection output of a light-emitting body according to an embodiment.

Referring to FIG. 5, the work surface daylight illuminance measurement system includes, but is not limited to, a lighting device 110, a light-emitting face 120, a photographing unit 130, and a lighting controller 140.

At least one lighting fixture 110 is installed on the ceiling or upper wall, that is, on the upper part of the work surface, in a preset lighting space.

The light emitting surface 120 is disposed on the upper part of the work surface located below the lighting device 110, and includes at least one diffusion surface that uniformly diffuses the main light regardless of the direction in which the main light is introduced. The first light emitting face 121 may be disposed on the work surface located below the lighting device 1 (111), and the second light emitting face 122 may be placed on the work surface located below the lighting device 2 (112).

The light emitting surface 120 is a light emitting surface with the same luminance in all directions regardless of the direction in which the diffusion surface 120a is viewed, and is finished with matte white paint, barium sulfate (BaSO4) coating, etc. to provide perfect diffusion characteristics. has

As shown in FIG. 6, this luminous facet may be formed in the form of a cube (or cube) with a side length of 100 mm, but may also be formed as a polyhedron such as a cuboid, pentahedron, or dodecahedron.

As shown in (a) of FIG. 7, the angle (θ _r ) of the reflected ray reflected from the specular reflector is the same as the angle (θ _i ) of the incident ray, so the If you know the angle of incidence, you can predict the reflector of the ray. However, in the light emitting facet 120 having a fully diffused surface (Lambertian surface, Lambertian surface), the reflection intensity is distributed over a wide range of angles and appears independently of the incident angle of the incident light.

Accordingly, the surface of the light-emitting body 120 having a completely diffusing surface has the same apparent brightness regardless of the angle from which the observer or the photographing unit 130 looks, that is, when the surface luminance is the same, the surface has Lambertian reflectance.

The photographing unit 130 is installed at the top of the lighting space and provides an image of the work surface including the light-emitting face 120. It can be a CCTV or CCD camera and is photographed at preset time intervals (for example, 5 minutes). Perform shooting actions.

The lighting controller 140 receives the work surface image from the photographing unit 130, tracks the light emitting surface 120 in the received work surface image, calculates the luminance value of the light emitting surface 120, and uses the calculated luminance value. Calculate the work surface illuminance using

This lighting controller 140 may be a wireless communication device that ensures portability and mobility. For example, it may be any type of handheld wireless communication device such as a smartphone, tablet PC, or laptop. Additionally, the lighting controller 200 may be a wired communication device such as a PC that can be connected to another terminal or server through a network.

At this time, when the lighting space is divided into a preset number of lighting groups, the lighting controller 140 is provided for each lighting group, and data collection and transmission processing is performed in connection with the lighting controller 140 for each lighting group. It may further include a central control device (not shown) responsible for lighting operation, including setting the target illuminance and controlling lighting brightness.

The lighting controller 140 performs HDR synthesis of the work surface image received from the photographing unit 130, and extracts the R, G, and B values of the luminescent face 120 for each pixel through an artificial intelligence-based image processing algorithm. At this time, the lighting controller 140 sets the exposure time of the photographing unit 130 to 1/2, 1/15, 1/125, and 1/1000 in consideration of the indoor lighting environment to capture four work surface images. , the four work surface images captured in this way are synthesized to create an HDR composite image.

FIG. 8 is a diagram illustrating the configuration of a CNN applied to the artificial intelligence-based image processing algorithm of a lighting controller according to an embodiment of the present invention, and FIG. 9 is a diagram illustrating object tracking using the artificial intelligence-based image processing algorithm of FIG. 8. This is an example diagram explaining the process.

As shown in Figures 8 and 9, the artificial intelligence-based image processing algorithm can apply CNN, but in addition to CNN, various algorithms such as RNN, YOLO (You Only Look Once), and Single Shot Detector (SSD) can be used. You can.

CNN consists of an input layer, an output layer, and several hidden layers between the input layer and the output layer. Each layer performs calculations that change the data to learn the characteristics of only that data. The most used layer is Includes convolution, activation/ReLU (Rectified Linear Unit), and pooling.

Convolution passes the input data through a set of convolutional filters that activate specific features in each workplane image. ReLU maps negative values to 0 and retains positive values, enabling faster and more effective learning. This process is also called activation because only activated features are passed to the next layer. Pooling simplifies the output by performing non-linear downsampling and reducing the number of parameters the network needs to learn.

This CNN uses a pre-trained learning dataset to analyze the pattern characteristics of the light-emitting facet 120 in the work surface image, extracts feature vectors to distinguish between different patterns, and determines which pattern the newly given work surface image corresponds to. Classify and recognize if applicable. In other words, the artificial intelligence-based image processing algorithm learns several sample images necessary for learning about various shapes of the luminous hexahedron 120, that is, various polyhedra such as cube shapes and icosahedrons, according to changes in daylight illuminance. Using the dataset, the luminous face 120 can be recognized by capturing the surrounding area of the target luminous face 120 as a box-shaped border using object tracking technology. The artificial intelligence-based image processing algorithm changes the illuminance value due to the influence of sunlight flowing into the room through the window during the day and the illuminance value caused by the lighting fixture 110 because sunlight does not flow into the room at night. It can be used as learning data for.

The lighting controller 140 calculates the luminance value (Y) using the extracted R, G, and B values for each pixel using Equation 1 below, and sets the representative luminance value by averaging the top 10% of the calculated luminance values. do.

[Equation 1]

Y=0.299R+0.587G+0.114B

The lighting controller 140 may calculate the work surface illuminance using a work surface illuminance conversion equation that pre-derived the representative luminance value.

Figure 10 is a diagram illustrating a process for calculating a work surface illuminance conversion formula using a work surface daylight illuminance measurement system according to an embodiment of the present invention.

Referring to FIG. 10, the luminous surface 120 and the illuminance meter 150 are placed on the work surface, and the artificial lighting brightness level is changed step by step at night to obtain the actual work surface illuminance measurement value and the work surface image through the illuminance meter 150. The representative luminance values of the light emitting surface 120 calculated through are compared. At this time, the illuminance meter 150 is placed immediately below the lighting fixture 110 (located 75 cm above the floor), and the illuminance meter 150 is not used when calculating the actual work surface illuminance.

By deriving a correction equation according to the brightness level of artificial lighting at night, the work surface daylight illuminance measurement system can be used to distinguish between the illuminance influence due to artificial lighting and the illuminance influence due to daylight when applied to the optical sensor dimming control system.

In addition, with all artificial lights turned off during the day, the actual work surface illuminance measured by the illuminance meter 150 according to the influx of daylight is compared with the representative luminance value of the luminous face 120 calculated through the work surface image to emit light. Derive the work surface illuminance conversion equation for each facet. At this time, the work surface illuminance conversion equation is derived by comparing the values measured at least 10 times, taking into account the influx of daylight.

With six lighting fixtures arranged in an indoor space, the first illuminance meter located directly below lighting fixture 1 can calculate the final work surface illuminance (ET ₁ ) using Equation 2 below.

[Equation 2]

In Equation 2, ED ₁ is the daylight illuminance at a position directly below lighting fixture 1, and E _IJ represents the work surface illuminance at a position directly below lighting fixture j in lighting fixture i. In this way, the final working surface illuminance is the sum of the daylight illuminance, the illuminance of the nearest lighting fixture, and the illuminance of the distant lighting fixture, and the final working surface illuminance (ET _j ) at all measurement points uses the standardized equation, Equation 3. It can be calculated by:

[Equation 3]

In Equation 3, n represents the number of lighting fixtures.

When the target work surface illuminance is set to 500lx and ED ₁ is 200 lx, the work surface illuminance required for work surface illuminance 1 (ER ₁ ) can be calculated using Equation 4. The required illuminance at a position directly below lighting fixture j (ER _j ) can be defined using Equation 4 according to Equation 5.

[Equation 4]

[Equation 5]

Figure 11 is a flowchart explaining a method of measuring daylight illuminance on a work surface according to an embodiment of the present invention.

Referring to FIG. 11, the method of measuring the daylight illuminance of a work surface includes placing the light emitting face 120 on the upper part of the work surface (S11), and measuring the light emitting face (120) at preset time intervals using the photographing unit 130 when the day light enters. An image of the work surface including 120) is taken and provided to the lighting controller 140 (S12, S13). At this time, unlike small-sized illuminance meters or illuminance sensors, the light emitting surface 120 placed on the upper part of the work surface is very unlikely to be obscured by documents or other obstacles, and does not require additional devices for power supply or data transmission. Unlike a light meter, there is no need for a separate additional device.

The lighting controller 140 recognizes the light emitting surface 120 in the work surface image, extracts the R, G, and B values of the light emitting surface for each pixel, and calculates the luminance value using the extracted R, G, and B values ( S14, S15). At this time, the lighting controller 140 generates an HDR composite image by combining a plurality of work surface images taken with different exposure times of the photographing unit 130, and applies the HDR composite image to an artificial intelligence-based image processing algorithm. This allows the light-emitting body 120 to be recognized.

The lighting controller 140 averages the top 10% of the calculated luminance values and sets them as a representative luminance value, and calculates the work surface illuminance using a work surface illuminance conversion equation that derives the representative luminance value in advance ( S16).

Meanwhile, steps S11 to S16 of FIG. 11 may be divided into additional steps or combined into fewer steps depending on the implementation of the present invention. Additionally, some steps may be omitted or the order between steps may be changed as needed.

The embodiments of the present invention described above can also be implemented in the form of a recording medium containing instructions executable by a computer, such as program modules executed by a computer. Such recording media includes computer-readable media, which can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Computer-readable media also includes computer storage media, both volatile and non-volatile implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data. , includes both removable and non-removable media.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

110: lighting fixtures
120: Luminous face
130: Filming department
140: lighting controller
150: Light meter

Claims (10)

At least one lighting fixture installed on the ceiling or upper wall in a preset lighting space;
a light-emitting face disposed on an upper part of a working surface located below the lighting device and including at least one diffusion surface that uniformly diffuses the main light regardless of the direction of inflow of the main light;
a photographing unit installed at an upper portion of the lighting space and configured to photograph and provide an image of a work surface including the light-emitting face;
an illuminance meter disposed immediately below the lighting fixture; and
It includes a lighting controller that receives a work surface image from the photographing unit, tracks the light emitting surface in the received work surface image, calculates the luminance value of the light emitting surface, and calculates the work surface illuminance using the calculated luminance value. And
The lighting controller changes the artificial lighting brightness step by step at night and compares the actual work surface illuminance measurement value through the illuminance meter with the representative luminance value of the luminous face calculated through the work surface image,
By deriving a correction equation according to the brightness level of artificial lighting at night, it can be used to distinguish between the illuminance effect due to artificial lighting and the illuminance effect due to daylight.
During the day, with all artificial lights turned off, the actual work surface illuminance measured by the illuminance meter according to the influx of daylight is compared with the representative luminance value of the luminous face calculated through the work surface image, and the work surface illuminance conversion formula for each luminous face is calculated. Derived from
A work surface daylight illuminance measurement system that calculates the final work surface illuminance of all measurement points.

Here, ET _j is the final working surface illuminance at all measurement points, ED _j is the daylight illuminance at the position directly below luminaire j, and E _ij is the working surface illuminance at the position directly below luminaire j at luminaire i, respectively. Meaning.
delete delete delete delete delete delete delete delete delete

Images