WO2023149101A1 - Weather observation system, weather observation method, trained model generation method, and program - Google Patents
Weather observation system, weather observation method, trained model generation method, and program Download PDFInfo
- Publication number
- WO2023149101A1 WO2023149101A1 PCT/JP2022/046247 JP2022046247W WO2023149101A1 WO 2023149101 A1 WO2023149101 A1 WO 2023149101A1 JP 2022046247 W JP2022046247 W JP 2022046247W WO 2023149101 A1 WO2023149101 A1 WO 2023149101A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- value
- correlation data
- weather observation
- pixel value
- solar radiation
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000005855 radiation Effects 0.000 claims abstract description 103
- 238000010248 power generation Methods 0.000 claims abstract description 82
- 238000003384 imaging method Methods 0.000 claims abstract description 29
- 238000005259 measurement Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 11
- 230000002596 correlated effect Effects 0.000 abstract description 7
- 238000006243 chemical reaction Methods 0.000 description 34
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006866 deterioration Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- PWPJGUXAGUPAHP-UHFFFAOYSA-N lufenuron Chemical compound C1=C(Cl)C(OC(F)(F)C(C(F)(F)F)F)=CC(Cl)=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F PWPJGUXAGUPAHP-UHFFFAOYSA-N 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/12—Sunshine duration recorders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/147—Details of sensors, e.g. sensor lenses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Definitions
- This disclosure relates to weather observation systems, weather observation methods, trained model generation methods, and programs.
- Patent Document 1 discloses a system for estimating solar radiation.
- Patent Document 2 discloses a system for estimating power generation based on cloud movement.
- Patent Document 1 Patent Publication No. 6952998
- Patent Document 2 Japanese Patent Laid-Open No. 2007 -184354 Outline of the invention
- the disclosure provides weather observation systems, weather observation methods, trained model generation methods, and programs that can estimate solar radiation or power generation in real time.
- the weather observation system of the present disclosure is equipped with an image acquisition unit that acquires an image acquired by a camera that contains at least a sky in an imaging area, a pixel value acquisition unit that acquires a pixel value of a specific area in the imaging area, and an estimation unit that generates an estimated value that is correlated with the pixel value using correlation data that represents the relationship between a measured value and the pixel value.
- the estimated value is one of an amount of solar radiation and an amount of power generation and a measured value is one of the amount of solar radiation and the amount of power generation.
- the estimated value may be one of an amount of solar radiation and an amount of power generation and a measured value is one of the amount of solar radiation and the amount of power generation.
- the specific area includes a natural object or an object fixed to the ground in the image.
- the specific area may include an object that is directly exposed to sunlight.
- the specific area may be arranged in a plurality of orientations as viewed from a location of the camera.
- the pixel value may be a lightness value or a brightness value.
- the pixel value may be a value based on statistical values in the specific area.
- the correlation data may be a trained model which outputs the estimated value when pixel value data obtained from the image captured by the camera is input, and the estimation unit is further configured to acquire an estimated value by inputting the pixel value data into the trained model.
- the weather observation system further includes a measured value acquisition unit which acquires a measured value measured by a device capable of measuring either the amount of solar radiation or the amount of power generation and a correlation data generation unit which generates the correlation data based on the measured value acquired by the measured value acquisition unit and the pixel value acquired by the pixel value acquisition unit.
- the weather observation system may further includes a weather condition acquisition unit which acquires weather conditions and the correlation data generation unit may generates a plurality of the correlation data based on each of the weather conditions.
- the correlation data may be generated by comparing the measured value with the pixel value based on an image captured during the same time period as the measured time of the measured value.
- the correlation data generation unit may generate the correlation data when there is a difference of a predetermined or larger value between the estimated value calculated using the correlation data and the acquired measurement value.
- the correlation data generation unit may generate the correlation data after a predetermined time elapses from the time when the correlation data is last generated.
- the weather observation system may further include a prediction unit which predicts an amount of solar radiation or an amount of power generation after the time of capturing the image based on weather information in the image captured by the camera.
- the image may be an image taken by an all-sky camera, and the specific area may be a fringe part in the image.
- a weather observation method includes acquiring an image captured by a camera that contains the sky in an imaging area, acquiring a pixel value of a specific area within the imaging area and generating an estimated value using correlation data representing a relationship between the pixel value and a measured value.
- a trained model generation method includes acquiring training data consisting of a pixel value obtained from an image containing the sky acquired by a camera and a measured value measured by a device capable of measuring one of an amount of solar radiation and an amount of power generation, and outputting an estimated value that is one of the amount of solar radiation and an amount of power generation when the pixel value is input, based on an acquired training data.
- a non-transitory computer-readable medium having stored thereon computer-executable instructions which, when executed by a computer, cause the computer to execute the weather observation method.
- the estimated value correlated with the pixel value is calculated using the correlation data representing the relationship between the pixel value and the measured value of the specific area in the image containing the sky.
- the amount of solar radiation or power generated can be estimated in real time.
- Fig. 1 is a block diagram showing the configuration of the weather observation system of the first embodiment
- Fig. 2 illustrates an example of an image captured by a camera
- Fig. 3 is an illustration of an imaging area in the image captured by the camera
- Fig. 4 is a perspective view of the camera structure
- Fig. 5 is an illustration of an area for which pixel values are calculated in the image
- Fig. 6 is a graph illustrating a change in average lightness over a given day
- Fig. 1 is a block diagram showing the configuration of the weather observation system of the first embodiment
- Fig. 2 illustrates an example of an image captured by a camera
- Fig. 3 is an illustration of an imaging area in the image captured by the camera
- Fig. 4 is a perspective view of the camera structure
- Fig. 5 is an illustration of an area for which pixel values are calculated in the image
- Fig. 6 is a graph illustrating a change in average lightness over a given day
- Fig. 1 is a block diagram showing
- FIG. 7 is a graph illustrating changes in solar radiation for the same day including the period shown in Fig. 6;
- Fig. 8 is a graph illustrating changes in power generation over the same day, including the period shown in Fig. 6;
- Fig. 9 is a flow chart illustrating weather observation method performed by the weather observation system of the first embodiment;
- Fig. 10 is a flow chart illustrating a trained model generation process performed by the weather observation system of the modified example of the first embodiment;
- Fig. 11 is a block diagram illustrating the configuration of the weather observation system of the modified example of the first embodiment.
- the weather observation system 1 of the first embodiment of the present disclosure will be described below with reference to the drawings.
- the weather observation system 1 of the first embodiment estimates an amount of solar radiation or power generation based on images captured by a camera.
- the weather observation system 1 has a camera 20 for imaging a target and a computer for processing the image captured by the camera 20.
- the camera 20 can be any camera as long as it can photograph the target.
- the camera 20 of the first embodiment uses an all-sky camera for meteorological observation and includes the sky in the imaging area with the all-sky camera pointed upward in the vertical direction.
- the all-sky camera uses a fisheye lens that allows a single camera to capture a wide area, including targets around the camera's location.
- Fig. 2 shows an example of an image captured by the camera 20.
- Fig. 3 is an explanatory view of an imaging area Ar1 in the image captured by the camera 20.
- the imaging area Ar1 of the camera 20 is rectangular.
- An sky region S1 is included in the center of the imaging area Ar1.
- the sky region S1 includes a sun S2, a cloud S3 and a blue sky S4 depending on weather conditions.
- a surrounding environment S5 of the camera 20 is visible.
- the surrounding environment S5 includes natural objects such as trees, mountains and the ground, as well as structures such as buildings.
- the camera 20 has a lens unit 22 provided on a top surface of the housing 21 and a transparent hemispherical dome cover 23 covering the lens unit 22.
- a transparent hemispherical dome cover 23 covering the lens unit 22.
- light containing sunlight is reflected by the top surface (top) of the housing 21 and reaches the lens unit 22, so that the housing 21 appears in the annular shape in the image captured by the camera 20.
- An image G1 obtained from the camera 20 has known pixels and orientation in the image. In particular, the positional relationship between the pixel position and the target is known in the areas other than the sky area S1.
- the weather observation system 1 has an image acquisition unit 11, a pixel value acquisition unit 12, and an estimation unit 10.
- the estimation unit 10 has a solar radiation estimation unit 13 and a power generation estimation unit 14.
- the weather observation system 1 has a storage 1a, and the storage 1a has a solar radiation conversion formula D1 (correlation data) and a power generation conversion formula D2 (correlation data).
- D1 solar radiation conversion formula
- D2 power generation conversion formula
- These units are realized by the cooperation of software and hardware in a computer equipped with a processor (processing circuitry) 1b such as a CPU, storage 1a such as a memory, various interfaces, etc., where the processor 1b executes a program stored in memory beforehand.
- each unit 11 ⁇ 18 is implemented in a cloud or server, and the camera 20, a solar radiation meter 24, and a solar power generation system 25 are configured to be able to communicate with the cloud or server.
- the image acquisition unit 11 acquires the image G1 acquired by a camera 20 that contains at least a sky in the imaging area Ar1.
- the imaging area Ar1 of the image G1 includes the housing 21 of the camera 20.
- Image G1 is a color image and contains RGB components or components convertible to RGB components.
- the pixel value acquisition unit 12 acquires a pixel value G2 of a specific area S6 in the imaging area Ar1 of the image G1 acquired by the image acquisition unit 11.
- the specific area S6 is at least a part of the housing 21 that appears annularly in the image G1.
- an average value (based on statistical values) of the pixel values of a plurality of pixels in a lower end P1 of the annular housing 21 in image G1 is used.
- the lightness value is acquired as the pixel value G2.
- the solar radiation estimation unit 13 (the estimation unit 10) generates a solar radiation estimate value G3 that correlates with the pixel value G2 acquired by the pixel value acquisition unit 12 using the solar radiation conversion formula D1 (correlation data) stored in the storage 1a. Specifically, the solar radiation estimation unit 13 generates the solar radiation estimate value G3 by inputting the pixel value G2 (lightness value) into the solar radiation conversion formula D1.
- the solar radiation conversion formula D1 can be said to be correlation data representing the relationship between solar radiation and pixel values (lightness values).
- the power generation estimation unit 14 calculates a power generation estimate value G4 that correlates with the pixel value G2 acquired by the pixel value acquisition unit 12. Specifically, the power generation estimation unit 14 calculates the power generation estimate value G4 by inputting the pixel value G2 (lightness value) into the power generation conversion formula D2.
- the power generation conversion formula D2 can be said to be correlation data representing the relationship between power generation and pixel values (lightness values).
- the weather observation system 1 does not have to have a function to store and use correlation data (the solar radiation conversion formula D1 and the power generation conversion formula D2) generated by another correlation data generation system in storage 1a and generate correlation data.
- the weather observation system 1 of the first embodiment has a measured value acquisition unit 15 and a correlation data generation unit 16, and can generate correlation data.
- the measured value acquisition unit 15 acquires a measured value measured by a device capable of measuring one of an amount of solar radiation and an amount of power generation. As shown in Fig. 1, the measured value acquisition unit 15 can acquire a solar radiation measured value G5 measured by the device (the solar radiation meter 24) that can measure solar radiation. In addition, the measured value acquisition unit 15 can acquire a power generation measured value G6 by a device (part of the photovoltaic power generation system 25) capable of measuring power generation.
- the measured values G5 and G6 acquired by the measured value acquisition unit 15 are stored in the storage 1a as solar radiation time-series data D4 and power generation time-series data D5, respectively.
- the pixel value G2 (lightness value) acquired by the pixel value acquisition unit 12 is stored in the storage 1a as pixel value time series data D3.
- the correlation data generation unit 16 generates correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) based on the measurement value (the solar radiation measured value G5, the power generation measured value G6) acquired by the measured value acquisition unit 15 and the pixel value G2 acquired by the pixel value acquisition unit 12.
- Fig. 6 is a graph illustrating a change in average lightness on a given day. It represents the number of minutes that have elapsed since about 8:30.
- Fig. 7 is a graph illustrating changes in solar radiation on the same day including the period shown in Fig. 6. The vertical axis shows the amount of solar radiation, and the horizontal axis shows the elapsed time.
- Fig. 8 is a graph illustrating changes in power generation over the same day, including the period shown in Fig. 6.
- the vertical axis shows the amount of power generated
- the horizontal axis shows the elapsed time.
- Times 0 to 180 in Fig. 6 corresponds to the period from about 220 to about 580 in Figs. 7 and 8. It is clear that the changes in the lightness values shown in Fig. 6, the changes in the amount of solar radiation shown in Fig. 7, and the changes in the amount of power generation shown in Fig. 8 are similar in shape, and it can be understood that a high correlation exists between the lightness values and the solar radiation and between the lightness values and the amount of power generation.
- the correlation data generation unit 16 generates correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) by comparing the measured values G5 and G6 with the pixel value G2 based on the image G1 captured in the same time period as the measurement time of the measured values G5 and G6. For example, the solar radiation measured value G5 measured at 9:00 on December 20, 2021 is compared with the pixel value G2 (lightness value) based on an image taken at the same time. In the example of Figs. 6 ⁇ 8, there is a comparison between the data shown in Fig. 6 and the data shown in Fig. 7, and there is a comparison between the data shown in Fig. 6 and the data shown in Fig. 8.
- the same time periods mentioned here are preferably the same, but need not be exactly the same.
- the same time zone is preferably, but is not limited to, the same time when the camera time and the instrument time are synchronized.
- the same time zone may have a time difference of about 10 minutes, more preferably within 2 minutes, more preferably within 1 minute, and more preferably within 10 seconds.
- the correlation data generation unit 16 may generate the correlation data not only by one set of the measured value and the pixel value, but also by comparing the pixel value with the multiple sets of the measured value within the same period among the multiple combinations of the measured value and the pixel value based on the image captured in the same time zone as the measurement time of the measured value.
- the correlation data is generated by comparing multiple sets of measured values and pixel values in the same period from 9:00 to 18:00 on the same day. This means that comparisons between measurements and pixel values are narrowed down to data within the same period, thereby improving the accuracy of correlation data.
- a fitting method such as the least-squares method is used to generate the transformation equation, but it is not limited to this example.
- the weather observation system 1 has a weather condition acquisition unit 17 that acquires weather conditions.
- Weather conditions include, for example, the percentage of clouds in the sky area S1, the season (date), and the temperature.
- the correlation data generation unit 16 may generate a plurality of correlation data based on weather conditions. For example, the correlation data generation unit 16 generates correlation data for cloudy weather and correlation data for clear weather. Cloudy weather means that the percentage of clouds in the sky area S1 is greater than a predetermined threshold, and clear weather means that the percentage of clouds in the sky area S1 is less than the predetermined threshold.
- the correlation data generation unit 16 may also generate correlation data in spring, correlation data in summer, correlation data in fall, and correlation data in winter.
- the estimation unit 10 (the solar radiation estimation unit 13, the power generation estimation unit 14) can switch the correlation data used by the weather condition acquisition unit 17 according to the weather condition.
- the correlation data generation unit 16 makes it possible to refer to the estimated value (the solar radiation estimate value G3, the power generation estimate value G4) estimated by the estimation unit 10 (the solar radiation estimation unit 13, the power generation estimation unit 14).
- the correlation data generation unit 16 can refer to the measurement value (the solar radiation measured value G5, the power generation measured value G6) acquired by the measured value acquisition unit 15.
- the correlation data generation unit 16 may generate correlation data again when there is a difference of a predetermined or larger value between the estimated value calculated using the correlation data and the acquired measurement value. This regenerates correlation data in the event of a discrepancy (difference) between the estimate and the actual measurement that is assessed as unacceptable.
- the estimation accuracy by the correlation data deteriorates as time elapses from the time when the last correlation data is generated, the correlation data is generated again, so that the estimation accuracy can be maintained.
- the correlation data generation unit 16 in the first embodiment may generate the correlation data again after a predetermined time elapses from the time when the correlation data is previously generated. Deterioration of estimation accuracy due to aging can be suppressed, and estimation accuracy can be maintained.
- the weather observation system 1 may have an output unit 19 that outputs the prediction results of a prediction unit 18 and the prediction unit 18.
- the prediction unit 18 refers to the image G1 acquired by the image acquisition unit 11 and the estimated value (the solar radiation estimate value G3, the power generation estimate value G4), and predicts the amount of solar radiation or power generation in the time after the time when the image is imaged based on the weather information in the image G1 captured by the camera 20.
- Weather information in image G1 includes cloud position, cloud advection, and sun position.
- the prediction unit 18 predicts the amount of solar radiation and the amount of power generated after 10 minutes, for example.
- the prediction unit 18 determines whether a cloud stream shields the sun or how long after shielding the sun it flows to a position that does not shield the sun, and predicts values based on estimates (the solar radiation estimate value G3, the power generation estimate value G4).
- the result predicted by the prediction unit 18 may be displayed on a Web screen by the output unit 19 or transmitted to the destination terminal via a distribution server.
- the output unit 19 may be called a display unit or a distribution unit.
- the correlation data generation unit 16 may generate the correlation data again when there is a difference of a predetermined or larger value between the predicted value predicted by the prediction unit 18 and the acquired measurement value. In this way, if a discrepancy (difference) occurs between the predicted value and the actual value that is evaluated as unacceptable, the correlation data is generated again. Thus, when the prediction accuracy of the prediction unit 18 referring to the value estimated by the correlation data deteriorates as time elapses from the time when the last correlation data is generated, the correlation data is generated again, so that the prediction accuracy can be maintained.
- Fig. 9 is a flow chart showing the weather observation method executed by the weather observation system 1 of the first embodiment.
- step ST100 shown in Fig. 9 the camera 20 captures the image G1 containing at least the sky in the imaging area Ar1.
- the image acquisition unit 11 acquires the image G1 captured by the camera 20.
- the image G1 captured by the camera 20 is recorded and transmitted via a communication section of the camera 20 to the server or cloud where the image acquisition unit 11 is mounted.
- the image acquisition unit 11 receives the image G1.
- the pixel value acquisition unit 12 acquires the pixel value G2 (lightness value) in the specific area S6 of the image G1 and stores it in the storage 1a.
- the estimation unit 10 (the Solar radiation estimation unit 13, the power generation estimation unit 14) acquires correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) representing the relationship between the measured value, which is either the amount of solar radiation or the amount of power generated, and the pixel value G2.
- the estimation unit 10 (the solar radiation estimation unit 13, the power generation estimation unit 14) generates an estimated value (the solar radiation estimate value G3, the power generation estimate value G4) correlated with the pixel value G2 using the correlation data.
- the all-sky camera is installed facing upward in the vertical direction, but it is not limited to this.
- an all-sky camera may be set sideways along a horizontal direction to image one or more targets in a particular orientation.
- the first all-sky camera, which is oriented in the first direction, and the second all-sky camera, which is oriented in the opposite direction to the first direction may be installed back-to-back.
- the camera 20 need not be an all-sky camera using a fisheye lens, but a non-all-sky camera capable of photographing only a specific orientation.
- the lightness value is used as the pixel value G2, but if it is a pixel value, it is not limited to the lightness value.
- brightness may be used as the pixel value G2.
- Brightness is a value based on the maximum or minimum value of each RGB component.
- the specific area S6 with a plurality of pixels to be calculated for the pixel value G2 may include natural objects in the image G1 or objects fixed on the ground.
- the housing 21 of the camera 20 is fixed to the ground, but it is not limited to this.
- specific areas include the sides of buildings such as buildings, concrete blocks, and the poles of streetlights.
- the specific area S6 is preferably a region other than the sky area S1, which can include the sun S2, the cloud S3 and the blue sky S4.
- the specific area S6 is a fringe part of the image.
- the specific area S6 of the first embodiment is the housing 21 of the camera 20, but it is not limited to this, and may be an object that is directly exposed to sunlight. It is preferable that the object receives direct sunlight, but it may be an object that does not receive direct sunlight if it is outdoors, for example, on the north side of a building.
- the specific area S6 of the first embodiment is only the lower end P1 shown in Fig. 5, it is not limited to this, and a plurality of places may be set and pixel values of a plurality of places may be used.
- the pixel value (lightness value, etc.) may be abnormally high due to the reflection of the dome cover 23 or the camera lens. Therefore, it may be assumed that the specific area S6 includes the lower end P1, the first part P2, a second part P3, and a third part P4, and that the specific area S6 is arranged in a plurality of orientations as viewed from the installation position of the camera 20.
- the pixel value G2 is an average value of the pixel values of a plurality of pixels in a specific area S6, but is not limited to a value based on a statistical value of the pixel values. For example, median, mode, etc. are available. Since the value is based on a statistical value, adverse effects caused by outliers can be reduced.
- the correlation data is a transformation expression, but is not limited to this.
- it may be a table that associates pixel values with estimates, or it may be a trained model (a solar radiation model D11, a power generation model D12) generated by machine learning, as shown in Fig. 11.
- trained models include deep neural networks (DNNs), neural networks other than DNNs, recurrent neural networks (RNNs), long-short term models (LSTMs), CNN, support vector machines (SVMs), Bayesian networks, linear regression, regression trees, multiple regression, random forests, ensembles and other learning algorithms.
- DNNs deep neural networks
- RNNs recurrent neural networks
- LSTMs long-short term models
- CNN support vector machines
- SVMs support vector machines
- Bayesian networks linear regression, regression trees, multiple regression, random forests, ensembles and other learning algorithms.
- the correlation data may be presented by a transformation equation with polynomial regression.
- the correlation data generation unit 16 becomes a so-called learning unit.
- the learning unit may generate a trained model that outputs an estimated value that is either the amount of solar radiation or the amount of power generated when pixel value data is input.
- the training data may consist, for example, of pixel-value data (the pixel-value time series data D3) obtained from the sky-containing image G1 acquired by the camera 20, and measurement data (the solar radiation time series data D4, the power generation time series data D5).
- Fig. 10 is a flow chart illustrating the trained model generation process executed by the weather observation system 1 of the modified example of the first embodiment.
- the camera 20 captures the image G1 containing at least the sky in the imaging area Ar1.
- the image acquisition unit 11 acquires the image G1 captured up by the camera 20.
- the image G1 captured by the camera 20 is recorded and transmitted via the communication section of the camera 20 to the server or cloud where the image acquisition unit 11 is mounted.
- the image acquisition unit 11 receives the image G1.
- the pixel value acquisition unit 12 acquires the pixel value G2 (lightness value) in the specific area S6 of the image G1 and stores it in the storage 1a.
- the measured value acquisition unit 15 acquires the measured value (the solar radiation measured value G5, the power generation measured value G6) measured by a device capable of measuring either the amount of solar radiation or the amount of power generated, and stores it in the storage 1a.
- the correlation data generation unit 16 acquires the measured value (the solar radiation measured value G5, the power generation measured value G6) measured by the device capable of measuring the measurement value of either solar radiation or power generation.
- the correlation data generation unit 16 generates a trained model (the solar radiation model D11, the power generation model D12) that outputs an estimated value that is either the amount of solar radiation or the amount of power generated when the pixel value data is input, based on the acquired training data.
- the correlation data generation unit 16 and the measured value acquisition unit 15 in the first embodiment can be omitted if they do not generate correlation data.
- the weather observation system 1 of the first embodiment is a system for estimating both solar radiation and power generation, but it may be a system for estimating only either solar radiation or power generation.
- the weather observation system 1 may be equipped with the image acquisition unit 11 that acquires the image G1 acquired by the camera 20 that contains at least the sky in the imaging area Ar1, the pixel value acquisition unit 12 that acquires the pixel value G2 of a specific area S6 within the imaging area Ar1, and the estimation unit 10 (the solar radiation estimation unit 13, the power generation estimation unit 14) that calculates an estimated value (the solar radiation estimate value G3, the power generation estimate value G4) that is either the amount of solar radiation or the amount of power generated that is correlated with the pixel value G2 using correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) that represents the relationship between the measured value, which is either the amount of solar radiation or the amount of power generated, and the pixel value G2.
- the image acquisition unit 11 that acquires the image G1 acquired by the camera 20 that contains at least the sky in the imaging area Ar1
- the pixel value acquisition unit 12 that acquires the pixel value G2 of a specific area S6 within the imaging area Ar1
- the estimation unit 10 the solar radiation estimation unit
- the meteorological observation method may acquire the image G1 acquired by the camera 20, which contains at least the sky in the imaging area Ar1, acquire the pixel value G2 of the specific area S6 within the imaging area Ar1, and calculate an estimate, which is either the amount of solar radiation or the amount of power generated, that correlates with the pixel value G2 using correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) that represents the relationship between the measured value, which is either the amount of solar radiation or the amount of power generated, and the pixel value G2.
- correlation data the solar radiation conversion formula D1, the power generation conversion formula D2
- the estimated value (the solar radiation estimate value G3, the power generation estimate value G4) correlated with the pixel value G2 is calculated using correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) representing the relationship between the pixel value G2 of the specific area S6 in the image G1 including the sky and the measured value (either the solar radiation measured value G5 or the power generation measured value G6), so that the solar radiation or power generation can be estimated in real time.
- correlation data the solar radiation conversion formula D1, the power generation conversion formula D2 representing the relationship between the pixel value G2 of the specific area S6 in the image G1 including the sky and the measured value (either the solar radiation measured value G5 or the power generation measured value G6), so that the solar radiation or power generation can be estimated in real time.
- the specific area S6 may include natural objects in image G1 or objects fixed on the ground. This is a preferred embodiment.
- the specific area S6 may include an object that directly receives the illumination of sunlight.
- Objects that are directly exposed to sunlight have variable pixel values depending on the amount of solar radiation, which can improve estimation accuracy.
- the specific area S6 may be arranged in a plurality of directions as viewed from the installation position of the camera 20. It makes it possible to reduce the influence of abnormal pixel values that may occur in response to the movement of the sun.
- the pixel value G2 may be a lightness value or a brightness value. Lightness or brightness values can be used to estimate solar radiation or power generation because they vary with solar radiation.
- the pixel value G2 may be a value based on a statistical value in a specific area S6, as in the first embodiment and variant. It is possible to reduce adverse effects caused by outliers.
- the system may further include, as in the weather observation system 1 of the first embodiment, the measured value acquisition unit 15 for acquiring measurement values (the solar radiation measured value G5, the power generation measured value G6) measured by a device capable of measuring either solar radiation or power generation, and the correlation data generation unit 16 for generating correlation data based on the measured values G5 and G6 acquired by the measured value acquisition unit 15 and the pixel value G2 acquired by the pixel value acquisition unit 12. Correlation data is generated based on the pixel values used for estimation and the measured measurements, thus facilitating system operation.
- the measured value acquisition unit 15 for acquiring measurement values (the solar radiation measured value G5, the power generation measured value G6) measured by a device capable of measuring either solar radiation or power generation
- the correlation data generation unit 16 for generating correlation data based on the measured values G5 and G6 acquired by the measured value acquisition unit 15 and the pixel value G2 acquired by the pixel value acquisition unit 12. Correlation data is generated based on the pixel values used for estimation and the measured measurements, thus facilitating system operation.
- the weather condition acquisition unit 17 for acquiring weather conditions may be further provided, and the correlation data generation unit 16 may generate a plurality of correlation data based on weather conditions. Since the plurality of correlation data are generated based on weather conditions, appropriate correlation data can be used according to weather conditions, which can improve estimation accuracy.
- the correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) may be generated by comparing the measured values G5 and G6 with the pixel value G2 based on the image G1 captured at the same time as the measured time of the measured value. This is a preferred embodiment.
- the correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) may be generated by comparing a plurality of sets of measured values and pixel values within the same period among a plurality of combinations of measured values G5, G6 and pixel value G2 based on image G1 captured in the same time period as the measurement time of the measured value.
- the accuracy of correlation data can be improved.
- the correlation data generation unit 16 may generate the correlation data again when there is a difference of a predetermined or larger value between the estimated value calculated using the correlation data and the acquired measurement value. Since the correlation data is generated again when the estimation accuracy by the correlation data deteriorates, the estimation accuracy can be maintained.
- the correlation data generation unit 16 may generate the correlation data again after a predetermined time elapses from the time when the correlation data is previously generated. Deterioration of estimation accuracy due to aging can be suppressed, and estimation accuracy can be maintained.
- the system may further include the prediction unit 18 that predicts the amount of solar radiation or the amount of power generated in the time period after the present time (after the time when the image is taken) based on the weather information in the image G1 captured by the camera 20. It will be possible to provide a system that can predict the amount of solar radiation or power generated at any time after the present.
- the correlation data generation unit 16 may acquire training data consisting of pixel value data obtained from an image including the sky acquired by the camera 20 and measurement value data measured by a device capable of measuring either the amount of solar radiation or the amount of power generated, and generate a trained model (correlation data) that outputs an estimated value that is either the amount of solar radiation or the amount of power generated when the pixel value data is input based on the acquired training data.
- the weather observation system 1 may further include a camera 20.
- the program according to the first embodiment is a program that causes one or more processors to execute the above method.
- the program according to the first embodiment may cause one or more processors to perform processing to acquire the image G1 acquired by the camera 20, which contains at least the sky in the imaging area Ar1, to acquire the pixel value of the specific area S6 in the imaging area Ar1, and to calculate an estimated value, which is either the amount of solar radiation or the amount of power generated, correlated with the pixel value G2, using correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) representing the relationship between the measured value, which is either the amount of solar radiation or the amount of power generated, and the pixel value.
- the program relating to the modified example of the first embodiment may have one or more processors execute processing to acquire training data consisting of pixel value data obtained from an image including the sky acquired by the camera 20 and measurement data measured by a device capable of measuring either the amount of solar radiation or the amount of power generated, and to generate a trained model (correlation data) that outputs an estimated value that is either the amount of solar radiation or the amount of power generated when the pixel value data is input based on the acquired training data.
- a temporary recording medium readable by a computer stores the above program.
- Each unit shown in Fig. 1 is realized by executing a prescribed program by one or a processor, but each unit may be composed of a dedicated memory or a dedicated circuit.
- the components are implemented in the processor of one computer, but the components may be distributed and implemented in a plurality of computers or clouds. That is, the above method may be performed on one or more processors.
- each unit is implemented for illustrative purposes, but some of these units can be omitted arbitrarily.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Environmental Sciences (AREA)
- Evolutionary Biology (AREA)
- Biodiversity & Conservation Biology (AREA)
- Atmospheric Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Ecology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Vascular Medicine (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
- Image Analysis (AREA)
Abstract
To provide a weather observation system, a weather observation method, a trained model generation method, and a program that can estimate solar radiation or power generation in real time. The weather observation system 1 has an image acquisition unit 11 that acquires an image G1 acquired by a camera 20 that contains at least a sky in an imaging area Ar1, a pixel value acquisition unit 12 that acquires a pixel value G2 of a specific area S6 in the imaging area Ar1, and an estimation unit 10 that generates an estimated value that is correlated with the pixel value G2 using correlation data that represents a relationship between a measured value and the pixel value G2.
Description
This disclosure relates to weather observation systems, weather observation methods, trained model generation methods, and programs.
Estimation of solar radiation or power generation is important in solar power generation.
The disclosure provides weather observation systems, weather observation methods, trained model generation methods, and programs that can estimate solar radiation or power generation in real time.
The weather observation system of the present disclosure is equipped with an image acquisition unit that acquires an image acquired by a camera that contains at least a sky in an imaging area, a pixel value acquisition unit that acquires a pixel value of a specific area in the imaging area, and an estimation unit that generates an estimated value that is correlated with the pixel value using correlation data that represents the relationship between a measured value and the pixel value. The estimated value is one of an amount of solar radiation and an amount of power generation and a measured value is one of the amount of solar radiation and the amount of power generation.
In an aspect, the estimated value may be one of an amount of solar radiation and an amount of power generation and a measured value is one of the amount of solar radiation and the amount of power generation.
In an aspect, the specific area includes a natural object or an object fixed to the ground in the image.
In an aspect, the specific area may include an object that is directly exposed to sunlight.
In an aspect, the specific area may be arranged in a plurality of orientations as viewed from a location of the camera.
In an aspect, the pixel value may be a lightness value or a brightness value.
In an aspect, the pixel value may be a value based on statistical values in the specific area.
In an aspect, the correlation data may be a trained model which outputs the estimated value when pixel value data obtained from the image captured by the camera is input, and the estimation unit is further configured to acquire an estimated value by inputting the pixel value data into the trained model.
In an aspect, the weather observation system further includes a measured value acquisition unit which acquires a measured value measured by a device capable of measuring either the amount of solar radiation or the amount of power generation and a correlation data generation unit which generates the correlation data based on the measured value acquired by the measured value acquisition unit and the pixel value acquired by the pixel value acquisition unit.
In an aspect, the weather observation system may further includes a weather condition acquisition unit which acquires weather conditions and the correlation data generation unit may generates a plurality of the correlation data based on each of the weather conditions.
In an aspect, the correlation data may be generated by comparing the measured value with the pixel value based on an image captured during the same time period as the measured time of the measured value.
In an aspect, the correlation data generation unit may generate the correlation data when there is a difference of a predetermined or larger value between the estimated value calculated using the correlation data and the acquired measurement value.
In an aspect, the correlation data generation unit may generate the correlation data after a predetermined time elapses from the time when the correlation data is last generated.
In an aspect, the weather observation system may further include a prediction unit which predicts an amount of solar radiation or an amount of power generation after the time of capturing the image based on weather information in the image captured by the camera.
In an aspect, the image may be an image taken by an all-sky camera, and the specific area may be a fringe part in the image.
A weather observation method includes acquiring an image captured by a camera that contains the sky in an imaging area, acquiring a pixel value of a specific area within the imaging area and generating an estimated value using correlation data representing a relationship between the pixel value and a measured value.
A trained model generation method includes acquiring training data consisting of a pixel value obtained from an image containing the sky acquired by a camera and a measured value measured by a device capable of measuring one of an amount of solar radiation and an amount of power generation, and outputting an estimated value that is one of the amount of solar radiation and an amount of power generation when the pixel value is input, based on an acquired training data.
A non-transitory computer-readable medium having stored thereon computer-executable instructions which, when executed by a computer, cause the computer to execute the weather observation method.
According to this configuration, the estimated value correlated with the pixel value is calculated using the correlation data representing the relationship between the pixel value and the measured value of the specific area in the image containing the sky. Thus, the amount of solar radiation or power generated can be estimated in real time.
The illustrated embodiments of the subject matter will be best understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and processes that are consistent with the subject matter as claimed herein:
Fig. 1 is a block diagram showing the configuration of the weather observation system of the first embodiment;
Fig. 2 illustrates an example of an image captured by a camera;
Fig. 3 is an illustration of an imaging area in the image captured by the camera;
Fig. 4 is a perspective view of the camera structure;
Fig. 5 is an illustration of an area for which pixel values are calculated in the image;
Fig. 6 is a graph illustrating a change in average lightness over a given day;
Fig. 7 is a graph illustrating changes in solar radiation for the same day including the period shown in Fig. 6;
Fig. 8 is a graph illustrating changes in power generation over the same day, including the period shown in Fig. 6;
Fig. 9 is a flow chart illustrating weather observation method performed by the weather observation system of the first embodiment;
Fig. 10 is a flow chart illustrating a trained model generation process performed by the weather observation system of the modified example of the first embodiment; and
Fig. 11 is a block diagram illustrating the configuration of the weather observation system of the modified example of the first embodiment.
Example apparatus are described herein. Other example embodiments or features may further be utilized, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein. In the following detailed description, reference is made to the accompanying drawings, which form a part thereof.
The example embodiments described herein are not meant to be limiting. It will be readily understood that the aspects of the present disclosure, as generally described herein, and illustrated in the drawings, can be arranged, substituted, combined, separated, and designed in a wide variety of different configurations, all of which are explicitly contemplated herein.
The weather observation system 1 of the first embodiment of the present disclosure will be described below with reference to the drawings. The weather observation system 1 of the first embodiment estimates an amount of solar radiation or power generation based on images captured by a camera.
As shown in Fig. 1, the weather observation system 1 has a camera 20 for imaging a target and a computer for processing the image captured by the camera 20. The camera 20 can be any camera as long as it can photograph the target. The camera 20 of the first embodiment uses an all-sky camera for meteorological observation and includes the sky in the imaging area with the all-sky camera pointed upward in the vertical direction. The all-sky camera uses a fisheye lens that allows a single camera to capture a wide area, including targets around the camera's location.
Fig. 2 shows an example of an image captured by the camera 20. Fig. 3 is an explanatory view of an imaging area Ar1 in the image captured by the camera 20. As shown in Fig. 2 and Fig. 3, the imaging area Ar1 of the camera 20 is rectangular. An sky region S1 is included in the center of the imaging area Ar1. The sky region S1 includes a sun S2, a cloud S3 and a blue sky S4 depending on weather conditions. Outside the sky area S1 in the imaging area Ar1, a surrounding environment S5 of the camera 20 is visible. The surrounding environment S5 includes natural objects such as trees, mountains and the ground, as well as structures such as buildings. On the outside of the surrounding environment S5, a part of a housing 21 of the camera 20 appears in an annular shape. As shown in Fig. 4, the camera 20 has a lens unit 22 provided on a top surface of the housing 21 and a transparent hemispherical dome cover 23 covering the lens unit 22. As shown by an arrow in Fig. 4, light containing sunlight is reflected by the top surface (top) of the housing 21 and reaches the lens unit 22, so that the housing 21 appears in the annular shape in the image captured by the camera 20. An image G1 obtained from the camera 20 has known pixels and orientation in the image. In particular, the positional relationship between the pixel position and the target is known in the areas other than the sky area S1.
As shown in Fig. 1, the weather observation system 1 has an image acquisition unit 11, a pixel value acquisition unit 12, and an estimation unit 10. The estimation unit 10 has a solar radiation estimation unit 13 and a power generation estimation unit 14. The weather observation system 1 has a storage 1a, and the storage 1a has a solar radiation conversion formula D1 (correlation data) and a power generation conversion formula D2 (correlation data). These units are realized by the cooperation of software and hardware in a computer equipped with a processor (processing circuitry) 1b such as a CPU, storage 1a such as a memory, various interfaces, etc., where the processor 1b executes a program stored in memory beforehand.
One example of a hardware configuration is that each unit 11 ~ 18 is implemented in a cloud or server, and the camera 20, a solar radiation meter 24, and a solar power generation system 25 are configured to be able to communicate with the cloud or server.
The image acquisition unit 11 acquires the image G1 acquired by a camera 20 that contains at least a sky in the imaging area Ar1. The imaging area Ar1 of the image G1 includes the housing 21 of the camera 20. Image G1 is a color image and contains RGB components or components convertible to RGB components.
The pixel value acquisition unit 12 acquires a pixel value G2 of a specific area S6 in the imaging area Ar1 of the image G1 acquired by the image acquisition unit 11. The specific area S6 is at least a part of the housing 21 that appears annularly in the image G1. As an example, as shown in Fig. 5, an average value (based on statistical values) of the pixel values of a plurality of pixels in a lower end P1 of the annular housing 21 in image G1 is used.
In the first embodiment, the lightness value is acquired as the pixel value G2. The lightness value can be calculated by the following formula:
Lightness value = Red component (R) x 0.299 + Green component (G) x 0.587 + Blue component (B) x 0.114
Lightness value = Red component (R) x 0.299 + Green component (G) x 0.587 + Blue component (B) x 0.114
The solar radiation estimation unit 13 (the estimation unit 10) generates a solar radiation estimate value G3 that correlates with the pixel value G2 acquired by the pixel value acquisition unit 12 using the solar radiation conversion formula D1 (correlation data) stored in the storage 1a. Specifically, the solar radiation estimation unit 13 generates the solar radiation estimate value G3 by inputting the pixel value G2 (lightness value) into the solar radiation conversion formula D1. The solar radiation conversion formula D1 can be said to be correlation data representing the relationship between solar radiation and pixel values (lightness values). An example of the solar radiation conversion formula D1 is a conversion equation such as solar radiation = lightness value x α 1 + α 2. α1 and α2 are constants.
Using the power generation conversion formula D2 (correlation data) stored in the storage 1a, the power generation estimation unit 14 (the estimation unit 10) calculates a power generation estimate value G4 that correlates with the pixel value G2 acquired by the pixel value acquisition unit 12. Specifically, the power generation estimation unit 14 calculates the power generation estimate value G4 by inputting the pixel value G2 (lightness value) into the power generation conversion formula D2. The power generation conversion formula D2 can be said to be correlation data representing the relationship between power generation and pixel values (lightness values). An example of the power generation conversion formula D2 is the conversion equation: power generation = lightness value x α3 + α 4. α3 and α4 are constants.
As shown in Fig. 1, the weather observation system 1 does not have to have a function to store and use correlation data (the solar radiation conversion formula D1 and the power generation conversion formula D2) generated by another correlation data generation system in storage 1a and generate correlation data. The weather observation system 1 of the first embodiment has a measured value acquisition unit 15 and a correlation data generation unit 16, and can generate correlation data.
The measured value acquisition unit 15 acquires a measured value measured by a device capable of measuring one of an amount of solar radiation and an amount of power generation. As shown in Fig. 1, the measured value acquisition unit 15 can acquire a solar radiation measured value G5 measured by the device (the solar radiation meter 24) that can measure solar radiation. In addition, the measured value acquisition unit 15 can acquire a power generation measured value G6 by a device (part of the photovoltaic power generation system 25) capable of measuring power generation. The measured values G5 and G6 acquired by the measured value acquisition unit 15 are stored in the storage 1a as solar radiation time-series data D4 and power generation time-series data D5, respectively. The pixel value G2 (lightness value) acquired by the pixel value acquisition unit 12 is stored in the storage 1a as pixel value time series data D3.
The correlation data generation unit 16 generates correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) based on the measurement value (the solar radiation measured value G5, the power generation measured value G6) acquired by the measured value acquisition unit 15 and the pixel value G2 acquired by the pixel value acquisition unit 12. Fig. 6 is a graph illustrating a change in average lightness on a given day. It represents the number of minutes that have elapsed since about 8:30. Fig. 7 is a graph illustrating changes in solar radiation on the same day including the period shown in Fig. 6. The vertical axis shows the amount of solar radiation, and the horizontal axis shows the elapsed time. Fig. 8 is a graph illustrating changes in power generation over the same day, including the period shown in Fig. 6. The vertical axis shows the amount of power generated, and the horizontal axis shows the elapsed time. Times 0 to 180 in Fig. 6 corresponds to the period from about 220 to about 580 in Figs. 7 and 8. It is clear that the changes in the lightness values shown in Fig. 6, the changes in the amount of solar radiation shown in Fig. 7, and the changes in the amount of power generation shown in Fig. 8 are similar in shape, and it can be understood that a high correlation exists between the lightness values and the solar radiation and between the lightness values and the amount of power generation.
The correlation data generation unit 16 generates correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) by comparing the measured values G5 and G6 with the pixel value G2 based on the image G1 captured in the same time period as the measurement time of the measured values G5 and G6. For example, the solar radiation measured value G5 measured at 9:00 on December 20, 2021 is compared with the pixel value G2 (lightness value) based on an image taken at the same time. In the example of Figs. 6 ~ 8, there is a comparison between the data shown in Fig. 6 and the data shown in Fig. 7, and there is a comparison between the data shown in Fig. 6 and the data shown in Fig. 8. The same time periods mentioned here are preferably the same, but need not be exactly the same. The same time zone is preferably, but is not limited to, the same time when the camera time and the instrument time are synchronized. For example, the same time zone may have a time difference of about 10 minutes, more preferably within 2 minutes, more preferably within 1 minute, and more preferably within 10 seconds.
In addition, the correlation data generation unit 16 may generate the correlation data not only by one set of the measured value and the pixel value, but also by comparing the pixel value with the multiple sets of the measured value within the same period among the multiple combinations of the measured value and the pixel value based on the image captured in the same time zone as the measurement time of the measured value. According to the example in Figs. 6 ~ 8, there are multiple sets of measured values and pixel values as data from 0:00 to 23:00 on December 20, 2021, and among them, the correlation data is generated by comparing multiple sets of measured values and pixel values in the same period from 9:00 to 18:00 on the same day. This means that comparisons between measurements and pixel values are narrowed down to data within the same period, thereby improving the accuracy of correlation data. In the first embodiment, a fitting method such as the least-squares method is used to generate the transformation equation, but it is not limited to this example.
As shown in Fig. 1, the weather observation system 1 has a weather condition acquisition unit 17 that acquires weather conditions. Weather conditions include, for example, the percentage of clouds in the sky area S1, the season (date), and the temperature. The correlation data generation unit 16 may generate a plurality of correlation data based on weather conditions. For example, the correlation data generation unit 16 generates correlation data for cloudy weather and correlation data for clear weather. Cloudy weather means that the percentage of clouds in the sky area S1 is greater than a predetermined threshold, and clear weather means that the percentage of clouds in the sky area S1 is less than the predetermined threshold. The correlation data generation unit 16 may also generate correlation data in spring, correlation data in summer, correlation data in fall, and correlation data in winter. Seasons can be classified by date, for example, winter from December to February, spring from March to May, summer from June to August, and autumn from September to November. The estimation unit 10 (the solar radiation estimation unit 13, the power generation estimation unit 14) can switch the correlation data used by the weather condition acquisition unit 17 according to the weather condition.
In the first embodiment, the correlation data generation unit 16 makes it possible to refer to the estimated value (the solar radiation estimate value G3, the power generation estimate value G4) estimated by the estimation unit 10 (the solar radiation estimation unit 13, the power generation estimation unit 14). In addition, the correlation data generation unit 16 can refer to the measurement value (the solar radiation measured value G5, the power generation measured value G6) acquired by the measured value acquisition unit 15. The correlation data generation unit 16 may generate correlation data again when there is a difference of a predetermined or larger value between the estimated value calculated using the correlation data and the acquired measurement value. This regenerates correlation data in the event of a discrepancy (difference) between the estimate and the actual measurement that is assessed as unacceptable. Thus, when the estimation accuracy by the correlation data deteriorates as time elapses from the time when the last correlation data is generated, the correlation data is generated again, so that the estimation accuracy can be maintained.
The correlation data generation unit 16 in the first embodiment may generate the correlation data again after a predetermined time elapses from the time when the correlation data is previously generated. Deterioration of estimation accuracy due to aging can be suppressed, and estimation accuracy can be maintained.
As shown in Fig. 1, the weather observation system 1 may have an output unit 19 that outputs the prediction results of a prediction unit 18 and the prediction unit 18. The prediction unit 18 refers to the image G1 acquired by the image acquisition unit 11 and the estimated value (the solar radiation estimate value G3, the power generation estimate value G4), and predicts the amount of solar radiation or power generation in the time after the time when the image is imaged based on the weather information in the image G1 captured by the camera 20. Weather information in image G1 includes cloud position, cloud advection, and sun position. The prediction unit 18 predicts the amount of solar radiation and the amount of power generated after 10 minutes, for example. For example, it determines whether a cloud stream shields the sun or how long after shielding the sun it flows to a position that does not shield the sun, and predicts values based on estimates (the solar radiation estimate value G3, the power generation estimate value G4). The result predicted by the prediction unit 18 may be displayed on a Web screen by the output unit 19 or transmitted to the destination terminal via a distribution server. The output unit 19 may be called a display unit or a distribution unit.
The correlation data generation unit 16 may generate the correlation data again when there is a difference of a predetermined or larger value between the predicted value predicted by the prediction unit 18 and the acquired measurement value. In this way, if a discrepancy (difference) occurs between the predicted value and the actual value that is evaluated as unacceptable, the correlation data is generated again. Thus, when the prediction accuracy of the prediction unit 18 referring to the value estimated by the correlation data deteriorates as time elapses from the time when the last correlation data is generated, the correlation data is generated again, so that the prediction accuracy can be maintained.
A weather observation method executed by the weather observation system 1 will be described with reference to Fig. 9. Fig. 9 is a flow chart showing the weather observation method executed by the weather observation system 1 of the first embodiment.
In step ST100 shown in Fig. 9, the camera 20 captures the image G1 containing at least the sky in the imaging area Ar1. In the next step ST101, the image acquisition unit 11 acquires the image G1 captured by the camera 20. The image G1 captured by the camera 20 is recorded and transmitted via a communication section of the camera 20 to the server or cloud where the image acquisition unit 11 is mounted.
The image acquisition unit 11 receives the image G1. In the next step ST102, the pixel value acquisition unit 12 acquires the pixel value G2 (lightness value) in the specific area S6 of the image G1 and stores it in the storage 1a. In the next step ST103, the estimation unit 10 (the Solar radiation estimation unit 13, the power generation estimation unit 14) acquires correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) representing the relationship between the measured value, which is either the amount of solar radiation or the amount of power generated, and the pixel value G2. In the next step ST104, the estimation unit 10 (the solar radiation estimation unit 13, the power generation estimation unit 14) generates an estimated value (the solar radiation estimate value G3, the power generation estimate value G4) correlated with the pixel value G2 using the correlation data.
(1) In the first embodiment, the all-sky camera is installed facing upward in the vertical direction, but it is not limited to this. For example, an all-sky camera may be set sideways along a horizontal direction to image one or more targets in a particular orientation. In addition, the first all-sky camera, which is oriented in the first direction, and the second all-sky camera, which is oriented in the opposite direction to the first direction, may be installed back-to-back.
Also, thecamera 20 need not be an all-sky camera using a fisheye lens, but a non-all-sky camera capable of photographing only a specific orientation.
Also, the
(2) In the first embodiment, the lightness value is used as the pixel value G2, but if it is a pixel value, it is not limited to the lightness value. For example, brightness may be used as the pixel value G2. Brightness is a value based on the maximum or minimum value of each RGB component.
(3) The specific area S6 with a plurality of pixels to be calculated for the pixel value G2 may include natural objects in the image G1 or objects fixed on the ground. In the first embodiment, the housing 21 of the camera 20 is fixed to the ground, but it is not limited to this. For example, specific areas include the sides of buildings such as buildings, concrete blocks, and the poles of streetlights. The specific area S6 is preferably a region other than the sky area S1, which can include the sun S2, the cloud S3 and the blue sky S4. The specific area S6 is a fringe part of the image.
(4) The specific area S6 of the first embodiment is the housing 21 of the camera 20, but it is not limited to this, and may be an object that is directly exposed to sunlight. It is preferable that the object receives direct sunlight, but it may be an object that does not receive direct sunlight if it is outdoors, for example, on the north side of a building.
(5) Although the specific area S6 of the first embodiment is only the lower end P1 shown in Fig. 5, it is not limited to this, and a plurality of places may be set and pixel values of a plurality of places may be used. In particular, in Fig. 5, in a first part P2 of a certain orientation of the sun, the pixel value (lightness value, etc.) may be abnormally high due to the reflection of the dome cover 23 or the camera lens. Therefore, it may be assumed that the specific area S6 includes the lower end P1, the first part P2, a second part P3, and a third part P4, and that the specific area S6 is arranged in a plurality of orientations as viewed from the installation position of the camera 20. By using specific areas arranged in the plurality of orientations, outliers of pixel values caused by the sun can be avoided to become dominant, which can improve estimation accuracy.
(6) The pixel value G2 is an average value of the pixel values of a plurality of pixels in a specific area S6, but is not limited to a value based on a statistical value of the pixel values. For example, median, mode, etc. are available. Since the value is based on a statistical value, adverse effects caused by outliers can be reduced.
(7) In the first embodiment, the correlation data is a transformation expression, but is not limited to this. For example, it may be a table that associates pixel values with estimates, or it may be a trained model (a solar radiation model D11, a power generation model D12) generated by machine learning, as shown in Fig. 11. Examples of trained models include deep neural networks (DNNs), neural networks other than DNNs, recurrent neural networks (RNNs), long-short term models (LSTMs), CNN, support vector machines (SVMs), Bayesian networks, linear regression, regression trees, multiple regression, random forests, ensembles and other learning algorithms. For example, when multiple regression with multiple types of variables is used, the correlation data may be presented by a transformation equation with polynomial regression.
(8) As described in (7) above, as shown in Fig. 11, when the correlation data is a trained model (the solar radiation model D11, the power generation model D12), the correlation data generation unit 16 becomes a so-called learning unit. Based on the training data, the learning unit may generate a trained model that outputs an estimated value that is either the amount of solar radiation or the amount of power generated when pixel value data is input. The training data may consist, for example, of pixel-value data (the pixel-value time series data D3) obtained from the sky-containing image G1 acquired by the camera 20, and measurement data (the solar radiation time series data D4, the power generation time series data D5).
(9) In the case of (8) above, it can be said that the weather observation system 1 executes the method of generating the trained model shown in Fig. 10. Fig. 10 is a flow chart illustrating the trained model generation process executed by the weather observation system 1 of the modified example of the first embodiment. In step ST200 shown in Fig. 10, the camera 20 captures the image G1 containing at least the sky in the imaging area Ar1. In the next step ST201, the image acquisition unit 11 acquires the image G1 captured up by the camera 20. The image G1 captured by the camera 20 is recorded and transmitted via the communication section of the camera 20 to the server or cloud where the image acquisition unit 11 is mounted. The image acquisition unit 11 receives the image G1. In the next step ST202, the pixel value acquisition unit 12 acquires the pixel value G2 (lightness value) in the specific area S6 of the image G1 and stores it in the storage 1a. In the next step ST203, the measured value acquisition unit 15 acquires the measured value (the solar radiation measured value G5, the power generation measured value G6) measured by a device capable of measuring either the amount of solar radiation or the amount of power generated, and stores it in the storage 1a. In the next step ST204, the correlation data generation unit 16 acquires the measured value (the solar radiation measured value G5, the power generation measured value G6) measured by the device capable of measuring the measurement value of either solar radiation or power generation. In the next step ST205, the correlation data generation unit 16 generates a trained model (the solar radiation model D11, the power generation model D12) that outputs an estimated value that is either the amount of solar radiation or the amount of power generated when the pixel value data is input, based on the acquired training data.
(10) The correlation data generation unit 16 and the measured value acquisition unit 15 in the first embodiment can be omitted if they do not generate correlation data.
(11) The weather observation system 1 of the first embodiment is a system for estimating both solar radiation and power generation, but it may be a system for estimating only either solar radiation or power generation.
Although not particularly limited to the above, as in the first embodiment and variants, the weather observation system 1 may be equipped with the image acquisition unit 11 that acquires the image G1 acquired by the camera 20 that contains at least the sky in the imaging area Ar1, the pixel value acquisition unit 12 that acquires the pixel value G2 of a specific area S6 within the imaging area Ar1, and the estimation unit 10 (the solar radiation estimation unit 13, the power generation estimation unit 14) that calculates an estimated value (the solar radiation estimate value G3, the power generation estimate value G4) that is either the amount of solar radiation or the amount of power generated that is correlated with the pixel value G2 using correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) that represents the relationship between the measured value, which is either the amount of solar radiation or the amount of power generated, and the pixel value G2. Although not particularly limited, as in the first embodiment and its variants, the meteorological observation method may acquire the image G1 acquired by the camera 20, which contains at least the sky in the imaging area Ar1, acquire the pixel value G2 of the specific area S6 within the imaging area Ar1, and calculate an estimate, which is either the amount of solar radiation or the amount of power generated, that correlates with the pixel value G2 using correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) that represents the relationship between the measured value, which is either the amount of solar radiation or the amount of power generated, and the pixel value G2.
The estimated value (the solar radiation estimate value G3, the power generation estimate value G4) correlated with the pixel value G2 is calculated using correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) representing the relationship between the pixel value G2 of the specific area S6 in the image G1 including the sky and the measured value (either the solar radiation measured value G5 or the power generation measured value G6), so that the solar radiation or power generation can be estimated in real time.
Although not particularly limited, as in the first embodiment, the specific area S6 may include natural objects in image G1 or objects fixed on the ground. This is a preferred embodiment.
Although not particularly limited, as in the first embodiment, the specific area S6 may include an object that directly receives the illumination of sunlight. Objects that are directly exposed to sunlight have variable pixel values depending on the amount of solar radiation, which can improve estimation accuracy.
Although not particularly limited, as in a variation of the first embodiment, the specific area S6 may be arranged in a plurality of directions as viewed from the installation position of the camera 20. It makes it possible to reduce the influence of abnormal pixel values that may occur in response to the movement of the sun.
Although not particularly limited, as in the first embodiment and variants, the pixel value G2 may be a lightness value or a brightness value. Lightness or brightness values can be used to estimate solar radiation or power generation because they vary with solar radiation.
Although not particularly limited, the pixel value G2 may be a value based on a statistical value in a specific area S6, as in the first embodiment and variant. It is possible to reduce adverse effects caused by outliers.
Although not particularly limited, the system may further include, as in the weather observation system 1 of the first embodiment, the measured value acquisition unit 15 for acquiring measurement values (the solar radiation measured value G5, the power generation measured value G6) measured by a device capable of measuring either solar radiation or power generation, and the correlation data generation unit 16 for generating correlation data based on the measured values G5 and G6 acquired by the measured value acquisition unit 15 and the pixel value G2 acquired by the pixel value acquisition unit 12. Correlation data is generated based on the pixel values used for estimation and the measured measurements, thus facilitating system operation.
Although not particularly limited, as in the weather observation system 1 of the first embodiment, the weather condition acquisition unit 17 for acquiring weather conditions may be further provided, and the correlation data generation unit 16 may generate a plurality of correlation data based on weather conditions. Since the plurality of correlation data are generated based on weather conditions, appropriate correlation data can be used according to weather conditions, which can improve estimation accuracy.
Although not particularly limited, as in the first embodiment, the correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) may be generated by comparing the measured values G5 and G6 with the pixel value G2 based on the image G1 captured at the same time as the measured time of the measured value. This is a preferred embodiment.
Although not particularly limited, as in the first embodiment, the correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) may be generated by comparing a plurality of sets of measured values and pixel values within the same period among a plurality of combinations of measured values G5, G6 and pixel value G2 based on image G1 captured in the same time period as the measurement time of the measured value. The accuracy of correlation data can be improved.
Although not particularly limited, as in the first embodiment, the correlation data generation unit 16 may generate the correlation data again when there is a difference of a predetermined or larger value between the estimated value calculated using the correlation data and the acquired measurement value. Since the correlation data is generated again when the estimation accuracy by the correlation data deteriorates, the estimation accuracy can be maintained.
Although not particularly limited, as in the first embodiment, the correlation data generation unit 16 may generate the correlation data again after a predetermined time elapses from the time when the correlation data is previously generated. Deterioration of estimation accuracy due to aging can be suppressed, and estimation accuracy can be maintained.
Although not particularly limited, as in the weather observation system 1 of the first embodiment, the system may further include the prediction unit 18 that predicts the amount of solar radiation or the amount of power generated in the time period after the present time (after the time when the image is taken) based on the weather information in the image G1 captured by the camera 20. It will be possible to provide a system that can predict the amount of solar radiation or power generated at any time after the present.
Although not particularly limited, as in a variation of the first embodiment, the correlation data generation unit 16 may acquire training data consisting of pixel value data obtained from an image including the sky acquired by the camera 20 and measurement value data measured by a device capable of measuring either the amount of solar radiation or the amount of power generated, and generate a trained model (correlation data) that outputs an estimated value that is either the amount of solar radiation or the amount of power generated when the pixel value data is input based on the acquired training data.
Although not particularly limited, as in the first embodiment, the weather observation system 1 may further include a camera 20.
The program according to the first embodiment is a program that causes one or more processors to execute the above method. Although not particularly limited, the program according to the first embodiment may cause one or more processors to perform processing to acquire the image G1 acquired by the camera 20, which contains at least the sky in the imaging area Ar1, to acquire the pixel value of the specific area S6 in the imaging area Ar1, and to calculate an estimated value, which is either the amount of solar radiation or the amount of power generated, correlated with the pixel value G2, using correlation data (the solar radiation conversion formula D1, the power generation conversion formula D2) representing the relationship between the measured value, which is either the amount of solar radiation or the amount of power generated, and the pixel value.
Although not particularly limited, the program relating to the modified example of the first embodiment may have one or more processors execute processing to acquire training data consisting of pixel value data obtained from an image including the sky acquired by the camera 20 and measurement data measured by a device capable of measuring either the amount of solar radiation or the amount of power generated, and to generate a trained model (correlation data) that outputs an estimated value that is either the amount of solar radiation or the amount of power generated when the pixel value data is input based on the acquired training data. A temporary recording medium readable by a computer stores the above program.
As described above, the embodiment of the present disclosure has been described based on the drawings, but the specific configuration should not be considered to be limited to these embodiments. The scope of this disclosure is indicated by the claims as well as by the description of the above embodiment, and further includes all modifications within the meaning and scope of the claims.
For example, the execution order of each process, such as operations, procedures, steps, and steps in the devices, systems, programs, and methods presented in the claims, description, and drawings, can be realized in any order unless the output of the previous process is used in the later process. The use of "first," "second," etc., for convenience in describing the flow in the claims, the description, and the drawings does not mean that it is mandatory to carry out the procedures in this order.
Each unit shown in Fig. 1 is realized by executing a prescribed program by one or a processor, but each unit may be composed of a dedicated memory or a dedicated circuit.
In the system of the above embodiment, the components are implemented in the processor of one computer, but the components may be distributed and implemented in a plurality of computers or clouds. That is, the above method may be performed on one or more processors.
It is possible to adopt the structure adopted in each of the above embodiment to any other embodiment. In Figure 1, each unit is implemented for illustrative purposes, but some of these units can be omitted arbitrarily.
List of Reference Numerals
1 Weather observation system
20 Camera
10 Estimation unit
11 Image acquisition unit
12 Pixel value acquisition unit
13 Solar radiation estimation unit (Estimation unit)
14 Power generation estimation unit (Estimation unit)
15 Measured value acquisition unit
16 Correlation data generation unit
17 Weather condition acquisition unit
18 Prediction unit
Ar1 imaging area
D1 Solar radiation conversion formula (correlation data)
D2 Power generation conversion formula (correlation Data)
S6 Specific area
1 Weather observation system
20 Camera
10 Estimation unit
11 Image acquisition unit
12 Pixel value acquisition unit
13 Solar radiation estimation unit (Estimation unit)
14 Power generation estimation unit (Estimation unit)
15 Measured value acquisition unit
16 Correlation data generation unit
17 Weather condition acquisition unit
18 Prediction unit
Ar1 imaging area
D1 Solar radiation conversion formula (correlation data)
D2 Power generation conversion formula (correlation Data)
S6 Specific area
Claims (18)
- A weather observation system (1), comprising:
an image acquisition unit (11) configured to acquire an image captured by a camera (20) that contains the sky in an imaging area (Ar1);
a pixel value acquisition unit (12) configured to acquire a pixel value of a specific area (S6) within the imaging area (Ar1); and
an estimation unit (10) configured to generate an estimated value using correlation data representing a relationship between the pixel value and a measured value. - The weather observation system (1) according to claim 1, wherein the estimated value is one of an amount of solar radiation and an amount of power generation and a measured value is one of the amount of solar radiation and the amount of power generation.
- The weather observation system (1) according to claim 1 or claim 2, wherein the specific area (S6) includes a natural object or an object fixed to the ground in the image.
- The weather observation system (1) according to any one of claim 1 to 3, wherein the specific area (S6) includes an object that is directly exposed to sunlight.
- The weather observation system (1) according to any one of claims 1 to 4, wherein the specific area (S6) is arranged in a plurality of orientations (P1, P2, P3, P4) as viewed from a location of the camera (20).
- The weather observation system (1) according to any one of claims 1 to 5, wherein the pixel value is a lightness value or a brightness value.
- The weather observation system (1) according to any one of claims 1 to 6, wherein the pixel value is a value based on statistical values in the specific area (S6).
- The weather observation system (1) according to any one of claims 1 to 7, wherein:
the correlation data is a trained model which outputs the estimated value when pixel value data obtained from the image captured by the camera (20) is input, and
the estimation unit (10) is further configured to acquire an estimated value by inputting the pixel value data into the trained model. - The weather observation system (1) according to any one of claims 1 to 8, further comprising:
a measured value acquisition unit (15) configured to acquire a measured value measured by a device capable of measuring either the amount of solar radiation or the amount of power generation; and
a correlation data generation unit (16) configured to generate the correlation data based on the measured value acquired by the measured value acquisition unit (15) and the pixel value acquired by the pixel value acquisition unit (12). - The weather observation system (1) according to claim 9, further comprising:
a weather condition acquisition unit (17) configured to acquire weather conditions, wherein:
the correlation data generation unit (16) is further configured to generate a plurality of the correlation data based on each of the weather conditions. - The weather observation system (1) according to claim 9 or 10, wherein the correlation data is generated by comparing the measured value with the pixel value based on an image captured during the same time period as the measured time of the measured value.
- The weather observation system (1) according to any one of claims 9 to 11, wherein the correlation data generation unit (16) generates the correlation data when there is a difference of a predetermined or larger value between the estimated value calculated using the correlation data and the acquired measurement value.
- The weather observation system (1) according to any one of claims 9 to 11, wherein the correlation data generation unit (16) generates the correlation data after a predetermined time elapses from the time when the correlation data is last generated.
- The weather observation system (1) according to any one of claims 1 to 13, further comprising a prediction unit configured to predict an amount of solar radiation or an amount of power generation after the time of capturing the image based on weather information in the image captured by the camera (20).
- The weather observation system (1) according to any one of claims 1 to 14, wherein:
the image is an image taken by an all-sky camera, and
the specific area (S6) is a fringe part in the image. - A weather observation method, comprising:
acquire an image captured by a camera (20) that contains the sky in an imaging area (Ar1);
acquire a pixel value of a specific area (S6) within the imaging area (Ar1); and
generate an estimated value using correlation data representing a relationship between the pixel value and a measured value. - A trained model generation method, comprising:
acquire training data consisting of a pixel value obtained from an image containing the sky acquired by a camera (20) and a measured value measured by a device capable of measuring one of an amount of solar radiation and an amount of power generation; and
outputs an estimated value that is one of an amount of solar radiation and an amount of power generation when the pixel value is input, based on an acquired training data. - A non-transitory computer-readable medium having stored thereon computer-executable instructions which, when executed by a computer, cause the computer to:
execute the weather observation method according to claim 16.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2022-015474 | 2022-02-03 | ||
JP2022015474A JP2023113256A (en) | 2022-02-03 | 2022-02-03 | Meteorological observation system, meteorological obversion method, generation method of learning model and program |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023149101A1 true WO2023149101A1 (en) | 2023-08-10 |
Family
ID=87552180
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2022/046247 WO2023149101A1 (en) | 2022-02-03 | 2022-12-15 | Weather observation system, weather observation method, trained model generation method, and program |
Country Status (2)
Country | Link |
---|---|
JP (1) | JP2023113256A (en) |
WO (1) | WO2023149101A1 (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007184354A (en) | 2006-01-05 | 2007-07-19 | Mitsubishi Electric Corp | Solar photovoltaic power generation system |
JP2019086325A (en) * | 2017-11-02 | 2019-06-06 | 国立大学法人九州工業大学 | Insolation quantity estimation system and insolation quantity estimation method |
DE102017129299A1 (en) * | 2017-12-08 | 2019-06-13 | Institut Für Luft- Und Kältetechnik Gemeinnützige Gmbh | Method for local weather forecast |
-
2022
- 2022-02-03 JP JP2022015474A patent/JP2023113256A/en active Pending
- 2022-12-15 WO PCT/JP2022/046247 patent/WO2023149101A1/en active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007184354A (en) | 2006-01-05 | 2007-07-19 | Mitsubishi Electric Corp | Solar photovoltaic power generation system |
JP2019086325A (en) * | 2017-11-02 | 2019-06-06 | 国立大学法人九州工業大学 | Insolation quantity estimation system and insolation quantity estimation method |
DE102017129299A1 (en) * | 2017-12-08 | 2019-06-13 | Institut Für Luft- Und Kältetechnik Gemeinnützige Gmbh | Method for local weather forecast |
Also Published As
Publication number | Publication date |
---|---|
JP2023113256A (en) | 2023-08-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR101879332B1 (en) | Method for calculating amount of cloud from whole sky image and apparatus thereof | |
KR101890673B1 (en) | Method for calculating amount of cloud from whole sky image and apparatus thereof | |
US9007460B2 (en) | Methods and systems for predicting cloud movement | |
WO2017193153A1 (en) | Solar power forecasting | |
US10989839B1 (en) | Ground-based sky imaging and irradiance prediction system | |
EP2891904A1 (en) | Solar irradiance forecasting | |
CN109167997B (en) | Video quality diagnosis system and method | |
KR100981428B1 (en) | Forest fire monitoring system and method | |
JP6817109B2 (en) | Lighting control method and lighting control system | |
US20180136366A1 (en) | Distributed solar energy prediction imaging | |
US20040169770A1 (en) | All sky imager | |
JP5567411B2 (en) | Sky pattern determination system and sky pattern determination method | |
WO2020179326A1 (en) | Cloud observation device, cloud observation method, and program | |
CN105611184A (en) | White balance debugging method and debugging system of digital video device | |
WO2023149101A1 (en) | Weather observation system, weather observation method, trained model generation method, and program | |
JP6601084B2 (en) | Inspection method and inspection system | |
Bruno et al. | Influence of illumination changes on image-based 3D surface reconstruction | |
KR20070028812A (en) | Method and apparatus for monitoring forest fire using images photographed by camera device | |
CN111882550A (en) | Hail detection method, hail detection device, computer equipment and readable storage medium | |
US20230015683A1 (en) | Moving object detection system and information management apparatus | |
KR20230145687A (en) | Monitoring system for photovoltaic electric power station | |
Herrera-Carrillo et al. | Solar irradiance estimation based on image analysis | |
RU2589463C1 (en) | Device for determining total amount of clouds on basis of direct digital wide-angle images of visible hemisphere of sky | |
CN114339028A (en) | Photographing method, electronic device and computer-readable storage medium | |
KR100615672B1 (en) | Fire observation system using xy axis projection graph and its fire observation method and computer-readable recording medium to realize fire observation method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22925005 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022925005 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2022925005 Country of ref document: EP Effective date: 20240903 |