WO2020179326A1 - 雲観測装置、雲観測方法、及びプログラム - Google Patents
雲観測装置、雲観測方法、及びプログラム Download PDFInfo
- Publication number
- WO2020179326A1 WO2020179326A1 PCT/JP2020/004220 JP2020004220W WO2020179326A1 WO 2020179326 A1 WO2020179326 A1 WO 2020179326A1 JP 2020004220 W JP2020004220 W JP 2020004220W WO 2020179326 A1 WO2020179326 A1 WO 2020179326A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- cloud
- image
- observation device
- sunshine
- movement information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/12—Sunshine duration recorders
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/02—Instruments for indicating weather conditions by measuring two or more variables, e.g. humidity, pressure, temperature, cloud cover or wind speed
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06V10/60—Extraction of image or video features relating to illumination properties, e.g. using a reflectance or lighting model
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W2203/00—Real-time site-specific personalized weather information, e.g. nowcasting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30192—Weather; Meteorology
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/10—Recognition assisted with metadata
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Definitions
- the present disclosure relates to a cloud observation device, a cloud observation method, and a program.
- Satellites are mainly used for conventional cloud observation. Since satellites observe clouds from the sky, it is not possible to obtain a detailed distribution of clouds near the ground. Therefore, it is not possible to grasp the amount of sunshine and the duration of sunshine on the ground.
- Patent Document 1 images of the sky taken sequentially by a camera are acquired, a sun region and a cloud region are specified for each image, the moving direction and moving speed of clouds are calculated based on each image, and a predetermined image is determined. There is a statement that the position of the cloud after the time is predicted and the ratio of hiding the sun by the cloud is calculated.
- Patent Document 1 has to calculate the moving locus of the cloud of interest until after a predetermined time has passed, and further to perform the predictive calculation of the moving locus of all clouds on the image, so that the calculation cost is low. Not low. Further, since the movement locus is calculated for each cloud, the prediction calculation method may be complicated in order to calculate the sunshine probabilities at a plurality of time points.
- the present disclosure has focused on such issues, and an object thereof is to provide a cloud observation device, a cloud observation method, and a program capable of predicting the sunshine probability by a simple method and reducing calculation cost. It is to be.
- the cloud observation device of the present disclosure is An image acquisition unit that acquires an image of the sky taken by the camera, A cloud extraction unit that extracts clouds in the image, A sun identification unit for identifying the sun position in the image, In the image, a determination area setting unit that sets a determination area based on the sun position, A sunshine calculation unit that calculates the sunshine probability after a predetermined time elapses based on the determination area and the extracted clouds, and Equipped with.
- Block diagram showing the configuration of the cloud observation system of the first embodiment of the present disclosure Flow chart executed by the cloud observation device of the first embodiment Image showing an image of the sky taken by the camera Block diagram showing a modification of the first embodiment Explanatory drawing about the algorithm which recognizes the same cloud from the 1st image and the 2nd image in 1st Embodiment Explanatory drawing about the algorithm which recognizes the same cloud from the 1st image and the 2nd image in 1st Embodiment Explanatory drawing about the algorithm which recognizes the same cloud from the 1st image and the 2nd image in 1st Embodiment Explanatory drawing regarding calculation of determination area and sunshine probability superimposed on image The figure which shows the modification of the determination area
- the cloud observation system 1 of the present embodiment includes a camera 10 that captures the sky and a computer 11 that processes an image of the sky captured by the camera 10.
- the camera 10 may be any camera as long as it can photograph the sky.
- an omnidirectional camera using a fisheye lens is installed facing upward in the vertical direction. Therefore, the center of the image obtained from the camera 10 is directly above (elevation angle 90 °), and the elevation angle becomes smaller toward the edge of the image from the center.
- the cloud observation device 11 realized by the computer of the present embodiment processes an image taken by the camera 10 in the sky.
- the cloud observation device 11 includes an image acquisition unit 12, a cloud extraction unit 13, a sun identification unit 14, a cloud movement information acquisition unit 15, and a determination area setting unit 16. , And a sunshine calculation unit 17.
- These units 12 to 17 cooperate with each other in software and hardware by causing the processor 11b to execute a program stored in advance in the memory 11a in a computer 11 including a processor 11b such as a CPU, a memory 11a, and various interfaces. Will be realized.
- the image acquisition unit 12 illustrated in FIG. 1 acquires images G1 and G2 in which the camera captures the sky.
- the second image G2 is an image taken one minute before the first image G1.
- the center of the image is directly above, and the clouds (C1, C2, C3) and the sun (S1) are shown.
- the image acquisition unit 12 acquires a plurality of images in which the camera sequentially captures the sky.
- the shooting timing is every one minute, but the timing is not limited to this, and may be a predetermined timing.
- the predetermined timing can be changed variously, such as every few seconds, every few minutes, when a random length of time elapses, when one or more predetermined times are reached, and the like.
- the image shown in FIG. 3 contains an RGB component and shows a blue sky, clouds (C1, C2, C3) and the sun (S1).
- the cloud extraction unit 13 shown in FIG. 1 extracts clouds in the image.
- the cloud extraction unit 13 identifies and extracts a pixel that is a cloud from a plurality of pixels constituting the image.
- An algorithm for determining a cloud and a sky in this embodiment will be described.
- the brightness value 255 is white and the brightness value 0 is black.
- the brightness value of the blue component and the brightness value of the red component of the cloud are both 0 to 255, and the brightness value of the blue component of the sky is 0 to 255. It was found that the brightness of the red component is 0 or almost 0.
- the difference between the brightness of the blue component and the brightness of the red component is large, it can be determined to be the sky, and when the difference between the two is small, it can be determined to be the cloud.
- the cloud identification method is not limited to this, and various methods may be adopted.
- the sun identifying unit 14 illustrated in FIG. 1 identifies the sun position in the image.
- the first specific example for determining the sun utilizes the fact that the position of a pixel reflected in an image can be specified based on the position (latitude / longitude) of the camera and the date and time of imaging by using astronomy. That is, the sun identifying unit 14 determines the pixel that is the sun based on the camera position and the date and time when the image was captured.
- the sun identification unit 14 is a region extending radially from the center point of the pixel group having the maximum brightness in the image, and the brightness gradually decreases as the distance from the center point increases. Then, it is determined that the area before the pulsation of the brightness starts is the sun.
- the method of identifying the sun is not limited to this, and various methods may be adopted.
- the cloud movement information acquisition unit 15 illustrated in FIG. 1 acquires cloud movement information in an image.
- the cloud movement information acquired by the cloud movement information acquisition unit 15 of the present embodiment includes the cloud movement direction and the cloud movement speed, but is not limited to this. For example, if the cloud movement information includes at least the cloud movement direction, the cloud movement speed can be omitted.
- the cloud movement information acquisition unit 15 calculates cloud movement information in each image based on a plurality of images that are sequentially captured. By doing so, cloud movement information (movement direction, movement speed) can be acquired only from the image. Specifically, the cloud movement information acquisition unit 15 calculates the cloud movement information of each of the clouds C1 to C3 by comparing the plurality of images G1 and G2. In FIG. 3, the moving directions of the clouds C1, C2, and C3 are indicated by arrows. The cloud movement speed can be expressed by the length of the arrow. The example of FIG. 3 shows that all the clouds C1, C2, and C3 are moving from west to east, so that the directions of the arrows indicating the moving directions are all the same, and the image illustrated in FIG.
- the cloud moving direction of each cloud C1, C2, and C3 is indicated by the curvature according to the distance from the position right above (center of the image).
- the auxiliary line is indicated by a dotted line for reference.
- ⁇ Same cloud identification unit 18> In the embodiment shown in FIG. 1, the same cloud that identifies the cloud in the second image G2 taken before the first image G1 is identified from the clouds (C1, C2, C3) in the first image G1. It has a cloud identification unit 18.
- the cloud C1 in the first image G1 is the corresponding cloud C1 in the second image G2
- the cloud C2 in the first image G1 is the corresponding cloud C2 in the second image G2
- the cloud C3 in is the corresponding cloud C3 in the second image G2.
- the cloud movement information acquisition unit 15 determines the cloud movement information based on the position of the cloud (C1, C2, C3) in the first image G1 and the position of the corresponding cloud (C1, C2, C3) in the second image G2. (See the arrow in FIG. 3) is calculated.
- the corresponding clouds are identified from the first image G1 and the second image G2, and the cloud movement information (movement direction, movement speed) is calculated based on the positions of the corresponding clouds. Therefore, the clouds can be processed only by image processing. Movement information can be acquired appropriately.
- the same cloud identification unit 18 includes a set setting unit 18a, a set removal unit 18b, and an identification unit 18c.
- the set setting unit 18a shown in FIG. 1 sets a plurality of sets in which the clouds in the first image and the clouds in the second image are combined in at least one-to-one, one-to-many, or many-to-one relationship.
- FIG. 5 is an example in which a plurality of sets (P1 to P4) are set in which the clouds (C01, C02) in the first image G1 and the clouds (C03, C04, C05, C06) in the second image G2 are combined one-on-one. Shown. In the figure, the positions of the centers of gravity of each cloud are shown in circles, and the closest centers of gravity are combined. The figure shows four sets P1, P2, P3, P4. FIG.
- FIG. 6 shows a cloud (C01, C02) in the first image G1 and a cloud (C03, C04, C05, C06) in the second image G2 for the plurality of sets (P1 to P4) shown in FIG. It is explanatory drawing for setting a plurality of sets which combined many-to-one.
- a synthetic cloud C0A, C0B, C0C
- the synthetic cloud C0A, C0B, C0C
- a plurality of pairs (P5, P6, P7) with clouds (C01, C02) are generated.
- the closest center of gravity positions are combined.
- the set removing unit 18b shown in FIG. 1 is set to at least one of the moving distance between clouds, the amount of size change, the change in brightness, the change in saturation, and the change in hue so that one set is set for one cloud.
- the set set based on the above is deleted.
- the moving distance can be calculated by comparing the barycentric positions of the clouds in the first image G1 and the second image G2.
- the size of the composite cloud can be calculated by the total area of the clouds from which the composite is created. For example, with respect to the set P7 shown in FIG. 6, the two clouds C03 and C05 forming the composite cloud C0C are too far from the center of gravity of the corresponding cloud C01, and thus may be deleted. Further, with regard to the set P3 shown in FIG.
- the size change amount of the cloud C05 of the second image G2 and the cloud C01 of the first image G1 is large, it may be targeted for deletion.
- the threshold value may be determined by a person, may be determined in advance by statistical processing, or a machine-learned model may be determined by teaching data.
- the identification unit 18c illustrated in FIG. 1 identifies that the cloud of the first image G1 and the corresponding cloud of the second image G2 are the same cloud based on the remaining set.
- the clouds corresponding to at least one of the moving distance between clouds, the size change amount, the luminance change, the saturation change, and the hue change are determined based on the index value.
- the set P5 based on at least one of the moving distance between clouds, the size change amount, the brightness change, the saturation change, and the hue change, it is assumed that the set P5 most meets the conditions. It is determined that the clouds C03 and 04 in the two images G2 and the clouds C01 in the first image G1 are the same cloud.
- the identification unit 18c needs to determine one set so that a plurality of sets are not set for one cloud, the evaluation value is the highest in consideration of the above index values comprehensively. Selecting a pair can be mentioned.
- At least one of the pair removing unit 18b and the identifying unit 18c has at least one of a moving distance between clouds, a size change amount, a brightness change, a saturation change, and a hue change as an input value, and is to be deleted.
- You may implement using the determination device which determines using the machine learning (For example, deep neural network (DNN)) which outputs the output value which shows whether it is a selection object.
- DNN deep neural network
- the set may be selected such that one set is set for one cloud based on one set.
- the cloud movement information acquisition unit 15 shown in FIG. 1 calculates cloud movement information based on the cloud position in the first image G1 and the corresponding cloud position in the second image G2, as shown in FIG.
- the cloud movement information can be calculated by comparing the barycentric position m1 of the cloud C01 in the first image G1 with the barycentric position m2 of the corresponding clouds C03 and C04 in the second image G2.
- the cloud movement information can be calculated by comparing the barycentric position m3 of the cloud C02 in the first image G1 with the barycentric position m4 of the corresponding cloud C06 in the second image G2.
- the cloud movement information acquisition unit 15 stores the position of the cloud in each image as time-series data, averages the cloud movement direction in each image, and calculates the cloud movement direction in the cloud movement information. It is preferable that the cloud moving speed in each image is averaged to calculate the cloud moving speed in the cloud moving information.
- various moving averages such as simple moving average, weighted moving average, and exponential moving average can be used.
- the determination area setting unit 16 shown in FIG. 1 sets the determination area Ar1 with the sun position S1 as the base point in the image.
- the determination area Ar1 is wider on the upstream side (west) in the cloud movement direction D1 than on the downstream side (east) with the sun position S1 as the base point.
- the base point of the sun position S1 may be the center or the circumference of the pixel or region indicating the sun, and what other points are based on the sun position S1.
- the determination region Ar1 preferably has a region extending from the sun position S1 side toward the upstream side (west) in the cloud movement direction.
- the upstream side (west) of the cloud movement direction D1 with the sun position S1 as the base point is the region where the possibility that the cloud will reach the sun over time is higher than the downstream side (east), and the prediction accuracy of the sunshine probability can be determined. This is to improve.
- the determination area Ar1 has a width equal to or larger than a predetermined value in the direction D3 orthogonal to the direction D2 moving away from the sun position S1.
- a predetermined value it is preferable that the width is 10 degrees or more about the virtual center line from the sun position S1 toward the upstream side D2 in the cloud movement direction D1. This is because the cloud moving direction may change with the passage of time, and if the determination region Ar1 has a width equal to or larger than a predetermined value, it is possible to cope with the possibility that the cloud moving direction changes. That is, if the width is wide, it is possible to cope with a large change in the cloud movement direction.
- the length W1 of the determination area Ar1 in the direction D2 away from the sun position S1 is preferably set according to the cloud moving speed with the sun position S1 as the starting point.
- the length W1 can be appropriately set according to the time width and cloud movement speed from the present to the future where the sunshine probability is expected. For example, when predicting after 10 minutes, if the cloud moving speed is fast, the length W1 needs to be set long, and conversely, if the cloud moving speed is slow, the length W1 needs to be set short.
- the determination region Ar1 has a shape in which the width widens toward the direction D2 away from the sun position S1.
- the sunshine calculation unit 17 illustrated in FIG. 1 calculates the sunshine probability after a predetermined time has elapsed, based on the determination area Ar1 and the extracted cloud. Specifically, as shown in FIG. 8, the sunshine calculation unit 17 calculates the sunshine probability after a lapse of a predetermined time based on the distance W2 from the extracted cloud to the sun position S1 and the cloud movement speed. In the example of FIG. 8, since the time for the cloud to reach the sun position S1 can be calculated based on the distance W2 and the cloud moving speed, it can be calculated that the cloud becomes cloudy after the calculated time elapses. Similarly, the time when the cloud passes through the sun position S1 can be calculated in the same manner.
- the sunshine calculation unit 17 can calculate the sunshine probability after 1 minute based on the overlapping area of the determination region Ar2 corresponding to after 1 minute and the extracted cloud, for example.
- the determination area Ar2 is an area having a predetermined radius centered on the sun position S1. If the overlapping area of the clouds occupying the determination region Ar2 is 100%, the solar radiation probability is 0%.
- the sunshine probability after 2 minutes can be calculated based on the overlapping area of the corresponding determination region Ar3 after 2 minutes and the extracted cloud.
- the sunshine probability with the passage of time can be calculated for each time series.
- step ST100 the image acquisition unit 12 acquires the image G1 obtained by the camera 10 capturing the sky.
- the cloud extraction unit 13 extracts clouds in the image.
- the cloud movement information acquisition unit 15 acquires the cloud movement information including at least the cloud movement direction in the image.
- the sun identification unit 14 identifies the position of the sun in the image.
- the determination area setting unit 16 sets the determination area Ar1 based on the sun position S1 in the image.
- the sunshine calculation unit 17 calculates the sunshine probability after a lapse of a predetermined time based on the determination area Ar1 and the extracted cloud.
- the embodiment shown in FIG. 1 is configured to acquire cloud movement information from a plurality of images, but is not limited to this.
- the cloud movement information acquisition unit 115 may be configured to acquire cloud movement information from a device 115a such as an external anemometer or meteorological server.
- the determination region Ar1 has a shape that widens in the direction away from the sun position S1, but is not limited to this.
- a shape having a constant width in the direction away from the sun position S1 may be used, as in the determination area Ar4 shown in FIG.
- the shape may have no width in the direction D3 orthogonal to the direction D2 away from the sun position S1.
- the phrase having no width means that the number of pixels constituting the width is one pixel.
- the shape has a region Ar60 extending from the sun position S1 side toward the upstream side of the cloud movement direction D1 and a region Ar61 near the periphery centered on the sun position S1.
- the shape extends from the sun position S1 side toward the upstream side in the cloud movement direction D1, but may have a shape avoiding the vicinity of the center of the sun position S1.
- the determination region Ar8 shown in FIG. 13 may have a fan shape without considering the curvature of the fisheye lens, or the determination region Ar8 may be corrected in consideration of the curvature of the fisheye lens as in the determination region Ar9 in the figure. You may make it into the shape.
- the cloud movement information acquisition unit 15 acquires a plurality of cloud movement information (cloud movement directions D1, D1'), and the determination area setting unit 16 acquires a plurality of cloud movement information (cloud movement directions). It is preferable that a plurality of determination regions Ar10 and Ar11 are set based on D1 and D1'), and the sunshine calculation unit 17 is configured to calculate the sunshine probability for each of the plurality of determination regions Ar10 and Ar11.
- the determination region is set based on the cloud movement direction, and the sunshine probability is calculated based on whether or not the determination region and the extracted cloud overlap, but the present invention is not limited to this.
- the determination area setting unit 16 sets the determination area Ar12 with the sun position S1 as a base point.
- the determination region Ar12 shown in FIG. 15 has a circular shape centered on the sun position S1, but may have any shape as long as the sun position S1 is used as a base point. As shown in FIG.
- the sunshine calculation unit 17 includes a weighting coefficient set in which the upstream side D2 in the cloud movement direction D1 is more important than the leeward side D1 with the sun position S1 as the base point, and the determination area Ar12.
- the sunshine probability after a predetermined time has elapsed is calculated based on the extracted cloud.
- the weighting coefficient is represented by a number, and the larger the weighting coefficient, the higher the importance.
- a weighting factor (1.0 to 0.9) indicating that the degree of importance is high is set in the portion corresponding to the fan-shaped determination area Ar1 shown in FIG.
- a weight coefficient (0.01) indicating that the degree of importance is low is set for the part. According to this configuration, it is possible to calculate the sunshine probability in the same meaning as the fan-shaped determination area Ar1 shown in FIG. Note that setting the determination region based on the cloud moving direction shown in FIGS. 1 to 14 and using the weighting factor can be used together.
- the cloud observation device 11 of the present embodiment is An image acquisition unit 12 that acquires an image G1 of the sky captured by the camera; A cloud extraction unit 13 for extracting clouds in the image G1, A sun identifying unit 14 that identifies the sun position S1 in the image G1, A determination area setting unit 16 for setting determination areas (Ar1, Ar4 to 12) based on the sun position S1 in the image G1; The sunshine calculation unit 17 that calculates the sunshine probability after a predetermined time elapses based on the determination area and the extracted clouds, and Equipped with.
- the cloud observation method of this embodiment is The camera acquires an image G1 of the sky (ST100), Extracting clouds in the image G1 (ST101), Specifying the sun position S1 in the image G1 (ST103), In the image G1, determination regions (Ar1, Ar4 to 12) having the sun position S1 as a base point are set (ST104), To calculate the sunshine probability after a predetermined time elapses based on the judgment area and the extracted clouds (ST105), including.
- the sunshine probability after a lapse of a predetermined time is calculated based on the determination regions (Ar1, Ar4 to 12) set with the sun position S1 as the base point and the clouds, the position after the lapse of the predetermined time is predicted for each cloud.
- the determination area (Ar1, Ar4 to 12) There is no need, and it suffices to determine whether or not a cloud exists in the determination area (Ar1, Ar4 to 12).
- the cloud movement information acquisition unit (15, 115) that acquires the cloud movement information including at least the cloud movement direction D1 in the image G1 is provided, and the determination area setting unit 16 is It is preferable to set the determination regions (Ar1, Ar4 to 11) based on the cloud movement direction with the position S1 as the base point.
- the determination regions (Ar1, Ar4 to 11) can be set in consideration of the cloud movement direction D1, and it is possible to improve the prediction accuracy of the sunshine probability.
- the determination region setting unit 16 determines the determination region (Ar1, Ar4 to Ar4 to be wider) on the upstream side D2 in the cloud moving direction D1 than on the downstream side D1 with the sun position S1 as a base point. It is preferable to set 11).
- the cloud is more likely to reach the sun over time on the upstream side D2 than on the downstream side D1 in the cloud movement direction with the sun position S1 as the base point. In this way, if there is a cloud, it is possible to set a region in which the cloud is likely to reach the sun over time in consideration of the cloud moving direction D1, and it is possible to improve the prediction accuracy of the sunshine probability. Become.
- the cloud movement information includes the cloud movement speed, and the length W1 of the determination area Ar1 in the direction D2 moving away from the sun position S1 depends on the cloud movement speed starting from the sun position S1. It is preferable to set.
- the length W1 can be set appropriately according to the time width and cloud movement speed from the present to the future where the sunshine probability is expected.
- the cloud movement information includes the cloud movement speed
- the sunshine calculation unit 17 elapses a predetermined time based on the distance from the extracted cloud to the sun position S1 and the cloud movement speed. It is preferable to calculate the later sunshine probability.
- the sunshine calculation unit 17 preferably calculates the sunshine probability after a lapse of a predetermined time based on the overlapping area of the determination area Ar1 (Ar2, Ar3) and the extracted cloud. ..
- the sunshine probability can be calculated from the ratio of the overlapping area to the judgment area.
- the determination regions (Ar1, Ar4 to 11) have a region extending from the sun position S1 side toward the upstream side D2 in the cloud movement direction D1.
- the upstream side D2 in the cloud movement direction D1 from the sun position S1 side sets a region in which the cloud is likely to reach the sun over time, so that the prediction accuracy of the sunshine probability can be improved. It will be possible.
- the determination regions (Ar1, Ar4, Ar6 to 11) have a width equal to or larger than a predetermined value in the direction D3 orthogonal to the direction D2 away from the sun position S1. Is preferable.
- the cloud moving direction D1 may change over time, and the cloud moving direction D1 may change when the determination regions (Ar1, Ar4, Ar6 to 11) have a width of a predetermined value or more. Therefore, it is possible to improve the prediction accuracy of the sunshine probability.
- the determination regions (Ar1, Ar4, Ar6 to 11) have a shape that widens in the direction D2 away from the sun position S1.
- the determination region (Ar1, Ar4, Ar6 to 11) is moved to the sun position S1.
- the sunshine calculation unit 17 determines that the weighting coefficient is set such that the upstream side D2 of the cloud movement direction D1 with the sun position S1 as the base point is set to have a higher degree of importance than the downstream side D1. It is preferable to calculate the sunshine probability after a predetermined time elapses based on the region Ar12 and the extracted clouds.
- the image acquisition unit 12 acquires a plurality of images G1 and G2 in which the camera sequentially captures the sky, and the cloud movement information acquisition unit 15 sequentially captures the images. It is preferable to calculate cloud movement information in each of the images G1 and G2 based on the plurality of images G1 and G2 that have been created.
- the cloud movement information acquisition unit 15 includes the same cloud identification unit 18 that identifies the cloud (C01) corresponding to C04), and the cloud movement information acquisition unit 15 includes the position of the cloud (C01) in the first image G1 and the corresponding cloud (C01) in the second image G2. It is preferable to calculate the cloud movement information based on the positions of C03 and C04).
- the clouds (C01, C02) in the first image G1 and the clouds (C03 to 06) in the second image G2 are one-to-one, one-to-many, or many-to-one.
- a set setting unit 18a for setting a plurality of sets (P1 to P7) combined in at least one of the relationships, and Set removal is performed based on at least one of moving distance between clouds, size change amount, brightness change, saturation change amount, and hue change amount so that one set is set for one cloud.
- Part 18b It is preferable to have an identification unit 18c that identifies that the cloud of the first image G1 and the corresponding cloud of the second image G2 are the same cloud based on the remaining set.
- the cloud movement information is calculated by averaging at least the movement directions of the clouds in the image G1 (G2).
- the cloud movement information is preferably calculated by a moving average over a plurality of images G1 and G2.
- the cloud movement information acquisition unit 15 acquires a plurality of cloud movement information
- the determination area setting unit 16 determines a plurality of determination areas Ar10 and Ar11 based on the plurality of cloud movement information. It is preferable that the sunshine calculation unit 17 calculates the sunshine probability for each of the determination regions Ar10 and Ar11.
- the moving direction and speed may differ for each cloud depending on the altitude of the cloud, and it is possible to calculate the sunshine probability independently for clouds with different cloud movement information.
- the cloud observation system 1 includes a camera 10 and the above-mentioned cloud observation device 11.
- the program according to the present embodiment is a program that causes a computer to execute the above method.
- the computer-readable temporary recording medium according to the present embodiment stores the above program.
- the cloud observation system 101 the cloud observation device 111, and the cloud observation method according to the second embodiment of the present disclosure will be described.
- the same components as those in the first embodiment are designated by the same reference numerals and the description thereof will be omitted.
- the cloud observation device 111 of the second embodiment does not provide the sunshine calculation unit 17, but instead provides the superimposed image generation unit 19.
- the superimposed image generation unit 19 generates an image in which the determination area Ar1 is superimposed on the image G1 (G2).
- the generated image is displayed on the display provided in the cloud observation device 11 or transmitted to an external computer, and finally displayed on the display.
- Each unit 12 to 17 shown in FIG. 2 is realized by executing a predetermined program by one or a processor, but each unit may be configured by a dedicated memory or a dedicated circuit.
- the respective units 12 to 17 are mounted on the processor 11b of one computer 11, but the respective units 12 to 17 may be dispersed and mounted on a plurality of computers or a cloud. That is, it may be executed by a plurality of processors.
- each of the above embodiments it is possible to adopt the structure adopted in each of the above embodiments in any other embodiment.
- the units 12 to 17 are mounted for convenience of description, but some of them may be omitted arbitrarily.
- an embodiment in which each part 12 to 14 is mounted can be mentioned.
- All processes described herein may be embodied by software code modules executed by a computing system including one or more computers or processors and may be fully automated.
- the code module can be stored on any type of non-transitory computer-readable medium or other computer storage device. Some or all of the methods may be embodied in dedicated computer hardware.
- any particular action, event, or function of any of the algorithms described herein may be performed in different sequences and may be added, merged, or excluded altogether. (For example, not all described acts or events are required to execute an algorithm). Further, in certain embodiments, the actions or events may be executed in parallel rather than serially, eg, via multithreaded processing, interrupt processing, or through multiple processors or processor cores, or on other parallel architectures. Can be done. In addition, different tasks or processes can be performed by different machines and / or computing systems that can work together.
- the various exemplary logic blocks and modules described in connection with the embodiments disclosed herein can be implemented or executed by a machine such as a processor.
- the processor may be a microprocessor, but instead, the processor may be a controller, a microcontroller, or a state machine, or a combination thereof.
- the processor can include electrical circuitry configured to process computer-executable instructions.
- the processor comprises an application specific integrated circuit (ASIC), field programmable gate array (FPGA), or other programmable device that performs logical operations without processing computer-executable instructions.
- ASIC application specific integrated circuit
- FPGA field programmable gate array
- a processor may also be a combination of computing devices, such as a combination of digital signal processors (digital signal processors) and microprocessors, multiple microprocessors, one or more microprocessors in combination with DSP cores, or any other thereof. It can be implemented as such a configuration. Although described primarily with respect to digital technology herein, the processor may also include primarily analog elements. For example, some or all of the signal processing algorithms described herein may be implemented by analog circuits or mixed analog and digital circuits.
- a computing environment includes any type of computer system including, but not limited to, a microprocessor, mainframe computer, digital signal processor, portable computing device, device controller, or computing engine-based computer system within an apparatus. be able to.
- conditional languages such as “capable”, “capable”, “possible”, or “possible” refer to particular features, elements and/or steps that a particular embodiment includes. Embodiments are understood in the sense of the context commonly used to convey what is not included. Thus, such conditional languages are generally any method in which features, elements and / or steps are required for one or more embodiments, or one or more embodiments are these features. It is not meant to necessarily include logic to determine whether an element and/or step is included in or executed by any particular embodiment.
- a disjunctive language such as the phrase "at least one of X, Y, and Z" is an item, term, etc., any of X, Y, Z, or any combination thereof, unless otherwise specified. Understood in the context commonly used to indicate that it can be (eg X, Y, Z). Thus, such a disjunctive language generally requires at least one of X, at least one of Y, or at least one of Z, each of which has a particular embodiment. Does not mean.
- Numerals such as “one” should generally be construed to include one or more described items unless specifically stated otherwise.
- terms such as “one device configured to” are intended to include one or more listed devices.
- Such one or more enumerated devices may also be collectively configured to perform the recited citations.
- a processor configured to perform A, B, and C below refers to a first processor configured to perform A and a second processor configured to perform B and C.
- a specific number enumeration of the introduced examples is explicitly recited, one of ordinary skill in the art will appreciate that such an enumeration will typically be at least the recited number (e.g., other modifiers).
- the term “horizontal” as used herein, regardless of its orientation, is a plane parallel to the plane or surface of the floor of the area in which the described system is used, or description. Is defined as the plane in which the method is performed.
- the term “floor” can be replaced with the terms “ground” or “water surface”.
- the term “vertical/vertical” refers to the direction vertical/vertical to the defined horizontal line. Terms such as “upper”, “lower”, “lower”, “upper”, “side”, “higher”, “lower”, “upper”, “beyond”, and “lower” are defined for the horizontal plane. ing.
- connection/coupling includes direct connection and/or connection having an intermediate structure between the two described components.
- the numbers preceded by terms such as “approximately,” “about,” and “substantially” as used herein include the enumerated numbers, and further. Represents an amount near the stated amount that performs a desired function or achieves a desired result. For example, “approximately,” “about,” and “substantially” mean values less than 10% of the stated values, unless otherwise stated.
- features of the embodiments in which the terms such as “approximately”, “about”, and “substantially” are previously disclosed perform the desired function as well. Or represents a feature with some variability in achieving that desired result.
Landscapes
- Engineering & Computer Science (AREA)
- Environmental & Geological Engineering (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Image Analysis (AREA)
Abstract
Description
カメラが空を撮影した画像を取得する画像取得部と、
前記画像における雲を抽出する雲抽出部と、
前記画像における太陽位置を特定する太陽特定部と、
前記画像において、前記太陽位置を基点とする判定領域を設定する判定領域設定部と、
前記判定領域と前記抽出された雲とに基づき所定時間経過後の日照確率を算出する日照算出部と、
を備える。
以下、本開示の第1実施形態を、図面を参照して説明する。
図1に示すように、本実施形態の雲観測システム1は、空を撮影するカメラ10と、カメラ10が空を撮影した画像を処理するコンピュータ11と、を有する。カメラ10は空を撮影することができれば、どのようなカメラでもよい。本実施形態では、空の広範囲を1つのカメラで撮影するために、魚眼レンズを用いた全天カメラを鉛直方向上向きに向けて設置している。そのため、カメラ10から得られる画像は、中心が真上(仰角90°)となり、中心から画像の端に向かうにつれて仰角が小さくなる。
図1に示す画像取得部12は、図3に示すように、カメラが空を撮影した画像G1、G2を取得する。図3の例では、第2画像G2は、第1画像G1の1分前に撮影された画像である。画像中央が真上であり、雲(C1、C2、C3)と太陽(S1)が写っている。本実施形態において画像取得部12は、カメラが空を逐次撮影した画像を複数取得する。本実施形態では撮影のタイミングは1分毎であるが、これに限定されず、所定タイミングであればよい。所定タイミングには、数秒毎、数分毎、ランダムな長さの時間が経過するごと、予め定められた1つ以上の時刻になったときなど、種々変更可能である。図3に示す画像は、RGB成分を含み、青色の空、雲(C1、C2、C3)及び太陽(S1)が写っている。
図1に示す雲抽出部13は、画像における雲を抽出する。雲抽出部13は、画像を構成する複数の画素から雲である画素を識別して抽出する。本実施形態における雲と空を判定するためのアルゴリズムについて説明する。輝度値255が白、輝度値0が黒とする。発明者らは研究の結果、雲の青色成分の輝度値及び赤色成分の輝度値は共に0~255の値になり、空の青色成分の輝度値は0~255の値になるが、空の赤色成分の輝度は0又はほぼ0になることが判明した。すなわち、青色成分の輝度と赤色成分の輝度の差が大きい場合には、空であり、両者の差が小さい場合には雲であると判定できる。本実施形態では、画像を構成する複数の画素について、画素の輝度に基づき雲であるかを判定する。具体的には、青色成分の輝度から赤色成分の輝度を引いた差値が所定閾値未満であれば、当該画素は雲であると判定し、前記差値が所定閾値以上であれば、当該画素は雲ではないと判定する。勿論、雲の識別方法は、これに限定されず、種々の方法を採用してもよい。
図1に示す太陽特定部14は、画像における太陽位置を特定する。太陽を判定するための第1の具体例は、天文学を利用すれば、カメラの位置(緯度経度)及び撮像した日時に基づき、画像に写り込む画素の位置が特定可能であることを利用する。すなわち、太陽特定部14は、カメラ位置及び撮像した日時に基づいて太陽である画素を判定する。太陽を判定するための第2の具体例は、太陽特定部14は、画像における輝度が最大となる画素群の中心点から放射状に広がる領域であって、中心点から離れるにつれて輝度が脈動なく漸減し且つ輝度の脈動が開始するまでの領域が太陽であると判定する。勿論、太陽の特定方法は、これに限定されず、種々の方法を採用してもよい。
図1に示す雲移動情報取得部15は、画像における雲移動情報を取得する。本実施形態の雲移動情報取得部15が取得する雲移動情報には、雲移動方向及び雲移動速度が含まれるが、これに限定されない。例えば、雲移動情報に少なくとも雲移動方向が含まれていれば、雲移動速度は省略可能である。
図1に示す実施形態では、第1画像G1における雲(C1、C2、C3)の中から、第1画像G1よりも前に撮影された第2画像G2における雲に対応する雲を識別する同一雲識別部18を有する。図3の例では、第1画像G1における雲C1が第2画像G2における対応する雲C1であり、第1画像G1における雲C2が第2画像G2における対応する雲C2であり、第1画像G1における雲C3が第2画像G2における対応する雲C3である、と識別する。そして雲移動情報取得部15は、第1画像G1における雲(C1、C2、C3)の位置と、第2画像G2における対応する雲(C1、C2、C3)の位置とに基づき、雲移動情報(図3の矢印参照)を算出する。このように、第1画像G1及び第2画像G2から対応する雲同士を識別し、対応する雲同士の位置に基づき雲移動情報(移動方向、移動速度)を算出するので、画像処理だけで雲移動情報を適切に取得可能となる。
図1に示す判定領域設定部16は、図8に示すように、画像において、太陽位置S1を基点とする判定領域Ar1を設定する。同図に示すように、判定領域Ar1は、太陽位置S1を基点として、雲移動方向D1の上流側の方(西)が下流側(東)よりも広いことが好ましい。太陽位置S1の基点とは、太陽を示す画素又は領域のうち、中心であっても良いし、円周上であっても良いし、その他、太陽位置S1を基準としていれば、どのような点であっても良い。また、図8に示すように、判定領域Ar1は、太陽位置S1側から雲移動方向の上流側(西)に向けて延びる領域を有することが好ましい。太陽位置S1を基点として雲移動方向D1の上流側の方(西)が、時間経過によって雲が太陽に到達する可能性が下流側(東)よりも高い領域であり、日照確率の予測精度を向上させるためである。
図1に示す日照算出部17は、判定領域Ar1と、抽出された雲とに基づき所定時間経過後の日照確率を算出する。具体的には、図8に示すように、日照算出部17は、抽出された雲から太陽位置S1までの距離W2と、雲移動速度とに基づき所定時間経過後の日照確率を算出する。図8の例では、距離W2と雲移動速度に基づき雲が太陽位置S1に到達する時間が算出できるため、算出した時間経過後には曇となることが算出できる。同様に、雲が太陽位置S1を通りぬける時間も同様に算出できる。
上記システム1が実行する、雲観測方法について図2を参照しつつ説明する。
図1に示す実施形態では、複数の画像から雲移動情報を取得するように構成されているが、これに限定されない。例えば、図4に示すように、外部の風速計、気象サーバなどの機器115aから雲移動情報を取得するように雲移動情報取得部115を構成してもよい。
図8に示す実施形態では、判定領域Ar1は、太陽位置S1から離れる方向に向かって幅が広がる形状であるが、これに限定されない。例えば、図9に示す判定領域Ar4のように、太陽位置S1から離れる方向に向かって幅が一定である形状でもよい。また、図10に示す判定領域Ar5のように、太陽位置S1から離れる方向D2に直交する方向D3に幅を有さない形状であってもよい。幅を有さないとは、幅を構成する画素が1ピクセルであることを意味する。また、図11に示す判定領域Ar6のように、太陽位置S1側から雲移動方向D1の上流側に向けて延びる領域Ar60と、太陽位置S1を中心とする周囲近傍の領域Ar61と、を有する形状であってもよい。
また、図12に示す判定領域Ar7のように、太陽位置S1側から雲移動方向D1の上流側に向けて延びているが、太陽位置S1の中心近傍を避けた形状にしてもよい。また、図13に示す判定領域Ar8のように魚眼レンズの曲率を考慮せずに扇形状にしてもよいし、同図における判定領域Ar9のように、判定領域Ar8を魚眼レンズの曲率を考慮して補正した形状にしてもよい。
上記の例では、全ての雲が同程度の高度にあり、雲移動方向及び雲移動速度が同じであるとしているが、これに限定されない。例えば、雲の高度によって雲毎に移動方向及び速度が異なる場合がある。このような場合には、単一の判定領域ではなく、複数の判定領域を設けることが好ましい。すなわち、図14に示すように、雲移動情報取得部15は、雲移動情報(雲移動方向D1、D1')を複数取得し、判定領域設定部16は、複数の雲移動情報(雲移動方向D1、D1')に基づいて複数の判定領域Ar10、Ar11を設定し、日照算出部17は、複数の判定領域Ar10、Ar11毎に日照確率を算出するように構成することが好ましい。
図1~14に示す実施形態では、雲移動方向に基づいて判定領域を設定し、判定領域と抽出された雲との重複の有無に基づき日照確率を算出しているが、これに限定されない。例えば、図15に示すように、判定領域設定部16は、判定領域Ar12を、太陽位置S1を基点として設定する。図15に示す判定領域Ar12は、太陽位置S1を中心とした円形であるが、太陽位置S1を基点としていれば、どのような形状でもよい。日照算出部17は、図15に示すように太陽位置S1を基点として雲移動方向D1の上流側D2の方が風下側D1よりも重要度が高く設定された重み係数と、判定領域Ar12と、抽出された雲とに基づき所定時間経過後の日照確率を算出する。図15では、重み係数を数字で表現しており、重み係数が大きければ重要度が高いことを意味する。図15の例では、図8に示す扇形状の判定領域Ar1に対応する部位に、重要度が高いことを示す重み係数(1.0~0.9)が設定されており、扇形状以外の部位には、重要度が低いことを示す重み係数(0.01)が設定されている。この構成によれば、図8に示す扇形状の判定領域Ar1と同じ意味で日照確率を算出することが可能となる。なお、図1~14に示す雲移動方向に基づき判定領域を設定することと、重み係数を用いることは併用可能である。
カメラが空を撮影した画像G1を取得する画像取得部12と、
画像G1における雲を抽出する雲抽出部13と、
画像G1における太陽位置S1を特定する太陽特定部14と、
画像G1において、太陽位置S1を基点とする判定領域(Ar1、Ar4~12)を設定する判定領域設定部16と、
判定領域と抽出された雲とに基づき所定時間経過後の日照確率を算出する日照算出部17と、
を備える。
カメラが空を撮影した画像G1を取得すること(ST100)、
画像G1における雲を抽出すること(ST101)、
画像G1における太陽位置S1を特定すること(ST103)、
画像G1において、太陽位置S1を基点とする判定領域(Ar1、Ar4~12)を設定する(ST104)、
判定領域と抽出された雲とに基づき所定時間経過後の日照確率を算出すること(ST105)、
を含む。
1つの雲に対して1つの組が設定されるように、雲同士の移動距離、サイズ変化量、輝度変化、彩度変化量、色相変化量の少なくとも1つに基づき、組を削除する組除去部18bと、
残った組に基づき、第1画像G1の雲と第2画像G2における対応する雲とが同一雲であると識別する識別部18cと、を有することが好ましい。
本開示の第2実施形態の雲観測システム101、雲観測装置111及び雲観測方法について説明する。第1実施形態と同じ構成については同じ符号を付して説明を省略する。第2実施形態の雲観測装置111は、図16に示すように、日照算出部17を設けずに、代わりに重畳画像生成部19を設けている。重畳画像生成部19は、図8に示すように、画像G1(G2)に判定領域Ar1を重畳させた画像を生成する。生成された画像は、雲観測装置11に設けられたディスプレイに表示される又は外部のコンピュータに向けて送信され、最終的にディスプレイに表示される。
12 画像取得部
13 雲抽出部
14 太陽特定部
15、115 雲移動情報取得部
16 判定領域設定部
17 日照算出部
18 同一雲識別部
18a 組設定部
18b 組除去部
18c 識別部
19 重畳画像生成部
G1 画像(第1画像)
G2 画像(第2画像)
Claims (21)
- カメラが空を撮影した画像を取得する画像取得部と、
前記画像における雲を抽出する雲抽出部と、
前記画像における太陽位置を特定する太陽特定部と、
前記画像において、前記太陽位置を基点とする判定領域を設定する判定領域設定部と、
前記判定領域と前記抽出された雲とに基づき所定時間経過後の日照確率を算出する日照算出部と、
を備える、雲観測装置。 - 請求項1に記載の雲観測装置であって、
前記画像における、少なくとも雲移動方向を含む雲移動情報を取得する雲移動情報取得部を備え、
前記判定領域設定部は、前記太陽位置を基点として、前記雲移移動方向に基づいた判定領域を設定する、雲観測装置。 - 請求項2に記載の雲観測装置であって、
前記判定領域設定部は、前記太陽位置を基点として、前記雲移動方向の上流側の方が下流側よりも広い判定領域を設定する、雲観測装置。 - 請求項2又は3に記載の雲観測装置であって、
前記雲移動情報は、雲移動速度を含み、
前記判定領域の前記太陽位置から離れる方向の長さは、前記太陽位置を始点として前記雲移動速度に応じて設定される、雲観測装置。 - 請求項2乃至請求項4のいずれか一項に記載の雲観測装置であって、
前記雲移動情報は、雲移動速度を含み、
前記日照算出部は、前記抽出された雲から前記太陽位置までの距離と、前記雲移動速度と、に基づき所定時間経過後の日照確率を算出する、雲観測装置。 - 請求項2乃至請求項5のいずれか一項に記載の雲観測装置であって、
前記日照算出部は、前記判定領域と、前記抽出された雲、との重複面積に基づき所定時間経過後の日照確率を算出する、雲観測装置。 - 請求項2乃至請求項6のいずれか一項に記載の雲観測装置であって、
前記判定領域は、前記太陽位置側から前記雲移動方向の上流側に向けて延びる領域を有する、雲観測装置。 - 請求項2乃至請求項7のいずれか一項に記載の雲観測装置であって、
前記判定領域は、前記太陽位置から離れる方向に直交する方向に所定値以上の幅を有する、雲観測装置。 - 請求項1乃至請求項8のいずれか一項に記載の雲観測装置であって、
前記判定領域は、前記太陽位置から離れる方向に向かって幅が広がる形状である、雲観測装置。 - 請求項1乃至請求項9のいずれか一項に記載の雲観測装置であって、
前記画像における、少なくとも雲移動方向を含む雲移動情報を取得する雲移動情報取得部を備え、
前記日照算出部は、前記太陽位置を基点として前記雲移動方向の上流側の方が下流側よりも重要度が高く設定された重み係数と、前記判定領域と、前記抽出された雲と、に基づき所定時間経過後の日照確率を算出する、雲観測装置。 - 請求項2乃至請求項10のいずれか一項に記載の雲観測装置であって、
前記画像取得部は、カメラが空を逐次撮影した画像を複数取得し、
前記雲移動情報取得部は、前記逐次撮影された複数の画像に基づいて、前記各画像における前記雲移動情報を算出する、雲観測装置。 - 請求項11に記載の雲観測装置であって、
第1画像における雲の中から、前記第1画像よりも前に撮影された第2画像における雲に対応する雲を識別する同一雲識別部を備え、
前記雲移動情報取得部は、前記第1画像における雲の位置と、前記第2画像における対応する雲の位置とに基づき、前記雲移動情報を算出する、雲観測装置。 - 請求項12に記載の雲観測装置であって、
前記同一雲識別部は、
前記第1画像における雲と前記第2画像における雲とを、一対一、一対多又は多対一の少なくともいずれかの関係で組み合わせた組を複数設定する組設定部と、
1つの雲に対して1つの組が設定されるように、雲同士の移動距離、サイズ変化量、輝度変化、彩度変化量、色相変化量の少なくとも1つに基づき、組を削除する組除去部と、
残った組に基づき、前記第1画像の雲と前記第2画像における対応する雲とが同一雲であると識別する識別部と、
を有する、雲観測装置。 - 請求項11乃至請求項13のいずれか一項に記載の雲観測装置であって、
前記雲移動情報は、前記画像における各々雲の少なくとも移動方向を平均して算出される、雲観測装置。 - 請求項14に記載の雲観測装置であって、
前記雲移動情報は、複数の画像にわたる移動平均により算出される、雲観測装置。 - 請求項2乃至請求項15のいずれかに記載の雲観測装置であって、
前記雲移動情報取得部は、前記雲移動情報を複数取得し、
前記判定領域設定部は、前記複数の雲移動情報に基づいて、複数の前記判定領域を設定し、
前記日照算出部は、前記複数の判定領域毎に日照確率を算出する、雲観測装置。 - カメラが空を撮影した画像を取得すること、
前記画像において雲を抽出すること、
前記画像における太陽位置を特定すること、
前記画像において、前記太陽位置を基点とする判定領域を設定すること、
前記判定領域と前記抽出された雲とに基づき所定時間経過後の日照確率を算出すること、
を含む、雲観測方法。 - 請求項17に記載の方法を1又は複数のプロセッサに実行させるプログラム。
- カメラが空を撮影した画像を取得する画像取得部と、
前記画像において雲を抽出する雲抽出部と、
前記画像における、少なくとも雲移動方向を含む雲移動情報を取得する雲移動情報取得部と、
前記画像における太陽位置を特定する太陽特定部と、
前記画像において、前記太陽位置を基点として、前記雲移動方向に基づいた判定領域を設定する判定領域設定部と、
前記画像に前記判定領域を重畳させた重畳画像を生成する重畳画像生成部と、
を備える、雲観測装置。 - カメラが空を撮影した画像を取得すること、
前記画像において雲を抽出すること、
前記画像における、少なくとも雲移動方向を含む雲移動情報を取得すること、
前記画像における太陽位置を特定すること、
前記画像において、前記太陽位置を基点として、前記雲移動方向に基づいた判定領域を設定すること、
前記画像に前記判定領域を重畳させた重畳画像を生成すること、
を含む、雲観測方法。 - 請求項20に記載の方法を1又は複数のプロセッサに実行させるプログラム。
Priority Applications (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP20767339.3A EP3936902B1 (en) | 2019-03-06 | 2020-02-05 | Cloud observation device, cloud observation method, and program |
| JP2021503473A JP7261861B2 (ja) | 2019-03-06 | 2020-02-05 | 雲観測装置、雲観測方法、及びプログラム |
| CN202080018880.9A CN113544548A (zh) | 2019-03-06 | 2020-02-05 | 云观测装置、云观测方法及程序 |
| US17/466,284 US11989907B2 (en) | 2019-03-06 | 2021-09-03 | Cloud observation device, cloud observation method, and program |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2019-040866 | 2019-03-06 | ||
| JP2019040866 | 2019-03-06 |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| US17/466,284 Continuation US11989907B2 (en) | 2019-03-06 | 2021-09-03 | Cloud observation device, cloud observation method, and program |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020179326A1 true WO2020179326A1 (ja) | 2020-09-10 |
Family
ID=72338283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2020/004220 Ceased WO2020179326A1 (ja) | 2019-03-06 | 2020-02-05 | 雲観測装置、雲観測方法、及びプログラム |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US11989907B2 (ja) |
| EP (1) | EP3936902B1 (ja) |
| JP (1) | JP7261861B2 (ja) |
| CN (1) | CN113544548A (ja) |
| WO (1) | WO2020179326A1 (ja) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2022064293A (ja) * | 2020-10-13 | 2022-04-25 | イボクラール ビバデント アクチェンゲゼルシャフト | 歯科補綴物を製造する方法 |
| WO2023091523A1 (en) * | 2021-11-17 | 2023-05-25 | Halio, Inc. | Cloud forecasting for electrochromic devices |
| US11900617B2 (en) | 2021-11-17 | 2024-02-13 | Halio, Inc. | Cloud forecasting for electrochromic devices |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020179326A1 (ja) * | 2019-03-06 | 2020-09-10 | 古野電気株式会社 | 雲観測装置、雲観測方法、及びプログラム |
| CN115565082B (zh) * | 2022-10-21 | 2026-04-28 | 云南电网有限责任公司电力科学研究院 | 一种卫星遥感图像云噪声去除方法、系统和装置 |
| CN117218555B (zh) * | 2023-09-12 | 2025-10-17 | 长光卫星技术股份有限公司 | 基于吉林一号高分系列卫星的多特征融合的云检测方法 |
| WO2025184210A1 (en) * | 2024-02-27 | 2025-09-04 | Accuweather, Inc. | Improved method for estimating solar irradiance at the earth's surface |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS60220843A (ja) * | 1985-03-29 | 1985-11-05 | Hitachi Ltd | 日射量の予測装置 |
| US20100309330A1 (en) * | 2009-06-08 | 2010-12-09 | Adensis Gmbh | Method and apparatus for forecasting shadowing for a photovoltaic system |
| JP2014011345A (ja) | 2012-06-29 | 2014-01-20 | Hitachi Information & Control Solutions Ltd | 発電量予測装置、発電量予測方法、プログラム、および電力制御システム |
| WO2015104281A1 (en) * | 2014-01-07 | 2015-07-16 | Abb Technology Ag | Solar irradiance forecasting |
Family Cites Families (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08335030A (ja) * | 1995-04-07 | 1996-12-17 | Hideo Matsushita | 太陽の経路と地方時を含む日の出日の入り位置推測器 |
| JP3377079B2 (ja) * | 1997-07-09 | 2003-02-17 | 日本電信電話株式会社 | 流速推定装置 |
| JP3345325B2 (ja) * | 1997-06-30 | 2002-11-18 | 株式会社日立製作所 | 液位計測方法及びその装置と量水標 |
| US7417397B2 (en) * | 2004-05-06 | 2008-08-26 | Mechoshade Systems, Inc. | Automated shade control method and system |
| US11187035B2 (en) * | 2004-05-06 | 2021-11-30 | Mechoshade Systems, Llc | Sky camera virtual horizon mask and tracking solar disc |
| CN101246545B (zh) * | 2008-02-22 | 2010-07-07 | 华南师范大学 | 一种光学遥感图像去云的泊松方法 |
| CN101344391B (zh) * | 2008-07-18 | 2011-05-11 | 北京工业大学 | 基于全功能太阳罗盘的月球车位姿自主确定方法 |
| JP2011214423A (ja) * | 2010-03-31 | 2011-10-27 | Jfe Engineering Corp | 廃棄物処理廃熱および太陽熱の複合利用発電装置 |
| US9069103B2 (en) * | 2010-12-17 | 2015-06-30 | Microsoft Technology Licensing, Llc | Localized weather prediction through utilization of cameras |
| WO2013030897A1 (ja) * | 2011-09-02 | 2013-03-07 | 株式会社 日立製作所 | 系統電圧安定化装置および安定化方法 |
| CN103309359B (zh) * | 2012-03-14 | 2018-11-09 | 亮源工业(以色列)有限公司 | 用于操作太阳能塔系统的方法和系统 |
| US9007460B2 (en) * | 2012-03-30 | 2015-04-14 | General Electric Company | Methods and systems for predicting cloud movement |
| JP5797599B2 (ja) * | 2012-04-19 | 2015-10-21 | 株式会社日立パワーソリューションズ | 発電量予測方法及びそのシステム |
| US20140083413A1 (en) * | 2012-09-24 | 2014-03-27 | Brightsource Industries (Israel) Ltd. | Method and apparatus for mapping cloud shading on the ground in a large area |
| CN103019261B (zh) * | 2012-12-27 | 2015-06-24 | 东方电气集团东方锅炉股份有限公司 | 双轴跟踪定日镜方位角标定和检测方法 |
| WO2014109020A1 (ja) * | 2013-01-09 | 2014-07-17 | 株式会社日立製作所 | 気象予測方法及び装置、並びに電力系統制御方法及び装置 |
| CN103513295B (zh) * | 2013-09-25 | 2016-01-27 | 青海中控太阳能发电有限公司 | 一种基于多相机实时拍摄与图像处理的天气监测系统与方法 |
| WO2015157643A1 (en) * | 2014-04-10 | 2015-10-15 | Vega-Avila Rolando | Solar energy forecasting |
| US10444406B2 (en) * | 2014-04-17 | 2019-10-15 | Siemens Aktiengesellschaft | Short term cloud coverage prediction using ground-based all sky imaging |
| US20150302575A1 (en) * | 2014-04-17 | 2015-10-22 | Siemens Aktiengesellschaft | Sun location prediction in image space with astronomical almanac-based calibration using ground based camera |
| CN103986534A (zh) * | 2014-05-29 | 2014-08-13 | 国家电网公司 | 基于辐射计和测距仪的卫星信号通道环境监测系统及方法 |
| EP3875996A1 (en) * | 2014-09-29 | 2021-09-08 | View, Inc. | Sunlight intensity or cloud detection with variable distance sensing |
| US10356317B2 (en) * | 2014-10-30 | 2019-07-16 | Technion Research & Development Foundation Limited | Wide-scale terrestrial light-field imaging of the sky |
| JP2016103900A (ja) * | 2014-11-28 | 2016-06-02 | 株式会社日立製作所 | 蓄電池システム |
| US10345483B2 (en) * | 2015-06-10 | 2019-07-09 | Escaype | Observer-based meteorology and image identification |
| FR3047830B1 (fr) * | 2016-02-12 | 2019-05-10 | Compagnie Nationale Du Rhone | Procede de determination de la direction de deplacement d'objets dans une scene |
| CN105791016A (zh) * | 2016-03-09 | 2016-07-20 | 浪潮通信信息系统有限公司 | 一种基于流式计算的分布式故障管理告警处理系统 |
| WO2017193153A1 (en) * | 2016-05-11 | 2017-11-16 | Commonwealth Scientific And Industrial Research Organisation | Solar power forecasting |
| US10692013B2 (en) * | 2016-06-07 | 2020-06-23 | International Business Machines Corporation | Solar irradiation modeling and forecasting using community based terrestrial sky imaging |
| US10007999B2 (en) * | 2016-08-10 | 2018-06-26 | International Business Machines Corporation | Method of solar power prediction |
| US10303942B2 (en) * | 2017-02-16 | 2019-05-28 | Siemens Aktiengesellschaft | Short term cloud forecast, improved cloud recognition and prediction and uncertainty index estimation |
| CN206684326U (zh) * | 2017-04-12 | 2017-11-28 | 杭州电子科技大学 | 一种全天候的可见光气象观测成像装置 |
| AU2018427962A1 (en) * | 2018-06-14 | 2020-12-24 | Siemens Aktiengesellschaft | Predicting sun light irradiation intensity with neural network operations |
| CN112292620B (zh) * | 2018-06-19 | 2023-06-06 | 古野电气株式会社 | 云观测装置、云观测系统、云观测方法及存储介质 |
| WO2020179326A1 (ja) * | 2019-03-06 | 2020-09-10 | 古野電気株式会社 | 雲観測装置、雲観測方法、及びプログラム |
| WO2020241130A1 (ja) * | 2019-05-29 | 2020-12-03 | 古野電気株式会社 | 情報処理システム、方法、及びプログラム |
| US11588437B2 (en) * | 2019-11-04 | 2023-02-21 | Siemens Aktiengesellschaft | Automatic generation of reference curves for improved short term irradiation prediction in PV power generation |
| JP2021182672A (ja) * | 2020-05-18 | 2021-11-25 | キヤノン株式会社 | 画像処理装置、画像処理方法、及びプログラム |
| EP4198579A4 (en) * | 2020-08-12 | 2024-06-26 | Furuno Electric Co., Ltd. | CLOUD OBSERVATION SYSTEM, CLOUD OBSERVATION METHOD AND PROGRAM |
| JP7655844B2 (ja) * | 2021-12-10 | 2025-04-02 | 株式会社東芝 | 情報処理装置、情報処理方法及びコンピュータプログラム |
-
2020
- 2020-02-05 WO PCT/JP2020/004220 patent/WO2020179326A1/ja not_active Ceased
- 2020-02-05 EP EP20767339.3A patent/EP3936902B1/en active Active
- 2020-02-05 JP JP2021503473A patent/JP7261861B2/ja active Active
- 2020-02-05 CN CN202080018880.9A patent/CN113544548A/zh not_active Withdrawn
-
2021
- 2021-09-03 US US17/466,284 patent/US11989907B2/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS60220843A (ja) * | 1985-03-29 | 1985-11-05 | Hitachi Ltd | 日射量の予測装置 |
| US20100309330A1 (en) * | 2009-06-08 | 2010-12-09 | Adensis Gmbh | Method and apparatus for forecasting shadowing for a photovoltaic system |
| JP2014011345A (ja) | 2012-06-29 | 2014-01-20 | Hitachi Information & Control Solutions Ltd | 発電量予測装置、発電量予測方法、プログラム、および電力制御システム |
| WO2015104281A1 (en) * | 2014-01-07 | 2015-07-16 | Abb Technology Ag | Solar irradiance forecasting |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP3936902A4 |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2022064293A (ja) * | 2020-10-13 | 2022-04-25 | イボクラール ビバデント アクチェンゲゼルシャフト | 歯科補綴物を製造する方法 |
| JP7813545B2 (ja) | 2020-10-13 | 2026-02-13 | イボクラール ビバデント アクチェンゲゼルシャフト | 歯科補綴物を製造する方法 |
| WO2023091523A1 (en) * | 2021-11-17 | 2023-05-25 | Halio, Inc. | Cloud forecasting for electrochromic devices |
| US11900617B2 (en) | 2021-11-17 | 2024-02-13 | Halio, Inc. | Cloud forecasting for electrochromic devices |
| US12394068B2 (en) | 2021-11-17 | 2025-08-19 | Smart Window Inc., Limited | Cloud forecasting for electrochromic devices |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113544548A (zh) | 2021-10-22 |
| JP7261861B2 (ja) | 2023-04-20 |
| EP3936902A4 (en) | 2023-03-01 |
| EP3936902B1 (en) | 2025-09-03 |
| JPWO2020179326A1 (ja) | 2020-09-10 |
| US20210398312A1 (en) | 2021-12-23 |
| EP3936902A1 (en) | 2022-01-12 |
| US11989907B2 (en) | 2024-05-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7261861B2 (ja) | 雲観測装置、雲観測方法、及びプログラム | |
| US8175336B2 (en) | Target tracker | |
| US8965107B1 (en) | Feature reduction based on local densities for bundle adjustment of images | |
| JP6947927B2 (ja) | 雲観測装置、雲観測システム、雲観測方法、及びプログラム | |
| US8538075B2 (en) | Classifying pixels for target tracking, apparatus and method | |
| EP3182067A1 (en) | Method and apparatus for determining spacecraft attitude by tracking stars | |
| US20090257680A1 (en) | Method and Device for Video Stitching | |
| KR101324250B1 (ko) | 영상 처리를 통한 광축 오차 보상 방법 및 시스템, 광축 오차 보상 기능이 구현된 줌 카메라 | |
| JP2020088647A (ja) | 情報処理装置、情報処理方法及びプログラム | |
| CN114071015A (zh) | 一种联动抓拍路径的确定方法、装置、介质及设备 | |
| JP4140126B2 (ja) | 領域分割および対象物抽出装置 | |
| JP6500428B2 (ja) | 動体検知装置、動体検知方法および動体検知プログラム | |
| JP2011258214A (ja) | 物体検出装置 | |
| JP2023061680A (ja) | エアロゾル濃度の推測方法及びシステム | |
| JP2003329780A (ja) | 夜間雲量測定方法および夜間雲量測定装置 | |
| US20230177803A1 (en) | Cloud observation system, cloud observation method, and computer-readable recording medium | |
| WO2023149101A1 (en) | Weather observation system, weather observation method, trained model generation method, and program | |
| JP2001023055A (ja) | 火炎検出装置および火炎検出方法 | |
| JP2023069619A (ja) | 雲位置算出システム、雲位置算出方法、及びプログラム | |
| JP6716769B1 (ja) | 画像検査方法、画像検査装置、及び画像検査プログラム | |
| JP6301202B2 (ja) | 撮影条件設定装置および撮影条件設定方法 | |
| US20230143999A1 (en) | Visibility determination system, visibility determination method, and non-transitory computer-readable medium | |
| US20180322638A1 (en) | Imaging apparatus | |
| WO2015146582A1 (ja) | エリア状態推定装置、エリア状態推定方法および環境制御システム | |
| JP2005106744A (ja) | 画像解析装置 |
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: 20767339 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2021503473 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| ENP | Entry into the national phase |
Ref document number: 2020767339 Country of ref document: EP Effective date: 20211006 |
|
| WWG | Wipo information: grant in national office |
Ref document number: 2020767339 Country of ref document: EP |