DETAILED ACTION
This Action is in response to Applicant’s response filed on 01/20/2026. Claims 1, 3-9, 15-17 and 19-20 are still pending in the present application. Claims 2, 10-14 and 18 are canceled. This Action is made FINAL.
Response to Arguments
Applicant's arguments filed on 01/20/2026 have been fully considered but they are not persuasive.
In the present application, applicant argues: “According to the claimed configuration, a cloud pixel is determined based on a threshold value that is dynamically computed using a representative statistic of the lightness values of pixels corresponding to the plurality of edges. The representative statistic may include a median of the lightness values, a mean of the lightness values, and/or a statistic based on the frequency of the lightness values. This dynamic approach provides significant advantages over fixed-threshold techniques disclosed in the cited references, including Lietzke, as discussed below. … However, each threshold in Lietzke is a fixed, predetermined value. For example, FIG. 6 (see "608") describes: …. Although these thresholds are applied to observed pixel values, they remain pre-fixed and do not adapt to the overall brightness of the sky. Under low-light conditions, such as nighttime, the absolute difference between R and G values will be small, making discrimination unreliable. In contrast, the claimed configuration dynamically derives the threshold from edge lightness statistics, ensuring robust cloud detection even under challenging illumination conditions. Therefore, Lietzke fails to disclose or suggest determining a cloud pixel having a lightness value greater than or equal to the threshold value where the threshold value is determined using at least one of a median of the lightness values of the pixels corresponding to the plurality of edges, a mean of the lightness values, or a statistic based on a frequency of the lightness values, in combination with the remaining features of amended claim 1, and does not cure the deficiencies of Yan. Absent these features, Yan and Lietzke would be unable to achieve the potential benefits discussed with respect to the claimed configuration. (Remark Pages 9-10)
Examiner respectfully disagrees. With respect to the Applicant’s arguments that “the claimed configuration dynamically derives the threshold from edge lightness statistics, ensuring robust cloud detection even under challenging illumination conditions. Therefore, Lietzke fails to disclose or suggest determining a cloud pixel having a lightness value greater than or equal to the threshold value where the threshold value is determined using at least one of a median of the lightness values of the pixels corresponding to the plurality of edges, a mean of the lightness values, or a statistic based on a frequency of the lightness values, in combination with the remaining features of amended claim 1, and does not cure the deficiencies of Yan.” (Remark Page 10)
Concerning the applicant’s arguments that claimed “dynamic approach” has unique advantages not realized or suggested in Yan et al (U.S. 20190325581 A1; Yan) and/or Lietzke et al (U.S. 20190064055 A1; Lietzke). For example, dynamically changing the threshold for low-light conditions. In response to applicant's arguments that the references fail to show certain features of applicant’s invention, it is noted that the features upon which the applicant relies (i.e., dynamically changing for low-light conditions) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
In response to applicant’s argument that the claims suggest dynamically changing the threshold value based on lighting conditions, the test for obviousness is not whether the features of a secondary reference may be bodily incorporated into the structure of the primary reference; nor is it that the claimed invention must be expressly suggested in any one or all of the references. Rather, the test is what the combined teachings of the references would have suggested to those of ordinary skill in the art. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981).
Here, there is no mentioning of dynamically adjusting, temporal updating, iterative recalculation, or any change of the threshold over time. Therefore, the feature that the applicant is arguing over the prior art is not recited in the claims. The independent claims are silent as to dynamic behavior. They simply require determining a threshold from edge pixel values in a sky image.
The primary reference Yan et al (U.S. 20190325581 A1: Yan) teaches Canny edge detector may be used to detect the boundaries of different objects, such as cloud, sun and non-sky objects. Before implementing Canny edge detection, the image data corresponding to a sky image may be converted into grey channel. Gaussian filter may be used for noise-removing and double thresholds may be used to select strong edge pixels with high gradient values. … a sky image may have a range of RGB average values from 0 to 255. The cloud area in the image may have a range of RGB average values approximately from 100 to 244 with a standard deviation lower than 50 … With respect to the gradients of RGB (Red, Green, Blue) values belonging to different objects, the contours of different objects may be formed by connecting all continuous points along the object edges is interpreted as “determine a threshold value using at least one of a median of the lightness values of the pixels corresponding to the plurality of edges, a mean of the lightness values, or a statistic based on a frequency of the lightness values”. (Paragraph 60-61) For purpose of examination, The Examiner is interpreted under Broadest Reasonable Interpretation of the claim limitation base on only “a median of the lightness values of the pixels corresponding to the plurality of edges” OR “a mean of lightness values”. This is met by the teachings of Yan.
Also, the second references Lietzke et al (U.S. 20190064055 A1; Lietzke) teaches using the cloud mask, the processor is configured to determine a specific measurement location in a non-cloud area that is spaced apart from a boundary of the cloud area(s) and from edges of the cloud mask as a desired location for the sensor 308 to measure an atmospheric condition. … Further, the various thresholds in the aforementioned tests can be adjusted according to the maximum level of cloud presence that is tolerable for measuring a particular atmospheric condition … the threshold values employed in the cloud detection algorithm may be configurable and uploaded to the computing apparatus …. A cloud mask can be created after each of the pixels of the image is examined by the cloud detection algorithm. For example, a pixel in a non-cloud area can be represented by zero (e.g., a black pixel) and a pixel in a cloud area can be represented by one (e.g., a white pixel) in a cloud mask, as shown in FIG. 4C is read as “determine a threshold value using at least one of a median of the lightness values of the pixels corresponding to the plurality of edges, a mean of the lightness values, or a statistic based on a frequency of the lightness values”. (Paragraph 32-36). The Examiner is interpreted under Broadest Reasonable Interpretation of the claim limitation base on only “a median of the lightness values of the pixels corresponding to the plurality of edges” OR “a mean of lightness values”. This is also met by the teachings of Lietzke .
The Examiner states that the Applicant is interpreting the claim narrowly compared to the prior art cited in the Non-Final Office Action and in light of MPEP 2111, the Examiner has interpreted the claims properly. Specifically, during patent prosecution, the pending claims must be “given their broadest reasonable interpretation assistant with the specification.” The Examiner has interpreted the claim language in reference to the specification. Because applicant has the opportunity to amend the claims during prosecution, given a claim in its broadest reasonable interpretation will reduce the possibility that the claim, once issued will be interpreted more or broadly than is justified. Although the cited reference is different from the invention disclosed, the language of Applicant's claims is sufficiently broad to reasonably read on the cited reference. A broad reading does not constitute “teaching away.”
Further, it has been held that nonpreferred embodiments failing to assert discovery beyond that known in the art does not constitute a “teaching away” unless such disclosure criticizes, discredits, or otherwise discourages the solution claimed. In re Susi, 440 F.2d 442, 169 USPQ 423 (CCPA 1971), In re Gurley, 27 F.3d 551, 554, 31 USPQ2d 1130, 1132 (Fed. Cir. 1994), In re Fulton, 391 F.3d 1195, 1201, 73 USPQ2d 1141, 1146 (Fed. Cir. 2004), (see MPEP §2124).
It has been show that these limitation are taught in the Lu and Mukherjee references. If
the applicant intends to different between “the Lu and Mukherjee references” and the present
application, then such differences should be made explicit in the claims. As a result, the argued
features are written such that they read upon the cited references; therefore, the previous
rejection still applies.
Claim Status
Claim(s) 1, 3 and 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yan et al (U.S. 20190325581 A1; Yan), in view of Lietzke et al (U.S. 20190064055 A1; Lietzke).
Claim(s) 4 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yan et al (U.S. 20190325581 A1; Yan), in view of Lietzke et al (U.S. 20190064055 A1; Lietzke), and in further view of Huo J et al (“Cloud determination of all-sky images under low-visibility conditions.”; Huo).
Claim(s) 6 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yan et al (U.S. 20190325581 A1; Yan), in view of Lietzke et al (U.S. 20190064055 A1; Lietzke), and in further view of Michael Mommert (“Cloud Identification from All-sky Camera Data with Machine Learning”; Mommert).
Claim(s) 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yan et al (U.S. 20190325581 A1; Yan), in view of Lietzke et al (U.S. 20190064055 A1; Lietzke), and in further view of Shen et al (U.S. 20170372167 A1; Shen).
Claim(s) 5 and 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yan et al (U.S. 20190325581 A1; Yan), in view of Lietzke et al (U.S. 20190064055 A1; Lietzke), and in further view of Huo J et al (“Cloud determination of all-sky images under low-visibility conditions.”; Huo), and in further view of Michael Mommert (“Cloud Identification from All-sky Camera Data with Machine Learning”; Mommert).
Claim(s) 8-9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yan et al (U.S. 20190325581 A1; Yan), in view of Lietzke et al (U.S. 20190064055 A1; Lietzke), and in further view of Huo J et al (“Cloud determination of all-sky images under low-visibility conditions.”; Huo), and in further view of Michael Mommert (“Cloud Identification from All-sky Camera Data with Machine Learning”; Mommert), and in further view of Shen et al (U.S. 20170372167 A1; Shen).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1, 3 and 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yan et al (U.S. 20190325581 A1; Yan), in view of Lietzke et al (U.S. 20190064055 A1; Lietzke).
Regarding claim 1, Yan discloses A cloud observation system, (Paragraph 33: FIG. 3 illustrates an example system 300 for determining cloud coverage) comprising: processing circuitry (Fig.1: processor 120; Fig.14: processor 1410) configured to:
acquire a sky image taken by a camera, the sky image containing the sky; (Paragraph 23: “The data collection devices 110 comprise cameras 112 for capturing sky images.
extract pixel values of a plurality of edges in the sky image, (Paragraph 35: “The edge detection engine 350 is capable of detecting boundaries of cloud, sun, non-sky objects in the sky images and determining a cloud coverage.”; Paragraph 59: “The edge detection engine 350 may detect contours of objects in a sky image and further determine a cloud coverage. … The edge detection engine 350 may analyze the data, combine or aggregate the data or extract portions of the data as appropriate.”; Paragraph 75: “Operation 1304 illustrates detecting edges of clouds within the cloud areas S.sub.0 and edges of objects within the non-cloud areas S.sub.1 using the edge detection engine 350.”; Paragraphs 75-76: “Operation 1304 illustrates detecting edges of clouds within the cloud areas S.sub.0 and edges of objects within the non-cloud areas S.sub.1 using the edge detection engine 350 … Operation 1306 illustrates determining the numbers of data elements (e.g., pixels) within the edges of the clouds or non-cloud objects, respectively.” )
determine lightness value of pixels (RGB average values) corresponding to the plurality of edges based on the pixel values of the plurality of edges; (Fig. 8A; Paragraphs 60-61: “Canny edge detector may be used to detect the boundaries of different objects, such as cloud, sun and non-sky objects. Before implementing Canny edge detection, the image data corresponding to a sky image may be converted into grey channel. Gaussian filter may be used for noise-removing and double thresholds may be used to select strong edge pixels with high gradient values. … a sky image may have a range of RGB average values from 0 to 255. The cloud area in the image may have a range of RGB average values approximately from 100 to 244 with a standard deviation lower than 50; the sun area may have RGB average values greater than 244; and the non-sky area may have RGB average values less than 80. With respect to the gradients of RGB (Red, Green, Blue) values belonging to different objects, the contours of different objects may be formed by connecting all continuous points along the object edges.”; Paragraph 76: “Operation 1306 illustrates determining the numbers of data elements (e.g., pixels) within the edges of the clouds or non-cloud objects, respectively.”)
determine a threshold value (color ranges) using at least one of a median of the lightness values of the pixels corresponding to the plurality of edges, a mean of the lightness values, or a statistic based on a frequency of the lightness values; (Fig.8A and Paragraphs 60-61: “FIG. 8A illustrates detected edges using the Canny edge detector. To improve the accuracy of edge detection. Gaussian filter may be used for noise-removing and double thresholds may be used to select strong edge pixels with high gradient values. … Clouds, sun, and non-sky objects are in different color ranges. For instance, a sky image may have a range of RGB average values from 0 to 255. The cloud area in the image may have a range of RGB average values approximately from 100 to 244 with a standard deviation lower than 50; the sun area may have RGB average values greater than 244; and the non-sky area may have RGB average values less than 80. With respect to the gradients of RGB (Red, Green, Blue) values belonging to different objects, the contours of different objects may be formed by connecting all continuous points along the object edges.”; Paragraph 77: Operation 1308 illustrates detecting color clusters associated with clouds and non-cloud objects using the color cluster engine 360. Operation 1310 illustrates determining the numbers of data elements (e.g., pixels) within the color clusters associated with the clouds and non-cloud objects, respectively. … The color cluster engine 360 may detect color clusters associated with clouds or non-cloud objects in the sky images using the algorithm”)
determine a cloud pixel having a lightness value to the threshold value (Paragraph 61: “Clouds, sun, and non-sky objects are in different color ranges. For instance, a sky image may have a range of RGB average values from 0 to 255. The cloud area in the image may have a range of RGB average values approximately from 100 to 244 with a standard deviation lower than 50;”; Paragraph 67: “the characteristic color value (e.g., RGB average) of clouds may be in a range of from 100 to 244 with a standard deviation less than 50. The characteristic color value (e.g., RGB average) of non-sky objects may be less than 80. The characteristic color value (e.g., RGB average) of the sun may be greater than 244.”) the cloud pixel indicating a cloud from a plurality of sky pixels constituting the sky image; (Paragraph 56: “the cloud locator engine 330 may further determine a cloud coverage using extracted information about locations of clouds and non-sky objects in the sky images. The number of data elements (e.g., pixels) within the area at the detected cloud location (L_cloud) may be determined.”) and
identify the cloud based on the cloud pixel indicating the cloud. (Paragraphs 56-57: “the cloud locator engine 330 may further determine a cloud coverage using extracted information about locations of clouds and non-sky objects in the sky images. The number of data elements (e.g., pixels) within the area at the detected cloud location (L_cloud) may be determined … A cloud coverage may be determined based on a proportion of a number of pixels in the cloud area (L_cloud) to a number of pixels in the sky area (L_sky)”; Paragraphs 79-80: “Operation 1312 illustrates averaging corresponding results obtained at operations 1306 and 1308. The number of pixels belonging to the clouds in the same sky image may be determined using the formula of S_cloud=average (S_cloudLocatorEdge, S_cloudClustering). … Operation 1314 illustrates determining a cloud coverage. The cloud coverage may be determined based on a proportion of a number of pixels belonging to the clouds (S_cloud) to a number of pixels belonging the sky area (S_skytotal).”)”)
However, Yan does not disclose determine a cloud pixel having a lightness value greater than or equal to the threshold value, the cloud pixel indicating a cloud from a plurality of sky pixels constituting the sky image
Lietzke discloses acquire a sky image taken by a camera, the sky image containing the sky; (Paragraphs 2-3: “To accurately measure atmospheric conditions such as greenhouse gas concentrations, sensors must be pointed toward cloud-free “open sky” areas.”; Paragraph 27: “The imager 304 is coupled to the computing apparatus 302 and configured to take images from overhead and transmit image data of the images to computing apparatus 302.”; Paragraph 30)
determine a threshold value using at least one of a median of the lightness values of the pixels corresponding to the plurality of edges, a mean of the lightness values, or a statistic based on a frequency of the lightness values; (Fig. 3 and 7; Paragraph 32: “the processor 302-2 applies a cloud detection algorithm to the image data to create a cloud mask. … . In FIG. 4C, cloud areas are represented by white color while non-cloud areas are represented by black color … using the cloud mask, the processor 302-2 is configured to determine a specific measurement location in a non-cloud area that is spaced apart from a boundary of the cloud area(s) and from edges of the cloud mask as a desired location for the sensor 308 to measure an atmospheric condition. … Thus, the threshold for what constitutes “substantially without cloud cover” can be relative to the operational requirements for obtaining a valid measurement of a particular atmospheric condition (e.g., the concentration of a specific substance).”; Paragraphs 36 and 41; Paragraph 45: “after an image is converted into a cloud mask by a cloud detection algorithm, the cloud mask can be convolved with an FOV mask having an FOV area of the sensor. In particular, a cloud mask may be a binary bitmap including pixels at the cloud area(s) having a value of one (white pixels) and pixels at the non-cloud area having a value of zero (black pixels).)
determine a cloud pixel having a lightness value greater than or equal to the threshold value, the cloud pixel indicating a cloud from a plurality of sky pixels constituting the sky image ( Figs. 3 and 6; Paragraphs 33: “in applying the cloud detection algorithm, the processor 302-2 converts red (R), green (G), and blue (B) (RGB) pixel data of the image data into hue (H), saturation (S), and value (V) data. The processor 302-2 then determines that a pixel is in the cloud area if an S value of the pixel is greater than a first threshold value and a V value of the pixel is less than a second threshold value. … the processor 302-2 determines a minimum of an R value, a G value, and a B value of a pixel, and determines that the pixel is in the cloud area if the minimum is greater than a fifth threshold value or that the pixel is in the non-cloud area if the minimum is less than a sixth threshold value. It will be appreciated that other tests or combinations of tests are possible for determining whether a pixel is in the cloud area or the non-cloud area.”; Paragraph 44)
Therefore, it would been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Yan by including a cloud detection algorithm to the image data to create a cloud mask that is taught by Lietzke, to make the invention that intelligently pointing a sensor to remotely measure atmospheric conditions by identifying substantially cloud-free regions; thus, one of ordinary skilled in the art would have been motivated to combine the references since this will improving the detection success rate by pointing the sensor to a substantially cloud-free location so that the data collected from sensing is usable and accurate. (Lietzke: Paragraph 42)
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention.
Regarding claim 3, Yan, as modified by Lietzke discloses all the claims invention. Yan further discloses the processing circuitry is further configured to:
set a plurality of areas for the sky image, (Fig.6; Paragraph 45: “ the three boxes in the upper area of the image indicate locations of clouds in the image. The cloud locations may be presented by coordinates of four corners of each corresponding box.”) determine a plurality of threshold values of each of the plurality of areas, and determine the cloud pixel indicating the cloud using the plurality of the threshold values for each of the plurality of areas. (Fig.8A and Paragraphs 60-61: “FIG. 8A illustrates detected edges using the Canny edge detector. To improve the accuracy of edge detection. Gaussian filter may be used for noise-removing and double thresholds may be used to select strong edge pixels with high gradient values. … Clouds, sun, and non-sky objects are in different color ranges. For instance, a sky image may have a range of RGB average values from 0 to 255. The cloud area in the image may have a range of RGB average values approximately from 100 to 244 with a standard deviation lower than 50; the sun area may have RGB average values greater than 244; and the non-sky area may have RGB average values less than 80. With respect to the gradients of RGB (Red, Green, Blue) values belonging to different objects, the contours of different objects may be formed by connecting all continuous points along the object edges.”) determine the cloud pixel indicating the cloud using the plurality of the threshold values for each of the plurality of areas. (Paragraph 62: “Whether objects having contours are cloud, sun, or non-sky object may be determined based on their respective characteristic color ranges. In some embodiments, the edge detection engine 350 may determine a cloud coverage by dividing a number of pixels indicative of clouds by a number of pixels indicative of the sky area.”)
Regarding claim 19, Yan discloses a cloud observation system, (Paragraph 33: FIG. 3 illustrates an example system 300 for determining cloud coverage) comprising: processing circuitry (Fig.1: processor 120; Fig.14: processor 1410) configured to:
acquiring a sky image taken by a camera, the sky image containing the sky; (Paragraph 23: “The data collection devices 110 comprise cameras 112 for capturing sky images.
extracting pixel values of a plurality of edges in the sky image, (Paragraph 35: “The edge detection engine 350 is capable of detecting boundaries of cloud, sun, non-sky objects in the sky images and determining a cloud coverage.”; Paragraph 59: “The edge detection engine 350 may detect contours of objects in a sky image and further determine a cloud coverage. … The edge detection engine 350 may analyze the data, combine or aggregate the data or extract portions of the data as appropriate.”; Paragraph 75: “Operation 1304 illustrates detecting edges of clouds within the cloud areas S.sub.0 and edges of objects within the non-cloud areas S.sub.1 using the edge detection engine 350.”; Paragraphs 75-76: “Operation 1304 illustrates detecting edges of clouds within the cloud areas S.sub.0 and edges of objects within the non-cloud areas S.sub.1 using the edge detection engine 350 … Operation 1306 illustrates determining the numbers of data elements (e.g., pixels) within the edges of the clouds or non-cloud objects, respectively.” )
determining lightness value of pixels (RGB average values) corresponding to the plurality of edges based on the pixel values of the plurality of edges; (Fig. 8A; Paragraph 61: “a sky image may have a range of RGB average values from 0 to 255. The cloud area in the image may have a range of RGB average values approximately from 100 to 244 with a standard deviation lower than 50; the sun area may have RGB average values greater than 244; and the non-sky area may have RGB average values less than 80. With respect to the gradients of RGB (Red, Green, Blue) values belonging to different objects, the contours of different objects may be formed by connecting all continuous points along the object edges.”; Paragraph 76: “Operation 1306 illustrates determining the numbers of data elements (e.g., pixels) within the edges of the clouds or non-cloud objects, respectively.”)
determining a threshold value (color ranges) using at least one of a median of the lightness values of the pixels corresponding to the plurality of edges, a mean of the lightness values, or a statistic based on a frequency of the lightness values; (Fig.8A and Paragraphs 60-61: “FIG. 8A illustrates detected edges using the Canny edge detector. To improve the accuracy of edge detection. Gaussian filter may be used for noise-removing and double thresholds may be used to select strong edge pixels with high gradient values. … Clouds, sun, and non-sky objects are in different color ranges. For instance, a sky image may have a range of RGB average values from 0 to 255. The cloud area in the image may have a range of RGB average values approximately from 100 to 244 with a standard deviation lower than 50; the sun area may have RGB average values greater than 244; and the non-sky area may have RGB average values less than 80. With respect to the gradients of RGB (Red, Green, Blue) values belonging to different objects, the contours of different objects may be formed by connecting all continuous points along the object edges.”; Paragraph 77: Operation 1308 illustrates detecting color clusters associated with clouds and non-cloud objects using the color cluster engine 360. Operation 1310 illustrates determining the numbers of data elements (e.g., pixels) within the color clusters associated with the clouds and non-cloud objects, respectively. … The color cluster engine 360 may detect color clusters associated with clouds or non-cloud objects in the sky images using the algorithm”)
determine a cloud pixel having a lightness value to the threshold value (Paragraph 61: “Clouds, sun, and non-sky objects are in different color ranges. For instance, a sky image may have a range of RGB average values from 0 to 255. The cloud area in the image may have a range of RGB average values approximately from 100 to 244 with a standard deviation lower than 50;”; Paragraph 67: “the characteristic color value (e.g., RGB average) of clouds may be in a range of from 100 to 244 with a standard deviation less than 50. The characteristic color value (e.g., RGB average) of non-sky objects may be less than 80. The characteristic color value (e.g., RGB average) of the sun may be greater than 244.”) the cloud pixel indicating a cloud from a plurality of sky pixels constituting the sky image; (Paragraph 56: “the cloud locator engine 330 may further determine a cloud coverage using extracted information about locations of clouds and non-sky objects in the sky images. The number of data elements (e.g., pixels) within the area at the detected cloud location (L_cloud) may be determined.”) and
identifying the cloud based on the cloud pixel indicating the cloud. (Paragraphs 56-57: “the cloud locator engine 330 may further determine a cloud coverage using extracted information about locations of clouds and non-sky objects in the sky images. The number of data elements (e.g., pixels) within the area at the detected cloud location (L_cloud) may be determined … A cloud coverage may be determined based on a proportion of a number of pixels in the cloud area (L_cloud) to a number of pixels in the sky area (L_sky)”; Paragraphs 79-80: “Operation 1312 illustrates averaging corresponding results obtained at operations 1306 and 1308. The number of pixels belonging to the clouds in the same sky image may be determined using the formula of S_cloud=average (S_cloudLocatorEdge, S_cloudClustering). … Operation 1314 illustrates determining a cloud coverage. The cloud coverage may be determined based on a proportion of a number of pixels belonging to the clouds (S_cloud) to a number of pixels belonging the sky area (S_skytotal).”)
However, Yan does not disclose determining a cloud pixel having a lightness value greater than or equal to the threshold value, the cloud pixel indicating a cloud from a plurality of sky pixels constituting the sky image
Lietzke discloses acquiring a sky image taken by a camera, the sky image containing the sky; (Paragraphs 2-3: “To accurately measure atmospheric conditions such as greenhouse gas concentrations, sensors must be pointed toward cloud-free “open sky” areas.”; Paragraph 27: “The imager 304 is coupled to the computing apparatus 302 and configured to take images from overhead and transmit image data of the images to computing apparatus 302.”; Paragraph 30)
determining a threshold value using at least one of a median of the lightness values of the pixels corresponding to the plurality of edges, a mean of the lightness values, or a statistic based on a frequency of the lightness values; (Fig. 3 and 7; Paragraph 32: “the processor 302-2 applies a cloud detection algorithm to the image data to create a cloud mask. … . In FIG. 4C, cloud areas are represented by white color while non-cloud areas are represented by black color … using the cloud mask, the processor 302-2 is configured to determine a specific measurement location in a non-cloud area that is spaced apart from a boundary of the cloud area(s) and from edges of the cloud mask as a desired location for the sensor 308 to measure an atmospheric condition. … Thus, the threshold for what constitutes “substantially without cloud cover” can be relative to the operational requirements for obtaining a valid measurement of a particular atmospheric condition (e.g., the concentration of a specific substance).”; Paragraph 36; Paragraph 45)
determining a cloud pixel having a lightness value greater than or equal to the threshold value, the cloud pixel indicating a cloud from a plurality of sky pixels constituting the sky image ( Figs. 3 and 6; Paragraphs 33: “in applying the cloud detection algorithm, the processor 302-2 converts red (R), green (G), and blue (B) (RGB) pixel data of the image data into hue (H), saturation (S), and value (V) data. The processor 302-2 then determines that a pixel is in the cloud area if an S value of the pixel is greater than a first threshold value and a V value of the pixel is less than a second threshold value. … the processor 302-2 determines a minimum of an R value, a G value, and a B value of a pixel, and determines that the pixel is in the cloud area if the minimum is greater than a fifth threshold value or that the pixel is in the non-cloud area if the minimum is less than a sixth threshold value. It will be appreciated that other tests or combinations of tests are possible for determining whether a pixel is in the cloud area or the non-cloud area.”; Paragraph 44)
Therefore, it would been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Yan by including a cloud detection algorithm to the image data to create a cloud mask that is taught by Lietzke, to make the invention that intelligently pointing a sensor to remotely measure atmospheric conditions by identifying substantially cloud-free regions; thus, one of ordinary skilled in the art would have been motivated to combine the references since this will improving the detection success rate by pointing the sensor to a substantially cloud-free location so that the data collected from sensing is usable and accurate. (Lietzke: Paragraph 42)
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention.
Regarding claim 20, Yan, as modified by Lietzke discloses all the claims invention. Yan further discloses a non-transitory computer-readable medium having stored thereon computer-executable instructions which, when executed by a computer, cause the computer to execute the cloud observation method according to claim 19. (Fig.14 and Paragraphs 85-87: “FIG. 14 illustrates such a general-purpose computing device 1400. In the illustrated embodiment, computing device 1400 includes one or more processors 1410 (which may be referred herein singularly as “a processor 1410” or in the plural as “the processors 1410”) are coupled through a bus 1420 to a system memory 1430.”)
Claim(s) 4 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yan et al (U.S. 20190325581 A1; Yan), in view of Lietzke et al (U.S. 20190064055 A1; Lietzke), in further view of Huo J et al (“Cloud determination of all-sky images under low-visibility conditions.”; Huo).
Regarding claim 4, Yan, as modified by Lietzke, discloses all the claims invention except wherein the sky image is an image taken by an all-sky camera, and the processing circuitry is further configured to determine the plurality of the threshold values of each of the plurality of areas based on the pixel values of the plurality of edges in the plurality of areas and the pixel values of a fringe part of the sky image.
Huo discloses the sky image is an image taken by an all-sky camera, (Figs 1 and 8; 2. Sky cameras and associated images: “The sky images used in this paper are provided by an all-sky imager system (ASIs-I)”) and the processing circuitry is further configured to determine the plurality of the threshold values of each of the plurality of areas based on the pixel values of the plurality of edges in the plurality of areas and the pixel values of a fringe part of the sky image. (Figs. 2-5; 4. Integrated method for cloud determination and contrast -b: Symmetrical Method- c. Procedure of cloud determination: “For each pixel, the B/R ratio difference for the symmetrical pixel is calculated. If the difference exceeds a predefined limit (i.e., 0.1, which is defined in our algorithm), the pixel with the lower ratio is thought of as cloudy and the other pixel as cloudless … The B/R ratios of those pixels are then averaged to obtain the threshold. The finial threshold is the average of the values obtained by the histogram and edge-searching methods. … (this is one of the reasons why TSI uses several thresholds, depending on different positions) … the symmetrical method is used on those regions where the zenith angle is greater than 75 degree (set in the integrated method). ”)
Therefore, it would been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Yan and Lietzke by including integrated method for cloud determination and contrast that is taught by Huo, to make the invention that Cloud Determination of All-Sky Images under Low-Visibility Conditions; thus, one of ordinary skilled in the art would have been motivated to combine the references since this will improving the accuracy of cloud determination in low visibility.
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention.
Regarding claim 16, Yan, as modified by Lietzke, discloses all the claims invention except wherein the sky image is an image taken by an all-sky camera, and the processing circuitry is further configured to extract the edge by removing a fringe part of the sky image from a target range for extracting edges.
Huo discloses the sky image is an image taken by an all-sky camera, (Figs 1 and 8; 2. Sky cameras and associated images: “The sky images used in this paper are provided by an all-sky imager system (ASIs-I)”) and the processing circuitry is further configured to extract the edge by removing the fringe part of the sky image from a target range for extracting edges. (Figs.7 and 10 ; 4a. FFT method: “To exclude the pixels of the sheltering device in the image and get the maximum areas for FFT, B/R ratios of a 512 3 512 pixel block are used to make FFTs (Fig. 7a). ; Figs. 2-5; 4. Integrated method for cloud determination and contrast -b: Symmetrical Method- c. Procedure of cloud determination: The B/R ratios of those pixels are then averaged to obtain the threshold. The finial threshold is the average of the values obtained by the histogram and edge-searching methods. … (this is one of the reasons why TSI uses several thresholds, depending on different positions) … the symmetrical method is used on those regions where the zenith angle is greater than 75 degree (set in the integrated method). ”)
Therefore, it would been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Yan and Lietzke by including integrated method for cloud determination and contrast that is taught by Huo, to make the invention that Cloud Determination of All-Sky Images under Low-Visibility Conditions ; thus, one of ordinary skilled in the art would have been motivated to combine the references since this will improving the accuracy of cloud determination in low visibility.
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention.
Claim(s) 6 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yan et al (U.S. 20190325581 A1; Yan), in view of Lietzke et al (U.S. 20190064055 A1; Lietzke), and in further view of Michael Mommert (“Cloud Identification from All-sky Camera Data with Machine Learning”; Mommert).
Regarding claim 6, Yan, as modified by Lietzke discloses all the claims invention. Yan further discloses the processing circuitry is further configured to: extract the plurality of edges in the sky image, (Paragraph 35: “The edge detection engine 350 is capable of detecting boundaries of cloud, sun, non-sky objects in the sky images and determining a cloud coverage.”; Paragraph 59: “The edge detection engine 350 may detect contours of objects in a sky image and further determine a cloud coverage. … The edge detection engine 350 may analyze the data, combine or aggregate the data or extract portions of the data as appropriate.”;
determine the threshold values for each of the plurality of sky pixels constituting the sky image based on a distance from the pixel to the edge and the pixel value of the edge, and determine the cloud pixel indicating the cloud using the threshold values of each sky pixel of the plurality of sky pixels constituting the sky image. (Paragraphs 56-57 and 61: “the cloud locator engine 330 may further determine a cloud coverage using extracted information about locations of clouds and non-sky objects in the sky images. The number of data elements (e.g., pixels) within the area at the detected cloud location (L_cloud) may be determined … A cloud coverage may be determined based on a proportion of a number of pixels in the cloud area (L_cloud) to a number of pixels in the sky area (L_sky)”; Paragraphs 79-80: “Operation 1312 illustrates averaging corresponding results obtained at operations 1306 and 1308. The number of pixels belonging to the clouds in the same sky image may be determined using the formula of S_cloud=average (S_cloudLocatorEdge, S_cloudClustering). … Operation 1314 illustrates determining a cloud coverage. The cloud coverage may be determined based on a proportion of a number of pixels belonging to the clouds (S_cloud) to a number of pixels belonging the sky area (S_skytotal).”)”)
However, Yan, as modified by Lietzke does not disclose determine the threshold values for each of the plurality of sky pixels constituting the sky image based on a distance from the pixel to the edge and the pixel value of the edge,
Momemrt discloses extract the plurality of edges in the sky image, determine the threshold values for each of the plurality of sky pixels constituting the sky image based on a distance from the pixel to the edge and the pixel value of the edge, (Fig.1 and 2.1: Data Preparation: “We blur the resulting combined image with a Gaussian filter to remove small-scale features and use a threshold to extract those parts of the image that do not show the sky. Finally, we smooth the edges of our selection by convolving the resulting mask with a square kernel … To roughly localize clouds in the image data, we divide each image into a set of subregions. The borders of these subregions are defined in terms of radial distance from Zenith and azimuth.”) and determine the cloud pixel indicating the cloud using the threshold values of each sky pixel of the plurality of sky pixels constituting the sky image. (5.1.1: Model Accuracy and Confusion Matrix: “The cloud detection probability for a single subregion is ∼85% using ResNet and ∼95% using lightGBM. Since clouds typically cover more than one subregion, the probability that any subregion in a set of N subregions that actually include clouds increases exponentially with N.”)
Therefore, it would been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Yan and Lietzke by including machine learning models to learn and predict the presence of clouds in image data that is taught by Mommert, to make the invention that Cloud Identification from All-sky Camera Data with Machine Learning; thus, one of ordinary skilled in the art would have been motivated to combine the references since this will improving the safety of observatories and enable automated monitoring of sky quality.
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention.
Regarding claim 17, Yan, as modified by Lietzke and Mommert, discloses all the claims invention. Mommert further discloses the processing circuitry is further configured to: detect moon pixels indicating the moon in the sky image, (Mommert: Fig.1 and 3.2.1. Feature Definitions - 2. Background properties: “ Depending on the illumination conditions (presence of the Moon or the Sun) clouds generally appear as dark or bright patches against the clear sky.) and extract the edge by removing a range of the moon from a target range for extracting edges. (Mommert: Fig.1 and 2.1: Data Preparation: “We blur the resulting combined image with a Gaussian filter to remove small-scale features and use a threshold to extract those parts of the image that do not show the sky. Finally, we smooth the edges of our selection by convolving the resulting mask with a square kernel … To roughly localize clouds in the image data, we divide each image into a set of subregions. The borders of these subregions are defined in terms of radial distance from Zenith and azimuth.”)
Claim(s) 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yan et al (U.S. 20190325581 A1; Yan), in view of Lietzke et al (U.S. 20190064055 A1; Lietzke), and in further view of Shen et al (U.S. 20170372167 A1; Shen).
Regarding claim 15, Yan, as modified by Lietzke, discloses all the claims invention. Yan further discloses the sky image is a first sky image, and the processing circuitry is further configured to: acquire a second sky image, the second sky image being taken in the same time zone on a different day from the date and time of the first sky image; (Paragraph 23: “the cameras 112 each may be fixed toward a particular view of sky, and they each may gather a series of time-sequenced sky images of a particular view every day (i.e., an image stream).”; Paragraph 55: “depending on the sky images' capture times and locations, the process 500 may be used to determine cloud information at a given location at different times, cloud information at different locations at the same time, or aggregate cloud information over a certain area within a certain time of period based on the timestamps and location information associated with the sky images.”) and
However, Yan, as modified by Lietzke, does not disclose adopt the threshold value determined based on the second sky image taken as the threshold value of the first sky image when the number of edges extracted based on the first sky image is equal to or less than a predetermined value.
Shen discloses the sky image is a first sky image, and the processing circuitry is further configured to: acquire a second sky image, the second sky image being taken in the same time zone on a different day from the date and time of the first sky image; (Fig.11: image taking for 3 day and Paragraph 73: “FIG. 11, the sun track extraction process 1100 uses previous three days' image streams of a view to estimate the forth day's sun track of the view. The image streams captured in three successive days may be referred herein as Day 1 image library, Day 2 image library, and Day 3 image library, respectively.”) and
adopt the threshold value determined based on the second sky image taken as the threshold value of the first sky image when the number of edges extracted based on the first sky image is equal to or less than a predetermined value. (Fig.9 and Paragraphs 58-68: “a sky portion extraction algorithm according to the present disclosure, such as the sky portion extraction process 900, uses a series of images (i.e., image stream) of a view, which may be captured at different times from morning to evening by at least one of the data collection devices 110, to extract a sky portion of the view. … At operation 906, one or more edge portions among image data corresponding to a single image may be detected by an edge detection algorithm … On the other hand, if a corresponding data element fails to simultaneously satisfy the first threshold and the second threshold, the corresponding data element is changed into an element of a non-sky portion. A binary representative of the image stream may be generated based on the results of operation 904 and operation 906. … At operation 912, one or more sky components are verified as real ones that constitute the sky portion of the view. A modified mask image is generated, and the modified mask image comprises a sky portion including the verified sky components”)
Therefore, it would been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Yan and Lietzke by including process for sky portion extraction using image stream by Shen, to make the invention that weather information extraction using image data; thus, one of ordinary skilled in the art would have been motivated to combine the references since this will improving the determine cloud coverage, cloud darkness, and cloud patterns at different times and locations so as to obtain comprehensive information relating to how a weather system or event..
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention.
Claim(s) 5 and 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yan et al (U.S. 20190325581 A1; Yan), in view of Lietzke et al (U.S. 20190064055 A1; Lietzke), and in further view of Huo J et al (“Cloud determination of all-sky images under low-visibility conditions.”; Huo), and in further view of Michael Mommert (“Cloud Identification from All-sky Camera Data with Machine Learning”; Mommert).
Regarding claim 5, Yan, as modified by Lietzke and Huo, discloses all the claims invention. Huo further discloses wherein the processing circuitry is further configured to the plurality of areas includes a first area containing or adjacent to the sun and a second area further away from the sun than the first area, (Fig.2-5; I. Introduction: “cloud is determined mainly through comparing the ratio of red channel to blue channel (or blue to red) of each pixel with a predefined threshold (the WSIs, TSIs, and WSCs all employ this method). TSI uses different thresholds, depending on the sector of the sky (area close to horizon, circumsolar area, etc.).”; a. Numerical simulation for cloudless sky under different AOD conditions: “The solar principal plane (pixels on it have the same azimuth angle as the sun; horizontal line on Fig. 2, right) is used to represent the hemisphere for a description so that all typical simulation results can be shown in one figure for comparison.”) and the processing circuitry is further configured to determine the threshold values of each of the areas based on the pixel values of the edges in a plurality of areas including the first area and the second area, and set the threshold values of the first area and the second area to different values. . (Figs. 2-5; 4. Integrated method for cloud determination and contrast -b: Symmetrical Method- c. Procedure of cloud determination: The B/R ratios of those pixels are then averaged to obtain the threshold. The finial threshold is the average of the values obtained by the histogram and edge-searching methods. … (this is one of the reasons why TSI uses several thresholds, depending on different positions) … the symmetrical method is used on those regions where the zenith angle is greater than 75 degree (set in the integrated method). ”)
However, Yan, as modified by Lietzke and Huo, does not disclose wherein the processing circuitry is further configured to detect moon pixels indicating a moon in the sky image, the plurality of areas includes a first area containing or adjacent to the moon and a second area further away from the moon than the first area
Mommert discloses the processing circuitry is further configured to detect moon pixels indicating a moon in the sky image, the plurality of areas includes a first area containing or adjacent to the moon and a second area further away from the moon than the first area (Fig.1 and 3.2.1. Feature Definitions - 2. Background properties: “ Depending on the illumination conditions (presence of the Moon or the Sun) clouds generally appear as dark or bright patches against the clear sky. We hence derive the average brightness, median brightness, and brightness standard deviation across each subregion.”, it shows that “ clouds appear dark” is interpreted as “area away from the moon” and “clouds appears bright” is interpreted as “area adjacent or close from the moon”)
Therefore, it would been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Yan ,Lietzke and Huo by including machine learning models to learn and predict the presence of clouds in image data that is taught by Mommert, to make the invention that Cloud Identification from All-sky Camera Data with Machine Learning; thus, one of ordinary skilled in the art would have been motivated to combine the references since this will improving the safety of observatories and enable automated monitoring of sky quality.
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention.
Regarding claim 7, Yan, as modified by Lietzke, Huo and Mommert, discloses the processing circuitry is further configured to: detect moon pixels indicating the moon in the sky image, (Momert: Fig.1 and 3.2.1. Feature Definitions - 2. Background properties: “ Depending on the illumination conditions (presence of the Moon or the Sun) clouds generally appear as dark or bright patches against the clear sky.) and extract the edge by removing a range of the moon from a target range for extracting edges. (Mommert: Fig.1 and 2.1: Data Preparation: “We blur the resulting combined image with a Gaussian filter to remove small-scale features and use a threshold to extract those parts of the image that do not show the sky. Finally, we smooth the edges of our selection by convolving the resulting mask with a square kernel … To roughly localize clouds in the image data, we divide each image into a set of subregions. The borders of these subregions are defined in terms of radial distance from Zenith and azimuth.”; Huo: Figs.7 and 10 ; 4a. FFT method: “To exclude the pixels of the sheltering device in the image and get the maximum areas for FFT, B/R ratios of a 512 3 512 pixel block are used to make FFTs (Fig. 7a).)
Claim(s) 8-9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Yan et al (U.S. 20190325581 A1; Yan), in view of Lietzke et al (U.S. 20190064055 A1; Lietzke), and in view of Huo J et al (“Cloud determination of all-sky images under low-visibility conditions.”; Huo), and in further view of Michael Mommert (“Cloud Identification from All-sky Camera Data with Machine Learning”; Mommert), and in further view of Shen et al (U.S. 20170372167 A1; Shen).
Regarding claim 8, Yan, as modified by Lietzke, Huo and Mommert, discloses all the claims invention. Yan further discloses wherein the sky image is a first sky image, and the processing circuitry is further configured acquire a second sky image, the second sky image being taken in the same time zone on a different day from the date and time of the first sky image; (Paragraph 23: “the cameras 112 each may be fixed toward a particular view of sky, and they each may gather a series of time-sequenced sky images of a particular view every day (i.e., an image stream).”; Paragraph 55: “depending on the sky images' capture times and locations, the process 500 may be used to determine cloud information at a given location at different times, cloud information at different locations at the same time, or aggregate cloud information over a certain area within a certain time of period based on the timestamps and location information associated with the sky images.”) and
However, Yan, as modified by Lietzke, Huo and Mommert, does not disclose adopt the threshold value determined based on the second sky image as the threshold value of the first sky image when the number of edges extracted based on the first sky image is equal to or less than a predetermined value.
Shen discloses the sky image is a first sky image, and the processing circuitry is further configured to: acquire a second sky image, the second sky image being taken in the same time zone on a different day from the date and time of the first sky image; (Fig.11: image taking for 3 day and Paragraph 73: “FIG. 11, the sun track extraction process 1100 uses previous three days' image streams of a view to estimate the forth day's sun track of the view. The image streams captured in three successive days may be referred herein as Day 1 image library, Day 2 image library, and Day 3 image library, respectively.”) and
adopt the threshold value determined based on the second sky image taken as the threshold value of the first sky image when the number of edges extracted based on the first sky image is equal to or less than a predetermined value. (Fig.9 and Paragraphs 58-68: “a sky portion extraction algorithm according to the present disclosure, such as the sky portion extraction process 900, uses a series of images (i.e., image stream) of a view, which may be captured at different times from morning to evening by at least one of the data collection devices 110, to extract a sky portion of the view. … At operation 906, one or more edge portions among image data corresponding to a single image may be detected by an edge detection algorithm … On the other hand, if a corresponding data element fails to simultaneously satisfy the first threshold and the second threshold, the corresponding data element is changed into an element of a non-sky portion. A binary representative of the image stream may be generated based on the results of operation 904 and operation 906. … At operation 912, one or more sky components are verified as real ones that constitute the sky portion of the view. A modified mask image is generated, and the modified mask image comprises a sky portion including the verified sky components”)
Therefore, it would been obvious to one having ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Yan, Lietzke , Huo and Mommert by including process for sky portion extraction using image stream by Shen, to make the invention that weather information extraction using image data; thus, one of ordinary skilled in the art would have been motivated to combine the references since this will improving the determine cloud coverage, cloud darkness, and cloud patterns at different times and locations so as to obtain comprehensive information relating to how a weather system or event..
Thus, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filling date of the claimed invention.
Regarding claim 9, Yan, as modified by Lietzke, Huo, Mommert and Shen, discloses all the claim invention. Huo further discloses the sky image is an image taken by an all-sky camera, (Figs 1 and 8; 2. Sky cameras and associated images: “The sky images used in this paper are provided by an all-sky imager system (ASIs-I)”) and the processing circuitry is further configured to extract the edge by removing the fringe part of the sky image from a target range for extracting edges. (Figs.7 and 10 ; 4a. FFT method: “To exclude the pixels of the sheltering device in the image and get the maximum areas for FFT, B/R ratios of a 512 3 512 pixel block are used to make FFTs (Fig. 7a). ; Figs. 2-5; 4. Integrated method for cloud determination and contrast -b: Symmetrical Method- c. Procedure of cloud determination: The B/R ratios of those pixels are then averaged to obtain the threshold. The finial threshold is the average of the values obtained by the histogram and edge-searching methods. … (this is one of the reasons why TSI uses several thresholds, depending on different positions) … the symmetrical method is used on those regions where the zenith angle is greater than 75 degree (set in the integrated method). ”)
Relevant Prior Art Directed to State of Art
Sun et al (U.S. 20150301226 A1), “Short Term Cloud Coverage Prediction Using Ground-based All Sky Imaging”, teaches about the computer determines a segmented cloud model based on the sky images, a future sun location corresponding to a future time value, and sun pixel locations at the future time value based on the future sun location. Next, the computer applies a back-propagation algorithm to the sun pixel locations using the estimated cloud velocity field to yield propagated sun pixel locations corresponding to a previous time value. Then, the computer predicts cloud coverage for the future sun location based on the propagated sun pixel locations and the segmented cloud model.
Zheng et al (U.S. 9,805,293 B2), “Method And Apparatus For Object Recognition In Image Processing”, teaches about A method is provided for recognition of a sky portion, a vertical object portion and a ground portion in an image. The image into a plurality of pixel sets by the electronic system. Expected values of each pixel sets with a sky distribution function, a vertical object distribution function and a ground distribution function by the electronic system are calculated and compared for each pixel set for determine each pixel set belonging to one of the sky portion, the vertical object portion or the ground portion.
Revell et al (U.S. 20170372120 A1), “Cloud Feature Detection”, teaches about a method of detecting cloud features comprise: obtaining image data, the image data defining a plurality of pixels and, for each pixel, a respective luminance value; defining one or more intervals for the luminance values of the pixels; partitioning the image data into one or more image segments, each respective image segment containing pixels having a luminance value in a respective interval; and classifying, as a cloud feature, each image segment containing pixels having luminance value greater than or equal to a threshold luminance value.
Yan et al (U.S. 20180372914 A1), “Local Weather Forecast”, teaches about raining a local weather forecast model using information extracted from images captured by a plurality of data collection devices, data measured by the sensors of the plurality of data collection devices, and historical weather forecast data provided by an existing forecast provider. Information indicative of cloud type, cloud moving direction and cloud cover is extracted from the images captured by the plurality of data collection devices. In some embodiments, a deep learning algorithm is trained using pre-labelled information relating to a plurality of cloud types. The trained deep learning algorithm is capable of recognizing cloud types.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Duy A Tran whose telephone number is (571)272-4887. The examiner can normally be reached Monday-Friday 8:00 am - 5:00 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, ONEAL R MISTRY can be reached at (313)-446-4912. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/DUY TRAN/Examiner, Art Unit 2674
/ONEAL R MISTRY/Supervisory Patent Examiner, Art Unit 2674
Prosecution Insights