DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . The Amendment filed 18 March 2026 (hereinafter “the Amendment”) has been entered and considered. Claims 1, 3-4, 9, 11, 15-17, and 19-20 have been amended. Claims 1-20, all the claims pending in the application, are rejected. All new grounds of rejection set forth in the present action were necessitated by Applicant’s claim amendments; accordingly, this action is made final.
Response to Amendment
Claim Interpretation
Independent claim 15 has been amended to recite sufficient structure (“processor”) that modifies the functional language of the claim. Accordingly, the interpretation of the claims as invoking 35 USC 112(f) is withdrawn.
Prior Art Rejections
In view of the amendments to independent claims 1, 9, and 15, the previously-applied prior art rejections are withdrawn. Applicant’s arguments are rendered moot in view of the new grounds of rejection set forth below.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 4-6, 9, 12-13, 15 and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over “Automatic Identification of Center Pivot Irrigation Systems from Landsat Images Using Convolutional Neural Networks” by Zhang et al. (hereinafter “Zhang”) in view of U.S. Patent Application Publication No. 2016/0029545 to Matthews (hereinafter “Matthews”).
As to independent claim 1, Zhang discloses a computer-implemented method for use in processing image data associated with fields (Abstract discloses that Zhang is directed to a Convolutional Neural Network trained for the “identification of center pivot systems” in images, wherein Figs. 1-4 show that the images are of fields, and wherein Section 6 discloses that the CNN is “implemented on a machine” which is necessarily a computer), the method comprising: accessing, by a computing device, at least one image of one or more fields (Section 3 discloses that “Landsat 5-TM images…were downloaded”, wherein Figs. 1-4 show that the images are of fields); applying, by the computing device, a trained model to identify at least one irrigation segment in the at least one image based on one or more labeling rules (Section 4 discloses that a “trained classifier classified filtered data to get clusters of [Center Pivot Irrigation Systems] CPIS” in the Landsat images, wherein “all training data were labeled, as either center pivot systems or non-center pivot systems”, such labeling necessarily requiring rules particular to center pivot systems or non-center pivot systems); compiling a map of the one or more fields including the at least one identified irrigation segment (Figs. 12-15 show “images processed after the classification” in which the identified CPIS are “displayed in red dots” or “marked by squares”); storing, by the computing device, the map of the at least one identified irrigation segment for the one or more fields; and causing display of the map of the at least one identified irrigation segment for the one or more fields (Figs. 12-15 show “images processed after the classification” in which the identified CPIS are displayed, wherein Section 6 discloses that the CNN is “implemented on a machine” which is necessarily a computer, and wherein storage and display of the maps are necessary in order to reproduce the maps in the Figures).
Although Zhang discloses a “machine” or computer that implements the CNN (Section 6), and thus appears to implicitly disclose memory and a display of the computer, Zhang does not expressly disclose these computer features. That is, Zhang does not expressly disclose a memory or an output device, as claimed. Zhang also does not expressly disclose that the labeling rules are specific to an irrigation system included in the at least one irrigation segment.
Matthews, like Zhang, is directed to using “optical recognition on satellite or aerial imagery to identify and subsequently determine one or more characteristics of a field(s) in the image, such as one or more center pivot irrigation system features” ([0013]). Specifically, Matthews discloses that such center pivot irrigation systems can be identified by “identifying an arm structure (hereinafter, arm) 20 of the center-pivot irrigation system 18 and locating an end of the arm corresponding to the center 16 of the field 12A” and “identifying a perimeter 22 of the field 12B presenting a fully-circular shape 24” based thereon ([0018]). Matthews further discloses a memory 76 in which information of the identified irrigation systems are stored and a user interface 58 including a display surface for presenting visual representations ([0029, 0040]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include within Zhang’s “machine” that implements the trained classifier, Matthews’ hardware including memory 76 and display 58 to arrive at the claimed invention discussed above because an ordinarily skilled artisan would need a known device such as the one taught by Matthews in order to implement the algorithm taught by Zhang in order to build a workable device. It is predictable that the memory and display of Matthews would have improved the user’s experience by facilitating storage and visualization of the maps.
Further, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zhang’s process of labeling irrigation systems such that the labeling is performed by identifying a specific feature of the irrigation system, such as an arm structure, and labeling the perimeter of the irrigation system based thereon, as taught by Matthews, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have enhanced the accuracy of the detection model by virtue of ensuring its training data was properly labeled.
As to claim 4, Zhang as modified by Matthews further teaches that the at least one irrigation segment defines at least a portion of a circle, thereby indicating pivot irrigation (Abstract and Figs. 4, 9, and 12 of Zhang show that the identified irrigation systems are “center pivot irrigation systems” that are circular) and wherein the one or more labeling rules identify features of the irrigation system, and wherein the features of the irrigation system include a well pad, an arm, a sprayer, a wheel, and/or a wheel track located concentrically around the well pad ([0018] of Matthews discloses that such center pivot irrigation systems can be identified by “identifying an arm structure (hereinafter, arm) 20 of the center-pivot irrigation system 18 and locating an end of the arm corresponding to the center 16 of the field 12A” and “identifying a perimeter 22 of the field 12B presenting a fully-circular shape 24” based thereon; the reasons for combining the references are the same as those discussed above in conjunction with claim 1).
As to claim 5, Zhang as modified above further teaches, prior to accessing the at least one image of the one or more fields: accessing a plurality of images of a plurality of fields, each including at least one irrigation segment; and training the model based on the accessed plurality of images and irrigation labels associated with the irrigation segments (Section 4 of Zhang discloses accessing a training dataset of images, wherein “all training data were labeled, as either center pivot systems or non-center pivot systems”, and wherein “the training data were fed into the three networks…to train the networks”).
As to claim 6, Zhang as modified above further teaches that accessing the plurality of images of the plurality of fields includes accessing the plurality of images for an interval (Section 3 of Zhang discloses that the Landsat images are “of the same area from the years 1986 and 2000”).
Independent claim 9 recites the same method steps as those recited in independent claim 1. Accordingly, claim 9 is rejected for reasons analogous to those discussed above in conjunction with claim 1 mutatis mutandis. Additionally, claim 9 recites a non-transitory computer-readable storage medium including executable instructions for processing image data associated with fields, which when executed by at least one processor, cause the at least one processor to perform the method steps. While Zhang does not expressly disclose such a medium, Matthews discloses a “computer readable storage medium” that “may contain or store a computer program” for performing Matthews’ method. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include within Zhang’s “machine” that implements the trained classifier, Matthews’ hardware including the computer readable storage medium to arrive at the claimed invention discussed above because an ordinarily skilled artisan would need a known device such as the one taught by Matthews in order to implement the algorithm taught by Zhang in order to build a workable device. It is predictable that implementing Zhang’s algorithm in software stored on a computer readable medium would have allowed the software to be reproduced for multiple images or at multiple workstations. Thus, claim 9 is rejected for this additional reason.
Claims 12-13 recite features nearly identical to those recited in claims 4-5, respectively. Accordingly, claims 12-13 are rejected for reasons analogous to those discussed above in conjunction with claims 4-5, respectively.
Independent claim 15 recites the same method steps as those recited in independent claim 1. Accordingly, claim 15 is rejected for reasons analogous to those discussed above in conjunction with claim 1 mutatis mutandis. Additionally, claim 15 recites a system comprising a computing device configured to perform the method steps. Zhang’s “machine” which implements the disclosed algorithm (Section 6) corresponds to the claimed “computing device” and claim 15 is rejected for this additional reason.
Claims 18-20 recite features nearly identical to those recited in claims 4-6, respectively. Accordingly, claims 18-20 are rejected for reasons analogous to those discussed above in conjunction with claims 4-6, respectively.
Claims 2, 10, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over “Automatic Identification of Center Pivot Irrigation Systems from Landsat Images Using Convolutional Neural Networks” by Zhang et al. (hereinafter “Zhang”) in view of U.S. Patent Application Publication No. 2016/0029545 to Matthews (hereinafter “Matthews”) and further in view of U.S. Patent Application Publication No. 2022/0210987 to Baldo (hereinafter “Baldo”).
As to claim 2, Zhang further discloses that the at least one image includes a series of images of the one or more fields over an interval (Section 3 discloses that the Landsat images are “of the same area from the years 1986 and 2000”). Although Zhang contemplates applying the model to “composite image[s]” (Section 4.1-4.2), these images are composited over color channels rather than temporally. That is, Zhang does not expressly disclose generating a composite of the images; and wherein applying the trained model includes applying the trained model to the composite of the images.
Baldo, like Zhang, is directed to the “detection of field irrigation through remote sensing” using “a trained classifier” which may be a “convolutional neural network” which produces an “output labeled map” (Abstract and [0015-0017, 0059] and Figs. 3-5). Baldo discloses that the field images “may be available on an irregular schedule…and may contain gaps” ([0046]). To address this problem, the “images are composited within pre-specified time windows” prior to being used for training the classifier and for applying the model in classification ([0046-0048, 0052, 0055-0056, 0065, 0106] and Steps 205 and 209-210 of Fig. 2).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the proposed combination of Zhang and Matthews to composite time-series images for training and applying the classifier, as taught by Baldo, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have “reduce[d] noise and lower[ed] the dimensionality of the problem, thereby enabling more efficient computation” while also allowing the model to cater to particular “phases of the growing season” ([0046, 0052] of Baldo).
Each of claims 10 and 16 recites features nearly identical to those recited in claim 2. Accordingly, claims 10 and 16 are rejected for reasons analogous to those discussed above in conjunction with claim 2.
Claims 3, 11, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Matthews and Baldo and further in view of U.S. Patent Application Publication No. 2023/0106749 to Hillebrand (hereinafter “Hillebrand”).
As to claim 3, Zhang as modified above by Baldo further teaches that the composite of the images includes an average of RGB values of all of the images in the series of images; and the interval includes an interval of months (Section 4.3 of Zhang discloses that the images are RGB images; [0052-0053] of Baldo discloses that the “images 108 are composited within pre-specified time windows” including “a first window [that] spans April and May, a second window [that] spans June and July, and a third window [that] spans August and September” and that the “compositing comprises performing a temporal linear interpolation” and “After interpolation, for each pixel or region, the average in time within a window is taken” (emphasis added); the reasons for combining the references are the same as those discussed above in conjunction with claim 2). Zhang as modified by Matthews and Baldo does not expressly disclose that the composition is a median of values.
Hillebrand, like Baldo, is directed to the “combination of the colors of the pixels from the temporal neighboring images” ([0087]). Hillebrand discloses the interchangeability of averaging and median synthesis, noting that the combination “can be averaging,…median, or any other type of combination ([0087]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to replace Baldo’s composition of temporally separate images by averaging with Hillebrand’s composition of temporally separate images by median synthesis, to arrive at the claimed invention discussed above. Such a modification is the result of simple substitution of one known element for another producing a predictable result. More specifically, Baldo’s composition of temporally separate images by averaging and Hillebrand’s composition of temporally separate images by median synthesis perform the same general and predictable function, the predictable function being combining temporally separate images. Since each individual element and its function are shown in the prior art, albeit shown in separate references, the difference between the claimed subject matter and the prior art rests not on any individual element or function but in the very combination itself - that is in the substitution of Baldo’s averaging by replacing it with Hillebrand’s median synthesis. Thus, the simple substitution of one known element for another producing a predictable result renders the claim obvious. It is predictable that median synthesis would have been resistant to extreme outliers that may skew data when averaging.
Claims 11 and 17 each recites features nearly identical to those recited in claim 3. Accordingly, claims 11 and 17 are rejected for reasons analogous to those discussed above in conjunction with claim 3.
Claims 7-8 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Matthews and further in view of U.S. Patent Application Publication No. 2018/0348714 to LaRue (hereinafter “LaRue”).
As to claim 7, Zhang as modified above does not expressly disclose instructing, by the computing device, operation of an irrigation system of the one or more fields based on the at least one identified irrigation segment.
LaRue, like Zhang, is directed to a “machine learning module” that analyzes data regarding “field objects” including “an irrigation system” (Abstract and [0002]). LaRue discloses that the output of the predictive model may be used “to make selected adjustments to the irrigation system” such as “speed correction” and a “corrected watering rate” which may be “automatically forwarded and executed by the irrigation system” ([0051-0052]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the proposed combination of Zhang and Matthews to use the prediction from the machine learning model to make and apply adjustments to the operation of the irrigation system, as taught by LaRue, to arrive at the claimed invention discussed above. Such a modification is the result of combining prior art elements according to known methods to yield predictable results. It is predictable that the proposed modification would have enabled a farmer to “predict and control irrigation and other outcomes in the field” ([0006] of LaRue).
As to claim 8, Zhang as modified by Matthews and LaRue above further teaches irrigating, by the irrigation system, the one or more fields ([0052] of LaRue discloses applying the adjustments to the operation of the irrigation system; the reasons for combining the references are the same as those discussed above in conjunction with claim 7).
Claim 14 recites features nearly identical to those recited in claim 7. Accordingly, claim 14 is rejected for reasons analogous to those discussed above in conjunction with claim 7 mutatis mutandis.
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 SEAN M CONNER whose telephone number is (571)272-1486. The examiner can normally be reached 10 AM - 6 PM Monday through Friday, and some Saturday afternoons.
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, Greg Morse can be reached at (571) 272-3838. 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.
/SEAN M CONNER/Primary Examiner, Art Unit 2663
Prosecution Insights