DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
Applicant’s Amendments filed on 07/06/2026 has been entered and made of record.
Currently pending Claim(s):
Independent Claim(s):
Amended Claim(s):
1–20
1, 11 and 20
1, 11 and 20
Response to Applicant’s Arguments
This office action is responsive to Applicant’s Arguments/Remarks Made in an Amendment received on 07/06/2026.
In view of the amendments filed on 07/06/2026 to the claim 11 the claim interpretation under 112(f) to claim 11 is withdrawn.
In view of applicant Arguments/Remarks and amendment filed on 07/06/2026 with respect to independent claims 1, 11 and 20 under 35 U.S.C 103, claim rejection has been fully considered and the arguments are found to be not persuasive (See Pages 11–14), therefore the claim rejection with respect to 35 U.S.C. 103 still applies.
Applicant argues, in summary (See pages 11–14) the applied prior art (Khait) and (Fu) does not disclose or suggest (specifically on page 12 of the Remarks):
“determining, based on the determined first likelihoods the plants are the first class of plant across the plurality of images, a probability that plants in the field are a second class of plant” [Emphasis added].
However, the Examiner respectfully disagrees with Applicant’s line of reasoning. Khait discloses feeding multiple images into the object detection model to classify the images “See Khait, [Col. 14, ln. 52 and 53], Test images may be sequentially fed into the trained machine learning model”. Khait determines the likelihoods on single image but uses multiple single images as well. “See Khait, [Col. 20, ln. 62–65], first weed species with probability of 50%, and the classifier, when fed a patch of the bounding box, identified a second weed specifies with probability of 90%”. The Examiner interprets the claims as determining a probability that multiple images include a plant identified as a first type. Based on the claim language the Examiner is interpreting that since Khait determines the likelihood that the image contains the first class in multiple images that it is the same as the new claim limitation as written “determined first likelihoods the plants are the first class of plant across the plurality of images”.
Applicant on page 13 of the Remarks argues by stating:
PNG
media_image1.png
485
723
media_image1.png
Greyscale
The Examiner respectfully disagrees. The claims do not recite “aggregate determination made by evaluating the first model’s output over multiple images as the farming machine travels through the field”. The claims merely recite “determining… a probability that plants in the field are a second class of plant”. Further, while the Examiner understands that the “determining” step may be meta-level inference about field composition, Khait discloses the “determining” step. Khait discloses a second class of plant as identified as second weed specifies at col. 20 lines 62-65 and suspicious object proposals 508 as illustrated in Figure 5, eventually leading to probability of 90% once it is decided to re-classified. Please note, the “determining” step is “based on the determined first likelihoods the plants are the first class of plant across the plurality of images”. Khait discloses test images that are sequentially fed into the trained machine learning model, at col. 14 lines 52-53 – this is interpreted as “first class of plant”.
Applicant on pages 13-14, regarding the cited reference of Fu, argues stating:
PNG
media_image2.png
229
720
media_image2.png
Greyscale
PNG
media_image3.png
426
696
media_image3.png
Greyscale
The Examiner respectfully disagrees. While the Examiner understands that the claimed invention is directed, as stated by the applicant, towards multi-model architecture in which the output of the first identification model output is aggregated across a plurality of images to determine a second class of plant, but claim 1 and 5 do not recite the aggregation of the images. As stated above, Khait is used to teach the “determining” step for the first likelihood across a plurality of images and determining a second likelihood. The limitation taught by Fu merely recites “treating” based on “…a plant identified as the second class of plant based on the determined second likelihood the plant is the second class of plant”. Fu is being incorporated to identify FIG. 2A, 230 second plant type, 220 first plant type, to apply a treatment to the second plant type ¶ [0081]. Khait and Fu are both pertinent to the field of agriculture and plant identification. Fu is being incorporated to better improve the accuracy and identification of plants for treatment ¶ [0003–0007].
Therefore, with this broad interpretation, Khait in combination with Fu teaches, discloses or suggests the Applicant’s invention, taking a plurality of images of plants in a farming field and feed into a first neural network to identify a first class of plant and determine a second class of plant and feed the image into a second neural network identify the second class of plant and treat the second class of plant. Thus, due to the Applicant’s broad claim language, Applicant’s invention is not far removed from the art of record. Accordingly, these limitations do not render claims patentably distinct over the prior art of record. As a result, it is respectfully submitted that the present application is not in condition for allowance.
Thus, the Examiner maintains that limitations as presented and as rejected were properly and adequately met. The rejection as presented in the Non-Final Rejection is maintained regarding the above limitation. Additional citations and/or modified citations may be present to more concisely address limitations. However, the grounds of the rejection remain the same.
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 non-obviousness.
Claim(s) 1, 5, 10, 11, 15 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Khait et al. (US 11393049 B2, hereafter, "Khait") in view of Fu et al. (US 20210089771 A1, hereafter, "Fu").
Regarding claim 1, Khait teaches a method for treating plants in a field (See Khait, [Abstract], There is provided a system for customized application of herbicides), the method comprising:
accessing a plurality of images of plants in the field as a farming machine travels through the field treating the plants (See Khait, [Col. 10, ln. 11–14], System 100 includes one or more imaging and treatment arrangements 108 connected to an agricultural machine 110, for example, a tractor, an airplane, an off-road vehicle, and a drone. [Col. 10, ln. 47–48], A computing device 104 receives the image(s) from image sensor(s) 112. [Col. 14, ln. 47–50], Optionally, the test images are captured by an imaging sensor at a resolution corresponding to a target resolution of a target imaging sensor that is designed to capture input image(s), as described herein);
applying, to the plurality of images (See Khait, [Col. 21, ln. 58–59], At 604, the test images are fed into a detection pipeline, for example, as described herein) a first plant identification model configured to identify a first class of plant in images (See Khait, [Col. 20, ln. 30–38], At 506, the input image is fed into an object detector component (e.g., neural network), that generates bounding boxes, each bounding box is associated with a probability value indicating likelihood of respective weed parameter(s) being depicted therein), the first plant identification model identifying plants as the first class of plant by determining first likelihoods the plants are the first class of plant (See Khait, [Col. 20, ln. 18–21], Reference is now made to FIG. 5, which is a flowchart of an exemplary detection pipeline for detecting one or more weed parameters, in accordance with some embodiments of the present invention. [Col. 20, ln. 30–38], At 506, the input image is fed into an object detector component (e.g., neural network), that generates bounding boxes, each bounding box is associated with a probability value indicating likelihood of respective weed parameter(s) being depicted therein. For example, bounding boxes are generated for specific weed species. The number of boxes may be, for example, over 10, over 25, over 50, and other numbers. It is noted that boxes may overlap, and/or multiple boxes may depict the same object therein);
determining, based on the determined first likelihoods the plants are the first class of plant across the plurality of images (See Khait, [Col. 14, ln. 52 and 53], Test images may be sequentially fed into the trained machine learning model. See Khait, [Col. 20, ln. 59–63], At 510, the weed parameter(s) identified in the respective bounding box may be re-classified based on the outcome generated by the classifier. For example, the detector identified a weed in a bounding box as a first weed species with probability of 50%, and the classifier), a probability that plants in the field are a second class of plant (See Khait, [Col. 20, ln. 59–66], At 510, the weed parameter(s) identified in the respective bounding box may be re-classified based on the outcome generated by the classifier. For example, the detector identified a weed in a bounding box as a first weed species with probability of 50%, and the classifier, when fed a patch of the bounding box, identified a second weed species with probability of 90%. The bounding box is re-classified to include the second weed species. Note: the second class is based on whether the second probability is higher than the first probability);
applying, based on the determination, a second plant identification model configured to identify the second class of plant to the plurality of images (See Khait, [Col. 20, ln. 47–53], At 508, the bounding boxes, which represent suspicious object proposals (i.e., not clear if an object is depicted therein or not), are fed into a classifier component (e.g., another neural network) that generates another probability indicating a numerical likelihood of the presence of each of multiple weed parameter(s) being depicted in the respective box), the second plant identification model identifying plants as the second class of plant by determining second likelihoods the plants are the second class of plant (See Khait, [Col. 20, ln. 47–53], At 508, the bounding boxes, which represent suspicious object proposals (i.e., not clear if an object is depicted therein or not), are fed into a classifier component (e.g., another neural network) that generates another probability indicating a numerical likelihood of the presence of each of multiple weed parameter(s) being depicted in the respective box. [Col. 20, ln. 59–66], At 510, the weed parameter(s) identified in the respective bounding box may be re-classified based on the outcome generated by the classifier. For example, the detector identified a weed in a bounding box as a first weed species with probability of 50%, and the classifier, when fed a patch of the bounding box, identified a second weed specifies with probability of 90%. The bounding box is re-classified to include the second weed species); and
[treating, with the farming machine, a plant identified as the second class of plant based on the determined second likelihood the plant is the second class of plant].
However, Khait fails to teach treating, with the farming machine, a plant identified as the second class of plant based on the determined second likelihood the plant is the second class of plant.
Fu, working in the same field of endeavor, teaches: treating, with the farming machine, a plant identified as the second class of plant based on the determined second likelihood the plant is the second class of plant (See Fu, ¶ [0081], The farming machine is configured to identify weeds (e.g. second plant type 230) in the field and treat the identified weeds by spraying them with an herbicide).
Thus, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify Khait’s reference to treating, with the farming machine, a plant identified as the second class of plant based on the determined second likelihood the plant is the second class of plant based on the method of Fu’s reference. The suggestion/motivation would have been to accurately rapidly identify plants (See Fu, ¶ [0003–0007]).
Further, one skilled in the art could have combined the elements as described above by known method with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Therefore, it would have been obvious to combine Fu with Khait to obtain the invention as specified in claim 1.
Regarding claim 5, Khait in view of Fu teaches the method of claim 1, wherein determining a probability that the plants in the field are a second class of plants (See Khait, [Col. 20, ln. 47–53], At 508, the bounding boxes, which represent suspicious object proposals (i.e., not clear if an object is depicted therein or not), are fed into a classifier component (e.g., another neural network) that generates another probability indicating a numerical likelihood of the presence of each of multiple weed parameter(s) being depicted in the respective box) comprises:
for each image in the plurality of images (See Khait, [Col. 10, ln. 11–14], System 100 includes one or more imaging and treatment arrangements 108 connected to an agricultural machine 110, for example, a tractor, an airplane, an off-road vehicle, and a drone. [Col. 10, ln. 47–48], A computing device 104 receives the image(s) from image sensor(s) 112. [Col. 14, ln. 47–50], Optionally, the test images are captured by an imaging sensor at a resolution corresponding to a target resolution of a target imaging sensor that is designed to capture input image(s), as described herein),
determining a first likelihood the image comprises plants of the first class of plant (See Khait, [Col. 20, ln. 30–38], At 506, the input image is fed into an object detector component (e.g., neural network), that generates bounding boxes, each bounding box is associated with a probability value indicating likelihood of respective weed parameter(s) being depicted therein. For example, bounding boxes are generated for specific weed species. The number of boxes may be, for example, over 10, over 25, over 50, and other numbers. It is noted that boxes may overlap, and/or multiple boxes may depict the same object therein), and
[calculating the probability the plants in the field are the second class based on one or more determined first likelihoods for one or more previous images in the plurality of images].
However, Khait fails to teach calculating the probability the plants in the field are the second class based on one or more determined first likelihoods for one or more previous images in the plurality of images.
Fu, working in the same field of endeavor, teaches: calculating the probability the plants in the field are the second class based on one or more determined first likelihoods for one or more previous images in the plurality of images (See Fu, ¶ [0064], FIG. 5 is a representation of a plant identification model based on accessed images and previously identified plants, according to one example embodiment. As described in greater detail below, the plant identification model can identify plants in both ideal and non-ideal operating conditions. The previously identified plants may have been identified by another plant identification model or a human identifier).
Thus, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify Khait’s reference to calculating the probability the plants in the field are the second class based on one or more determined first likelihoods for one or more previous images in the plurality of images based on the method of Fu’s reference. The suggestion/motivation would have been to accurately rapidly identify plants (See Fu, ¶ [0003–0007]).
Further, one skilled in the art could have combined the elements as described above by known method with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Therefore, it would have been obvious to combine Fu with Khait to obtain the invention as specified in claim 5.
Regarding claim 10, Khait teaches the method of claim 1, wherein applying the second plant identification model configured to identify the second class of plant to the plurality of images occurs autonomously responsive to the determined probability that plants in the field are a second class of plant being above a threshold probability (See Khait, [Col. 20, ln. 39–45], For bounding boxes with probabilities higher than a threshold, the process proceeds to 512 (skipping 508 and 510). For example, probability is >90%. Alternatively, for bounding boxes with probabilities lower than the threshold, but optionally higher than a second lower threshold, the process proceeds to 508 (and then 510, before returning to 512). Note: the second lower threshold is being interpreted as the threshold probability. [Col. 20, ln. 47–53], At 508, the bounding boxes, which represent suspicious object proposals (i.e., not clear if an object is depicted therein or not), are fed into a classifier component (e.g., another neural network) that generates another probability indicating a numerical likelihood of the presence of each of multiple weed parameter(s) being depicted in the respective box).
Regarding claim 11, claim 11 is rejected the same as claim 1 and the arguments similar to that presented above for claim 1 are equally applicable to the claim 11, and all of the other limitations similar to claim 1 are not repeated herein, but incorporated by reference. Furthermore, Khait teaches a farming machine comprising: an image acquisition system configured to capture images of plants in a field as the farming machine traverses past the plants in the field; a plurality of treatment mechanisms configured to treat identified plants in the field; one or more processors; and a non-transitory computer readable storage medium computer program instructions that, when executed by the one or more processors, cause the farming machine to (See Khait, [FIG. 1], Image Sensor(s) 112, Agricultural machine 110, Treatment storage compartment(s) 150, Processor(s) 102, Storage device (e.g., memory) 106).
Regarding claim 15, claim 15 is rejected the same as claim 5 and the arguments similar to that presented above for claim 5 are equally applicable to the claim 15, and all of the other limitations similar to claim 5 are not repeated herein, but incorporated by reference.
Regarding claim 20, claim 20 is rejected the same as claim 1 and the arguments similar to that presented above for claim 1 are equally applicable to the claim 20, and all of the other limitations similar to claim 1 are not repeated herein, but incorporated by reference. Furthermore, Khait teaches a non-transitory computer-readable storage medium storing computer program instructions for treating plants in a field, the computer program instructions, when executed by one or more processors, causing the one or more processors to (See Khait, [FIG. 1], Processor(s) 102, Storage device (e.g., memory) 106).
Claim(s) 2 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Khait et al. (US 11393049 B2, hereafter, "Khait") in view of Fu et al. (US 20210089771 A1, hereafter, "Fu") further in view of Yayun et al. (See NPL attached, "Deep-CNN based Robotic Multi-Class Under-Canopy Weed Control in Precision Farming", hereafter, "Yayun").
Regarding claim 2, Khait in view of Fu teaches the method of claim 1, [wherein the first plant identification model and the second plant identification model are a single plant identification model configured to identify both the first class of plant and the second class of plant].
However, Khait and Fu fail to teach wherein the first plant identification model and the second plant identification model are a single plant identification model configured to identify both the first class of plant and the second class of plant.
Yayun, working in the same field of endeavor, teaches: wherein the first plant identification model and the second plant identification model are a single plant identification model configured to identify both the first class of plant and the second class of plant (See Yayun, [Pg. 2275, Col. 2, ln. 39-40], In this section, we illustrate the pipeline for a multi-class weed classification scheme. See also, [FIG. 3]. Note: 3 classes are predicted by the model).
Thus, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify Khait’s and Fu’s reference to wherein the first plant identification model and the second plant identification model are a single plant identification model configured to identify both the first class of plant and the second class of plant based on the method of Yayun’s reference. The suggestion/motivation would have been to accurately identify plant classes (See Yayun, [Fig. 6]).
Further, one skilled in the art could have combined the elements as described above by known method with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Therefore, it would have been obvious to combine Yayun with Khait and Fu to obtain the invention as specified in claim 2.
Regarding claim 12, claim 12 is rejected the same as claim 2 and the arguments similar to that presented above for claim 2 are equally applicable to the claim 12, and all of the other limitations similar to claim 2 are not repeated herein, but incorporated by reference.
Claim(s) 3, 4, 13 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Khait et al. (US 11393049 B2, hereafter, "Khait") in view of Fu et al. (US 20210089771 A1, hereafter, "Fu") further in view of Sergeev et al. (US 20230252624 A1, hereafter, "Sergeev").
Regarding claim 3, Khait in view of Fu teaches the method of claim 1, wherein applying, based on the determination, the second plant identification model to the plurality of images (See Khait, [Col. 20, ln. 47–53], At 508, the bounding boxes, which represent suspicious object proposals (i.e., not clear if an object is depicted therein or not), are fed into a classifier component (e.g., another neural network) that generates another probability indicating a numerical likelihood of the presence of each of multiple weed parameter(s) being depicted in the respective box) comprises [reconfiguring one or more parameters of the first plant identification model and applying the reconfigured first plant identification model to the plurality of images as the second plant identification model].
However, Khait and Fu fail to teach reconfiguring one or more parameters of the first plant identification model and applying the reconfigured first plant identification model to the plurality of images as the second plant identification model.
Sergeev, working in the same field of endeavor, teaches: reconfiguring one or more parameters of the first plant identification model and applying the reconfigured first plant identification model to the plurality of images as the second plant identification model (See Sergeev, ¶ [0113], The point detection module may be pretrained at step 1020 using the pretraining image data. Pretraining model weights may be determined at step 1030 based on the pretraining. The pretrained model weights may be more representative of an image dataset (e.g., a weed image dataset, a crop image dataset, a farm image dataset, a region image dataset, a company image dataset, a weed image dataset, or a species image dataset) than weights from the untrained model. The pretrained point detection module may receive labeled image data at step 1040, ... , The point detection module may be trained at step 1050 to identify object parameters (e.g., location, size, category, or type) for objects of interest (e.g., plants, weeds, a type of weed, crops, or a type of crop). Note: Examiner is interpreting the pretraining to the training as the reconfiguring the model to make the second (e.g., more precise) classification).
Thus, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify Khait’s and Fu’s reference reconfiguring one or more parameters of the first plant identification model and applying the reconfigured first plant identification model to the plurality of images as the second plant identification model based on the method of Sergeev’s reference. The suggestion/motivation would have been to accurately identify plant in unpredictable environments (See Sergeev, ¶ [0002–0006]).
Further, one skilled in the art could have combined the elements as described above by known method with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Therefore, it would have been obvious to combine Sergeev with Khait and Fu to obtain the invention as specified in claim 3.
Regarding claim 4, Khait in view of Fu teaches the method of claim 1, wherein applying the first plant identification model to the plurality of images (See Khait, [Col. 21, ln. 58–59], At 604, the test images are fed into a detection pipeline, for example, as described herein) comprises [receiving, from an operator of the farming machine, an instruction to identify first class of plants in the field].
However, Khait and Fu fail to teach receiving, from an operator of the farming machine, an instruction to identify first class of plants in the field.
Sergeev, working in the same field of endeavor, teaches: receiving, from an operator of the farming machine, an instruction to identify first class of plants in the field (See Sergeev, ¶ [0125], In some embodiments, a computer system may implement the object identification and targeting methods based on instructions provided by a human user through a detection terminal).
Thus, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify Khait’s and Fu’s reference receiving, from an operator of the farming machine, an instruction to identify first class of plants in the field based on the method of Sergeev’s reference. The suggestion/motivation would have been to accurately identify plant in unpredictable environments in real time (See Sergeev, ¶ [0002–0006]).
Further, one skilled in the art could have combined the elements as described above by known method with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Therefore, it would have been obvious to combine Sergeev with Khait and Fu to obtain the invention as specified in claim 4.
Regarding claim 13, claim 13 is rejected the same as claim 3 and the arguments similar to that presented above for claim 3 are equally applicable to the claim 13, and all of the other limitations similar to claim 3 are not repeated herein, but incorporated by reference.
Regarding claim 14, claim 14 is rejected the same as claim 4 and the arguments similar to that presented above for claim 4 are equally applicable to the claim 14, and all of the other limitations similar to claim 4 are not repeated herein, but incorporated by reference.
Claim(s) 6, 7, 16 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Khait et al. (US 11393049 B2, hereafter, "Khait") in view of Fu et al. (US 20210089771 A1, hereafter, "Fu") further in view of Huapeng et al. (See NPL attached, "Temporal Sequence Object-based CNN (TS-OCNN) for crop classification from fine resolution remote sensing image time-series", hereafter, "Huapeng").
Regarding claim 6, Khait in view of Fu teaches the method of claim 5, wherein calculating the probability the plants in the field are the second class (See Khait, [Col. 20, ln. 59–66], At 510, the weed parameter(s) identified in the respective bounding box may be re-classified based on the outcome generated by the classifier. For example, the detector identified a weed in a bounding box as a first weed species with probability of 50%, and the classifier, when fed a patch of the bounding box, identified a second weed specifies with probability of 90%. The bounding box is re-classified to include the second weed species) comprises [applying a smoothing function to the one or more determined first likelihoods for the one or more previous images].
However, Khait and Fu fail to teach wherein applying a smoothing function to the one or more determined first likelihoods for the one or more previous images.
Huapeng, working in the same field of endeavor, teaches: applying a smoothing function to the one or more determined first likelihoods for the one or more previous images (See Huapeng, [Pg. 1509, Col. 2, ln. 9–13], Combine represents a function to combine the
i
-
t
h
image
M
i
with the probabilities generated at the previous iteration. In other words, the function combines spatially the bands contained in
P
X
ⅈ
-
1
produced at the previous iteration with those in the
i
-
t
h
image (
M
i
) as the input for current iteration. See also [Fig. 1]. Note: Examiner is interpreting the combining as smoothing the probabilities).
Thus, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify Khait’s and Fu’s reference wherein: applying a smoothing function to the one or more determined first likelihoods for the one or more previous images based on the method of Huapeng’s reference. The suggestion/motivation would have been to accurately classify the crops and refine the predictions (See Huapeng, [Fig. 6]).
Further, one skilled in the art could have combined the elements as described above by known method with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Therefore, it would have been obvious to combine Huapeng with Khait and Fu to obtain the invention as specified in claim 6.
Regarding claim 7, Khait in view of Fu teaches the method of claim 1, further comprising:
[determining, based on the determined second likelihoods the plants are the second class of plant, an additional probability that plants in the field are a third class of plant;
applying, based on the probability, a third plant identification model configured to identify the third class of plant to the plurality of images, the third plant identification model identifying plants as the third class of plant by determining third likelihoods the plants are the third class of plant]; and
treating, with the farming machine, a different plant identified as the third class of plant based on the determined third likelihood the plant is the third class of plants (See Khait, [Col. 22, ln. 10-16], For example, weed parameters which are accurately detected and/or classified by the detection pipeline, such as when the probability values are above a threshold, are identified. A specific substance, optionally an herbicide, is selected for each identified weed parameter).
However, Khait and Fu fail to teach determining, based on the determined second likelihoods the plants are the second class of plant, an additional probability that plants in the field are a third class of plant; applying, based on the probability, a third plant identification model configured to identify the third class of plant to the plurality of images, the third plant identification model identifying plants as the third class of plant by determining third likelihoods the plants are the third class of plant.
Huapeng, working in the same field of endeavor, teaches: determining, based on the determined second likelihoods the plants are the second class of plant, an additional probability that plants in the field are a third class of plant (See Huapeng, [Pg. 1509, Col. 1, ln. 17-19], The general procedure of the TS-OCNN approach is demonstrated in Fig. 1, in which crop classifications are refined gradually along with the temporal sequence of image time-series. [Pg. 1509, Col. 2, ln. 9–13], Combine represents a function to combine the i-th image M_i with the probabilities generated at the previous iteration. In other words, the function combines spatially the bands contained in P(X)^(ⅈ-1) produced at the previous iteration with those in the i-th image (M_i) as the input for current iteration. See also [Fig. 1]. Note: Multiple classifications are made in FIG. 1 of the crop. At least three. The Examiner is interpreting the refined classification as a first, second and third probability);
applying, based on the probability, a third plant identification model configured to identify the third class of plant to the plurality of images, the third plant identification model identifying plants as the third class of plant by determining third likelihoods the plants are the third class of plant (See Huapeng, [Pg. 1509, Col. 2, ln. 9–13], Combine represents a function to combine the i-th image M_i with the probabilities generated at the previous iteration. In other words, the function combines spatially the bands contained in P(X)^(ⅈ-1) produced at the previous iteration with those in the i-th image (M_i) as the input for current iteration. See also [Fig. 1]).
Thus, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify Khait’s and Fu’s reference determining, based on the determined second likelihoods the plants are the second class of plant, an additional probability that plants in the field are a third class of plant; applying, based on the probability, a third plant identification model configured to identify the third class of plant to the plurality of images, the third plant identification model identifying plants as the third class of plant by determining third likelihoods the plants are the third class of plant based on the method of Huapeng’s reference. The suggestion/motivation would have been to accurately classify the crops and refine the predictions (See Huapeng, [Fig. 6]).
Further, one skilled in the art could have combined the elements as described above by known method with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Therefore, it would have been obvious to combine Huapeng with Khait and Fu to obtain the invention as specified in claim 7.
Regarding claim 16, claim 16 is rejected the same as claim 6 and the arguments similar to that presented above for claim 6 are equally applicable to the claim 16, and all of the other limitations similar to claim 6 are not repeated herein, but incorporated by reference.
Regarding claim 17, claim 17 is rejected the same as claim 7 and the arguments similar to that presented above for claim 7 are equally applicable to the claim 17, and all of the other limitations similar to claim 7 are not repeated herein, but incorporated by reference.
Claim(s) 8 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Khait et al. (US 11393049 B2, hereafter, "Khait") in view of Fu et al. (US 20210089771 A1, hereafter, "Fu") further in view of Huapeng et al. (See NPL attached, "Temporal Sequence Object-based CNN (TS-OCNN) for crop classification from fine resolution remote sensing image time-series", hereafter, "Huapeng") and further in view of Yayun et al. (See NPL attached, "Deep-CNN based Robotic Multi-Class Under-Canopy Weed Control in Precision Farming", hereafter, "Yayun").
Regarding claim 8, Khait in view of Fu further in view of Huapeng teaches the method of claim 7, [wherein the first plant identification model, the second plant identification model, and the third plant identification model are a single plant identification model configured to identify the first class of plant, the second class of plant, and the third class of plant].
However, Khait, Fu and Huapeng fail to teach wherein the first plant identification model, the second plant identification model, and the third plant identification model are a single plant identification model configured to identify the first class of plant, the second class of plant, and the third class of plant.
Yayun, working in the same field of endeavor, teaches: wherein the first plant identification model, the second plant identification model, and the third plant identification model are a single plant identification model configured to identify the first class of plant, the second class of plant, and the third class of plant (See Yayun, [Pg. 2275, Col. 2, ln. 39–40], In this section, we illustrate the pipeline for a multi-class weed classification scheme. See also, [FIG. 3]. Note: 3 classes are predicted by the model).
Thus, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify Khait’s, Fu’s and Huapeng’s reference wherein the first plant identification model, the second plant identification model, and the third plant identification model are a single plant identification model configured to identify the first class of plant, the second class of plant, and the third class of plant based on the method of Yayun’s reference. The suggestion/motivation would have been to accurately identify plant classes (See Yayun, [Fig. 6]).
Further, one skilled in the art could have combined the elements as described above by known method with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Therefore, it would have been obvious to combine Yayun with Khait, Fu and Huapeng to obtain the invention as specified in claim 8.
Regarding claim 18, claim 18 is rejected the same as claim 8 and the arguments similar to that presented above for claim 8 are equally applicable to the claim 18, and all of the other limitations similar to claim 8 are not repeated herein, but incorporated by reference.
Claim(s) 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Khait et al. (US 11393049 B2, hereafter, "Khait") in view of Fu et al. (US 20210089771 A1, hereafter, "Fu") further in view of Miresmailli et al. (US 20170032258 A1, hereafter, "Miresmailli") and further in view of Sergeev et al. (US 20230252624 A1, hereafter, "Sergeev").
Regarding claim 9, Khait in view of Fu teaches the method of claim 1, wherein applying, based on the determination, the second plant identification model configured to identify the second class of plant to the plurality of images (See Khait, [Col. 20, ln. 47–53], At 508, the bounding boxes, which represent suspicious object proposals (i.e., not clear if an object is depicted therein or not), are fed into a classifier component (e.g., another neural network) that generates another probability indicating a numerical likelihood of the presence of each of multiple weed parameter(s) being depicted in the respective box) comprises:
[transmitting, to an operator of the farming machine, a notification comprising the determined probability that plants in the field are the second class of plant; and
receiving, from the operator of the farming machine, an instruction to identify plants of the second class of plants in the field].
However, Khait and Fu fail to teach transmitting, to an operator of the farming machine, a notification comprising the determined probability that plants in the field are the second class of plant; and receiving, from the operator of the farming machine, an instruction to identify plants of the second class of plants in the field;
Miresmailli, working in the same field of endeavor, teaches: transmitting, to an operator of the farming machine, a notification comprising the determined probability that plants in the field are the second class of plant (See Miresmailli, ¶ [0108], At 1040 information about the crop is transmitted to a non-expert, such as 585 in FIG. 5. For example, this information could be delivered to a worker each morning to guide the worker to specific areas of the crop that need intervention based on analysis and classification of sensor data gathered overnight for the entire crop by mobile sensory platform 510 performing activity 900).
Thus, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify Khait’s and Fu’s reference to transmitting, to an operator of the farming machine, a notification comprising the determined probability that plants in the field are the second class of plant based on the method of Miresmailli’s reference. The suggestion/motivation would have been to accurately and timely predict classifications of the crops (See Miresmailli, ¶ [0002–0008]).
However, Khait, Fu and Miresmailli fail to teach receiving, from the operator of the farming machine, an instruction to identify plants of the second class of plants in the field.
Sergeev, working in the same field of endeavor, teaches: receiving, from the operator of the farming machine, an instruction to identify plants of the second class of plants in the field (See Sergeev, ¶ [0125], In some embodiments, a computer system may implement the object identification and targeting methods based on instructions provided by a human user through a detection terminal).
Thus, it would have been obvious to one of ordinary skills in the art before the effective filing date of the claimed invention to modify Khait’s, Fu’s and Miresmailli’s reference to receiving, from the operator of the farming machine, an instruction to identify plants of the second class of plants in the field based on the method of Sergeev’s reference. The suggestion/motivation would have been to accurately identify plant in unpredictable environments (See Sergeev, ¶ [0002–0006]).
Further, one skilled in the art could have combined the elements as described above by known method with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Therefore, it would have been obvious to combine Miresmailli with Khait, Fu and Sergeev to obtain the invention as specified in claim 9.
Regarding claim 19, claim 19 is rejected the same as claim 9 and the arguments similar to that presented above for claim 9 are equally applicable to the claim 19, and all of the other limitations similar to claim 9 are not repeated herein, but incorporated by reference.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Weimer et al. (US 20230394815 A1) teaches a method for classifying plants. In the method, the plants or their plant components are detected within an evaluation region at the first evaluation point in time with the aid of an optical and/or infrared detection unit, and the detected image data of the detection unit are evaluated with the aid of an algorithm. Using the evaluation, it is possible to distinguish at least one first plant type from at least one second plant type. The second plant type being treated in particular with a medium, preferably a liquid spray.
Redden (US 20150027044 A1) teaches a plant treatment method including, by a computing system: identifying a plant, in situ, within a geographic area; identifying an interleaf insertion point relative to leaves of the plant; positioning a treatment mechanism at the insertion point; and operating a treatment mechanism to apply a fluid treatment to a plant.
THIS ACTION IS MADE FINAL. 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 DION J SATCHER whose telephone number is (703)756-5849. The examiner can normally be reached Monday - Thursday 5:30 am - 2:30 pm, Friday 5:30 am - 9:30 am PST.
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, Henok Shiferaw can be reached at (571) 272-4637. 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.
/DION J SATCHER/Patent Examiner, Art Unit 2676
/SHEFALI D GORADIA/Primary Patent Examiner, Art Unit 2676
Prosecution Insights