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 Amendments
The amended Drawings, filed 09/18/2025, are accepted and entered. Please see the Petition Decision mailed on 01/15/2026 regarding this matter.
Claims 1-20 are pending regarding this application.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 03/11/2025 is considered and attached.
Claim Objections
Claims 16 and 19 are objected to because of the following informalities:
Claim 16 recites “a location” in line 2. However, claim 15, upon which claim 16 depends, recites “locations of the at least one crop row”. From para. [0040] of applicant’s specification, it is clear applicant intended for the location as referenced in claim 16 to refer to a location of the agricultural vehicle. As such, please amend line 2 of claim 16 to recite “a location of an agricultural vehicle” in order to clearly distinguish the recitation of the location in claim 16 from the recitation of the locations of the at least one crop row in claim 15.
Claim 19 recites “wherein the sys one or more processors” in line 1. It is believed that “sys” is a mistype. Please amend the above phrase to recite “wherein the one or more processors”.
Appropriate correction is required.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 2, 4, 11, 13, 14, 15, and 17 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Jochem et al. (U.S. Publication No. 2007/0269114 A1), hereinafter Jochem.
Regarding claim 1, Jochem teaches a method for visually identifying crop rows (Jochem teaches a method for visually identifying crop rows in FIG. 1 and para. [0023]) comprising:
acquiring imagery from at least one imaging device operatively connected to an agricultural vehicle while the agricultural vehicle is traversing a field, the imagery including a plurality of plants arranged in rows (Jochem teaches an agricultural vehicle wherein “an imaging unit 10 (e.g., a video camera) can be directly or indirectly coupled to a vision data processor 12, where the imaging unit 10 can be mounted on a vehicle” while the vehicle is operated within an agricultural field for determining the position of crop rows as shown in para. [0023] and FIGs. 2 and 5A);
processing the imagery at a computing device to preserve spatial information along a first dimension while reducing data complexity along a second dimension to generate processed data (Jochem teaches “FIG. 4B is a one-dimensional mean intensity vector used by the confidence module 26 or the vision data processor 12 to determine a reliability level or confidence level. Each point in the vector is the mean pixel intensity along the corresponding scan line” as shown in para. [0039]. Here, the one-dimensional mean intensity vector, generated from the collected image data, preserves spatial information (peak/trough data as shown in para. [0035]), and reduces data complexity along a second dimension, as the collected image data is two-dimensional); and
analyzing the processed data to identify locations of the rows within the field (Jochem teaches “the peak intensity of the second scan line profile generally corresponds to a center of a crop row 402, whereas the minimum intensity generally corresponds to a ground row 404 between the crop rows 402” as shown in para. [0045]).
Regarding claim 2, Jochem teaches the method of claim 1 wherein the processing the imagery comprises:
dividing the imagery into multiple sections along a direction of travel of the agricultural vehicle (Jochem teaches dividing the image into sections using scan lines wherein the scan lines occur in the direction of travel of the vehicle as shown in FIG. 4a); and
for each section, performing statistical analysis to generate a one-dimensional intensity profile (Jochem teaches determining a one-dimensional mean intensity vector along a corresponding scan line in para. [0039] and FIG. 4B).
Regarding claim 4, Jochem teaches the method of claim 1
wherein the analyzing the processed data comprises identifying peaks within the processed data, wherein the peaks correspond to centers of the rows or centers of space between rows (Jochem teaches “the peak intensity of the second scan line profile generally corresponds to a center of a crop row 402” in para. [0045]).
Regarding claim 11, Li and Jochem teach the method of claim 1 further comprising
generating a guidance line based on the locations of the rows within the field (Jochem teaches “in the automatic steering mode, the control port 16 outputs guidance information (e.g., heading, angle data) to the steering controller 30, and the steering controller 30 generates an output for actuating the vehicle steering system 32 based on the guidance information” in para. [0024], wherein “the vision guidance system 11 controls the heading or position of the vehicle with respect to the one or more crop rows” as shown in para. [0025]. See also para. [0051]-[0052] wherein the heading of the vehicle is determined based on a scan line profile with a confidence score exceeding a minimum threshold level, and wherein the scan line profile is in turn based on the crop row positions. Here, the identified scan line profile for the preferential heading of the vehicle is interpreted as equivalent to the claimed guidance line. See also para. [0060] which describes the scan line profile as the “target path” for the vehicle).
Regarding claim 13, Li and Jochem teach the method of claim 11 further comprising
generating steering commands for the agricultural vehicle based on the guidance line (Jochem teaches an automatic steering mode wherein “the vision guidance system 11 controls the heading or position of the vehicle with respect to the one or more crop rows” in para. [0025]. Furthermore, Jochem teaches determining the preferential heading of the vehicle using a scan line profile (see the mapping of claim 11). As such, it is clear that Jochem teaches controlling the heading of the vehicle using a steering mode based on a guidance line).
Regarding claim 14, Li and Jochem teach the method of claim 13 further comprising
autonomously or semi-autonomously steering the agricultural vehicle using the steering commands (Jochem teaches an automatic steering mode wherein “the automatic steering mode may be referred to as an auto-steer mode, an autonomous mode, a vision-guidance mode, an unmanned mode, or some otherwise automated mode” and “the vision guidance system 11 controls the heading or position of the vehicle with respect to the one or more crop rows” in para. [0025]).
Regarding claim 15, Jochem teaches a system for identifying crop rows in real-time comprising:
at least one camera (Jochem teaches “an imaging unit 10 (e.g., a video camera) can be directly or indirectly coupled to a vision data processor 12” as shown in para. [0023]);
one or more processors (Jochem teaches a vision data processor 12 as shown in FIG. 1 which is configured to carry out the functions of the embodiment(s). See also para. [0023]) configured to:
acquire an image of a crop field from the at least one camera, the image including a portion of at least one crop row (Jochem teaches an agricultural vehicle wherein “an imaging unit 10 (e.g., a video camera) can be directly or indirectly coupled to a vision data processor 12, where the imaging unit 10 can be mounted on a vehicle” while the vehicle is operated within an agricultural field for determining the position of crop rows as shown in para. [0023] and FIGs. 2 and 5A);
process the image to preserve spatial information along a first dimension while reducing data complexity along a second dimension to generate processed data (Jochem teaches “FIG. 4B is a one-dimensional mean intensity vector used by the confidence module 26 or the vision data processor 12 to determine a reliability level or confidence level. Each point in the vector is the mean pixel intensity along the corresponding scan line” as shown in para. [0039]. Here, the one-dimensional mean intensity vector, generated from the collected image data, preserves spatial information (peak/trough data as shown in para. [0035]), and reduces data complexity along a second dimension, as the collected image data is two-dimensional);
analyze the processed data to identify locations of the at least one crop row (Jochem teaches “the peak intensity of the second scan line profile generally corresponds to a center of a crop row 402, whereas the minimum intensity generally corresponds to a ground row 404 between the crop rows 402” as shown in para. [0045]).
Regarding claim 17, Jochem teaches the system of claim 15 wherein the one or more processors is further configured to analyze the processed data by
identifying peaks within the processed data, wherein the peaks correspond to centers of the rows (Jochem teaches “the peak intensity of the second scan line profile generally corresponds to a center of a crop row 402” in para. [0045]).
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.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Jochem et al. (U.S. Publication No. 2007/0269114 A1), hereinafter Jochem in view of Li et al. (CN 113643231 A, see attached English translation), hereinafter Li.
Regarding claim 3, Jochem teaches the teach the method of claim 1.
While Jochem teaches utilizing a first technique to generate scan line profiles which represent the peak-to-trough difference of crops in a crop row in para. [0035], Jochem fails to teach wherein the processing the imagery comprises: applying an edge detection operation to identify predominantly vertical features within the imagery; and filtering out predominantly horizontal features to isolate plant stalks.
However, Li teaches wherein the processing the imagery comprises:
applying an edge detection operation to identify predominantly vertical features within the imagery (Li teaches determining the height of the crop row within the original image to generate a local image, and further using the local image “to transverse one-dimensional accumulation and projection to obtain a crop row height characteristic distribution curve, as shown in fig. 1, each peak in the curve represents a crop, and the crop height can be reflected” as shown in para. [0054]-[0058]. Here, since determining the height of a crop inherently involves edge detection, as determining the height of a crop involves determining the highest vertical point of the crop’s edge, it is clear that Li teaches an edge detection operation through the generation of the row height characteristic curve, wherein the crop height is interpreted as equivalent to the claimed vertical feature); and
filtering out predominantly horizontal features to isolate plant stalks (Li teaches “carrying out screenshot on the original depth image according to the height h and the width w to obtain a local image of the crop row” and, using the local image, obtaining a one-dimensional accumulation and projection to obtain a crop row height characteristic distribution curve as shown in para. [0054]-[0059]. Here, it is clear that the width (horizontal) data is filtered out in order to obtain the one-dimensional data, since the one-dimensional data represents the height (vertical) data).
Jochem and Li are both considered to be analogous to the claimed invention because they are in the same field of determining positions of crop rows through image analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Jochem to incorporate the teachings of Li and include “wherein the processing the imagery comprises: applying an edge detection operation to identify predominantly vertical features within the imagery; and filtering out predominantly horizontal features to isolate plant stalks”. The motivation for doing so would have been that “the embodiment provides a crop emergence quality detection method based on a depth image, which can accurately detect the position and height of a crop and effectively evaluate the sowing quality”, as suggested by Li in para. [0043]. Therefore, it would have been obvious to one of ordinary skill at the time the invention was filed to combine Jochem with Li to obtain the invention specified in claim 3.
Claims 5, 10, 12, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Jochem et al. (U.S. Publication No. 2007/0269114 A1), hereinafter Jochem in view of Rust et al. (U.S. Publication No. 2023/0229163 A1), hereinafter Rust.
Regarding claim 5, Jochem teaches the method of claim 1.
While Jochem teaches identifying spatial relationships between neighboring rows (Jochem teaches determining the spacing between two crop rows as shown in para. [0042]), Jochem fails to teach identifying spatial relationships between neighboring rows; and using the spatial relationships to validate row identification.
However, Rust teaches identifying spatial relationships between neighboring rows (Rust teaches identifying scan lines which indicate one or more crop rows, wherein the crop rows are separated from neighboring crop rows by row spacing in para. [0064]); and
using the spatial relationships to validate row identification (Rust teaches that the crop row spacing is used to determine the offset/heading error when navigating between crop rows as shown in para. [0069]. Here, the crop row spacing is used to determine heading error which is used to determine an estimate of crop row curvature as shown in para. [0070], which is interpreted as equivalent to the claimed validation process).
Jochem and Rust are both considered to be analogous to the claimed invention because they are in the same field of determining positions of crop rows through image analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Jochem to incorporate the teachings of Rust and include “identifying spatial relationships between neighboring rows; and using the spatial relationships to validate row identification”. The motivation for doing so would have been “to detect row curvature and correct measured TKE and XTE so that the corrected TKE and XTE more accurately represent where the vehicle should be steered in a row”, as suggested by Rust in para. [0012]. Therefore, it would have been obvious to one of ordinary skill at the time the invention was filed to combine Jochem and Rust to obtain the invention specified in claim 5.
Regarding claim 10, Jochem teaches the method of claim 1.
While it may be inherent that the vision guidance system (11) as taught by Jochem is onboard the vehicle, it is not explicitly recited in Jochem, and, therefore, Jochem fails to explicitly teach wherein the computing device is onboard the agricultural vehicle.
However, Rust teaches wherein the computing device is onboard the agricultural vehicle (Rust teaches “ the agricultural vehicle 100 includes a control module, such as a vehicle electronic controller unit (ECU) or other computing device” in para. [0041]).
Jochem and Rust are both considered to be analogous to the claimed invention because they are in the same field of determining positions of crop rows through image analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Jochem to incorporate the teachings of Rust and include “wherein the computing device is onboard the agricultural vehicle”. The motivation for doing so would have been such that processing is done locally, which decreases network delays, increases security, and ensures functionality independent from internet connection (See “Computational Offloading: When to Process Data Locally vs Remotely”). As such, it would have been obvious to a person of ordinary skill in the art to implement the system as taught by Jochem in a local manner, such as through the computing device onboard the agricultural vehicle as taught by Rust. Therefore, it would have been obvious to one of ordinary skill at the time the invention was filed to combine Jochem and Rust to obtain the invention specified in claim 10.
Regarding claim 12, Jochem teaches the method of claim 11.
However, Jochem fails to teach wherein the guidance line is curved.
However, Rust teaches wherein the guidance line is curved (Rust teaches “a system for determining crop row curvature and using the determined crop row curvature for enhanced steering controller performance in curved crop rows or furrows” in para. [0070]. See also para. [0009] and [0004] which specifically teaches the guidance path being curved).
Jochem and Rust are both considered to be analogous to the claimed invention because they are in the same field of determining positions of crop rows through image analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Jochem to incorporate the teachings of Rust and include “wherein the guidance line is curved”. The motivation for doing so would have been “to detect row curvature and correct measured TKE and XTE so that the corrected TKE and XTE more accurately represent where the vehicle should be steered in a row”, as suggested by Rust in para. [0012]. Therefore, it would have been obvious to one of ordinary skill at the time the invention was filed to combine Jochem and Rust to obtain the invention specified in claim 12.
Regarding claim 18, Jochem teaches the system of claim 15.
While Jochem teaches identifying spatial relationships between neighboring rows (Jochem teaches determining the spacing between two crop rows as shown in para. [0042]), Jochem fails to teach wherein the one or more processors is further configured to identify spatial relationships between neighboring rows, and use the spatial relationships to validate row identification.
However, Rust teaches identifying spatial relationships between neighboring rows (Rust teaches identifying scan lines which indicate one or more crop rows, wherein the crop rows are separated from neighboring crop rows by row spacing in para. [0064]); and
using the spatial relationships to validate row identification (Rust teaches that the crop row spacing is used to determine the offset/heading error when navigating between crop rows as shown in para. [0069]. Here, the crop row spacing is used to determine heading error which is used to determine an estimate of crop row curvature as shown in para. [0070], which is interpreted as equivalent to the claimed validation process).
Jochem and Rust are both considered to be analogous to the claimed invention because they are in the same field of determining positions of crop rows through image analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Jochem to incorporate the teachings of Rust and include “wherein the one or more processors is further configured to identify spatial relationships between neighboring rows, and use the spatial relationships to validate row identification”. The motivation for doing so would have been “to detect row curvature and correct measured TKE and XTE so that the corrected TKE and XTE more accurately represent where the vehicle should be steered in a row”, as suggested by Rust in para. [0012]. Therefore, it would have been obvious to one of ordinary skill at the time the invention was filed to combine Jochem and Rust to obtain the invention specified in claim 18.
Claims 6 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Jochem et al. (U.S. Publication No. 2007/0269114 A1), hereinafter Jochem in view of Rust et al. (U.S. Publication No. 2023/0229163 A1), hereinafter Rust and Shao et al. (CN 116151748 A, see attached English translation for citations), hereinafter Shao.
Regarding claim 6, Jochem and Rust teach the method of claim 5 further comprising
(Rust teaches identifying scan lines which indicate one or more crop rows, wherein the crop rows are separated from neighboring crop rows by row spacing in para. [0064], wherein the crop row spacing may be known or determined as shown in para. [0069]. Since the crop row spacing may be determined, it is apparent that the row spacing may be dynamic).
While Rust may teach determining row spacing, dynamically, Jochem and Rust fail to specifically teach dynamically determining row spacing based on the spatial relationships between neighboring rows.
However, Shao teaches dynamically determining row spacing based on the spatial relationships between neighboring rows (Shao teaches “After dividing the plants into columns, the processor may determine the pixel row spacing between each column of plants, from which the actual row spacing between each column of plants may be determined” in para. [0056]. Here, since the row spacing is determined between each column of plants, it is clear that the row spacing determination is dynamic. Additionally, the row spacing is determined based on the spatial relationship between rows as further shown in para. [0056]).
Jochem, Rust, and Shao are all considered to be analogous to the claimed invention because they are in the same field of determining positions of crop rows through image analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Jochem (as modified by Rust) to incorporate the teachings of Shao and include “dynamically determining row spacing based on the spatial relationships between neighboring rows”. The motivation for doing so would have been such that “the actual row spacing of the plants is adjusted to be within the range of the preset row spacing, so that the plants are uniformly distributed and are consistent in density, the using amount of the plants is saved, the production cost of the plants is reduced, the quality and the yield of the plant planting are improved, and the later management of the plants is facilitated”, as suggested by Shao in para. [0063]. Therefore, it would have been obvious to one of ordinary skill at the time the invention was filed to combine Jochem and Rust with Shao to obtain the invention specified in claim 6.
Regarding claim 19, Jochem teaches the system of claim 18 wherein the sys one or more processors are further configured to (Rust teaches identifying scan lines which indicate one or more crop rows, wherein the crop rows are separated from neighboring crop rows by row spacing in para. [0064], wherein the crop row spacing may be known or determined as shown in para. [0069]. Since the crop row spacing may be determined, it is apparent that the row spacing may be dynamic).
While Rust may teach determining row spacing, dynamically, Jochem and Rust fail to specifically teach wherein the sys one or more processors are further configured to dynamically determine row spacing based on the spatial relationships between neighboring rows.
However, Shao teaches dynamically determining row spacing based on the spatial relationships between neighboring rows (Shao teaches “After dividing the plants into columns, the processor may determine the pixel row spacing between each column of plants, from which the actual row spacing between each column of plants may be determined” in para. [0056]. Here, since the row spacing is determined between each column of plants, it is clear that the row spacing determination is dynamic. Additionally, the row spacing is determined based on the spatial relationship between rows as further shown in para. [0056]).
Jochem, Rust, and Shao are all considered to be analogous to the claimed invention because they are in the same field of determining positions of crop rows through image analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Jochem (as modified by Rust) to incorporate the teachings of Shao and include “wherein the sys one or more processors are further configured to dynamically determine row spacing based on the spatial relationships between neighboring rows”. The motivation for doing so would have been such that “the actual row spacing of the plants is adjusted to be within the range of the preset row spacing, so that the plants are uniformly distributed and are consistent in density, the using amount of the plants is saved, the production cost of the plants is reduced, the quality and the yield of the plant planting are improved, and the later management of the plants is facilitated”, as suggested by Shao in para. [0063]. Therefore, it would have been obvious to one of ordinary skill at the time the invention was filed to combine Jochem and Rust with Shao to obtain the invention specified in claim 19.
Claims 7, 16, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Jochem et al. (U.S. Publication No. 2007/0269114 A1), hereinafter Jochem in view of Palomares et al. (U.S. Publication No. 2019/0239502 A1), hereinafter Palomares.
Regarding claim 7, Jochem teaches the method of claim 1.
Jochem fails to teach generating a mathematical representation of the identified rows using continuous functions; and using the mathematical representation to interpolate row locations between identified points.
However, Palomares teaches generating a mathematical representation of the identified rows using continuous functions (Palomares teaches “the autonomous machine 100 can store the pixel projection corresponding to the pixel representing a target plant using any suitable mathematical description (e.g., projective coordinates, vector descriptions, linear functions, etc.)” in para. [0082]. Here, linear functions are interpreted as equivalent to the claimed continuous function. Additionally, the target plants are used to represent the rows are further shown in para. [0066]-[0067]); and
using the mathematical representation to interpolate row locations between identified points (Palomares teaches detecting a location of the target plant in para. [0069], which may be a continuous function as shown in and [0082], wherein crop row locations are interpolated between sequential target plant locations within the first set of crop rows as shown in para. [0069]).
Jochem and Palomares are both considered to be analogous to the claimed invention because they are in the same field of determining positions of crop rows through image analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Jochem to incorporate the teachings of Palomares and include “generating a mathematical representation of the identified rows using continuous functions; and using the mathematical representation to interpolate row locations between identified points”. The motivation for doing so would have been that, “by detecting the target plant in the interaction image via feature mapping with an entry image of the same plant, the autonomous machine 100 can detect the target plant more quickly (i.e. with less computational power) thereby improving detection time for a target plant in an interaction image and allowing for quicker calculation of longitudinal and lateral offsets” and to detect locations of target plants and interpolate crop rows locations by using the location of sequential target plants in a first set of crop rows in order to “implement closed-loop controls to veer left or veer right in order to maintain the first set of crop rows approximately centered within the width of the autonomous machine 100”, as suggested by Palomares in para. [0106] and [0069], respectively. Therefore, it would have been obvious to one of ordinary skill at the time the invention was filed to combine Jochem and Palomares to obtain the invention specified in claim 7.
Regarding claim 16, Jochem teaches the system of claim 15.
Jochem fails to teach further comprising a location determination receiver operatively connected to the one or more processors to provide a location.
However, Palomares teaches further comprising a location determination receiver operatively connected to the one or more processors to provide a location (Palomares teaches that “the autonomous machine 100 can also include: geospatial position sensors 108 (e.g., GPS) configured to output the autonomous machine's location in space”, wherein the onboard navigation system is configured to gather data from the GPS as shown in para. [0021] in order to generate the crop row locations. Additionally, Palomares further teaches that the navigation system may utilize a processor to carry out the method steps of the invention as shown in para. [0132]).
Jochem and Palomares are both considered to be analogous to the claimed invention because they are in the same field of determining positions of crop rows through image analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Jochem to incorporate the teachings of Palomares and include “further comprising a location determination receiver operatively connected to the one or more processors to provide a location”. The motivation for doing so would have been that, “by detecting the target plant in the interaction image via feature mapping with an entry image of the same plant, the autonomous machine 100 can detect the target plant more quickly (i.e. with less computational power) thereby improving detection time for a target plant in an interaction image and allowing for quicker calculation of longitudinal and lateral offsets”, as suggested by Palomares in para. [0106]. Therefore, it would have been obvious to one of ordinary skill at the time the invention was filed to combine Jochem and Palomares to obtain the invention specified in claim 16.
Regarding claim 20, Jochem teaches the system of claim 15.
Jochem fails to teach wherein the one or more processors is further configured to generate a mathematical representation of the identified rows using continuous functions.
However, Palomares teaches generating a mathematical representation of the identified rows using continuous functions (Palomares teaches “the autonomous machine 100 can store the pixel projection corresponding to the pixel representing a target plant using any suitable mathematical description (e.g., projective coordinates, vector descriptions, linear functions, etc.)” in para. [0082]. Here, linear functions are interpreted as equivalent to the claimed continuous function. Additionally, the target plants are used to represent the rows are further shown in para. [0066]-[0067]).
Jochem and Palomares are both considered to be analogous to the claimed invention because they are in the same field of determining positions of crop rows through image analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Jochem to incorporate the teachings of Palomares and include “wherein the one or more processors is further configured to generate a mathematical representation of the identified rows using continuous functions”. The motivation for doing so would have been that, “by detecting the target plant in the interaction image via feature mapping with an entry image of the same plant, the autonomous machine 100 can detect the target plant more quickly (i.e. with less computational power) thereby improving detection time for a target plant in an interaction image and allowing for quicker calculation of longitudinal and lateral offsets” and to detect locations of target plants and interpolate crop rows locations by using the location of sequential target plants in a first set of crop rows in order to “implement closed-loop controls to veer left or veer right in order to maintain the first set of crop rows approximately centered within the width of the autonomous machine 100”, as suggested by Palomares in para. [0106] and [0069], respectively. Therefore, it would have been obvious to one of ordinary skill at the time the invention was filed to combine Jochem and Palomares to obtain the invention specified in claim 20.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Jochem et al. (U.S. Publication No. 2007/0269114 A1), hereinafter Jochem in view of Arakawa et al. (U.S. Publication No. 2024/0428583 A1), hereinafter Arakawa.
Regarding claim 8, Jochem teaches the method of claim 1.
Jochem fails to teach wherein the imagery comprises a region of interest ahead of the agricultural vehicle, and further comprising generating steering commands based on the identified row locations within the region of interest.
However, Arakawa teaches wherein the imagery comprises a region of interest ahead of the agricultural vehicle (Arakawa teaches a method of generating a region of interest ahead of an agricultural machine, wherein “the region of interest is preferably determined as a region that includes, in its center, a region interposed between the right and left wheels of the agricultural machine” in para. [0063]), and further comprising
generating steering commands based on the identified row locations within the region of interest (Arakawa further teaches “by selecting such a region of interest and performing image processing for the selected region of interest, it becomes possible to efficiently detect a crop row or ridge existing on a target path for the agricultural machine” in para. [0063]. Arakawa further teaches that “after detecting the crop row 12, the processor 122 determines an approximation line (a straight line or a curve) of the crop row 12, and determines a target path for the agricultural machine 100 along the approximation line” wherein the target path is fed to the automatic steering device 124 of the agricultural machine 100 and the automatic steering device 124 performs steering control for the agricultural machine 100 as shown in para. [0077]. Here, it is clear that the target path is generated based on the location of the crop row, which is within the region of interest selected in para. [0063]).
Jochem and Arakawa are both considered to be analogous to the claimed invention because they are in the same field of determining positions of crop rows through image analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Jochem to incorporate the teachings of Arakawa and include “wherein the imagery comprises a region of interest ahead of the agricultural vehicle, and further comprising generating steering commands based on the identified row locations within the region of interest”. The motivation for doing so would have been, “by selecting such a region of interest and performing image processing for the selected region of interest, it becomes possible to efficiently detect a crop row or ridge existing on a target path for the agricultural”, as suggested by Arakawa in para. [0063]. Therefore, it would have been obvious to one of ordinary skill at the time the invention was filed to combine Jochem and Arakawa to obtain the invention specified in claim 8.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Jochem et al. (U.S. Publication No. 2007/0269114 A1), hereinafter Jochem in view of Kuenzi et al. (U.S. Publication No. 2021/0153500 A1), hereinafter Kuenzi.
Regarding claim 9, Jochem teaches the method of claim 1.
Jochem fails to teach identifying plants that deviate from the identified row locations; and characterizing the deviating plants as one of weeds or volunteer plants.
However, Kuenzi teaches identifying plants that deviate from the identified row locations (Kuenzi teaches a method for plant treatment involving the identification of “weed grass based on location outside of a crop row” as shown in para. [0070] and FIG. 7); and
characterizing the deviating plants as one of weeds or volunteer plants (Kuenzi teaches “a model can use a combination of factors such as color, morphology, and location relative to crop rows to increase the likelihood of correctly predicting which plants are weeds and which plants are crops” in para. [0070]. Please note that, due to the “or” language in the claim, the prior art need only teach that deviating plants are characterized as weeds OR volunteer plants (not both). As such, Kuenzi sufficiently teaches that the deviating plants may be characterized as weeds as shown above. However, it is believed that Kuenzi additionally teaches identifying volunteer plants, as Kuenzi additionally teaches identifying whether the plants outside of the crop rows are crop plants (volunteer plants) or weeds, as shown in para. [0020] and [0070]).
Jochem and Kuenzi are both considered to be analogous to the claimed invention because they are in the same field of determining positions of crop rows through image analysis. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Jochem to incorporate the teachings of Kuenzi and include “identifying plants that deviate from the identified row locations; and characterizing the deviating plants as one of weeds or volunteer plants”. The motivation for doing so would have been to “provide information indicating the locations of the identified weeds, the crop plants, or both the weeds and the crop plants in the captured in the image” such that targeted treatment may be applied in order “to enable higher accuracy of automated imaging-based treatment equipment”, as suggested by Kuenzi in para. [0026] and [0047], respectively. Therefore, it would have been obvious to one of ordinary skill at the time the invention was filed to combine Jochem and Kuenzi to obtain the invention specified in claim 9.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Baynes et al. (U.S. Publication No. 2019/0258859 A1) teaches a system for mapping locations of crop rows.
Davidovics et al. (U.S. Publication No. 2025/0285434 A1) teaches “methods for vision-based plant detection” wherein a location of a crop row is determined.
Any inquiry concerning this communication or earlier communications from the examiner
should be directed to KYLA G ALLEN whose telephone number is (703)756-5315. The examiner can
normally be reached M-F 7:30am - 4:30pm EST.
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,
John Villecco can be reached on (571) 272-7319. 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.
/Kyla Guan-Ping Tiao Allen/
Examiner, Art Unit 2661
/JOHN VILLECCO/Supervisory Patent Examiner, Art Unit 2661
