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 .
Election/Restrictions
Applicant’s election without traverse of claims 1-8 and 15-20 in the reply filed on 05/26/2026 is acknowledged.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The information disclosure statement filed 10/08/2024 fails to comply with 37 CFR 1.98(a)(2), which requires a legible copy of each cited foreign patent document; each non-patent literature publication or that portion which caused it to be listed; and all other information or that portion which caused it to be listed. It has been placed in the application file, but the information referred to therein has not been considered.
Claim Objections
Claim 2 is objected to because of the following informalities:
Claim 2 recites the limitation “comprises convolutional encoder-decoder neural network”. This limitation should be amended to clarify whether the model comprises a singular, or plural, convolutional encoder-decoder neural networks. For example, the limitation should be amended to “comprises a convolutional encoder-decoder neural network.”
Appropriate correction is required.
Claim Rejections - 35 USC § 103
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.
Claims 1-2, 6-8, 15, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over US 20200088538 A1, with an earliest priority date of November 22nd, 2017, hereinafter “Sekiyama”, in view of US 20250052591 A1, with an earliest priority date of December 23rd, 2021, hereinafter “Tran”.
Regarding claim 1, Sekiyama teaches A method for identifying changes in road geometry. See at least [0074] and figure 7.
the method comprising: obtaining an image of an initial road geometry for a geographical area. See at least [0078]-[0079] and figure 7, step S13, wherein map information is retrieved and converted into a raster map image form.
obtaining an image of movement data for the geographical area. See at least [0077], [0080], and figure 7, steps S12 and S14, wherein movement data is obtained from a plurality of probe vehicles. The movement data is rendered into a movement track image.
forming a composite image from at least the image of the initial road geometry and the image of the movement data, and generating an image of road geometry corrections. See at least [0085] and figure 7, step S16, wherein the movement track image and the map image are passed to difference extractor 25. See at least [0060] and figures 5A-D, wherein difference extractor 25 acquires the map image (figure 5B) and movement track image (figure 5A) and creates a composite image (figure 5C). The composite image is then used to create a difference data image (figure 5D), which represents road geometry corrections.
wherein the image of the road geometry corrections identifies one or more differences between the actual road geometry of the geographical area and the initial road geometry. See at least [0060] and figure 5D, wherein the difference data image identifies differences between the actual road geometry and the initial road geometry.
Sekiyama remains silent on applying a trained road geometry correction model to the composite image. Sekiyama instead teaches applying the trained road geometry correction model to the image of road geometry corrections (see at least [0061]).
Tran teaches applying a trained road geometry correction model to the composite image. See at least [0076] and figure 2, step 203, wherein a trained deep neural network model is applied to ground truth image data. See at least [0053], wherein ground truth image data is an image where, pixel by pixel, obtained information is composited with digital geographical map data.
One having ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to modify Sekiyama with Tran’s trained road geometry model. It would have been obvious to modify because doing so enables improvements in accuracy and effectiveness when updating map information from satellite information, as recognized by Tran (see at least [0001]-[0005]).
Regarding claim 2, Sekiyama and Tran in combination teach all of the limitations of claim 1 as discussed above, and Sekiyama remains silent on wherein the trained road geometry correction model comprises convolutional encoder-decoder neural network.
Tran teaches wherein the trained road geometry correction model comprises convolutional encoder-decoder neural network. See at least [0056], wherein the trained deep neural network model includes an encoder and a decoder with convolutional layers.
One having ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to modify Sekiyama with Tran’s trained road geometry model comprising a convolutional encoder-decoder neural network. It would have been obvious to modify because doing so enables improvements in accuracy and effectiveness when updating map information from satellite information, as recognized by Tran (see at least [0001]-[0005]).
Regarding claim 6, Sekiyama and Tran in combination teach all of the limitations of claim 1 as discussed above, and Sekiyama remains silent on wherein the image of the initial road geometry is an image mask.
Tran teaches wherein the image of the initial road geometry is an image mask. See at least [0097]-[0100] and figure 4, wherein, when creating the ground truth image data (composite image), remotely captured image data is composited with digital geographical map data (road geometry) by applying road segmentation masks in the image data.
One having ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to modify Sekiyama with Tran’s image mask data representing initial road geometry. It would have been obvious to modify because doing so enables improvements in accuracy and effectiveness when updating map information from satellite information, as recognized by Tran (see at least [0001]-[0005]).
Regarding claim 7, Sekiyama and Tran in combination teach all of the limitations of claim 1 as discussed above, and Sekiyama additionally teaches wherein the one or more differences comprises any of: a road segment present in the actual road geometry and not present in the initial road geometry; a road segment present in the initial road geometry and not present in the actual road geometry; and a road segment displaced in the actual road geometry relative to the initial road geometry. See at least [0060], [0100], figures 5A-5D, and figures 10A-E, wherein a road segment (D2) displaced in the road geometry relative to the initial road geometry, and is corrected by deleting a road segment D4 present in the initial geometry and not in the actual geometry, and adding a road segment D2 present in the actual geometry and not the initial geometry.
Regarding claim 8, Sekiyama and Tran in combination teach all of the limitations of claim 1 as discussed above, and Sekiyama additionally teaches wherein the method further comprises updating the initial road geometry according to the image of the road geometry corrections to form an updated road geometry for the geographical area. See at least [0087]-[0088] and figure 7, step S19, wherein the map information is updated based on the extracted difference data image.
Regarding claim 15, Sekiyama teaches An apparatus that identifies changes in road geometry, comprising: a processor. See at least [0008], [0041] and figure 3.
configured to: obtain an image of an initial road geometry for a geographical area. See at least [0078]-[0079] and figure 7, step S13, wherein map information is retrieved and converted into a raster map image form.
obtain an image of movement data for the geographical area. See at least [0077], [0080], and figure 7, steps S12 and S14, wherein movement data is obtained from a plurality of probe vehicles. The movement data is rendered into a movement track image.
form a composite image from at least the image of the initial road geometry and the image of the movement data, and generate an image of road geometry corrections. See at least [0085] and figure 7, step S16, wherein the movement track image and the map image are passed to difference extractor 25. See at least [0060] and figures 5A-D, wherein difference extractor 25 acquires the map image (figure 5B) and movement track image (figure 5A) and creates a composite image (figure 5C). The composite image is then used to create a difference data image (figure 5D), which represents road geometry corrections.
wherein the image of the road geometry corrections identifies one or more differences between the actual road geometry of the geographical area and the initial road geometry. See at least [0060] and figure 5D, wherein the difference data image identifies differences between the actual road geometry and the initial road geometry.
Sekiyama remains silent on applying a trained road geometry correction model to the composite image. Sekiyama instead teaches applying the trained road geometry correction model to the image of road geometry corrections (see at least [0061]).
Tran teaches applying a trained road geometry correction model to the composite image. See at least [0076] and figure 2, step 203, wherein a trained deep neural network model is applied to ground truth image data. See at least [0053], wherein ground truth image data is an image where, pixel by pixel, obtained information is composited with digital geographical map data.
One having ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to modify Sekiyama with Tran’s trained road geometry model. It would have been obvious to modify because doing so enables improvements in accuracy and effectiveness when updating map information from satellite information, as recognized by Tran (see at least [0001]-[0005]).
Regarding claim 18, Sekiyama teaches A non-transitory computer-readable medium storing instructions which, when executed by a processor, cause the processor to perform a method for identifying changes in road geometry. See at least [0008], [0041] and figure 3.
the method comprising: obtaining an image of an initial road geometry for a geographical area. See at least [0078]-[0079] and figure 7, step S13, wherein map information is retrieved and converted into a raster map image form.
obtaining an image of movement data for the geographical area. See at least [0077], [0080], and figure 7, steps S12 and S14, wherein movement data is obtained from a plurality of probe vehicles. The movement data is rendered into a movement track image.
forming a composite image from at least the image of the initial road geometry and the image of the movement data, and generating an image of road geometry corrections. See at least [0085] and figure 7, step S16, wherein the movement track image and the map image are passed to difference extractor 25. See at least [0060] and figures 5A-D, wherein difference extractor 25 acquires the map image (figure 5B) and movement track image (figure 5A) and creates a composite image (figure 5C). The composite image is then used to create a difference data image (figure 5D), which represents road geometry corrections.
wherein the image of the road geometry corrections identifies one or more differences between the actual road geometry of the geographical area and the initial road geometry. See at least [0060] and figure 5D, wherein the difference data image identifies differences between the actual road geometry and the initial road geometry.
Sekiyama remains silent on applying a trained road geometry correction model to the composite image. Sekiyama instead teaches applying the trained road geometry correction model to the image of road geometry corrections (see at least [0061]).
Tran teaches applying a trained road geometry correction model to the composite image. See at least [0076] and figure 2, step 203, wherein a trained deep neural network model is applied to ground truth image data. See at least [0053], wherein ground truth image data is an image where, pixel by pixel, obtained information is composited with digital geographical map data.
One having ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to modify Sekiyama with Tran’s trained road geometry model. It would have been obvious to modify because doing so enables improvements in accuracy and effectiveness when updating map information from satellite information, as recognized by Tran (see at least [0001]-[0005]).
Claims 3-5, 16-17, and 19-20 under 35 U.S.C. 103 as being unpatentable over Sekiyama and Tran as applied to claims above, and further in view of US 20230358563 A1, filed May 5th, 2022, hereinafter “Tang”.
Regarding claim 3, Sekiyama and Tran in combination teach all of the limitations of claim 1 as discussed above, and Sekiyama remains silent on wherein the composite image comprises at least one channel corresponding to the initial road geometry and at least one other channel corresponding to the movement data.
Tang teaches wherein the composite image comprises at least one channel corresponding to the initial road geometry and at least one other channel corresponding to the movement data. See at least [0070]-[0071], wherein images comprise different channels representing probe trajectory information and representing map objects within the image.
One having ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to further modify Sekiyama with Tang’s technique of an image comprising multiple channels, with channels representing trajectory data and map object data. It would have been obvious to modify, because doing so enables map systems to generate and correct lane geometries, increasing the effectiveness of route guidance and vehicle autonomy, as recognized by Tang (see at least [0002]-[0004]).
Regarding claim 4, Sekiyama and Tran in combination teach all of the limitations of claim 1 as discussed above, and Sekiyama additionally teaches wherein the composite image is formed from the image of the initial road geometry and the image of the movement data. See at least [0060] and figures 5A-D, wherein the composite image 5C is formed from the initial road geometry image 5B and the movement image 5A.
Sekiyama remains silent on a satellite image of the geographical area.
Tang teaches a satellite image of the geographical area. See at least [0057] and figure 3, wherein the observation generators generate images from satellite image data and map representation image data of a specific area.
One having ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to further modify Sekiyama with Tang’s usage of satellite image data of the geographical area. It would have been obvious to modify, because doing so enables map systems to generate and correct lane geometries, increasing the effectiveness of route guidance and vehicle autonomy, as recognized by Tang (see at least [0002]-[0004]).
Regarding claim 5, Sekiyama and Tran in combination teach all of the limitations of claim 1 as discussed above, and Sekiyama remains silent on wherein the method comprises forming a further composite image from the image of the initial road geometry and a satellite image of the area, wherein the trained road geometry correction model is applied to the composite image and the further composite image to generate the image of road geometry corrections, wherein the trained road geometry correction model comprises: a first encoder arranged to receive as input a composite image comprising at least one channel corresponding to the initial road geometry and at least one other channel corresponding to the movement data; and a second encoder arranged to receive as input a further composite image comprising at least one channel corresponding to the initial road geometry and at least one other channel corresponding to a satellite image.
Tran teaches wherein the method comprises forming a further composite image from the image of the initial road geometry and a satellite image of the area. See at least [0057], wherein the observation generators generate images from satellite image data and map representation image data of a specific area.
wherein the trained road geometry correction model is applied to the composite image and the further composite image to generate the image of road geometry corrections. See at least [0061]-[0062] and figure 4, wherein the embeddings 404, 414, and 424 are fed to encoders at step 430 to generate map information. See at least [0057]-[0060], wherein the embeddings 404, 414, and 424 are merged pairs of image data representing probe data and satellite data against stored map representation data.
wherein the trained road geometry correction model comprises: a first encoder arranged to receive as input a composite image comprising at least one channel corresponding to the initial road geometry and at least one other channel corresponding to the movement data. See at least [0060] and figure 4, wherein the model comprises a first encoder 400, arranged to receive as input observations 402 including probe data. Additionally, see at least [0070]-[0071], wherein images comprise different channels representing probe trajectory information and representing map objects within the image.
and a second encoder arranged to receive as input a further composite image comprising at least one channel corresponding to the initial road geometry and at least one other channel corresponding to a satellite image. See at least [0060] and figure 4, wherein the model comprises a second encoder 410, arranged to receive as input observations 412 including satellite. Additionally, see at least [0070]-[0071], wherein images comprise different channels representing satellite image information and representing map objects within the image.
One having ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to further modify Sekiyama with Tang’s further composite image from satellite imagery and map images, and trained road geometry model with two encoders arranged to receive composite images with channels representing probe data and satellite image data. It would have been obvious to modify, because doing so enables map systems to generate and correct lane geometries, increasing the effectiveness of route guidance and vehicle autonomy, as recognized by Tang (see at least [0002]-[0004]).
Regarding claim 16, Sekiyama and Tran in combination teach all of the limitations of claim 15 as discussed above, and Sekiyama remains silent on wherein the composite image comprises at least one channel corresponding to the initial road geometry and at least one other channel corresponding to the movement data.
Tang teaches wherein the composite image comprises at least one channel corresponding to the initial road geometry and at least one other channel corresponding to the movement data. See at least [0070]-[0071], wherein images comprise different channels representing probe trajectory information and representing map objects within the image.
One having ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to further modify Sekiyama with Tang’s technique of an image comprising multiple channels, with channels representing trajectory data and map object data. It would have been obvious to modify, because doing so enables map systems to generate and correct lane geometries, increasing the effectiveness of route guidance and vehicle autonomy, as recognized by Tang (see at least [0002]-[0004]).
Regarding claim 17, Sekiyama and Tran in combination teach all of the limitations of claim 15 as discussed above, and Sekiyama remains silent on wherein the processor is configured to: form a further composite image from the image of the initial road geometry and a satellite image of the area, wherein the trained road geometry correction model is applied to the composite image and the further composite image to generate the image of road geometry corrections, wherein the trained road geometry correction model comprises: a first encoder arranged to receive as input a composite image comprising at least one channel corresponding to the initial road geometry and at least one other channel corresponding to the movement data; and a second encoder arranged to receive as input a further composite image comprising at least one channel corresponding to the initial road geometry and at least one other channel corresponding to a satellite image.
Tran teaches wherein the processor is configured to: form a further composite image from the image of the initial road geometry and a satellite image of the area. See at least [0057], wherein the observation generators generate images from satellite image data and map representation image data of a specific area.
wherein the trained road geometry correction model is applied to the composite image and the further composite image to generate the image of road geometry corrections. See at least [0061]-[0062] and figure 4, wherein the embeddings 404, 414, and 424 are fed to encoders at step 430 to generate map information. See at least [0057]-[0060], wherein the embeddings 404, 414, and 424 are merged pairs of image data representing probe data and satellite data against stored map representation data.
wherein the trained road geometry correction model comprises: a first encoder arranged to receive as input a composite image comprising at least one channel corresponding to the initial road geometry and at least one other channel corresponding to the movement data. See at least [0060] and figure 4, wherein the model comprises a first encoder 400, arranged to receive as input observations 402 including probe data. Additionally, see at least [0070]-[0071], wherein images comprise different channels representing probe trajectory information and representing map objects within the image.
and a second encoder arranged to receive as input a further composite image comprising at least one channel corresponding to the initial road geometry and at least one other channel corresponding to a satellite image. See at least [0060] and figure 4, wherein the model comprises a second encoder 410, arranged to receive as input observations 412 including satellite. Additionally, see at least [0070]-[0071], wherein images comprise different channels representing satellite image information and representing map objects within the image.
One having ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to further modify Sekiyama with Tang’s further composite image from satellite imagery and map images, and trained road geometry model with two encoders arranged to receive composite images with channels representing probe data and satellite image data. It would have been obvious to modify, because doing so enables map systems to generate and correct lane geometries, increasing the effectiveness of route guidance and vehicle autonomy, as recognized by Tang (see at least [0002]-[0004]).
Regarding claim 19, Sekiyama and Tran in combination teach all of the limitations of claim 18 as discussed above, and Sekiyama remains silent on wherein the composite image comprises at least one channel corresponding to the initial road geometry and at least one other channel corresponding to the movement data.
Tang teaches wherein the composite image comprises at least one channel corresponding to the initial road geometry and at least one other channel corresponding to the movement data. See at least [0070]-[0071], wherein images comprise different channels representing probe trajectory information and representing map objects within the image.
One having ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to further modify Sekiyama with Tang’s technique of an image comprising multiple channels, with channels representing trajectory data and map object data. It would have been obvious to modify, because doing so enables map systems to generate and correct lane geometries, increasing the effectiveness of route guidance and vehicle autonomy, as recognized by Tang (see at least [0002]-[0004]).
Regarding claim 20, Sekiyama and Tran in combination teach all of the limitations of claim 18 as discussed above, and Sekiyama remains silent on wherein the method comprises for each composite image, forming a respective further composite image from the image of the respective modified road geometry of the respective geographical area and a satellite image of the respective geographical area, wherein the road geometry correction model comprises: a first encoder arranged to receive as input a composite image comprising at least one channel corresponding to the initial road geometry and at least one other channel corresponding to the movement data; and a second encoder arranged to receive as input a further composite image comprising at least one channel corresponding to the initial road geometry and at least one other channel corresponding to a satellite image.
Tran teaches wherein the method comprises for each composite image, forming a respective further composite image from the image of the respective modified road geometry of the respective geographical area and a satellite image of the respective geographical area. See at least [0057]-[0058], wherein the observation generators generate images from satellite image data and map representation image data of a specific area. The map representation image data is updated as the road geometries are updated,
wherein the road geometry correction model comprises: a first encoder arranged to receive as input a composite image comprising at least one channel corresponding to the initial road geometry and at least one other channel corresponding to the movement data. See at least [0060] and figure 4, wherein the model comprises a first encoder 400, arranged to receive as input observations 402 including probe data. Additionally, see at least [0070]-[0071], wherein images comprise different channels representing probe trajectory information and representing map objects within the image.
and a second encoder arranged to receive as input a further composite image comprising at least one channel corresponding to the initial road geometry and at least one other channel corresponding to a satellite image. See at least [0060] and figure 4, wherein the model comprises a second encoder 410, arranged to receive as input observations 412 including satellite. Additionally, see at least [0070]-[0071], wherein images comprise different channels representing satellite image information and representing map objects within the image.
One having ordinary skill in the art, before the effective filing date of the claimed invention, would have found it obvious to further modify Sekiyama with Tang’s further composite image from satellite imagery and map images, and trained road geometry model with two encoders arranged to receive composite images with channels representing probe data and satellite image data. It would have been obvious to modify, because doing so enables map systems to generate and correct lane geometries, increasing the effectiveness of route guidance and vehicle autonomy, as recognized by Tang (see at least [0002]-[0004]).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Selena M. Jin whose telephone number is (408)918-7588. The examiner can normally be reached Monday - Thursday and alternate Fridays, 7:30-4:30 PT.
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, Faris Almatrahi can be reached at (313) 446-4821. 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.
/S.M.J./Examiner, Art Unit 3667
/FARIS S ALMATRAHI/Supervisory Patent Examiner, Art Unit 3667
Prosecution Insights