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 Arguments
Applicant's arguments filed February 19, 2026 with respect to claims 1-20 have been considered but are moot in view of new grounds of rejection.
Regarding claim 1, applicant's following arguments filed February 19, 2026 have been fully considered but are not persuasive.
(1) applicant states that “Hu is focused solely on detecting static defects like potholes on road surfaces, not on identifying fatigue points in infrastructure elements (e.g., bridges) based on movement. Hu does not compare multiple depth representations to identify points of movement or track fatigue based on such identification.”. Examiner disagrees with this statement. Hu identifies fatigue points within the infrastructure element (A SELF-SUPERVISED LEARNING TECHNIQUE FOR ROAD DEFECTS DETECTION BASED ON MONOCULAR THREE-DIMENSIONAL RECONSTRUCTION. Abstract) according to at least movement shown by the depth maps in the infrastructure element (
PNG
media_image1.png
332
658
media_image1.png
Greyscale
. Page 4 left column 1st paragraph). Hu identifies fatigue points in infrastructure elements (i.e., pothole in the road) by comparing depth maps to identify points of movement on the road surface.
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.
Claim 1-3, 6-7, 9-11, 14-16 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Hu (A SELF-SUPERVISED LEARNING TECHNIQUE FOR ROAD DEFECTS DETECTION BASED ON MONOCULAR THREE-DIMENSIONAL RECONSTRUCTION, Proceedings of the ASME 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference IDETC/CIE2019), hereinafter Hu, in view of Zhang (Chinese Patent Pub. No.: CN117351367A), hereinafter Zhang, further in view of Shao (Monocular vision based 3D vibration displacement measurement for civil engineering structures, Engineering Structures 293 (2023) 116661), hereinafter Shao.
Regarding claim 1, Hu teaches an infrastructure system, comprising: one or more processors (It is common knowledge that a processor is a necessary component in conventional computer systems such as a convolutional neural network in Hu, Abstract.); a memory (It is common knowledge that a memory is a necessary component in conventional computer systems of a CNN in Hu.) communicably coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to: acquire sensor data (Only images from one camera are needed as the inputs to the model without human labeling. Abstract) about an infrastructure element (A SELF-SUPERVISED LEARNING TECHNIQUE FOR ROAD DEFECTS DETECTION BASED ON MONOCULAR THREE-DIMENSIONAL RECONSTRUCTION. Abstract); generate depth maps from the sensor data using a depth model (
PNG
media_image2.png
332
658
media_image2.png
Greyscale
. Page 4 left column 1st paragraph) that performs monocular depth estimation (A SELF-SUPERVISED LEARNING TECHNIQUE FOR ROAD DEFECTS DETECTION BASED ON MONOCULAR THREE-DIMENSIONAL RECONSTRUCTION. Title); analyze the depth maps to determine a condition of the infrastructure element (
PNG
media_image1.png
332
658
media_image1.png
Greyscale
. Page 4 left column 1st paragraph), wherein the instructions to analyze the depth maps include instructions to identify fatigue points within the infrastructure element (A SELF-SUPERVISED LEARNING TECHNIQUE FOR ROAD DEFECTS DETECTION BASED ON MONOCULAR THREE-DIMENSIONAL RECONSTRUCTION. Abstract) according to at least movement shown by the depth maps in the infrastructure element (
PNG
media_image1.png
332
658
media_image1.png
Greyscale
. Page 4 left column 1st paragraph).
Hu does not teach the following limitations as further recited, but Zhang further teaches responsive to determining that the condition satisfies a health threshold (The Technical Condition Index (BCI) of bridge and tunnel structures is calculated according to the following formula: BCI = min(100 - GD<sub>iBCI</sub>), where GD<sub>iBCI</sub> is the total deduction for damage to the i-th type of structure, with a maximum score of 100, and i is the type of structure. [0032]. Step S6.1: Generate a report document from the obtained data, the calculated pavement performance index (PQI), and the bridge and tunnel structure technical condition index (BCI), and store it. [0040]), modify a maintenance recommendation for the infrastructure element (For example, based on the technical condition of the bridge mentioned above, the model generated the following maintenance recommendations. [0168]. The bridge's technical condition has been assessed as Level III, requiring repair and maintenance. The following measures are recommended. [0169]. The cracks in the bridge deck pavement are cleaned, filled, and sealed to prevent moisture and debris from seeping in, restoring the smoothness and waterproofness of the bridge deck. [0170]); and provide the maintenance recommendation (This maintenance analysis model is a model that uses a large language model and low-rank adaptation method to analyze the technical condition of highway pavement and bridges and culverts, and generate corresponding maintenance suggestions, which can provide effective support for highway maintenance and management. [0162]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Hu to incorporate the teachings of Zhang to modify a maintenance recommendation for the infrastructure element and provide the maintenance recommendation, responsive to determining that the condition satisfies a health threshold, in order to improve maintenance efficiency and accuracy.
The combination of Hu and Zhang does not teach the following limitations as further recited, but Shao further teaches to determine an extent of deflection at the fatigue points on the infrastructure element (Monocular vision based 3D vibration displacement measurement for civil engineering structures. Title) from the depth maps (The depth map has the same dimensions as the image frames, with the value representing the distance (depth) from the 3D object to the camera plane at each pixel location. Page 4 right column last paragraph).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Hu and Zhang to incorporate the teachings of Shao to determine an extent of deflection at the fatigue points on the infrastructure element from the depth maps by using monocular vision in order to provide a more cost-effective method to monitor the health of infrastructure that is convenient to set up and use in practice.
Claims 2-3 and 6-7, unamended and are rejected based on the revised combination of Hu, in view of Zhang, further in view of Shao as applied to claim 1 above. The grounds of rejection established in the last Office Action is fully incorporated herein.
Method claims 14, 16 and 19-20 are drawn to the method of using the corresponding apparatus claimed in claims 1-3 and 6-7. Therefore method claims 14-16 and 19-20 correspond to apparatus claims 1-3 and 6-7 and are rejected for the same reasons of obviousness as used above.
Claims 9-11 are drawn to a non-transitory computer-readable storage medium having executable instructions stored for executing the method of using the corresponding apparatus as claimed in claims 1-3. Therefore, claims 9-11 correspond to apparatus claims 1-3, and are rejected for the same reasons of obviousness as used above.
Regarding claim 15, Hu in the combination teaches the method of claim 14, wherein acquiring the sensor data includes acquiring monocular images (Only images from one camera are needed as the inputs to the model without human labeling. Abstract) from a vehicle (
PNG
media_image3.png
614
536
media_image3.png
Greyscale
) of the infrastructure element (A SELF-SUPERVISED LEARNING TECHNIQUE FOR ROAD DEFECTS DETECTION BASED ON MONOCULAR THREE-DIMENSIONAL RECONSTRUCTION. Abstract) as the vehicle traverses an area of the infrastructure element (Figure 3 shows the system developed to capture road surface images. A Field-programmable gate array (FPGA) is used as the central controller for the system which synchronizes two cameras and GPS together with the vehicle speed coming from the On-board diagnostics-II (OBD-II). Page 6 left column 2nd paragraph).
Shao in the combination further teaches wherein generating the depth maps using the depth model includes folding encoded features into separate channels to iteratively reduce spatial dimensions (The encoder progressively converts the image to a lower-dimensional latent representation, while the decoder upsamples it back to the input size. Page 5 left column 2nd paragraph.
PNG
media_image4.png
666
1320
media_image4.png
Greyscale
) while packing additional channels with information about embedded states of features (The image features can be effectively extracted by deep convolutional neural networks (CNNs), which ultimately learns the underlying mapping between the input and output. Page 5 left column 3rd paragraph).
Claims 8, 4-5, 12-13 and 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Hu (A SELF-SUPERVISED LEARNING TECHNIQUE FOR ROAD DEFECTS DETECTION BASED ON MONOCULAR THREE-DIMENSIONAL RECONSTRUCTION, Proceedings of the ASME 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference IDETC/CIE2019), hereinafter Hu, in view of Zhang (Chinese Patent Pub. No.: CN117351367A), hereinafter Zhang, further in view of Shao (Monocular vision based 3D vibration displacement measurement for civil engineering structures, Engineering Structures 293 (2023) 116661), hereinafter Shao, further in view of Wook (Korean Patent Pub. No.: KR 10-2397419 B1), hereinafter Wook.
Claim 8, unamended and is rejected based on the revised combination of Hu, in view of Zhang, further in view of Shao, as applied to claim 1 above, and further in view of Wook. The ground of rejection established in the last Office Action is fully incorporated herein.
Regarding claim 4, Hu in the combination teaches the infrastructure system of claim 1, wherein the instructions to analyze the depth maps include instructions to identify the fatigue points within the infrastructure element by the depth maps in the infrastructure element (
PNG
media_image1.png
332
658
media_image1.png
Greyscale
. Page 4 left column 1st paragraph).
Wook in the combination further teaches wherein the instructions to analyze the depth maps include instructions to track the condition of the infrastructure element by identifying the fatigue points within the infrastructure element according to at least movement shown by the sensor data in the infrastructure element (It relates to a system and method for detecting a critical point in a concrete structure based on a crack sensor that can inform a time (i.e., track) when repair or reinforcement is required by evaluating a trend to determine a critical point in time. Page 2 4th paragraph) and determine whether the fatigue points exhibit a degradation of the condition (The control module 11 may determine whether the crack width value measured by the crack measurement module 10 deviates from a structural crack reference value. Page 8 5th paragraph).
Regarding claim 5, Wook in the combination teaches the infrastructure system of claim 4, (The control module 11 may determine whether the crack width value (i.e., at least one crack is present) measured by the crack measurement module 10 deviates from a structural crack reference value. Page 8 5th paragraph) and characteristics of the cracks (Accordingly, the countermeasure presentation unit 24 can present the recommended construction method information according to the crack state using the derived optimal recommended construction method information, thereby making it easier to maintain the structure. Page 13 4th paragraph).
Method claims 17-18 are drawn to the method of using the corresponding apparatus claimed in claims 4-5. Therefore method claims 17-18 correspond to apparatus claims 4-5 and are rejected for the same reasons of obviousness as used above.
Claims 12-13 are drawn to a non-transitory computer-readable storage medium having executable instructions stored for executing the method of using the corresponding apparatus as claimed in claims 4-5. Therefore, claims 12-13 correspond to apparatus claims 4-5, and are rejected for the same reasons of obviousness as used above.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LEI ZHAO whose telephone number is (703)756-1922. The examiner can normally be reached Monday - Friday 8:00 am - 5:00 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, VU LE can be reached at (571)272-7332. 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.
/LEI ZHAO/Examiner, Art Unit 2668
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights