DETAILED ACTION
This is a non-final Office Action in response to communications received on 09/03/2024. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority or Provisional
Priority to 01/25/2024 is recognized.
Drawings
The drawings filed on 09/03/2024 are acknowledged.
Information Disclosure Statement
No information disclosure statement (IDS) has been filed for this application. The Examination is conducted without any Prior Art search help from the Applicant. Applicant is reminded of the duty to disclose from section 2100 of the MPEP: 37 C.F.R. 1.56; Duty to disclose information material to patentability. A patent by its very nature is affected with a public interest. The public interest is best served, and the most effective patent examination occurs when, at the time an application is being examined, the Office is aware of and evaluates the teachings of all information material to patentability. Each individual associated with the filing and prosecution of a patent application has a duty of candor and good faith in dealing with the Office, which includes a duty to disclose to the Office all information known to that individual to be material to patentability as defined in this section.
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, 3-4, 6, and 8-9 are rejected under 35 U.S.C. 103 over He (CN 115239632) in view of Rodrigues (US 11,467,128).
Regarding claim 1, He discloses the limitations of claim 1 as follows:
A method for fault-in-rail analysis based on multimodal data to determine rail line faults, the method comprising: acquiring optical images of a rail surface to produce optical rail data; acquiring sonic based rail data; correlating the optical rail data and the sonic based rail data; and using the optical rail data and the sonic based rail data to determine the rail line faults. He, Paras. [0003]-[0007], [0013], [0026], [0053]-[0057], teaches a method for detecting rail surface damage by fusing inspection images and ultrasonic images. Specifically teaches acquiring rail inspection images (camera images), and ultrasonic B-display/B-mode images corresponding to the same rail location using a dual track flaw detection trolley. And further teaches preprocessing the ultrasonic B-mode images using a noise reduction algorithm, preprocessing the rail inspection images, extracting features from the camera images and ultrasonic B-scan images using separate feature extraction networks, and fusing the extracted features using a multi-scale feature fusion network to detect rail surface damage. And teaches deploying the trained fusion model within an ultrasonic rail flaw detector for intelligent rail inspection.
He does not explicitly disclose:
Computing image data of the rail from the acquired sonic based rail data.
However, Rodrigues, Abstract, Col. 2, ll. 9-26, Col. 3, ll. 5-48, Col. 5, ll. 8-32, Col. 6, ll. 60-68, Col. 7, ll. 1-53, Col. 8, ll. 16-44, teaches processing ultrasonic scan data to generate image data suitable for automated defect detection. Teaches obtaining ultrasound scan data derived from an ultrasound scan of an object, processing the ultrasound scan data by filtering echo amplitude values, an image generator configured to generate at least one image from the filtered ultrasound scan data, converting filtered raw scan data into image representations, and converting filtered raw scan sub-matrices into an image for subsequent automated defect detection. And further teaches applying machine learning to generate ultrasonic images to identify defects.
It would have been obvious to one of ordinary skill in the art before the effective filling date of the invention to modify the multimodal rail inspection method of He to compute ultrasonic scan data using the processing techniques as taught by Rodrigues, to provide ultrasonic image data suitable for the feature extraction and multimodal fusion network, in order to enhance rail defect detection.
As per claim 6, claim 6 encompass same or similar scope as claim 1. Therefore, claim 6 is rejected based on the reasons set forth above in rejecting claim 1.
Regarding claim 3, He and Rodrigues disclose the limitations of claim1. He and Rodrigues discloses:
The method of claim 1, wherein the sonic based rail data is preprocessed. He, Paras. [0003]-[0007], [0013], [0026], [0053]-[0057], teaches preprocessing ultrasonic image data before performing multimodal feature extraction and defect detection. He specifically teaches filtering noise from ultrasonic B-mode/B-scan images and enhancing the ultrasonic images prior to constructing the multimodal images and inputting the ultrasonic images into the CUFuse feature extraction network (S4 and related description). Therefore, teaches preprocessing ultrasonic image data before defect analysis.
Rodrigues, Abstract, Col. 2, ll. 9-26, Col. 3, ll. 5-48, Col. 5, ll. 8-32, Col. 6, ll. 60-68, Col. 7, ll. 1-53, Col. 8, ll. 16-44, teaches preprocessing ultrasound scan data prior to image generation. And teaches processing ultrasound scan data by filtering echo amplitude values, applying thresholding, performing a patch filtering, and converting the filtered ultrasound scan data into image representations for automated defect detection.
The same motivation to combine utilized in claim 1 is equally applicable in the instant claim.
As per claim 8, claim 8 encompass same or similar scope as claim 3. Therefore, claim 8 is rejected based on the reasons set forth above in rejecting claim 3.
Regarding claim 4, He and Rodrigues disclose the limitations of claim1. He and Rodrigues discloses:
The method of claim 1, wherein the detected rail line faults are classified. He, Paras. [0003]-[0007], [0013], [0026], [0039]-[0041], [0053]-[0057], [0083]-[0086], teaches classifying detected rail surface defects. Specifically teaches constructing a rail surface damage detection model (CUFuse) based on multimodal data fusion and deep learning that extracts features from camera images and ultrasonic B-scan images, fuses the extracted features, and outputs rail surface damage classifications (S5 and the accompanying description discussing the CFUuse model and its evaluation).
Rodrigues, Abstract, Col. 2, ll. 9-26, Col. 3, ll. 5-48, Col. 5, ll. 8-32, Col. 6, ll. 60-68, Col. 7, ll. 1-53, Col. 8, ll. 16-44, teaches performing automated defect recognition on generated ultrasonic images using a machine learning model to determine whether a defect is present in the inspected object. The machine learning model identifies defect based on the generated ultrasonic image representation.
The same motivation to combine utilized in claim 1 is equally applicable in the instant claim.
As per claim 9, claim 9 encompass same or similar scope as claim 4. Therefore, claim 9 is rejected based on the reasons set forth above in rejecting claim 4.
Claims 2 and 7 are rejected under 35 U.S.C. 103 over He (CN 115239632) in view of Rodrigues (US 11,467,128), and further in view of Main (US 2010/0100275).
Regarding claim 2, He and Rodrigues disclose the limitations of claim 1. Main discloses:
The method of claim 1, wherein the rail line faults are determined by an expert system. He and Rodrigues teach the limitations of claim 1 as discussed above.
Main, Paras. [0054]-[0059], teaches determining faults using an expert system. Specifically teaches an advanced analysis component that evaluates detected conditions using rule-based analysis, Bayesian or neural network processing. And further teaches that a decision making component implements a complex automated expert system or a rule-based system to determine actions based on the detected conditions. The image processing utilizes expert system recognition to identify features and defects.
It would have been obvious to one of ordinary skill in the art before the effective filling date of the invention to incorporate the expert system decision techniques of Main into the multimodal rail defect detection as taught by He, in order to improve determination and evaluation of detected rail faults.
As per claim 7, claim 7 encompass same or similar scope as claim 2. Therefore, claim 7 is rejected based on the reasons set forth above in rejecting claim 2.
Claims 5 and 10 are rejected under 35 U.S.C. 103 over He (CN 115239632) in view of Rodrigues (US 11,467,128), and further in view of Wu (CN 116092027).
Regarding claim 5, He and Rodrigues disclose the limitations of claim1. Wu discloses:
The method of claim 1, wherein the rail line faults are detected by use of an R-DETR or YOLO inspection algorithm. He and Rodrigues teach the limitations of claim 1 as discussed above.
Wu, Paras. [0011]-[0018], [0033]-[0039], [0046]-[0057], “The lightweight target detection algorithm YOLOv3-tiny is used as the basic model of the first level detection network. The SPP module is added to the backbone network of YOLOv3-tiny to enable the backbone network to extract more feature information from different dimensions (the improved YOLOv3-tiny network structure is shown in Figure 3) ”, teaches detecting rail defects using YOLO inspection algorithm.
It would have been obvious to one of ordinary skill in the art before the effective filling date of the invention to incorporate the known YOLOv3-tiny rail defect detection algorithm of Wu into multimodal rail inspection system as taught by He, because both references are directed to automated rail defect detection using deep learning techniques, in order to improve detection accuracy and efficiency.
As per claim 10, claim 10 encompass same or similar scope as claim 5. Therefore, claim 10 is rejected based on the reasons set forth above in rejecting claim 5.
References Considered But Not Relied Upon
Song (CN 111024728) describes a railway detection method and system based on computer vision and ultrasonic flaw detection by collecting a railway image in front of a train through a camera, collecting an ultrasonic flaw detection signal of a track in front of the train through an ultrasonic flaw detection device, and collecting environment data through environment sensing equipment.
Witte (US 2016/0305915) describes a system for inspecting railroad rail using phased array ultrasonic technology includes both high-speed and high-resolution inspection modes that obviate the need for an operator to dismount the truck to perform detail inspection.
Conclusion
Accordingly, claims 1-10 are pending.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PEGAH BARZEGAR whose telephone number is (703)756-4755.
The examiner can normally be reached M-F, 9:00 - 5:00. Examiner interviews are available via telephone 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, Samuel Morano can be reached on 571-272-6684. 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/patentcenter 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.
/P.B./ Examiner, Art Unit 3615
/S. Joseph Morano/ Supervisory Patent Examiner, Art Unit 3615
Prosecution Insights