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 .
Prior arts cited in this office action:
Hofman et al. (US 20110280448 A1, hereinafter “Hofman”)
Laroca et al. ( Automatic Counting and Identification of Train Wagons Based on Computer Vision and Deep Learning , Oct. 2020, hereinafter “Laroca”)
Monnard (US 20220334141 A1, hereinafter “Monnard”)
Response to Arguments
Applicant Arguments/Remarks filed on 03/30/2026 have been fully considered but they are not persuasive.
Applicant Arguments/Remarks: Applicant argues that as described in paragraphs 0078-0079 of Hofman, for example, different cameras "take several shots from different angles and positions and under different illumination levels," and thereafter, the results are analyzed to select the "most accurate result."
In other words, in Hofman, multiple cameras are used to take images of overlapping areas
of a vehicle/container. In Laroca ("2. The Dataset"), it is stated that "images of the same train" were collected "with two different cameras, one on each side of the track."
Examiner’ Response: Examiner disagrees with applicant assertion above the combination of the cited prior arts does not teach or suggest applicant invention as argued above. Hofman teaches Image capturing unit 110--including several cameras 112 the number of which varies according to the specific application (i.e. vehicle access-control system and other systems as will be described in FIGS. 6-14) The position and operation of the cameras are also adjustable depending on the specific application. The image capturing unit provides the system with fast and accurate images to process [0052]. Cameras 55, mounted on horizontal pipe 65, are connected to illumination units 57 and 59 and to reflectors 67, 69 and 71. Camera 55 takes images of the side marking of container, while cameras 51 and camera 53 take images of chassis and truck identification number [0182], fig. 14b. as we can see Hofman clearly teaches a plurality of cameras maybe place on one side of the road or tracks to take a plurality of images of different regions at different angle and/or position.
The same argument above is applicable to claim 13 as well since it contains similar limitation.
Therefore, examiner maintains that claims 1-23 are not allowable over the cited prior arts.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-11, 13-22 are rejected under 35 U.S.C. 103 as being unpatentable over Hofman et al. (US 20110280448 A1, hereinafter “Hofman”) in view of Laroca et al. ( Automatic Counting and Identification of Train Wagons Based on Computer Vision and Deep Learning , Oct. 2020, hereinafter “Laroca”).
Regarding claims 1 and 13:
Hofman teaches a method of detecting a railcar identifier of a railcar (Hofman [0130], fig. 10a, where Hofman teaches with reference to FIG. 10a, an exemplary embodiment of a container code recognition method, system for identifying containers on rail cars TOCRS 900 (train optical container recognition system) is shown and included controller(s)), the method comprising:
receiving a first railcar data set from a first image capture device (Hofman [0130]-[0133], where Hofman teaches a sequence of images in different illumination levels are captured according to sensors (as was described in FIGS. 1-2)), the first railcar data set including a first image of a first portion of a first railcar, the first image including a representation of a first railcar identifier (Hofman [0135]-[0136], figs. 10a and 10b, where Hofman teaches Cameras 911, 913, 917 and 919 are located at 4 corners. Side cameras 911 and 919 take images of the side marking of container, while back cameras 913 and 917 take images of the back/front of container. Camera 911 is connected to illumination units 921, and 923 and camera 919 is connected to illumination unit 927 and 929. Four sensors 931 are located at the right side of the trail and four sensors 933 are located at the left side of the trail),
receiving a second railcar data set from a second image capture device, the second railcar data set including a second image of a second portion of the railcar, the second image including a representation of a second railcar identifier (Hofman [0135]-[0136], figs. 8, 10a and 10b, where Hofman teaches Cameras 911, 913, 917 and 919 are located at 4 corners. Side cameras 911 and 919 take images of the side marking of container, while back cameras 913 and 917 take images of the back/front of container. Camera 911 is connected to illumination units 921, and 923 and camera 919 is connected to illumination unit 927 and 929. Four sensors 931 are located at the right side of the trail and four sensors 933 are located at the left side of the trail),
wherein the first and second image capture devices are configured to capture the first and second images, respectively, in different regions on a same side of the first railcar (Hofman [0052], [0154]-[0156], [0182]-[0183], figs. 1, 11b, and 14, where Hofman teaches an array of 6 cameras 975-980 and illumination units mounted on land side and sea side of the crane. In other words, the more cameras can be installed on each side of the road. Each camera unit can be a plurality of cameras (112));
using the representation of the first railcar identifier, identifying one or more characters in the first railcar identifier (Hofman [0140]-[0150], figs. 10a and 10b, where Hofman teaches Recognition application starts recognition process 234 which includes the following steps; i) a sequence of images in different illumination levels are captured according to the sensors and predefined sequence (the illumination level is controlled by 10 cart. ii) Images are sent to recognition application for container marking identification. iii) Identification results are sent to recognition application database. 4) a single message is generated for each passing container. The message includes recognition results, which contain container ID number, and additional information (such as track/lane number date and time);
using the representation of the second railcar identifier, identifying one or more characters in the second railcar identifier (Hofman [0140]-[0150], figs. 10a and 10b, where Hofman teaches Recognition application starts recognition process 234 which includes the following steps; i) a sequence of images in different illumination levels are captured according to the sensors and predefined sequence (the illumination level is controlled by 10 card. ii) Images are sent to recognition application for container marking identification. iii) Identification results are sent to recognition application database. 4) a single message is generated for each passing container. The message includes recognition results, which contain container ID number, and additional information (such as track/lane number date and time); and
determining a railcar identifier recognition result for the first railcar based on a correspondence between the identified characters in the first and second railcar identifiers Hofman [0054], [0085]-0088], where Hofman teaches the integration process includes the following steps: i. Comparison of all target code results generated from a certain image with those generating from other images of the same target code 10. For example, if in one image the first character was identified as the number 8 while in others it was identified as the letter B the final result will show B as the first character. ii. Each character in the target code receives a mark according to the relative accuracy of identification. As In the example given above if the number 8 has a final mark of 40% while the letter B has a final mark of 90% the letter B will be shown in the final code identification results (FTC 90). iii. The integration process also includes comparison of data generated with preset data from the program database file. If, for example, the first character in the target code was identified as the number 1, and according to the data in the program file the first character is always the letter I, the letter I will be chosen and will be shown in the final code identification results (FTC 90)).
Hofman does not explicitly disclose if the first railcar identifier is the same as the second railcar identifier and whether they are located in different location or not.
However, Laroca teaches Automatic Counting and Identification of Train Wagons Based on Computer Vision and Deep Learning wherein, when possible, we collected images of the same train with two different cameras, one on each side of the track, as Liya & Jilin [21]. In this way, if the code region is damaged on only one side of the wagon, we can still correctly identify the wagon since we have information redundancy (Laroca 2. The Dataset).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the application to obtain railcar identifier in more than one location of the railcar in this way, if the code region is damaged on only one side of the wagon, we can still correctly identify the wagon since we have information redundancy (Laroca 2. The Dataset).
Regarding claim 2:
Hofman in view of Laroca teaches wherein the first railcar identifier and the second railcar identifier are located in different locations of the same side of the first railcar (Laroca 2. The Dataset).
Regarding claims 3 and 14:
Hofman in view of Laroca teaches wherein the first image capture device compiles the first railcar data set from a first set of images captured by a first camera, and wherein the first camera is configured to capture the first portion of the first railcar when the first railcar is at a first railcar location (Hofman [0029]-[0030], fig. 8; Laroca 2. The Dataset).
Regarding claims 4 and 15:
Hofman in view of Laroca teaches wherein the second image capture device compiles the second railcar data set from a second set of images captured by a second camera, and wherein the second camera is configured to capture the second portion of the first railcar when the first railcar is at a second railcar location (Hofman [0029]-[0030]; Laroca 2. The Dataset).
Regarding claims 5 and 16:
Hofman in view of Laroca teaches wherein respective fields of view of the first camera and the second camera are non-overlapping (Hofman [0029]-[0030], fig. 8; Laroca 2. The Dataset).
Regarding claims 6 and 17:
Hofman in view of Laroca teaches wherein the first camera is located in a first location along a railroad, and wherein the second camera is located in a second location along the railroad (Hofman [0029]-[0030], fig. 8; Laroca 2. The Dataset).
Regarding claims 7 and 18:
Hofman in view of Laroca teaches wherein the first location along the railroad is upstrearn the second location along the railroad (Hofman [0029]-[0030], fig. 8; Laroca 2. The Dataset).
Regarding claims 8 and 19:
Hofman in view of Laroca teaches wherein the first camera and the second camera are configured to capture images of different portions of the first railcar (Hofman [0029]-[0030], [0052], [0154]-[0156], [0182]-[0183], figs. 1, 11b, and 14, Laroca 2. The Dataset).
Regarding claims 9 and 20:
Hofman in view of Laroca teaches wherein the first camera and the second camera are mounted to be adjacent to each other (Hofman [0052], [0154]-[0156], [0182]-[0183], figs. 1, 11b, and 14).
Regarding claims 10 and 21:
Hofman in view of Laroca teaches wherein the first railcar data set comprises a first confidence level, and wherein the second railcar data set comprises a second confidence level, wherein the confidence levels indicate a perceived accuracy of railcar identifiers found in the first data set and the second data set, respectively (Hofman [0052], [0078]-[0079], [0083]-[0088], claim 54, fig. 1; Laroca 2. The Dataset).
Regarding claims 11 and 22:
Hofman in view of Laroca teaches comprising:
comparing the first confidence level and the second confidence level to identify a highest confidence level, and determining the railcar identifier recognition result based on the railcar data set corresponding to the highest confidence level (Hofman [0054], [0078]-[0079], [0083]-[0088]).
Claims 12 and 23 are rejected under 35 U.S.C. 103 as being unpatentable over Hofman et al. (US 20110280448 A1, hereinafter “Hofman”) in view of Laroca et al. ( Automatic Counting and Identification of Train Wagons Based on Computer Vision and Deep Learning , Oct. 2020, hereinafter “Laroca”) and in view of Monnard (US 20220334141 A1, hereinafter “Monnard”).
Regarding claims 12 and 23:
Hofman in view of Laroca fail to explicitly teach comprising:
storing the railcar identifier and the first railcar data set;
comparing a third rail data set, received from the first image capture device, with the first railcar data set, the third rail data set including a third railcar identifier, determining a degradation of the railcar identifier on condition that the third railcar identifier has a lower confidence level than the first railcar identifier, and transmitting information about degradation of the railcar identifier.
However, Monnard teaches a method for classifying the identification tag 9 on the sample tube 5 is described. In step 20 the identification tag 9 is read by the classifying reader device 7, thereby, generating measured tag data indicative of tag characteristics for identification tag 9. In step 21, by analyzing the measured tag data, the tag characteristics which may also be referred to as tag features are determined. For example, the tag characteristics may be indicative of a level of deterioration for the identification tag 9.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the application to analyze a picture of the tag and based on the condition of the tag determine its level of degradation (weather damage over time ) especially in comparison to other tags on the train or the railroad which could be an indication of the age of the railcar and to determine whether it need to be replaced or not for increase safety.
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 WEDNEL CADEAU whose telephone number is (571)270-7843. The examiner can normally be reached Mon-Fri 9:00-5:00.
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, Chieh Fan can be reached at 571-272-3042. 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.
/WEDNEL CADEAU/Primary Examiner, Art Unit 2632 April 23, 2026
Prosecution Insights