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 with respect to claim 1 have been considered and are persuasive. Thus, the previous rejection has been withdrawn. The new reference of Karins, in combination with LI, Sohrab, and Ballou, disclose the limitations of claim 1.
In addition, Applicant argues that LI does not teach images captured by a satellite, as well as compiling data comprising a group of factors, nor comparing that group of factors to determine whether to trigger an alert. Examiner would like to point out that LI was not depended on for those teachings. Ballou taught both the group of factors as well as the alert trigger (see Ballou ¶39 and FIG. 5B, wherein the error notification, or alert, can be visual, audible, tactile, or a combination thereof whenever there is a positioning error of the vehicle).
Lastly, Applicant argues that the cited references do not provide any reasonable basis for a prima facie case. Examiner respectfully disagrees. All the cited references disclose some form of vehicle detection that one of obvious skill in the art would be able to able to perform. Applicant mentions that Sohrab does not use images from surveillance cameras, but Sohrab discloses vision sensors, which can include a camera, for object detection (see Sohrab ¶56 and FIG. 11). Additionally, Ballou is used for the extraction of factors of a detected vehicle using radar images. Both Ballou and LI are utilizing images for their vehicle detections.
Therefore, this action is made NON-FINAL.
Applicant argues that the use of “a group” overcomes the Superguide Interpretation of claim 7. Regardless of the Superguide decision, Examiners are held to follow the MPEP, wherein MPEP 2111.01 requires the broadest reasonable interpretation to be that of the plain meaning in view of the Specification. In this case, the Examiner finds the Specification to support a broadest reasonable interpretation of the limitations in claim 7 to be conjunctive.
Examiner’s Comments
Claim 1 objected to because of the following informalities: claim 1 is marked as “Previously Amended,” although the word “with” was removed in the Claims dated 02/26/2026. The claim will be interpreted as Currently Amended. Appropriate correction is required.
Claim 1 recites the limitation “identifying by means of a neural network” and “classifying by means of a neural network” in page 3 of the Claims dated 02/26/2026. Examiner would like to note that the use of “means of” is problematic casual language. It would be clearer to disclose, “identifying/classifying, using a neural network…” to avoid a means + method interpretation.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 1 recites the limitation “identifying by means of a neural network” and “classifying by means of a neural network” in page 3 of the Claims dated 02/26/2026. It is unclear whether the neural networks are two separate neural networks or the same neural network. Appropriate correction is required.
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.
Claims 1-3, 5, and 7 are rejected under 35 U.S.C. 103 as being unpatentable over Hailiang LI US-20180082131-A1, hereinafter LI, in further view of James P. Karins US-20120143808-A1, hereinafter Karins, Sohrab Vossoughi US-20200134332-A1, hereinafter Sohrab, and Philip J. Ballou US-20150054674-A1, hereinafter Ballou.
As per claim 1, LI discloses A method for classifying vehicles in an image comprising: receiving in a computer a current image of a geographic region captured, the image comprising one or more objects in an area of interest (see LI ¶21, wherein a video captures vehicles, one or more objects, on the highway, i.e., geographic area of interest);preprocessing at least the area of interest, the preprocessing comprising at least scaling the area of interest to a predetermined size (see LI ¶24 and FIG. 2, wherein the image of the area is perspective and scale transformed. See also LI ¶39 and FIG. 10, wherein the objects are normalized into a similar size), detecting at least some of the objects and enclosing each of one or more of the detected objects within a bounding box associated with that detected object (see LI ¶34-36 and FIGS. 5-6, wherein the detection box for detecting vehicles is disclosed), identifying by means of a model one or more of the detected objects enclosed within their associated bounding boxes (see LI ¶39, wherein the license plate is identified by a generative model; the license plate being within the bounding box of the vehicle detection), classifying by means of a model one or more of the identified objects (see LI ¶37 and FIG. 8, wherein a regression algorithm with local features assist in vehicle classification in later stages. See also ¶41 and FIG. 11, wherein a trained SVM classifier is used to detect features about the vehicle plate)
While LI discloses preprocessing the area of interest comprising scaling and a generative model for the identification, it fails to explicitly disclose where Karins teaches:preprocessing at least the area of interest, the preprocessing comprising at least normalizing contrast (see Karins ¶68 and ¶72, wherein image data, as well as the area around of the detected objection, i.e., area of interest, is collected. See also Karins ¶133, wherein the contrast of the image data is normalized during preprocessing);identifying by means of a neural network one or more of the detected objects (see Karins ¶173, wherein a Bayesian network, which is a part of the artificial intelligence module 208, is used to identify a target object. Additionally, Karins ¶103 states “while example embodiments of the artificial intelligence module 208 are described below that use a Bayesian network artificial intelligence model, those of skill in the art, in light of this disclosure, will recognize other artificial intelligence models that the artificial intelligence module 208 may use to estimate probabilities as described herein,” wherein earlier in ¶103, an example of another artificial intelligence model is an artificial neural network).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify LI’s method by using Karins’s teaching by including a normalized contrast and a neural network in order to acquire cleaner images for faster object detection using a neural network.
LI, in combination with Karins, however, fails to explicitly disclose where Sohrab teaches:classifying by means of a neural network one or more of the identified objects in accordance with a library of objects (see Sohrab ¶61, wherein the LIME Agent uses a pretrained detection library of object for classification. See also ¶75, wherein vehicles are verified and classified)
for the identified and classified objects, compiling data for the area of interest comprising at least some of a group of factors comprising the count of each class of object, the orientation of one or more objects within a class of object, the position of each object within a class, the size of each object within a class (see Sohrab ¶61, wherein the vehicle type, size, location, license plate, etc., are deciphered from the LIME Agent. See also ¶62 and FIG. 10, wherein the detection area, i.e., area of interest, is disclosed)
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify LI’s, in combination with Karins, method by using Sohrab’s teaching by including a library of objects and compiling data for the area of interest to the identified and classified objects in order to acquire, store, and refer back to more accurate data of vehicles.
While LI, in combination with Karins and Sohrab, teaches a group of factors, Ballou also teaches a group of factors (see Ballou ¶31-32 and ¶37-39, wherein the ship positions, vessels size, alignment, etc., i.e., group of factors). Additionally, Ballou teaches where LI, in combination with Sohrab, fails to explicitly disclose:receiving in a computer a current image of a geographic region captured by a satellite (see Ballou ¶18, ¶25, and FIG. 2, wherein GPS data, i.e., satellite image, and surrounding environmental area is acquired),comparing at least some of the group of factors for objects in the area of interest with those factors compiled for a baseline image for the area of interest and generating an alert if one or more of the comparisons exceeds a predetermined threshold (see Ballou ¶31-32 and ¶37-39, wherein the ship positions, vessels size, alignment, etc., i.e., group of factors, are used for comparison of the different positions systems, wherein the GPS data would be the baseline image. If the threshold offset exceeds a value, a notification is provided to the crew. See also Ballou ¶17, wherein any vehicle, including land vehicles, can be used).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify LI’s in combination with Karins and Sohrab, by using Ballou’s teaching by including satellite images and a comparison alert to LI’s vehicle detection in order to acquire more precise vehicle positioning.
As per claim 2, LI, in combination with Karins, Sohrab, and Ballou, discloses the method of claim 1 further comprising displaying to a user results of the comparing step that exceed the threshold and including an indicia representative of the significance of the change between the current image and the baseline image (see Ballou ¶39 and FIG. 5B, wherein the notification can be visual, audible, tactile, or a combination thereof. The GPS image would be the baseline image and the current image would be the radar image or any other positional image).
As per claim 3, LI, in combination with Karins, Sohrab, and Ballou, discloses the method of claim 1 wherein the objects are vehicles (see LI ¶20-21, wherein the object detection is about vehicles).
As per claim 5, LI, in combination with Karins, Sohrab, and Ballou, disclose the method of claim 1 wherein the images are satellite images (see Ballou ¶18, ¶25, and FIG. 2, wherein GPS data, i.e., satellite image, and surrounding environmental area is acquired).
As per claim 7, LI, in combination with Karins, Sohrab, and Ballou, discloses the method of claim 1 further including determining a confidence value for at least one of a group comprising the detecting step, the identifying step, and the classifying step (see LI ¶90, ¶101, and ¶115, wherein confidence scores for the detecting, identifying, and classifying steps are disclosed).
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over LI, in combination with Karins, Sohrab, and Ballou, in further view of Wen-bin ZOU CN-110119148-A, hereinafter ZOU.
As per claim 4, LI, in combination with Karins, Sohrab, and Ballou, fails to explicitly disclose where ZOU teaches:The method of claim 1 wherein the detecting step comprises a feature extractor having different levels of granularity (see ZOU pages 4-5/28, wherein the multi-scale feature extraction network contains different scales, such that n x n is used for the feature map, i.e., different levels of granularity).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify LI’s, in combination with Karins, Sohrab, and Ballou, method by using ZOU's teaching by including a feature extractor with different levels of granularity to LI’s, in combination with Ballou, detecting step in order to overcome the need for fixed-size input images.
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over LI, in combination with Karins, Sohrab, and Ballou, in further view of Madhuri Mahendra NAGARE US-20200065946-A1, hereinafter NAGARE.
As per claim 6, LI, in combination with Karins, Sohrab, and Ballou, fails to explicitly disclose where NAGARE teaches:The method of claim 2 further comprising the steps of detecting and compensating for cloud cover (see NAGARE ¶83-86, wherein cloud cover correction is disclosed).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify LI’s, in combination with Karins, Sohrab, and Ballou, method by using NAGARE’s teaching by including cloud cover compensation to the object detection in order to obtain a clearer satellite image.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Bradley Obas Felix whose telephone number is (703)756-1314. The examiner can normally be reached M-F 8-5 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, Vincent Rudolph can be reached at 5712728243. 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.
/BRADLEY O FELIX/Examiner, Art Unit 2671
/VINCENT RUDOLPH/Supervisory Patent Examiner, Art Unit 2671
Prosecution Insights