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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 5/12/26 has been entered.
Response to Arguments
Applicant’s arguments have been considered but are not persuasive. Please see the additional reference Kossyk (2020/0151500) which teaches detecting and analyzing changes in real world objects using feature vectors and calculating the change the time series feature vectors (see pars. 19-22, 29-36).
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(s) 1 and 9 are rejected under 35 U.S.C. 103 as being unpatentable over Huang (“An automatic change detection method for monitoring newly constructed building areas using time-series multi-view high-resolution optical satellite images”) in view of Boriah (US 2014/0212055) and further in view of Kossyk (US 2020/0151500).
Regarding claim 1, Huang teaches a method comprising detecting a building within a set of measurements using an object detector (see Huang, abstract and section 3.2, detecting newly constructed building areas and distinguishing building areas from non-building areas using planar-vertical features);
determining a timeseries of building representations for the detected building (see Huang, abstract, section 3, and sections 3.3-3.4, using time-series multi-view high-resolution optical satellite images and time-series planar-vertical building features);
determining building parameters of each building representation based on the building detection (see Huang, section 3.2 and Table 2, determining planar and vertical building features including structure, corner, texture, shadow, height, and angle features);
determining a building segment for each of the building representations, based on the building parameters, using a segmentation model (see Huang, section 3.3, object-based segmentation and object-based temporal correction); and
generating a timeseries of changes for the building based on relationships between pairs of consecutive building representations (see Huang, sections 3.3-3.4 and Figs. 4-5, calculating dynamics of consecutive feature values, determining change timing, and determining change magnitude).
Huang teaches that Fig. 4 illustrates typical time series of planar-vertical features for newly constructed building areas and non-newly constructed building areas. Huang further teaches calculating the dynamics of three consecutive feature values within a moving temporal window, identifying the change start point and change end point, determining the point with the maximum increment of the feature value as the change point, and calculating change magnitude. See Huang, section 3.4 and Fig. 5.
Boriah teaches determining a relationship between consecutive representations within a timeseries based on state transitions.
Boriah teaches using a transition matrix representing probabilities of transitioning between a first land cover state at time t-1 and a second land cover state at time t. See Boriah, pars. [0042]-[0043]. Boriah further teaches a state change type indicating a first land cover state at a first time and a second land cover state at a later time, including examples such as Vegetation-Urban, Urban-Water, and other state change types. See Boriah, par. [0071]. Boriah further teaches determining the probability of state sequences and computing probabilities of paths that pass through a state change type at selected capture times. See Boriah, pars. [0072]-[0074].
It would have been obvious prior to the effective filing date of the invention to one of ordinary skill in the art to include in Huang the ability to determine the relationship between consecutive timepoints as taught by Boriah. The reason is to allow the system to model changes over time.
Huang and Boriah do not expressly teach that each building segment is defined by a feature vector and that the relationship is based on a distance between the feature vectors defining the building segments.
Kossyk teaches this feature.
Kossyk teaches detecting and analyzing changes in real world objects using feature vectors and calculating the change the time series feature vectors (see pars. 19-22, 29-36).
It would have been obvious prior to the effective filing date of the invention to one of ordinary skill in the art to include in Boriah and Huang improved neural-network-based change detection from remotely sensed time-series images of real-world objects, including roofs and buildings, using CNN-generated time-series feature vectors as taught by Kossyk. The reason is to improve the representation and comparison of building features over time and would have allowed the system to determine a change between consecutive building representations.
Regarding claim 9, see the rejection of claim 1.
Claim(s) 2-8, 10-16 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Huang in view of Boriah in view of Kossyk in further view of Kottenstette (20170076438).
Regarding claim 2, Huang uses high definition images in section 3.1, pansharpening.
Kottenstette teaches segmenting the segments using the segmentation model (see pars. 95-98, 161-162).
It would have been obvious prior to the effective filing date of the invention to one of ordinary skill in the art to include in Kossyk, Huang and Boriah the ability to segment specific objects as taught by Kottenstette. The reason is to allow specific ROI extraction as taught by Kottenstette.
Regarding claim 3, wherein the building parameters comprise a geographic extent, wherein the higher resolution image depicts the geographic extent (see pars. 112 and 119 of Kottenstette and section 3.1 of Huang, polygon foot print of the terrain.
Regarding claim 4, section 3.1 of Huang has high resolution RGB image and prs. 34 of Kottenstette.
Regarding claim 5, see section 3.2-3.3 of Huang, planar vertical bulding features.
Regarding claim 6-8, see pars. 28 and 113 of Kottenstette.
Regarding claims 10-16, see the rejection of claims 2-8.
Regarding claim 19, see section 3.2 of Huang and pars. 30-32 of Kottenstette.
Claim(s) 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Huang in view of Boriah in view of Kossyk and in further view of Szegedy (20150170002).
Regarding claim 17, Szegedy teaches wherein the object detector is trained on a set of bounding boxes drawn around building segments identified within training images, wherein the building segments are determined using a segmentation model (see pars. 35-48, using bounding boxes to train. The rejection of claim 1 already teaches building segmetns).
It would have been obvious prior to the effective fling date of the invention to one of ordinary skill in the art to include in Kossyk, Huang and Boriah the ability train based on ROIs in bounding boxes as taught by Szegedy. The reason is to specify a region for training.
Regarding claim 18, see pars. 66-78 of Szegedy, picking only the best bounding boxes.
Claim(s) 20 is rejected under 35 U.S.C. 103 as being unpatentable over Huang in view of Boriah in view of Kossyk and in further view of Kim (20070115284).
Regarding claim 20, Kim teaches wherein the building component comprises a shadow, wherein the height parameter is determined based on a length of the detected shadow, the geolocation of the measurement, and a sampling time for the measurement (see pars. 21-25 and pars. 40-41).
It would have been obvious prior to the effective fling date of the invention to one of ordinary skill in the art to include in Huang the ability to measure building height as taught by Kim. The reason is to measure building height.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HADI AKHAVANNIK whose telephone number is (571)272-8622. The examiner can normally be reached 9 AM - 5 PM Monday to Friday.
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, Henok Shiferaw can be reached at (571) 272-4637. 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.
/HADI AKHAVANNIK/ Primary Examiner, Art Unit 2676
Prosecution Insights