DETAILED ACTION
This Office action for U.S. Patent Application No. 18/556,666 is responsive to communications filed 31 March 2026, in reply to the Non-Final Rejection of 16 January 2026.
Claims 1 and 3–16 are pending.
In the previous Office action, claims 1–15 were rejected under 35 U.S.C. § 102(a)(1) as anticipated by U.S. Patent Application Publication No. 2020/0294310 A1 (“Lee”). Claim 16 was rejected under 35 U.S.C. § 103 as obvious over Lee in view of U.S. Patent Application Publication No. 2020/0257317 A1 (“Musk”).
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 with respect to claim 1 have been fully considered but they are not persuasive. Applicant has amended claim 1 to recite that the claimed segmentations are “within a semantic segmentation framework”, and that the first segment has a type that “is a type of parking spot”. Applicant alleges that the Lee object detection does not qualify as this semantic segmentation, and that the Musk “high-level goal” is “not linked to any image processing output”. Applicant further alleges that any modification of or combination with Lee to include the invention as amended would be based on improper hindsight.
With respect to “semantic segmentation”, it is unclear how this is different from object detection. From the specification, the only apparent special feature of the semantic segmentation is that detected objects are given labels in human-recognizable language. Specification at ¶¶ 0016, 0050 (class information of semantic segments include “built-up area, signs, plants, vehicles, two-wheeled vehicles”); 0033 (classes include “curb, street, person, car, road marking” and “parking space”). The specific algorithms presented in the specification for determining free parking spaces including determining parking space boundary lines as a subclass of road markings or as a specific separate class (¶¶ 0033–34), and merging clusters of point clouds to form polygons (¶ 0035) are not claimed. Lee classifies visual data (¶ 0158) and Musk detects and receives named objects based on sensor data, including curbs, vehicles, pedestrians, and cones (¶ 0059). Also, in Musk, a charging location may be found and updated based on “recently captured and analyzed sensor data” (¶ 0026). Considering this, the amendments fail to present a patentable distinction from the combination of Lee and Musk.
With respect to the hindsight argument, it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 U.S.P.Q. 209 (C.C.P.A. 1971).
Claim Rejections - 35 U.S.C. § 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 and 3–16 are rejected under 35 U.S.C. § 103 as being unpatentable over U.S. Patent Application Publication No. 2020/0294310 A1 (“Lee”)1 in view of U.S. Patent Application Publication No. 2020/0257317 A1 (“Musk”).
Lee, directed to object detection for a vehicular application, teaches with respect to claim 1:
a method for training a machine learning system (¶ 0069, a method for training a machine learning module)
within a semantic segmentation framework (¶ 0158, classifying visual data)
for segmenting and identifying individual free marked target areas (¶ 0069, Figs. 5B–6; parking spaces)
from an image of a vehicle (¶¶ 0039–40, 0042; camera of vehicle),
the free marked target areas being suitable areas to park the vehicle (Title, “Object Detection Using Skewed Polygons Suitable For Parking Space Detection”),
wherein training data, which comprise training input images an assigned training target segmentations, are provided (¶ 0063, training samples and associated anchor boxes),
parameters of the machine learning system are adjusted by the training data such that the machine learning system, on inputting the training input images, produces output data which correspond to the training target segmentations (¶¶ 0196–197, updating training data), and
wherein the training target segmentations used in the training comprise:
a first segment which corresponds to the individual free marked target areas and defines or includes a position and size of the first segment (¶ 0063, anchor boxes; ¶¶ 0069–82, parking spaces), and
at least one second segment of at least one additional class of a captured environment of the vehicle (¶¶ 0050–52, feature classification),
wherein the at least one additional class relates to an animate or inanimate object, condition, or characterization associated with or present in the environment of the vehicle (¶¶ 0155–56, neural network also used for reading traffic signs.
The claimed invention differs from Lee in that the claimed invention specifically indicates a first segment type as “a type of parking spot”. Lee recognizes parking spaces, but it is unclear whether Lee does more than that, for example, only recognizing free parking spaces and not even considering occupied spaces as parking spaces at all. However, Musk, directed to remote vehicle summoning, teaches with respect to claim 16:
wherein the training target segmentations additionally indicate a type of the first segment [that] is a type of parking spot (¶¶ 0025–26, recognizing electronic charging station based on “recently captured and analyzed sensor data”).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to modify Lee to look for and plan specifically for electric charging stations, as taught by Musk, in order to effect an electric vehicle being charged while parked. Musk ¶¶ 0025–26.
Regarding claim 3, Lee teaches the method according to claim 1, wherein the at least one second segment comprises objects and at least one item of class information of the objects (¶ 0101, various recognized objects such as street sign and traffic light).
Regarding claim 4, Lee teaches the method according to claim 1, wherein the camera system comprises:
a camera having a fisheye lens (e.g. ¶ 0110, fisheye cameras),
and wherein the training input images are images having fisheye imaging without rectification (¶ 0150, “stereo rectification” is only rectification mentioned in Lee; ¶¶ 0091–93, distinction between stereo cameras 1168 and wide-view cameras 1170 including fisheye cameras) from the fisheye lens camera (¶¶ 0196–98, updating training data based on images received from the vehicles without limitation to a specific set or type of camera), and
the training target segmentations correspond to the fisheye imaging (id.).
Regarding claim 5, Lee teaches a method for segmenting and identifying individual free marked target areas from images of a camera system of a vehicle, the method comprising:
capturing at least one image of an environment of the vehicle by the camera system (¶ 0176, capturing image data around the vehicle);
segmenting the individual free marked target areas from the at least one image by a machine learning system trained according to claim 1 (¶¶ 0046–49, grids and anchor boxes),
outputting, to a controller, a first segment which corresponds to the individual free marked target area and second segments of at least one additional class of the captured environment of the vehicle (¶ 0178, camera as part of Advanced Driver Assistance System (ADAS)), the controller at least partly controlling movement of the vehicle (id.).
Regarding claim 6, Lee teaches the method according to claim 5, wherein the camera system comprises at least one camera having a fisheye lens (¶ 0110, fisheye cameras).
Regarding claim 7, Lee teaches the method according to claim 6, wherein the segmenting is performed on the at least one image from the fisheye lens camera (¶ 0110, fisheye cameras provide “information used to create and update the occupancy grid”).
Regarding claim 8, Lee teaches the method according to claim 6, wherein the camera system comprises multiple cameras which are arranged and configured such that a 360° capturing of the environment of the vehicle is effected (¶ 0110, fisheye cameras are positioned for surround view).
Regarding claim 9, Lee teaches the method according to claim 5, wherein the controller provides support for moving the vehicle to the free target area by an optical display on the basis of the output segments (¶¶ 0181–86; display for driver feedback).
Regarding claim 10, Lee teaches the method according to claim 5, wherein the control unit provides support for moving the vehicle to the free target area by audible or haptic measures or measures partially controlling the movement of the vehicle on the basis of the output segments (¶¶ 0181–186, speaker and vibrating component for driver feedback).
Regarding claim 11, Lee teaches the method according to claim 5, wherein the control unit moves the movement device to the free target area fully automatically on the basis of the output segments (¶¶ 0095, 0097; full automation vehicle).
Regarding claim 12, Lee teaches the method according to claim 5, wherein the controller transmits an item of information for locating the free marked target areas to an infrastructure apparatus external to the vehicle on the basis of the output segments which correspond to individual free marked target areas (¶¶ 0161–62, communication with outside network).
Regarding claim 13, Lee teaches the method according to claim 5, wherein the free marked target area is a free parking space or an area for inductive charging of an electric vehicle (title, “Object Detection Using Skewed Polygons Suitable for Parking Space Detection”)2.
Regarding claim 14, Lee teaches a device for segmenting and identifying individual free marked target areas (Fig. 5B, highlighted parking spaces) from image of a camera system of a movement device (Fig. 11B, car cameras), the device comprising:
- at least one input which is configured to receive at least one image (Fig. 11C, cache 1112 or data store 1116);
- a data processing unit comprising at least one microcontroller or processor (id., CPU 1106 or processor 1110) which is configured to execute the method according to claim 5 (claim 5 rejection supra) and
to output to a controller (id., controller 1136)
a first segment which corresponds to the individual free marked target area (¶ 0063, anchor boxes) and
at least one second segment of at least one additional class of a captured environment of the movement device (¶¶ 0050–52, feature classification).
Regarding claim 15, Lee teaches a vehicle comprising:
a camera system (passim, vehicle camera),
a control unit (¶ 0178, camera as part of Advanced Driver Assistance System (ADAS)),
[and the claim 14 device] (claim 14 rejection supra).
Regarding claim 16, Lee in view of Musk teaches the method according to claim 1,
wherein the type of parking spot is a free parking space, an area for inductive charging of an electric vehicle, a handicapped parking space, an electric vehicle parking space, or a parking space for families with children (Musk ¶¶ 0025, path planning toward electric charging station).
Conclusion
The following prior art was found using an Artificial Intelligence assisted search using an internal AI tool that uses the classification of the application under the Cooperative Patent Classification (CPC) system, as well as from the specification, including the claims and abstract, of the application as contextual information. The documents are ranked from most to least relevant. Where possible, English-language equivalents are given, and redundant results within the same patent families are eliminated. See “New Artificial Intelligence Functionality in PE2E Search”, 1504 OG 359 (15 November 2022), “Automated Search Pilot Program”, 90 F.R. 48,161 (8 October 2025).
US 2017/0232890 A1
US 2019/0202446 A1
US 2020/0090519 A1
US 2024/0054793 A1 (Abstract, “an available parking space is searched for on the basis of the 3D semantic segmentation image”; further amendments or arguments should also distinguish from this reference).
Applicant's amendment necessitated the new grounds of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See M.P.E.P. § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 C.F.R. § 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 C.F.R. § 1.17(a)) pursuant to 37 C.F.R. § 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 David N Werner whose telephone number is (571)272-9662. The examiner can normally be reached M--F 7:30--4:00 Central.
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, Dave Czekaj can be reached at 571.272.7327. 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.
/David N Werner/Primary Examiner, Art Unit 2487
1 This reference was cited as an ‘X’ reference in the International Search Report for PCT/DE2022/200073 and was listed in the 21 October 2023 Information Disclosure Statement.
2 Under the Broadest Reasonable Interpretation standard, only one of the free parking space or inductive charging area is required to anticipate the claimed set of two options presented in disjunctive format.
Prosecution Insights