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 .
Response to Arguments
Applicant’s arguments, see remarks pages 5-12, filed 12/09/2025, with respect to the rejection(s) of claim(s) 1, 7 and 8 under 35 U.S.C. 103 as being unpatentable over U.S. Patent 9672434, Wu et al. (hereinafter Wu) in view of U.S. Patent Application 2024/0185445 Duan et al. (hereinafter Duan). have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of 35 U.S.C. 103 as being unpatentable over U.S. Patent Application 2024/0233381 Jung et al. (hereinafter Jung) in view of KR-10-2173121 B1 Woo [English Translation/Google translation provided] further in view of U.S. Patent Application 2014/0003710, Seow et al (hereinafter Seow).
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 12/09/2025 was filed after the mailing date of the claims on 9/17/2024. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
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.
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.
1. Claim(s) 1 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application 2024/0233381 Jung et al. (hereinafter Jung) in view of KR-10-2173121 B1 Woo [English Translation/Google translation provided] further in view of U.S. Patent Application 2014/0003710, Seow et al (hereinafter Seow).
2. Regrading Claim 1, Jung discloses A video-based parking space occupancy detection artificial intelligence learning method performed by a computer (Fig. 1; [0003], “a parking recognition system capable of efficiently recognizing vehicles parked on corresponding parking surfaces.” [0077], “deep learning network according to an embodiment of the present invention may be learned in advance through vehicle image data photographed by a plurality of cameras…implemented in various forms of artificial neural networks”), comprising:
detecting objects from a video taken of a plurality of parking spaces in a parking lot (Figs. 3-6; [0060], “parking recognition server 300 may acquire a plurality of images for at least one parking surface and vehicle photographed by at least one camera”); and
learning artificial intelligence for detecting whether the object occupies the parking space based on the learning data ([0077], “deep learning network according to an embodiment of the present invention may be learned in advance through vehicle image data photographed by a plurality of cameras…implemented in various forms of artificial neural networks”).
Jung discloses generating learning data that includes cumulative data accumulated over a preset time period for use in the occupancy determination ([0074]; see also Remarks, arguments for claim 1, acknowledging that “such learning data may include cumulative data for an expected range during a preset time period”; [0077])
However, Jung does not explicitly disclose video; and generating learning data based on cumulative feature information that accumulates, over a certain period of time, feature information corresponding to the object detected from each image constituting the video.
Woo teaches video (Page 7 para 2, “video information provided by the corresponding parking lot management server 200”);
generating learning data based on cumulative feature information that accumulates, over a certain period of time, feature information corresponding to the object detected from each image constituting the video (page 8 para 6, “That is, the server 100 accesses (or works in conjunction with) a plurality of content management servers (not shown) that provide various types of content, and collects vehicle images through a crawling method” and the seven paragraphs that follow, in conjunction with the description of Figure 1). Woo then accumulates that per-pixel vehicle information over time: “the server 100 sorts, in descending order, information on whether a car accumulated for each pixel has ever been parked among all predictions of the AI model accumulated for more than one day” (page p paras 7-10, in which a weight is assigned to each pixel of the image and the positions of the pixels with the higher number of 1 are sorted in descending order), and trains the AI model using the processed vehicle image or processed data set (page 9 para 2).
It would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the invention to modify Jung with the teaching of Woo in order to facilitate the training of the artificial intelligence model, using video of the parking spaces and learning data based on observations accumulated over time rather than a single image.
However, Jung in view of Woo does not explicitly disclose extracting feature information for each detected object from each image of the video and accumulating that object feature information over a period of time to generate the learning data.
Seow teaches identifying an objects in each video frames (Fig. 1; Fig. 3, step 310, [0053], “a foreground object in a video frame”) and generating feature information for each detected object from each frame (Fig. 2, micro-feature classifier 255, [0036], “track[s] objects frame-to-frame and generate[s] micro-feature vectors for each foreground object at a rate of , e.g., 5 Hz,”), accumulating that feature information over time (context processor, [0031], “a vector packaging the kinematic data of a particular foreground object in successive frames or samples,”; Fig. 2, statistical engines 270, [0043], “the statistical engine may keep counts of how many input vectors map to each cluster,”; [0041], “the ART network may be permitted to mature over a period of time (e.g., days),”, and learning from the accumulated feature information (Fig. 1, [0023], “over time, the machine learning engine 140 learns expected patterns of behavior for objects that map to a given cluster”)
It would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the invention to modify the combination of Jung in view of Woo with the teachings of Seow so that the learning data is generated from feature information corresponding to each detected object, extracted from each image of the video and accumulated over a period of time, in order to learn from the behavior of the detected objects without requiring object classifications to be defined in advance (Seow [0038], “does not require the different object type classifications to be defined in advance,”), yielding predictable results.
3. Regrading Claim 7, Jung discloses A video-based parking space occupancy detection method performed by a computer (Figs. 1-3; [0003], “a parking recognition system capable of efficiently recognizing vehicles parked on corresponding parking surfaces.”), comprising:
detecting objects included in an image within a video taken of a plurality of parking spaces in a parking lot (Figs. 3-6; [0060], “parking recognition server 300 may acquire a plurality of images for at least one parking surface and vehicle photographed by at least one camera”);
inputting the feature information into an artificial intelligence learned in advance to detect whether the parking space is occupied and detecting whether the object occupies the parking space ([0077], “deep learning network according to an embodiment of the present invention may be learned in advance through vehicle image data photographed by a plurality of cameras…implemented in various forms of artificial neural networks”),
wherein the artificial intelligence is learned with learning data based on cumulative feature information that accumulates, over a certain period of time, feature information corresponding to the object detected from each image constituting the video taken of the parking space ([0074], learning data that includes cumulative data for a preset time period).
However, Jung does not explicitly disclose video; extracting feature information corresponding to the detected objects; and inputting the feature information into an artificial intelligence; and learning data based on cumulative feature information that accumulates, over a certain period of time, feature information corresponding to the object detected from each image constituting the video.
Woo teaches video (Page 7 para 2, “video information provided by the corresponding parking lot management server 200”);
extracting feature information corresponding to the detected objects (Page 7 para 6, “the server 100 extracts a specific image (or a specific frame) from image information received in real time according to a preset analysis unit for a plurality of images (or a plurality of frames) constituting the received image information, Preprocessing is performed on the extracted specific image.” Page 8 para 1-2); and
inputting the feature information into an artificial intelligence to detecting parking space occupancy (Page 6 para 3 the server 100 sorts the space occupied by a large number of cars among the total predictions of the AI model in descending order”); and learning data based on information corresponding to the detected vehicle that is derived from each image and accumulated over a period of time (Page 6 para 4, “information on whether a car accumulated foreach pixel has ever been parked among all predictions of the AI model accumulated for more than one day.”)
It would have obvious to a person or ordinary skill in the art prior to the effective filing date of the invention to modify Jung with the teachings of Woo in order to facilitate the training of the artificial intelligence model, using video of the parking spaces and learning data based on observations accumulated over time rather than a single image.
However, Jung in view of Woo does not explicitly disclose feature information for each detected object, extracted from each image of the video, that is accumulated over a period of time to form the learning data.
Seow teaches extracting feature information corresponding to each detected objected from each frame and accumulating it over time for learning as set for above for claim 1 (Fig. 2, micro-feature classifier 255, [0036], “generate micro-feature vectors for each foreground object at a rate of, e.g., 5 Hz.” Context processor, [0031], “a vector packaging the kinematic data of a particular foreground object in successive frames or samples.” Fig. 1, [0023], “Over time, the machine learning engine 140 learns expected patterns of behavior for objects that map to a given cluster.”)
It would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the invention to modify the combination of Jung in view of Woo with the teachings of Seow so that the learning data is generated from feature information corresponding to each detected object, extracted from each image of the video and accumulated over a period of time, in order to learn from the behavior of the detected objects without requiring object classifications to be defined in advance (Seow [0038], “does not require the different object type classifications to be defined in advance,”), yielding predictable results.
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.
4. Claim(s) 8 is rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application 2024/0233381 Jung et al. (hereinafter Jung) in view of KR-10-2173121 B1 Woo [English Translation/Google translation provided] further in view of U.S. Patent Application 2014/0003710, Seow et al (hereinafter Seow) further in view of KR 20230003769 A Byun [English Translation provided].
5. Regrading Claim 8, Jung discloses A video-based parking space occupancy detection system (Fig. 1; [0003], “a parking recognition system capable of efficiently recognizing vehicles parked on corresponding parking surfaces.”), comprising:
a communication module (Fig. 2: communication module 310) configured to receive a video taken of a plurality of parking spaces in a parking lot from a camera ([0047], “the communication module 310 may be connected to a communication module of the camera 100 through a network, so as to transmit and receive data to each other.”);
a memory (Fig. 2: memory 330) configured to store a program for generating learning data based on the video and learning an artificial intelligence that detects whether the parking space is occupied based on the learning data ([0048], “The processor 320 may execute an operation of generally controlling the parking recognition system 1 using a variety of programs stored in the memory 330” [0077], “deep learning network according to an embodiment of the present invention may be learned in advance through vehicle image data photographed by a plurality of cameras…implemented in various forms of artificial neural networks”); and
a processor configured to execute the program stored in the memory [0048], “The processor 320 may execute an operation of generally controlling the parking recognition system 1 using a variety of programs stored in the memory 330”),
However, Jung does not explicitly disclose thereby detecting an object from the video,
generating learning data based on cumulative feature information that accumulates, over a certain period of time, feature information corresponding to the object detected from each image constituting the video, and performing unsupervised learning of the artificial intelligence based on the learning data.
Woo teaches thereby detecting an object from the video (Page 7 para 2, “video information provided by the corresponding parking lot management server 200”);
generating learning data based on cumulative feature information that accumulates, over a certain period of time, feature information corresponding to the object detected from each image constituting the video, (page 8 para 6, “That is, the server 100 accesses (or works in conjunction with) a plurality of content management servers (not shown) that provide various types of content, and collects vehicle images through a crawling method” and the seven paragraphs that follow, in conjunction with the description of Figure 1) collecting vehicle images from content management servers that may be parking lot CCYV management servers through a crawling method; in this way the server 100 may collect vehicle images, which are unstructured data for A1 learning).
It would have obvious to a person or ordinary skill in the art prior to the effective filing date of the invention to modify Jung with the teachings of Woo in order to facilitate the training of the artificial intelligence model, using video of the parking spaces and learning data based on observations accumulated over time rather than a single image.
However, Jung in view of Woo does not explicitly disclose feature information for each detected object, extracted from each image of the video, that is accumulated over a period of time to generate the learning data; and Woo does not disclose performing unsupervised learning of the artificial intelligence based on the learning data
Seow teaches generating feature information for each detected object from each frame (Fig. 2, micro-feature classifier 255, [0036], “track[s] objects frame-to-frame and generate[s] micro-feature vectors for each foreground object at a rate of , e.g., 5 Hz,”), accumulating that feature information over time (context processor, [0031], “a vector packaging the kinematic data of a particular foreground object in successive frames or samples,”; Fig. 2, statistical engines 270, [0043], “the statistical engine may keep counts of how many input vectors map to each cluster,”; [0041], “the ART network may be permitted to mature over a period of time (e.g., days),”, and learning from the accumulated feature information (Fig. 1, [0023], “over time, the machine learning engine 140 learns expected patterns of behavior for objects that map to a given cluster”)
It would have been obvious to a person of ordinary skill in the art prior to the effective filing date of the invention to modify the combination of Jung in view of Woo with the teachings of Seow so that the learning data is generated from feature information corresponding to each detected object, extracted from each image of the video and accumulated over a period of time, in order to learn from the behavior of the detected objects without requiring object classifications to be defined in advance (Seow [0038], “does not require the different object type classifications to be defined in advance,”), yielding predictable results.
However, Jung in view of Woo and Seow does not explicitly disclose performing unsupervised learning of the artificial intelligence based on the learning data
Further, Byun teaches performing unsupervised learning of the artificial intelligence based on the learning data (Abstract, “detecting the localization of an object based on unsupervised learning according to an embodiment of the present disclosure may include the steps of: (a) allowing a conversion image generation part to convert a learning image and generate a conversion image; (b) allowing an object extraction part to extract a first object region from the learning image and a second object region from the conversion image; and (c) allowing an artificial intelligence learning part to compare the first object region and the second object region and train an artificial intelligence model.”)
It would have obvious to a person or ordinary skill in the art prior to the effective filing date of the invention to modify the combination of Jung in view of Woo and Seow to perform unsupervised learning of the artificial intelligence based on the learning data as taught in Byun in order to yield predictable results.
Allowable Subject Matter
Claims 2-3,4-6 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
Regrading Claim 2, Jung discloses The video-based parking space occupancy detection artificial intelligence learning (Fig. 1; [0003], “a parking recognition system capable of efficiently recognizing vehicles parked on corresponding parking surfaces.”) method of claim 1, wherein the generating of the learning data ([0077], “deep learning network according to an embodiment of the present invention may be learned in advance through vehicle image data photographed by a plurality of cameras…implemented in various forms of artificial neural networks”) comprises:
setting predetermined location coordinates and characteristics from an object area of the detected object as feature information ([0071]-[0073], “a plurality of random coordinates for the parking surface occupying-judgment area before transformation, or a plurality of random coordinates for the vehicle recognition area before transformation; p.sub.1′(x.sub.1′, y.sub.1′), p.sub.2′(x.sub.2′, y.sub.2′), p.sub.3′(x.sub.3′, y.sub.3′) indicate a plurality of coordinates corresponding to the parking surface occupying-judgment area after transformation, or a plurality of coordinates corresponding to the vehicle recognition area. An equation expressing a homogeneous coordinate transformation matrix”); and
Jung in view of Woo does not explicitly disclose setting a random axis for the feature information of each image, and generating, as the cumulative feature information, statistical distribution information accumulated and densely displayed over a certain period of time on a relative coordinate system formed by the axis.
Regrading Claim 4, Jung discloses The video-based parking space occupancy detection artificial intelligence learning (Fig. 1; [0003], “a parking recognition system capable of efficiently recognizing vehicles parked on corresponding parking surfaces.”) method of claim 1, wherein the learning of the artificial intelligence ([0077], “deep learning network according to an embodiment of the present invention may be learned in advance through vehicle image data photographed by a plurality of cameras…implemented in various forms of artificial neural networks”) comprises:
Jung in view of Woo does not explicitly disclose inputting feature information included in the cumulative feature information into the artificial intelligence and generating candidate cluster information by clustering the cumulative feature information according to an arbitrary standard; and
re-clustering the candidate cluster information through the artificial intelligence and generating cluster information corresponding to the parking space.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to OMER KHALID whose telephone number is (571)270-5997. The examiner can normally be reached Monday- Friday 9am-7pm.
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, John Miller can be reached at (571) 272-7353. 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.
/OMER KHALID/Examiner, Art Unit 2422
/JOHN W MILLER/Supervisory Patent Examiner, Art Unit 2422