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 .
Applicant’s Response
In the Applicant’s Response dated 2/4/26, the Applicant amended Claims 1, 8, 10, 18, 19, 25, 27, 35, 38 and argued Claims previously rejected in the Office Action dated 12/10/25. Claims 1-15, 18-32 and 35-38 are pending.
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 2/4/26 has been entered.
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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-5, 10, 12-14, 18-22, 27, 29-31 and 35-38 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Patil, United States Patent Publication 2018/0035082 (hereinafter “Patil”), in view of Lerner, United States Patent No. 5677308, in further view of Oztireli (hereinafter “Oztireli”).
Claim 1:
Patil discloses:
A method, comprising:
receiving a set of 2D images of a child in a bed, acquired by a camera positioned over the bed (see paragraphs [0031]-[0035]). Patil teaches receiving images of an infant in bed during a given period of time;
in each of the images:
identifying a head and body of the child (see paragraphs [0046]-[0058]). Patil teaches segmenting and identifying a head and a body;
using a skeleton model, extracting head key-points from the identified head and body joints from the identified body (see paragraphs [0044]-[0058]). Patil teaches using the skeleton model and extracting details from the head and body to identify other features.
based on the extracted head key-points and body points, computing a head posture of the child in at least some of the images (see paragraphs [0066] and [0067]). Patil teaches computing a head posture based extracted features.
based on the head posture of the child in the at least some of the images, identifying a difficulty of the child, (see paragraphs [0092]-[0094], [0108]). Patil teaches in response to exceeding a threshold indicating a potential unsafe issue. A tilt in the head or neck can be an abnormal development issue such as SIDS;
in response to identifying the difficulty, indicating, to a user, a potentially abnormal child development issue (see paragraphs [0092]-[0094], [0108]). Patil teaches in response to identifying a potential unsafe issue and taking action by sending an alert.
Patil fails to identify improperly functioning sternocleidomastoid muscle of the child.
Lerner discloses:
based on the head posture of the child in the at least some of the images, identifying a difficulty of the child, due to an improperly functioning sternocleidomastoid muscle of the child, in changing the head posture (see column 1 lines 15-23). Lerner teaches abnormal movement of the sternocleidomastoid muscle based on posture.
Accordingly, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention was made to modify the method by Patil to include identifying abnormal movement of the sternocleidomastoid muscle of the child for the purpose of efficiently treating involuntary muscle spasms cause by spasmodic torticollis, as taught by Lerner.
Patil and Lerner fail to expressly disclose acquiring 2D images using a 2D camera and applying 2D skeleton model.
Oztireli discloses:
receiving a set of 2D images acquired by a 2D camera (see paragraph [0047]). Oztireli teaches receiving images acquired by a camera.
by applying a 2D skeleton model to the image, extracting head key-points from the identified head and body joints from the identified body (see paragraphs [0039], [0050]). Oztireli teaches using the 2D skeleton model and extracting details from the head and body to identify other features.
based on the extracted head key-points and body joints, computing a head posture of the child in at least some of the images (see paragraph [0051]). Oztireli teaches computing the pose of the body based on the model and the images;
Accordingly, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention was made to modify the method by Patil and Lerner to include acquiring 2D images by a 2D camera and applying 2d skeleton model for the purpose of efficiently estimate the pose of a body, as taught by Oztireli.
Claim 2:
Patil discloses:
further comprising, using the extracted body joints, classifying a body posture of the child in each of the images (see paragraph [0092]). Patil teaches using the extracted features to determine a body posture such as lying belly-up, belly-down or sideways;
wherein computing the head posture comprises computing the head posture using the classified body posture and the extracted head key-points (see paragraphs [0090]-[0092]). Patil teaches using the body posture positions and head features to determine the head posture.
Claim 3:
Patil discloses:
wherein classifying the body posture comprises classifying the body posture into one of six labeled classes of “back,” “belly,” “crawling,” “side,” “standing,” and “sitting,” and omitting from head posture classification head postures related to body postures of “side,” and “standing,” and “sitting (see paragraphs [0090]-[0092]). Patil teaches classified body types such as belly, side, etc.
wherein computing the head posture comprises computing the head posture in response to the body not being classified as any of the “side,” and “standing,” and “sitting (see paragraphs [0090]-[0092]). Patil teaches classified body types such as belly, side, etc. Also classifying as safe and unsafe.
Claim 4:
Patil discloses:
wherein computing the head posture comprises classifying the head posture into one of three labeled classes of “left,” “straight,” and “right.” (see paragraphs [0078]-[0084] and [0118]). Patil teaches classifying head posture such as left straight and right. Patil teaches determining the head posture.
Claim 5:
Patil discloses:
wherein computing the head posture comprises computing the head posture using a machine learning (ML) model that was trained using images of children in beds (see paragraphs [0060]-[0061] and [0090]). Patil teaches using machine learning model to train images of children in cribs with different positions.
Claim 10:
Patil discloses:
wherein computing the head posture comprises computing the head posture based on heatmaps of the head key-points (see paragraphs [0044]-[0059]). Patil teaches extracting body features.
Patil and Lerner fail to expressly disclose acquiring 2D images using a 2D camera and applying 2D skeleton model.
Oztireli discloses:
2D heat maps (see paragraphs [0035]-[0037]). Oztireli teaches 2D heat maps.
Patil and Lerner fail to expressly disclose using a heatmap to extract features.
Accordingly, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention was made to modify the method by Patil and Lerner to include acquiring 2D images by a 2D camera and applying 2d skeleton model for the purpose of efficiently estimate the pose of a body, as taught by Oztireli.
Claim 12:
Patil discloses:
wherein the child is one of an infant and a toddler, and the bed is a crib (see paragraphs [0021] and [0026]). Patil teaches an infant in a crib/cradle.
Claim 13:
Patil discloses:
wherein indicating of potentially abnormal child development issue (see paragraphs [0108]-[0109]). Patil teaches indicating an abnormality such as SIDS which is also based on a tilting of the head/neck.
Patil fails to identify improperly functioning sternocleidomastoid muscle of the child.
Lerner discloses:
potential Torticollis (see column 1 lines 15-23). Lerner teaches abnormal movement of the sternocleidomastoid muscle based on posture that can indicate Torticollis.
Accordingly, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention was made to modify the method by Patil to include identifying abnormal movement of the sternocleidomastoid muscle of the child for the purpose of efficiently treating involuntary muscle spasms cause by spasmodic torticollis, as taught by Lerner.
Claim 14:
Patil discloses:
wherein indicating the potentially abnormal child development issue comprises sending an alert to a physician (see paragraphs [0107]-[0109] and [0145]). Patil teaches sending an important alert remotely.
Claims 18-22, 27, 29-31:
Although Claims 18-22, 27, 29-31 are system claims, they are interpreted for the same reasons as the method of Claims 1-5, 10, 12-14, respectively.
Claims 35-38:
Although Claims 35-38 are computer software product claims, they are interpreted for the same reasons as the method of Claims 1-4, 8, respectively.
Claims 6, 7, 23 and 24 are rejected under 35 U.S.C. 103 as being unpatentable over Patil, in view of Lerner and Oztireli, in further view of Iyer et al., United States Patent Publication 20210201082 (hereinafter “Iyer”).
Claim 6:
Patil, Lerner and Oztireli fail to expressly disclose an ARN or ANN.
Iyer discloses:
wherein the ML model is selected from the group consisting of an action recognition network (ARN) class and a classification network type of artificial neural network (ANN) (see paragraph [0087]). Iyer teaches using a ML model and ANNs to classify images and determining body posture.
Accordingly, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention was made to modify the method by Patil, Lerner and Oztireli to include using ANN for the purpose of accurately classify posture images, as taught by Iyer.
Claim 7:
Patil, Lerner and Oztireli fails to expressly disclose an MLP or CNN class of ANN.
Iyer discloses:
wherein the ML model is selected from the group consisting of a multilayer perceptron (MLP) class and a convolutional neural network (CNN) class of artificial neural network (ANN) (see paragraph [0087]). Iyer teaches using a ML model and CNNs to classify images and determining body posture.
Accordingly, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention was made to modify the method by Patil, Lerner and Oztireli to include using CNN for the purpose of accurately classify posture images, as taught by Iyer.
Claims 23, 24:
Although Claims 23 and 24 are system claims, they are interpreted for the same reasons as the method of Claims 6 and 7, respectively.
Claims 8, 9, 25 and 26 are rejected under 35 U.S.C. 103 as being unpatentable over Patil, in view of Lerner and Oztireli, in further view of Nakamura et al., United States Patent Publication 20220108468 (hereinafter “Nakamura”).
Claim 8:
Oztireli discloses:
2D heat maps (see paragraphs [0035]-[0037]). Oztireli teaches 2D heat maps.
Patil and Lerner fail to expressly disclose using a heatmap to extract features.
Patil, Lerner and Oztireli fails to disclose computing the head posture based on the heatmap.
Nakamura discloses:
wherein computing the head posture comprises computing the head posture based on heatmaps of the body joints (see paragraph [0075]). Nakamura teaches using a heatmap to extract body joint features.
Accordingly, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention was made to modify the method by Patil, Lerner and Oztireli to include using a heat map to extract features for the purpose of providing motion measurement with a high accuracy similar to that with an optical motion capture, as taught by Nakamura.
Claim 9:
Patil, Lerner and Oztireli fail to expressly disclose using a heatmap to extract features.
Nakamura discloses:
wherein the head key-points include at least a nose, eyes and ears (see paragraph [0088]). Nakamura teaches using a heatmap to extract head features such as nose and eyes.
Accordingly, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention was made to modify the method by Patil, Lerner and Oztireli to include using a heat map to extract features for the purpose of providing motion measurement with a high accuracy similar to that with an optical motion capture, as taught by Nakamura.
Claims 25-26:
Although Claims 25-26 are system claims, they are interpreted for the same reasons as the method of Claims 8, 9, respectively.
Claims 11 and 28 are rejected under 35 U.S.C. 103 as being unpatentable over Patil, in view of Lerner and Oztireli, in further view of Cong et al., United States Patent Publication 8699766 (hereinafter “Cong”).
Claim 11:
Patil discloses:
wherein computing the head posture comprises computing the head posture based on the extracted feature (see paragraphs [0090]-[0092]). Patil teaches using the body posture positions and head features to determine the head posture.
Patil, Lerner and Oztireli fail to expressly disclose extract head features such as head circumference.
Cong discloses:
further comprising extracting, from the identified head, at least one feature selected from the group consisting of facial features and features located at a head circumference, (see column 8 lines 18-30). Nakamura teaches using a heatmap to extract body joint features and computing head circumference.
Accordingly, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention was made to modify the method by Patil, Lerner and Oztireli to include extracting head features and head circumference for the purpose of efficiently estimating the condition of fetal growth and screening fetus abnormalities, as taught by Cong.
Claim 28:
Although Claim 28 is a system claim, it is interpreted for the same reasons as the method of Claims 11, respectively.
Claims 15 and 32 are rejected under 35 U.S.C. 103 as being unpatentable over Patil, Lerner and Oztireli, in view of Claussen et al., United States Patent No. 6473717 (hereinafter “Claussen”).
Claim 15:
Patil, Lerner and Oztireli fail to expressly disclose using movement patterns to determine Torticollis.
Claussen discloses:
classifying from the images a pattern of movement of the child, generating a movement score based on a pattern, and comparing the movement score to a threshold, wherein indicating the potentially abnormal child development issue comprises indicating the potentially abnormal child development issue based on the comparison (see column 4 lines 13-47). Claussen teaches classifying image and determining a movement, using a comparison with the patterns to indicate torticollis.
Accordingly, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention was made to modify the method by Patil, Lerner and Oztireli to include identifying patterns of movement to determine if torticollis is evident for the purpose of efficiently calculating the movement deviations, as taught by Claussen.
Claim 32:
Although Claims 32 are system claims, they are interpreted for the same reasons as the method of Claim 15, respectively.
Response to Arguments
Applicant’s arguments, see REM, filed 2/4/26, with respect to the rejection of claims 1-15, 18-32, 35-38 under 35 USC 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new grounds of rejection is made in view of Patil, Lerner and Oztireli.
Applicant argues Although Patil also describes using 2D images, these images are not acquired by a 2D camera, but rather, are obtained by retaining only the intensity component of the 3D images, i.e., disregarding the depth component ([0031], [0032]). Furthermore, Patil does not apply a 2D skeleton model to these images, but rather, uses the images for other purposes such as for labeling the various parts of the image ([0076]) or for determining if the eyes are open or closed ([0113], [0119]).
The Examiner agrees.
The Examiner introduced new art, Oztireli, to teach acquiring 2D images from a 2D camera and applying a 2D skeleton model to determine the joints and bones of the body within the images (see the above rejection of Claim 1). The combination of Patil, Lerner and Oztireili disclose the limitations of the claims.
Applicant argues Moreover, the dependent claims recite additional patentable subject matter. For example, claims 8, 10, 25, 27, and 38 recite that the head posture is computed based on 2D heatmaps of the body joints or head key-points. In contrast, Nakamura's heatmaps are used for estimating joint positions ([0075]).
The Examiner agrees that Nakamura does not use 2D heatmaps.
Oztireli does teach using 2D heat maps to determine the posture of the body. Nakamura teaches using heatmaps to determine the head posture, Thus the combination of art, teach the limitations of the claims (see the above rejections for mentioned claims).
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 TIONNA M BURKE whose telephone number is (571)270-7259. The examiner can normally be reached M-F 8a-4p.
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, Stephen Hong can be reached at (571)272-4124. 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.
/TIONNA M BURKE/Examiner, Art Unit 2178 3/7/26