公开(公告)号：US20230394877A1

公开(公告)日：2023-12-07

申请号：US18205226

申请日：2023-06-02

Applicant: Northeastern University

Inventor： Sarah OSTADABBAS ,  Emily ZIMMERMAN ,  Xiaofei HUANG ,  Michael WAN

IPC: G06V40/16 ,  G06V10/82 ,  G06V10/774 ,  G06V20/70

CPC classification number: G06V40/172 ,  G06V10/82 ,  G06V40/171 ,  G06V10/774 ,  G06V20/70

Abstract: Provided herein are methods and systems for identifying a face of an infant in an image including providing a computer comprising a processor and a memory trained with a set of training images and programmed with a convolutional neural network (CNN) model for identifying a face of an infant in a test image suspected of comprising an infant's face, wherein each image of the set of training images includes a plurality of facial landmark annotations and at least one pose attribute annotation, providing a test image suspected of comprising an image of an infant's face, and processing the test image using the computer, whereby the infant's face is identified in the test image.

公开(公告)号：US20220412804A1

公开(公告)日：2022-12-29

申请号：US17777091

申请日：2020-11-16

Applicant: Northeastern University

Inventor： Swastik KAR ,  Davoud HEJAZI ,  Sarah OSTADABBAS

IPC: G01J3/46 ,  G01J3/51

Abstract: Devices and methods of the present technology utilize wavelength-dependent transmittance of 2D materials to identify the wavelength of an electromagnetic radiation. A wide range of 2D materials can be used, making possible the use of the technology over a large portion of the electromagnetic spectrum, from gamma rays to the far infrared. When combined with appropriate algorithms and artificial intelligence, the technology can identify the wavelength of one or more monochromatic sources, or can identify color through the use of a training set. When applied in an array format, the technology can provide color imaging or spectral imaging using different regions of the electromagnetic spectrum.

公开(公告)号：US20230332955A1

公开(公告)日：2023-10-19

申请号：US18126364

申请日：2023-03-24

Applicant: Northeastern University

Inventor： Swastik KAR ,  Davoud HEJAZI ,  Sarah OSTADABBAS

IPC: G01J3/51

CPC classification number: G01J3/51 ,  G01J2003/466

Abstract: The present technology provides devices and methods to determine the spectrum or other spectral characteristic, such as color, of a beam of light or other electromagnetic radiation. The beam of light or other electromagnetic radiation is modified without dispersion by broadband transmissive windows and then transmitted onto a detector. Signals from the detector are measured from a training set of radiation having known spectra and used to train the device, after which the device can estimate the spectrum or color of an unknown light or other electromagnetic radiation with exceptionally high accuracy.

公开(公告)号：US20240378890A1

公开(公告)日：2024-11-14

申请号：US18696091

申请日：2022-10-31

Applicant: Northeastern University

Inventor： Sarah OSTADABBAS ,  Shuangjun LIU

IPC: G06V20/50 ,  G06V10/50 ,  G06V10/764 ,  G06V10/94 ,  G06V40/10

Abstract: Systems and methods are provided for in-bed pose and posture determination and tracking for a human subject including an imaging device, the imaging device positioned proximate to a bed and oriented to capture images of the subject lying in the bed, and a processing unit operative to receive the captured images, the captured images including a plurality of image frames, the processing unit including a pose estimation module trained with a dataset of lying poses and operative to estimate poses of the subject lying in the bed based the image frames, and a posture classification module trained with the dataset of lying poses and operative to classify positions of the subject lying in the bed based on the image frames, the processing unit operative to determine a pose and posture of the subject lying in the bed.

公开(公告)号：US20240193809A1

公开(公告)日：2024-06-13

申请号：US18287518

申请日：2022-05-09

Applicant: Northeastern University

Inventor： Sarah OSTADABBAS ,  Xiaofei HUANG ,  Nihang FU ,  Shuangjun LIU

IPC: G06T7/73 ,  G06T15/04

CPC classification number: G06T7/74 ,  G06T7/75 ,  G06T15/04 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/10048 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196

Abstract: Methods are provided for estimating a pose of an infant using image analysis and artificial intelligence. A classifier is trained using a dataset containing hybrid synthetic and real infant pose data. Multi-stage invariant representation machine learning strategies are employed that transfer knowledge from adjacent domains of adult poses and synthetic infant images into a fine-tuned domain-adapted infant pose estimation model.

公开(公告)号：US20240350032A1

公开(公告)日：2024-10-24

申请号：US18642362

申请日：2024-04-22

Applicant: Northeastern University

Inventor： Sarah OSTADABBAS ,  Xiafei Huang ,  Lingfei Luan ,  Elaheh Hatamimajoumerd ,  Micheal Wan

IPC: A61B5/11 ,  A61B5/00

CPC classification number: A61B5/11 ,  A61B5/0077 ,  A61B5/7267 ,  A61B2503/06

Abstract: Provided herein are methods and systems for recognizing an infant action in a recorded video. The infant action recognition technique includes performing pose estimation for each frame of the video, where pose corresponds to skeletal joint locations and joint angles. A posture classifier uses the pose estimations to classify each pose estimation as one of five postures and a probability value for the posture. The infant action recognition technique further includes using the identified postures for each frame and the probability values to determine a period of uncertainty that corresponds to a transition segment. The infant action recognition technique further includes using the first and last frames of the transition segment to distinguish start and end stable postures. The technique further includes performing filtering and majority voting to remove outlier posture classifications and determine an infant action label for the video based on the start and end stable postures.

公开(公告)号：US20220386898A1

公开(公告)日：2022-12-08

申请号：US17831993

申请日：2022-06-03

Applicant: Northeastern University

Inventor： Sarah OSTADABBAS ,  Shuangjun LIU

IPC: A61B5/11 ,  G06T7/73 ,  G06T7/90 ,  G06V40/10 ,  H04N5/33

Abstract: Provided herein are systems and methods for estimating contact pressure of a human lying on a surface including one or more imaging devices having imaging sensors oriented toward the surface, a processor and memory, including a trained model for estimating human contact pressure trained with a dataset including a plurality of human lying poses including images generated from at least one of a plurality of imaging modalities including at least one of a red-green-blue modality, a long wavelength infrared modality, a depth modality, or a pressure map modality, wherein the processor can receive one or more images from the imaging devices of the human lying on the surface and a source of one or more physical parameters of the human to determine a pressure map of the human based on the one or more images and the one or more physical parameters.