-
公开(公告)号：US12097050B2
公开(公告)日：2024-09-24
申请号：US17434333
申请日：2020-02-27
Applicant: UNIVERSITY OF IOWA RESEARCH FOUNDATION
Inventor： Stephen Baek , Yusen He , Xiaodong Wu , Yusung Kim , Bryan G. Allen , John Buatti , Brian J. Smith
CPC classification number: A61B5/7264 , A61B5/7275 , G06T7/11 , G06T2200/04 , G06T2207/10081 , G06T2207/10104 , G06T2207/20084 , G06T2207/30096
Abstract: Methods and systems for image segmentation and analysis are described. A predictive model may be trained to identify and/or extract a rich set of image features with extensive prognostic value. For example, the predictive model may be trained to identify and/or extract features that that may be visualized to identify areas of interest (e.g., high-risk regions, etc.) within or adjacent to an object of interest, such a tumor. The predictive model may be trained to identify and/or extract features that that may predict a health related outcome, such as cancer patient survival/death, and modify therapeutic outcomes, such as diagnosis and treatment.
-
2.发明授权公开(公告)号：US11324439B2
公开(公告)日：2022-05-10
申请号：US17473526
申请日：2021-09-13
Applicant: University of Iowa Research Foundation
Inventor： Alec Diaz-Arias , Mitchell Messmore , Dmitry Shin , John Rachid , Stephen Baek , Jean Robillard
Abstract: A method can include receiving (1) images of at least one subject and (2) at least one total mass value for the at least one subject. The method can further include executing a first machine learning model to identify joints of the at least one subject. The method can further include executing a second machine learning model to determine limbs of the at least one subject based on the joints and the images. The method can further include generating three-dimensional (3D) representations of a skeleton based on the joints and the limbs. The method can further include determining a torque value for each limb, based on at least one of a mass value and a linear acceleration value, or a torque inertia and an angular acceleration value. The method can further include generating a risk assessment report based on at least one torque value being above a predetermined threshold.
-
Patent Agency Ranking
3.发明授权公开(公告)号：US11957478B2
公开(公告)日：2024-04-16
申请号：US17714681
申请日：2022-04-06
Applicant: University of Iowa Research Foundation
Inventor： Alec Diaz-Arias , Mitchell Messmore , Dmitry Shin , John Rachid , Stephen Baek , Jean Robillard
CPC classification number: A61B5/45 , G06N20/20 , G06T7/70 , G06T19/20 , G06V40/23 , G16H20/30 , G06T2207/20044
Abstract: A method can include receiving (1) images of at least one subject and (2) at least one total mass value for the at least one subject. The method can further include executing a first machine learning model to identify joints of the at least one subject. The method can further include executing a second machine learning model to determine limbs of the at least one subject based on the joints and the images. The method can further include generating three-dimensional (3D) representations of a skeleton based on the joints and the limbs. The method can further include determining a torque value for each limb, based on at least one of a mass value and a linear acceleration value, or a torque inertia and an angular acceleration value. The method can further include generating a risk assessment report based on at least one torque value being above a predetermined threshold.
-
公开(公告)号：US11775902B2
公开(公告)日：2023-10-03
申请号：US17717714
申请日：2022-04-11
Applicant: UNIVERSITY OF IOWA RESEARCH FOUNDATION
Inventor： Stephen Baek , Nathan B. Fethke , Jean Robillard , Joseph A. V. Buckwalter , Pamela Villacorta
IPC: G06Q10/0635 , G06Q10/0631 , G06N20/00 , G06V40/20
CPC classification number: G06Q10/0635 , G06N20/00 , G06Q10/063114 , G06V40/23
Abstract: A prevention and safety management system utilizes a non-intrusive imaging sensor (e.g. surveillance cameras, smartphone cameras) and a computer vision system to record videos of workers not wearing sensors. The videos are analyzed using a deep machine learning algorithm to detect kinematic activities (set of predetermined body joint positions and angles) of the workers and recognizing various physical activities (walk/posture, lift, push, pull, reach, force, repetition, duration etc.). The measured kinematic variables are then parsed into metrics relevant to workplace ergonomics, such as number of repetitions, total distance travelled, range of motion, and the proportion of time in different posture categories. The information gathered by this system is fed into an ergonomic assessment system and is used to automatically populate exposure assessment tools and create risk assessments.
-
5.发明申请公开(公告)号：US20220386942A1
公开(公告)日：2022-12-08
申请号：US17714681
申请日：2022-04-06
Applicant: University of Iowa Research Foundation
Inventor： Alec Diaz-Arias , Mitchell Messmore , Dmitry Shin , John Rachid , Stephen Baek , Jean Robillard
Abstract: A method can include receiving (1) images of at least one subject and (2) at least one total mass value for the at least one subject. The method can further include executing a first machine learning model to identify joints of the at least one subject. The method can further include executing a second machine learning model to determine limbs of the at least one subject based on the joints and the images. The method can further include generating three-dimensional (3D) representations of a skeleton based on the joints and the limbs. The method can further include determining a torque value for each limb, based on at least one of a mass value and a linear acceleration value, or a torque inertia and an angular acceleration value. The method can further include generating a risk assessment report based on at least one torque value being above a predetermined threshold.
-
公开(公告)号：US11328239B2
公开(公告)日：2022-05-10
申请号：US16825692
申请日：2020-03-20
Applicant: UNIVERSITY OF IOWA RESEARCH FOUNDATION
Inventor： Stephen Baek , Nathan B. Fethke , Jean Robillard , Joseph A. V. Buckwalter , Pamela Villacorta
Abstract: A prevention and safety management system utilizes a non-intrusive imaging sensor (e.g. surveillance cameras, smartphone cameras) and a computer vision system to record videos of workers not wearing sensors. The videos are analyzed using a deep machine learning algorithm to detect kinematic activities (set of predetermined body joint positions and angles) of the workers and recognizing various physical activities (walk/posture, lift, push, pull, reach, force, repetition, duration etc.). The measured kinematic variables are then parsed into metrics relevant to workplace ergonomics, such as number of repetitions, total distance travelled, range of motion, and the proportion of time in different posture categories. The information gathered by this system is fed into an ergonomic assessment system and is used to automatically populate exposure assessment tools and create risk assessments.
-
7.发明申请公开(公告)号：US20220079510A1
公开(公告)日：2022-03-17
申请号：US17473526
申请日：2021-09-13
Applicant: University of Iowa Research Foundation
Inventor： Jean Robillard , Alec Diaz-Arias , Mitchell Messmore , Dmitry Shin , John Rachid , Stephen Baek
Abstract: A method can include receiving (1) images of at least one subject and (2) at least one total mass value for the at least one subject. The method can further include executing a first machine learning model to identify joints of the at least one subject. The method can further include executing a second machine learning model to determine limbs of the at least one subject based on the joints and the images. The method can further include generating three-dimensional (3D) representations of a skeleton based on the joints and the limbs. The method can further include determining a torque value for each limb, based on at least one of a mass value and a linear acceleration value, or a torque inertia and an angular acceleration value. The method can further include generating a risk assessment report based on at least one torque value being above a predetermined threshold.
-
-
-
-
-
-
Search Results
7
records
(took 0.021 seconds)
