专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11282298B2 Monitoring the performance of physical exercises 有权
公开(公告)号：US11282298B2
公开(公告)日：2022-03-22
申请号：US16113507
申请日：2018-08-27
申请人： Kaia Health Software GmbH
发明人： Konstantin Mehl , Maximilian Strobel
IPC分类号： G06T7/73 , G06T7/246 , A61B5/11 , A61B5/00 , G06V40/20 , A63B24/00
摘要： A method for monitoring a person performing a physical exercise based on a sequence of image frames showing the person's exercise activity is described. The method comprises the steps of extracting, based on the sequence of image frames, for each image frame a set of body key points using a neural network, the set of body key points being indicative of the person's posture in the image frame, and deriving, based on a subset of the body key points in each image frame, at least one characteristic parameter indicating the progression of the person's movement. The method further comprises detecting a start loop condition by evaluating the time progression of at least one of the characteristic parameters, said start loop condition indicating a transition from a start posture of the person to the person's movement when performing the physical exercise.

2. 发明授权

US11797602B2 Evaluation data structure for evaluating a specific motion pattern and dashboard for setting up the evaluation data structure 有权
公开(公告)号：US11797602B2
公开(公告)日：2023-10-24
申请号：US17887920
申请日：2022-08-15
申请人： Kaia Health Software GmbH
发明人： Konstantin Mehl , Maximilian Strobel
IPC分类号： G06F16/51 , G06N20/20 , G06T7/20 , G06T7/60 , G06T7/70 , G06V40/20 , G06F18/21 , G06F18/24 , G06N5/01 , G06V10/75 , G06V10/764 , G06V10/82 , G06V10/62
CPC分类号： G06F16/51 , G06F18/21 , G06F18/24 , G06N5/01 , G06N20/20 , G06T7/20 , G06T7/60 , G06T7/70 , G06V10/62 , G06V10/757 , G06V10/764 , G06V10/82 , G06V40/20 , G06V40/23 , G06T2200/24 , G06T2207/20081 , G06T2207/30196 , G06T2207/30244
摘要： An editor application configured for setting up at least one evaluation data structure, each evaluation data structure being configured for evaluating a corresponding specific motion pattern in a sequence of image data structures Each evaluation data structure includes a machine learning (ML) model artifact of an exercise specific ML model configured for evaluating the particular physical exercise. Further, the ML model is trained based on a plurality of sequences of image data structures showing different variants of the specific motion pattern for the particular physical exercise, and for each image data structure, a set of key data elements is provided, a key data element indicating a respective position of a landmark in the image data structure, said training being further based on class labels provided for each image data structure. In addition, the ML model is configured to determine, based on input data comprising key data elements provided for at least one image data structure, class labels for each image data structure, said class labels identifying at least one of: at least one motion phase of the specific motion pattern, at least one evaluation point of the specific motion pattern, wherein the key data elements indicate positions of landmarks in the image data structures; generate geometric evaluation data and perform a geometric evaluation of a configuration of key data elements of a particular image data structure that corresponds to an evaluation point or for performing a geometric evaluation of at least one motion phase of the specific motion pattern; and generate feedback data for providing a feedback to the user, said feedback depending on the result of the geometric evaluation. Further, the editor application comprises at least one graphical user interface, the graphical user interface being configured for accepting user input for training the ML model underlying the ML model artefact.

3. 发明授权

US11727728B2 Monitoring the performance of physical exercises 有权
公开(公告)号：US11727728B2
公开(公告)日：2023-08-15
申请号：US17470423
申请日：2021-09-09
申请人： Kaia Health Software GmbH
发明人： Konstantin Mehl , Maximilian Strobel
IPC分类号： A61B5/11 , A61B5/00 , G06V40/20 , G06T7/73 , G06T7/246 , A63B24/00
CPC分类号： G06V40/23 , A61B5/1116 , A61B5/1118 , A61B5/1128 , A61B5/725 , A61B5/7405 , A63B24/0062 , G06T7/248 , G06T7/74 , A63B2024/0068 , A63B2220/806 , A63B2230/62 , G06T2207/10016 , G06T2207/20084 , G06T2207/30196
摘要： A method for monitoring a person performing a physical exercise based on a sequence of image frames showing an exercise activity of the person. The method includes extracting, based on the sequence of image frames, for each image frame a set of body key points using a neural network, the set of body key points being indicative of a posture of the person in the image frame; deriving, based on a subset of the body key points in each image frame, at least one characteristic parameter indicating a progression of a movement of the person; detecting a start loop condition by evaluating the time progression of the at least one characteristic parameter, said start loop condition indicating a transition from a start posture of the person to the movement of the person when performing the physical exercise, wherein a loop of exercising encompasses one single repetition of the physical exercise; detecting an end loop condition by evaluating the time progression of at least one of the characteristic parameters, said end loop condition indicating a transition from the movement of the person when performing the physical exercise to an intermediate posture, wherein, as a result, the start of the loop and the end of the loop are determined; and deriving the time period for a single loop of the physical exercise based on the start of the loop and the end of the loop and evaluating the time period.

4. 发明授权

US11328534B2 Monitoring the performance of physical exercises 有权
公开(公告)号：US11328534B2
公开(公告)日：2022-05-10
申请号：US17016144
申请日：2020-09-09
申请人： Kaia Health Software GmbH
发明人： Konstantin Mehl , Maximilian Strobel
IPC分类号： A61B5/11 , A61B5/00 , G06V40/20 , G06T7/73 , G06T7/246 , A63B24/00
摘要： A method for monitoring a person performing a physical exercise based on a sequence of image frames showing an exercise activity of the person. The method includes extracting, based on the sequence of image frames, for each image frame a set of body key points using a neural network, the set of body key points being indicative of a posture of the person in the image frame; deriving, based on a subset of the body key points in each image frame, at least one characteristic parameter indicating a progression of a movement of the person; detecting a start loop condition by evaluating the time progression of the at least one characteristic parameter, said start loop condition indicating a transition from a start posture of the person to the movement of the person when performing the physical exercise, wherein a loop of exercising encompasses one single repetition of the physical exercise; detecting an end loop condition by evaluating the time progression of at least one of the characteristic parameters, said end loop condition indicating a transition from the movement of the person when performing the physical exercise to an intermediate posture, wherein, as a result, the start of the loop and the end of the loop are determined; and deriving the time period for a single loop of the physical exercise based on the start of the loop and the end of the loop and evaluating the time period.

5. 发明授权

US11604998B2 Upgrading a machine learning model's training state 有权
公开(公告)号：US11604998B2
公开(公告)日：2023-03-14
申请号：US16669088
申请日：2019-10-30
申请人： Kaia Health Software GmbH
发明人： Konstantin Mehl , Maximilian Strobel
IPC分类号： G06N3/08 , G06N3/084 , G06F16/901 , G06N20/00
摘要： A method for upgrading a training state of a machine learning model is described, the machine learning model being configured for supporting a model update. The method comprises predicting a set of target data elements based on the input data structure using the machine learning model, a target data element corresponding to a respective characteristic of the input data structure, and determining, for at least one of the predicted target data elements, whether or not a respective target data element is presumably erroneous. The method further comprises determining, for each presumably erroneous target data element detected in the previous step, an estimated corrected target data element, and performing, based on at least one estimated corrected target data element, a step of updating the training state of the machine learning model.

6. 发明授权

US11482047B2 ML model arrangement and method for evaluating motion patterns 有权
公开(公告)号：US11482047B2
公开(公告)日：2022-10-25
申请号：US16735132
申请日：2020-01-06
申请人： Kaia Health Software GmbH
发明人： Konstantin Mehl , Maximilian Strobel
IPC分类号： G06K9/00 , G06V40/20 , G06T7/20 , G06T7/70 , G06K9/62 , G06N5/00 , G06N3/04
摘要： A ML model arrangement configured for evaluating motion patterns in a sequence of image data structures is described. The ML model arrangement comprises a first ML model configured for predicting a set of key data elements for each image data structure of the sequence of image data structures, a key data element indicating a respective position of a landmark in the image data structure. The ML model arrangement further comprises at least one second ML model, each second ML model being a ML model configured for evaluating a corresponding specific motion pattern. Each second ML model is configured for determining, based on input data comprising at least one of the key data elements predicted for at least one image data structure or data derived therefrom, class labels for each image data structure, said class labels identifying at least one of: at least one motion phase of the specific motion pattern, at least one evaluation point of the specific motion pattern.

7. 发明授权

US11450147B2 Evaluation data structure for evaluating a specific motion pattern and dashboard for setting up the evaluation data structure 有权
公开(公告)号：US11450147B2
公开(公告)日：2022-09-20
申请号：US16735101
申请日：2020-01-06
申请人： Kaia Health Software GmbH
发明人： Konstantin Mehl , Maximilian Strobel
IPC分类号： G06V40/20 , G06F16/51 , G06N20/20 , G06N5/00 , G06T7/20 , G06T7/60 , G06K9/62 , G06T7/70
摘要： An editor application configured for setting up at least one evaluation data structure is described, wherein each evaluation data structure is configured for evaluating a corresponding specific motion pattern in a sequence of image data structures. Each evaluation data structure comprises a ML model artifact configured for determining, based on input data comprising key data elements provided for at least one image data structure, class labels for each image data structure, said class labels identifying at least one of: at least one motion phase of the specific motion pattern, at least one evaluation point of the specific motion pattern. A key data element indicates a respective position of a landmark in the image data structure. Each evaluation data structure further comprises geometric evaluation data for performing a geometric evaluation of a configuration of key data elements of a particular image data structure that corresponds to an evaluation point or for performing a geometric evaluation of at least one motion phase of the specific motion pattern. Each evaluation data structure further comprises feedback data for providing a feedback to the user, said feedback depending on the result of the geometric evaluation. The editor application comprises at least one graphical user interface, the graphical user interface being configured for accepting user input for setting up and editing the geometric evaluation data and the feedback data.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式