公开(公告)号：US12254670B2

公开(公告)日：2025-03-18

申请号：US17877575

申请日：2022-07-29

Applicant: Infineon Technologies AG

Inventor： Souvik Hazra ,  Avik Santra

IPC: G06V10/764 ,  G01S13/89 ,  G06V10/82 ,  G06V10/84 ,  G06V40/20

Abstract: In an embodiment, a method includes: receiving raw data from a millimeter-wave radar sensor; generating a first radar-Doppler image based on the raw data; generating a first radar point cloud based on the first radar-Doppler image; using a graph encoder to generate a first graph representation vector indicative of one or more relationships between two or more parts of the target based on the first radar point cloud; generating a first cadence velocity diagram indicative of a periodicity of movement of one or more parts of the target based on the first radar-Doppler image; and classifying an activity of a target based on the first graph representation vector and the first cadence velocity diagram.

公开(公告)号：US20230393259A1

公开(公告)日：2023-12-07

申请号：US17834557

申请日：2022-06-07

Applicant: Infineon Technologies AG ,  Friedrich-Alexander-Universität Erlangen-Nürnberg

Inventor： Souvik Hazra ,  Avik Santra ,  Thomas Reinhold Stadelmayer

IPC: G01S13/534 ,  G01S7/41

CPC classification number: G01S13/534 ,  G01S7/411

Abstract: In an embodiment, a method includes: generating a target displacement signal indicative of a movement of a human target based on raw digital data generated by a millimeter-wave radar sensor; and estimating a vital sign of the human target based on the target displacement signal, where generating the target displacement signal includes: generating target in-phase (I) and quadrature (Q) (I/Q) data associated with the human target based on the raw digital data, classifying the target I/Q data as high quality data or as low quality data using a first neural network, when the target I/Q data is classified as low quality data, discarding the target I/Q data, when the target I/Q data is classified as high quality data, performing ellipse fitting on the target I/Q data to generate compensated I/Q data, and generating the target displacement signal based on the compensated I/Q data.

公开(公告)号：US20240255631A1

公开(公告)日：2024-08-01

申请号：US18407930

申请日：2024-01-09

Applicant: Infineon Technologies AG

Inventor： Xiangyuan Peng ,  Souvik Hazra ,  Lorenzo Servadei

IPC: G01S13/58 ,  G06F18/2415

CPC classification number: G01S13/582 ,  G06F18/2415

Abstract: In accordance with an embodiment, a method includes: obtaining radar data from a scene; determining cadence-velocity data and micro range-Doppler data from the radar data; encoding the cadence-velocity data to obtain a cadence-velocity feature vector using a first trained autoencoder and encoding the micro range-Doppler data to obtain a range-Doppler feature vector using a second trained autoencoder; decoding the cadence-velocity feature vector to obtain reconstructed cadence-velocity data using a first trained decoder and decoding the range-Doppler feature vector to obtain reconstructed range-Doppler data using a second trained decoder; determining first reconstruction loss information based on the cadence-velocity data and the reconstructed cadence-velocity data and determining second reconstruction loss information based on the micro range-Doppler data and the reconstructed range-Doppler data; and classifying the radar data based on the first reconstruction loss information and the second reconstruction loss information.

公开(公告)号：US20210158138A1

公开(公告)日：2021-05-27

申请号：US16691021

申请日：2019-11-21

Applicant: Infineon Technologies AG

Inventor： Souvik Hazra ,  Ashutosh Baheti ,  Avik Santra

IPC: G06N3/08 ,  G06N3/04 ,  G06F3/01 ,  G06K9/62 ,  G06K9/00 ,  G01S7/41

Abstract: A method for operating a distributed neural network having a plurality of intelligent devices and a server includes: generating, by a first intelligent device of the plurality of intelligent devices, a first output using a first neural network model running on the first intelligent device and using a first input vector to the first neural network model; outputting, by the first intelligent device, the first output; receiving, by the first intelligent device, a gesture feedback on the first output from a user; determining, by the first intelligent device, a user rating of the first output from the gesture feedback; labeling, by the first intelligent device, the first input vector with a first label in accordance with the user rating; and training, by the first intelligent device, the first neural network model using the first input vector and the first label.

公开(公告)号：US20240111040A1

公开(公告)日：2024-04-04

申请号：US17949608

申请日：2022-09-21

Applicant: Infineon Technologies AG

Inventor： Thomas Reinhold Stadelmayer ,  Kevin Kaiser ,  Souvik Hazra ,  Avik Santra

IPC: G01S13/04 ,  G01S13/89

CPC classification number: G01S13/04 ,  G01S13/89

Abstract: In an embodiment, a method includes: receiving radar digital data; processing the radar digital data with a plurality of sine filters to generate a respective plurality of range-slow-time data, where each sine filter is associated with a respective range zone of a plurality of range zones; generating a first presence score based on a first range-slow-time data of the plurality of range-slow-time data, where the first range-slow-time data is associated with the first range zone; and when the first presence score is higher than a predetermined threshold, generating a plurality of synthetic antennas based on the first range-slow-time data, performing angle estimation based on the plurality of synthetic antennas to generate first probability values for a plurality of angle zones associated with the first range zone, and updating an occupancy grid map based on the first probability values.

公开(公告)号：US20230068523A1

公开(公告)日：2023-03-02

申请号：US17886264

申请日：2022-08-11

Applicant: Infineon Technologies AG

Inventor： Avik Santra ,  Souvik Hazra ,  Thomas Reinhold Stadelmayer

IPC: G06V40/20 ,  G06V10/762 ,  G06V10/74 ,  G06V10/82

Abstract: In an embodiment, a method includes: obtaining one or more positional time spectrograms of a radar measurement of a scene comprising an object; and based on the one or more positional time spectrograms and based on a feature embedding of a variational auto-encoder neural network, predicting a gesture class of a gesture performed by the object.

公开(公告)号：US20240037908A1

公开(公告)日：2024-02-01

申请号：US17877575

申请日：2022-07-29

Applicant: Infineon Technologies AG

Inventor： Souvik Hazra ,  Avik Santra

IPC: G06V10/764 ,  G06V10/82 ,  G06V10/84 ,  G06V40/20 ,  G01S13/89

CPC classification number: G06V10/764 ,  G06V10/82 ,  G06V10/84 ,  G06V40/23 ,  G01S13/89

Abstract: In an embodiment, a method includes: receiving raw data from a millimeter-wave radar sensor; generating a first radar-Doppler image based on the raw data; generating a first radar point cloud based on the first radar-Doppler image; using a graph encoder to generate a first graph representation vector indicative of one or more relationships between two or more parts of the target based on the first radar point cloud; generating a first cadence velocity diagram indicative of a periodicity of movement of one or more parts of the target based on the first radar-Doppler image; and classifying an activity of a target based on the first graph representation vector and the first cadence velocity diagram.

公开(公告)号：US20230393240A1

公开(公告)日：2023-12-07

申请号：US18317749

申请日：2023-05-15

Applicant: Infineon Technologies AG

Inventor： Lorenzo Servadei ,  Souvik Hazra ,  Julius Ott ,  Avik Santra ,  Huawei Sun ,  Michael Stephan

IPC: G01S7/41 ,  G01S13/58

CPC classification number: G01S7/417 ,  G01S13/584 ,  G01S7/415

Abstract: In accordance with an embodiment, a method includes estimating a people count of one or more persons included in the scene based on a first range-Doppler measurement map and the second range-Doppler measurement map derived from a radar measurement dataset. Estimating the people count includes inputting the first range-Doppler measurement map into a first data processing pipeline of a neural network algorithm, and inputting the second range-Doppler measurement map into a second data processing pipeline of the neural network algorithm. The first data processing pipeline and the second data processing pipeline includes range-Doppler convolutional layers implementing two-dimensional convolutions along the range dimension and the Doppler dimension, and the neural network algorithm includes an output section for processing a combination of a first output of the first data processing pipeline and a second output of the second data processing pipeline in a regression block.

公开(公告)号：US11640208B2

公开(公告)日：2023-05-02

申请号：US16691021

申请日：2019-11-21

Applicant: Infineon Technologies AG

Inventor： Souvik Hazra ,  Ashutosh Baheti ,  Avik Santra

IPC: G06N3/08 ,  G06N3/04 ,  G01S7/41 ,  G06K9/62 ,  G06F3/01 ,  G06V40/20 ,  G06V10/82

Abstract: A method for operating a distributed neural network having a plurality of intelligent devices and a server includes: generating, by a first intelligent device of the plurality of intelligent devices, a first output using a first neural network model running on the first intelligent device and using a first input vector to the first neural network model; outputting, by the first intelligent device, the first output; receiving, by the first intelligent device, a gesture feedback on the first output from a user; determining, by the first intelligent device, a user rating of the first output from the gesture feedback; labeling, by the first intelligent device, the first input vector with a first label in accordance with the user rating; and training, by the first intelligent device, the first neural network model using the first input vector and the first label.