Back to results
US 12,529,777 B2Granted
Radar-based motion classification using one or more time series
AssigneeInfineon Technologies AG
InventorsThomas Reinhold Stadelmayer, Avik Santra
Life of this patent
Estimating the term…
Abstract
In accordance with an embodiment, a computer-implemented method includes obtaining a time sequence of measurement frames of a radar measurement of a scene comprising an object; based on multiple subsequent measurement frames of the time sequence of measurement frames, determining one or more one-dimensional (1-D) time series of respective observables of the radar measurement associated with the object; and based on the one or more 1-D time series, determining a motion class of a motion performed by the object using a classification algorithm.
Claims21
A computer-implemented method, the method comprising:
- obtaining a time sequence of measurement frames of a radar measurement of a scene comprising an object, wherein each measurement frame of the time sequence of measurement frames comprises data samples along a fast-time dimension, a slow-time dimension, and a channel dimension, a slow time of the slow-time dimension being incremented with respect to adjacent radar chirps of the radar measurement, a fast time of the fast-time dimension being incremented with respect to adjacent data samples, a channel of the channel dimension being incremented for different receiver antennas used for the radar measurement;
- based on multiple subsequent measurement frames of the time sequence of measurement frames, determining one or more one-dimensional (1-D) time series of respective observables of the radar measurement associated with the object, wherein determining the one or more 1-D time series comprises using only time-domain signal processing, and at least one 1-D time series of the one or more 1-D time series is indicative of at least one angular position of the object;
- and
- based on the one or more 1-D time series, determining a motion class of a motion performed by the object using a classification algorithm.
1 more element
A millimeter-wave radar system comprising:
- a millimeter-wave radar sensor configured to transmit radar signals, receive reflected radar signals, and generate radar digital data based on the reflected radar signals;
- and
- a processing system configured to:
- obtain a time sequence of measurement frames of a radar measurement of a scene comprising an object from the radar digital data, wherein each measurement frame of the time sequence of measurement frames comprises data samples along a fast-time dimension, a slow-time dimension, and a channel dimension, a slow time of the slow-time dimension being incremented with respect to adjacent radar chirps of the radar measurement, a fast time of the fast-time dimension being incremented with respect to adjacent data samples, a channel of the channel dimension being incremented for different receiver antennas used for the radar measurement,
- based on multiple subsequent measurement frames of the time sequence of measurement frames, determine one or more one-dimensional (1-D) time series of respective observables of the radar measurement associated with the object, wherein determining the one or more 1-D time series comprises using only time-domain signal processing, and at least one 1-D time series of the one or more 1-D time series is indicative of at least one angular position of the object, and
- based on the one or more 1-D time series, determine a motion class of a motion performed by the object using a classification algorithm.
3 more elements
A method comprising:
- obtaining a time sequence of measurement frames of a radar measurement of a scene comprising an object;
- applying a plurality of complex-valued bandpass filters to the radar measurement along a fast-time dimension to produce a corresponding plurality of complex-valued time-domain signals resolved along a slow-time dimension;
- determining at least one phase difference between the plurality of complex-valued time-domain signals to determine an angular position of the object;
- and
- determining a class of motion performed by the object based on the plurality of complex-valued time-domain signals and the determined angular position.
2 more elements
Dependencies are inferred from the claim text.