System and method for identifying a target using radar sensors
AssigneeInfineon Technologies AG
InventorsSaverio Trotta, Ashutosh Baheti, Reinhard-Wolfgang Jungmaier, Avik Santra
Life of this patent
Estimating the term…
Abstract
In accordance with an embodiment, a method of recognizing a biological target includes performing radar measurements for a plurality of sites on the biological target using a millimeter-wave radar sensor, producing a target data set for the plurality of sites based on the radar measurements, extracting features from the target data set, comparing the extracted features to stored features, and determining whether the extracted features match the stored features based on the comparing.
Claims22
A method of recognizing a biological target, the method comprising:
- performing radar measurements for a plurality of sites on the biological target using a millimeter-wave radar sensor;
- producing a target data set for the plurality of sites based on the radar measurements;
- extracting features from the target data set;
- producing a set of stored features comprising:
- performing a set of reference radar measurements for a plurality of reference sites on the biological target using the millimeter-wave radar sensor,
- producing a training data set for the plurality of reference sites based on the reference radar measurements, and
- forming the stored features based on the training data set;
- comparing the extracted features to the stored features;
- and
- determining whether the extracted features match the stored features based on the comparing.
A system comprising:
- a processing system configured to be coupled to a millimeter-wave radar sensor, the processing system configured to
- receive radar measurements for a plurality of sites of a biological target from the millimeter-wave radar sensor;
- produce a target data set for the plurality of sites based on the radar measurements performed by the millimeter-wave radar sensor;
- extract features from the target data set;
- produce a set of stored features by:
- receiving a set of reference radar measurements for a plurality of reference sites on the biological target from the millimeter-wave radar sensor,
- producing a training data set for the plurality of reference sites based on the reference radar measurements, and
- forming the stored features based on the training data set, wherein forming the stored features comprises iteratively adjusting the forming of the stored features using a machine learning algorithm;
- compare the extracted features to stored features;
- and
- determine whether the extracted features match the stored features based on the comparing.
A non-transitory computer readable storage medium with an executable program stored thereon, the executable program including instructions to:
- receive radar measurements for a plurality of sites of a biological target from a millimeter-wave radar sensor;
- produce a target data set for the plurality of sites based on the radar measurements performed by the millimeter-wave radar sensor;
- extract features from the target data set;
- produce a set of stored features by:
- receiving a set of reference radar measurements for a plurality of reference sites on the biological target from the millimeter-wave radar sensor,
- producing a training data set for the plurality of reference sites based on the reference radar measurements, and
- forming the stored features based on the training data set, wherein forming the stored features comprises iteratively adjusting the forming of the stored features using a machine learning algorithm;
- compare the extracted features to stored features;
- and
- determine whether the extracted features match the stored features based on the comparing.
Dependencies are inferred from the claim text.