Radar detection and classification using an auto regressive spectral estimator with machine learning
AssigneeElta Systems Ltd.
InventorArie AMARA
Life of this patent
Estimating the term…
Abstract
A processing circuitry-based method of detecting radar targets, comprising: receiving a series of radar pulse measurements; generating an autoregressive (AR) spectral estimation, of a given order, from the received data, thereby resulting in two or more complex coefficients of an estimated AR model; utilizing the two or more complex coefficients as input to one or more trained machine learning models, thereby resulting in, at least: an indication of presence or absence of a target, and responsive to presence of the target: a distance, an energy, and a velocity of the target, the one or more models having been trained to receive data derivative of complex coefficients and output data informative of target depth, energy, and velocity.
Claims13
A processing circuitry-based method of detecting radar targets, the processing circuitry-based method comprising:
- a) receiving data derivative of a series of radar pulse measurements;
- b) generating an autoregressive (AR) spectral estimation, of a given order, from the received data, thereby resulting in two or more complex coefficients of an estimated AR model;
- c) utilizing data derivative of the two or more complex coefficients as input to one or more trained machine learning models, thereby resulting in, at least:
- a. an indication of presence or absence of a target, and
- b. responsive to presence of the target:
- a distance, an energy, and a velocity of the target,
- the one or more models having been trained to receive data derivative of complex coefficients and output data informative of target depth, energy, and velocity.
A system of detecting radar targets, the system comprising:
- a processing circuitry configured to:
- a) receive data derivative of a series of radar pulse measurements;
- b) generate an autoregressive (AR) spectral estimation, of a given order, from the received data, thereby resulting in two or more complex coefficients of an estimated AR model;
- c) utilize data derivative of the two or more complex coefficients as input to one or more trained machine learning models, thereby resulting in, at least:
- a. an indication of presence or absence of a target, and
- b. responsive to presence of the target:
- a distance, an energy, and a velocity of the target,
- the one or more models having been trained to receive data derivative of complex coefficients and output data informative of target depth, energy, and velocity.
A computer program product comprising a computer readable non-transitory storage medium containing program instructions, which program instructions when read by a processor, cause the processing circuitry to perform a method of detecting radar targets, the method comprising:
- a) receiving data derivative of a series of radar pulse measurements;
- b) generating an autoregressive (AR) spectral estimation, of a given order, from the received data, thereby resulting in two or more complex coefficients of an estimated AR model;
- c) utilizing data derivative of the two or more complex coefficients as input to one or more trained machine learning models, thereby resulting in, at least:
- a. an indication of presence or absence of a target, and
- b. responsive to presence of the target:
- a distance, an energy, and a velocity of the target,
- the one or more models having been trained to receive data derivative of complex coefficients and output data informative of target depth, energy, and velocity.
Dependencies are inferred from the claim text.