公开(公告)号：US12032089B2

公开(公告)日：2024-07-09

申请号：US16923916

申请日：2020-07-08

申请人： Infineon Technologies AG

发明人： Paul Meissner ,  Franz Pernkopf ,  Johanna Rock ,  Wolfgang Roth ,  Mate Andras Toth

IPC分类号： G01S7/295 ,  G01S7/02 ,  G01S7/282 ,  G01S7/41 ,  G01S13/02 ,  G06N3/063 ,  G06N3/08 ,  G06N3/084 ,  G06N5/04 ,  G06N5/046 ,  G01S7/35 ,  G01S13/34 ,  G01S13/44 ,  G01S13/58 ,  G01S13/931 ,  G06N3/045

CPC分类号： G01S7/023 ,  G01S7/282 ,  G01S7/295 ,  G01S7/417 ,  G01S13/02 ,  G06N3/063 ,  G06N3/084 ,  G06N5/046 ,  G01S7/352 ,  G01S7/354 ,  G01S7/356 ,  G01S13/343 ,  G01S13/4454 ,  G01S13/584 ,  G01S13/931 ,  G06N3/045

摘要： A radar device may include a radar receiver to receive a radio frequency (RF) radar signal and generate a digital signal based on the RF radar signal. The digital signal may comprise a plurality of signal segments. The radar device may include a neural network comprising a plurality of layers to process the plurality of signal segments. Each layer of the plurality of layers may have one or more neurons. The plurality of layers may process the plurality of signal segments using weighting factors having values selected from a predetermined set of discrete values. At least one neuron in an output layer of the plurality of layers may provide an output value that indicates whether a respective signal segment or a sample, associated with the at least one neuron, is overlaid with an interfering signal.

公开(公告)号：US11907829B2

公开(公告)日：2024-02-20

申请号：US17121295

申请日：2020-12-14

申请人： Infineon Technologies AG

发明人： Paul Meissner ,  Franz Pernkopf ,  Johanna Rock ,  Wolfgang Roth ,  Mate Andras Toth ,  Alexander Fuchs

IPC分类号： G06N3/063 ,  G06N3/04 ,  G01S7/41 ,  G01S7/35 ,  G06N3/048 ,  G01S13/58 ,  G06N3/084 ,  G01S7/02 ,  G06N3/045 ,  G01S13/34 ,  G01S13/44 ,  G01S13/931

CPC分类号： G06N3/063 ,  G01S7/417 ,  G06N3/04 ,  G01S7/023 ,  G01S7/352 ,  G01S7/354 ,  G01S7/356 ,  G01S13/343 ,  G01S13/4454 ,  G01S13/584 ,  G01S13/931 ,  G06N3/045 ,  G06N3/048 ,  G06N3/084

摘要： A radar device may include a radar transmitter to output a radio frequency (RF) transmission signal including a plurality of frequency-modulated chirps. The radar device may include a radar receiver to receive an RF radar signal, and generate, based on the RF radar signal, a dataset including a set of digital values, the dataset being associated with a chirp or a sequence of successive chirps. The radar device may include a neural network to filter the dataset to reduce an interfering signal included in the dataset, the neural network being a convolutional neural network. At least one layer of the neural network may be a complex-valued neural network layer includes complex-valued weighting factor, where the complex-valued neural network layer is configured to perform one or more operations according to a complex-valued computation.