Radar super resolution
AssigneesDENSO International America, Inc., Denso Corporation, Carnegie Mellon University
InventorsShawn Hunt, Matthew O'Toole, Kris Kitani, Yu-Jhe Li
Life of this patent
Estimating the term…
Abstract
Systems, methods, and other embodiments described herein relate to improving radar data. In one embodiment, a method includes, responsive to acquiring radar data from a radar sensor, transforming the radar data into improved data according to a super-resolution model. The method includes converting the improved data into a range-azimuth-Doppler map. The method includes generating a high-resolution map from the range-azimuth-Doppler map by applying the super-resolution model to the range-azimuth-Doppler map. The method includes providing the high-resolution map.
Claims14
A radar system for improving radar data, comprising:
- one or more processors;
- a memory communicably coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the one or more processors to:
- responsive to acquiring the radar data from a radar sensor, transform the radar data into improved data according to a first path of a super-resolution model for super-resolving the radar data that is raw digital data from the radar sensor, wherein the instructions to transform the radar data include instructions to apply a convolutional network in combination with three-dimensional (3D) pixel shuffling to super-resolve the improved data;
- convert the improved data into a range-azimuth-Doppler (RAD) map;
- generate a high-resolution map from the RAD map by applying a second path of the super-resolution model to the RAD map for super-resolving the RAD map into the high-resolution map;
- and
- provide the high-resolution map.
A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:
- responsive to acquiring radar data from a radar sensor, transform the radar data into improved data according to a first path of a super-resolution model for super-resolving the radar data that is raw digital data from the radar sensor, wherein the instructions to transform the radar data include instructions to apply a convolutional network in combination with three-dimensional (3D) pixel shuffling to super-resolve the improved data;
- convert the improved data into a range-azimuth-Doppler (RAD) map;
- generate a high-resolution map from the RAD map by applying a second path of the super-resolution model to the RAD map for super-resolving the RAD map into the high-resolution map;
- and
- provide the high-resolution map.
A method, comprising:
- responsive to acquiring radar data from a radar sensor, transforming the radar data into improved data according to a first path of a super-resolution model for super-resolving the radar data that is raw digital data from the radar sensor, including applying a convolutional network in combination with three-dimensional (3D) pixel shuffling to super-resolve the improved data;
- converting the improved data into a range-azimuth-Doppler (RAD) map;
- generating a high-resolution map from the RAD map by applying a second path of the super-resolution model to the RAD map for super-resolving the RAD map into the high-resolution map;
- and
- providing the high-resolution map.
Dependencies are inferred from the claim text.