In-vehicle motion identification with ultrawideband radar
A computer includes a processor and a memory, the memory storing instructions executable by the processor to receive radar data from an ultrawideband radar in a passenger compartment of a vehicle, determine a starting-time for a time-window based on a second derivative of the radar data, identify a motion inside the passenger compartment based on the radar data received during the time-window, and actuate a component of the vehicle based on the identification of the motion.
1 . A computer comprising a processor and a memory, the memory storing instructions executable by the processor to:
receive radar data from an ultrawideband radar in a passenger compartment of a vehicle;
set a first starting-time for a first time-window in real time based on a second derivative of fast time in the radar data with respect to slow time in the radar data;
identify a motion inside the passenger compartment based on the radar data received during the first time-window and based on the radar data received during a second time-window, the second time-window starting at an ending time of the first time-window; and
actuate a component of the vehicle based on the identification of the motion.
2 . The computer of claim 1 , wherein the instructions further include instructions to refrain from using the radar data received before the first starting-time to identify the motion inside the passenger compartment.
3 . The computer of claim 1 , wherein the instructions further include instructions to convert the radar data received during the first time-window to a frequency domain, and identify the motion in the passenger compartment based on the radar data in the frequency domain.
4 . The computer of claim 3 , wherein the instructions further include instructions to convert the radar data received during the first time-window to the frequency domain by applying a fast Fourier transform.
5 . The computer of claim 1 , wherein the first time-window has a preset duration.
6 . The computer of claim 1 , wherein the instructions further include instructions to apply a filter to the radar data, and the second derivative is of the radar data after the application of the filter.
7 . The computer of claim 6 , wherein the filter is a smoothing filter.
8 . The computer of claim 6 , wherein the filter is a bandpass filter isolating frequencies for human respiration.
9 . The computer of claim 1 , wherein the instructions further include instructions to, in response to the second derivative being below a threshold amount for at least a threshold duration, refrain from using the radar data received after a current time-window to identify the motion inside the passenger compartment.
10 . The computer of claim 1 , wherein the instructions further include instructions to classify the motion as a type of animate bulk motion based on the radar data received during the first time-window.
11 . The computer of claim 10 , wherein the instructions further include instructions to classify the motion as a type of animate bulk motion by executing a neural network classifier with the radar data received during the first time-window as an input.
12 . The computer of claim 1 , wherein the instructions further include instructions to identify a number of respirating individuals based on the radar data received during the first time-window.
13 . The computer of claim 1 , wherein the instructions further include instructions to command a user interface to output an alert to an occupant of the passenger compartment based on the identification of the motion.
14 . A method comprising:
receiving radar data from an ultrawideband radar in a passenger compartment of a vehicle;
setting a first starting-time for a first time-window in real time based on a second derivative of fast time in the radar data with respect to slow time in the radar data;
identifying a motion inside the passenger compartment based on the radar data received during the first time-window and based on the radar data received during a second time-window, the second time-window starting at an ending time of the first time-window; and
actuating a component of the vehicle based on the identification of the motion.
15 . The method of claim 14 , further comprising refraining from using the radar data received before the first starting-time to identify the motion inside the passenger compartment.
16 . The method of claim 14 , further comprising converting the radar data received during the first time-window to a frequency domain, and identifying the motion in the passenger compartment based on the radar data in the frequency domain.
17 . The method of claim 14 , further comprising commanding a user interface to output an alert to an occupant of the passenger compartment based on the identification of the motion.
18 . The computer of claim 1 , wherein the instructions to set the first starting-time include instructions to, in real time, set the first starting-time to a time at which the second derivative of the fast time with respect to the slow time exceeds a threshold.
19 . The method of claim 14 , wherein setting the first starting-time includes, in real time, setting the first starting-time to a time at which the second derivative of the fast time with respect to the slow time exceeds a threshold.