Systems for estimating three-dimensional trajectories of physical objects
In implementations of systems for estimating three-dimensional trajectories of physical objects, a computing device implements a three-dimensional trajectory system to receive radar data describing millimeter wavelength radio waves directed within a physical environment using beamforming and reflected from physical objects in the physical environment. The three-dimensional trajectory system generates a cloud of three-dimensional points based on the radar, each of the three-dimensional points corresponds to a reflected millimeter wavelength radio wave within a sliding temporal window. The three-dimensional points are grouped into at least one group based on Euclidean distances between the three-dimensional points within the cloud. The three-dimensional trajectory system generates an indication of a three-dimensional trajectory of a physical object corresponding to the at least one group using a Kalman filter to track a position and a velocity a centroid of the at least one group in three-dimensions.
1. A method comprising:
receiving, by a processing device, radar data describing millimeter wavelength radio waves transmitted using beamforming that reflect from physical objects in a physical environment;
generating, by the processing device, a cloud of three-dimensional points corresponding to reflected millimeter wavelength radio waves by grouping the three-dimensional points from the radar data using density-based spatial clustering;
determining, by the processing device, velocities of the three-dimensional points;
generating, by the processing device, a moving cloud of three-dimensional points by removing three-dimensional points having velocities below a threshold velocity from the cloud of the three-dimensional points and by removing three-dimensional points moving in a different direction than other points from the cloud of the three-dimensional points, the moving cloud of the three-dimensional points having a centroid;
determining, by the processing device, a change in position of the centroid of the moving cloud of the three-dimensional points from a first three-dimensional position to a second three-dimensional position; and
identifying, by the processing device, a three-dimensional trajectory of a physical object based on a path indicating the change in the position of the centroid of the moving cloud of the three-dimensional points from the first three-dimensional position to the second three-dimensional position.
2. The method of claim 1 , wherein the moving cloud of the three-dimensional points corresponds to the physical object.
3. The method of claim 2 , further comprising using a Kalman filter to track the position of the moving cloud of the three-dimensional points in an x-plane, a y-plane, and a z-plane.
4. The method of claim 1 , further comprising filtering out reflected radio waves received outside of a sliding temporal window from the radar data.
5. The method of claim 1 , further comprising generating an indication of the three-dimensional trajectory of the physical object for display in a user interface.
6. The method of claim 5 , wherein the indication of the three-dimensional trajectory is displayed relative to a three-dimensional representation of the physical environment.
7. The method of claim 1 , wherein the three-dimensional trajectory of the physical object is a path followed by the physical object moving through the physical environment.
8. The method of claim 1 , further comprising determining a velocity of the physical object by performing a doppler fast Fourier transform.
9. The method of claim 1 , further comprising identifying a static object in the physical environment corresponding to the three-dimensional points having the velocities below the threshold velocity.
10. The method of claim 1 , further comprising presenting the three-dimensional trajectory of the physical object in an augmented reality environment.
11. The method of claim 1 , further comprising identifying three-dimensional points having a different trajectory than the three-dimensional trajectory of the physical object.
12. The method of claim 11 , further comprising identifying a second three-dimensional trajectory of a second physical object based on the three-dimensional points having the different trajectory.
13. A system comprising:
a memory component; and
a processing device to perform operations comprising:
generating radar data by transmitting millimeter wavelength radio waves using beamforming that reflect from physical objects in a physical environment;
generating a cloud of three-dimensional points, each three-dimensional point corresponding to reflected millimeter wavelength radio wave by grouping the three-dimensional points from the radar data using density-based spatial clustering;
determining, by the processing device, velocities of the three-dimensional points;
generating, by the processing device, a moving cloud of three-dimensional points by removing three-dimensional points having velocities below a threshold velocity from the cloud of the three-dimensional points and by removing three-dimensional points moving in a different direction than other points from the cloud of the three-dimensional points, the moving cloud of the three-dimensional points having a centroid;
determining a change in position of the moving cloud of the three-dimensional points from a first three-dimensional position to a second three-dimensional position; and
tracking a position of a physical object based on a path indicating the change in position of the centroid of the moving cloud of the three-dimensional points from the first three-dimensional position to the second three-dimensional position.
14. The system of claim 13 , wherein the moving cloud of the three-dimensional points corresponds to the physical object.
15. The system of claim 13 , further comprising using a Kalman filter to track the position of the moving cloud of the three-dimensional points in an x-plane, a y-plane, and a z-plane.
16. The system of claim 13 , further comprising filtering out reflected radio waves received outside of a sliding temporal window from the radar data.
17. The system of claim 13 , further comprising generating an indication of a three-dimensional trajectory of the physical object for display in a user interface.
18. A non-transitory computer-readable storage medium storing executable instructions, which when executed by a processing device, cause the processing device to perform operations comprising:
receiving radar data describing millimeter wavelength radio waves transmitted using beamforming that reflect from physical objects in a physical environment;
generating a cloud of three-dimensional points corresponding to reflected millimeter wavelength radio waves by grouping the three-dimensional points from the radar data using density-based spatial clustering;
determining, by the processing device, velocities of the three-dimensional points;
generating, by the processing device, a moving cloud of three-dimensional points by removing three-dimensional points having velocities below a threshold velocity from the cloud of the three-dimensional points and by removing three-dimensional points moving in a different direction than other points from the cloud of the three-dimensional points, the moving cloud of the three-dimensional points having a centroid;
determining a change in position of the centroid of the moving cloud of the three-dimensional points from a first three-dimensional position to a second three-dimensional position; and
identifying a three-dimensional trajectory of a physical object based on a path indicating the change in the position the centroid of the moving cloud of the three-dimensional points from the first three-dimensional position to the second three-dimensional position.
19. The non-transitory computer-readable storage medium of claim 18 , wherein the moving cloud of the three-dimensional points corresponds to the physical object.
20. The non-transitory computer-readable storage medium of claim 18 , further comprising filtering out reflected radio waves received outside of a sliding temporal window from the radar data.