Method for disambiguating ambiguous detections in sensor fusion systems
US-2020142026-A1 · May 7, 2020 · US
US11454716B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11454716-B2 |
| Application number | US-201916730759-A |
| Country | US |
| Kind code | B2 |
| Filing date | Dec 30, 2019 |
| Priority date | Dec 30, 2019 |
| Publication date | Sep 27, 2022 |
| Grant date | Sep 27, 2022 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Systems, methods, and non-transitory computer-readable media provide an adaptive gating mechanism for radar tracking initialization. Specifically, the radar system obtains measurement data of target points, and then determines, based on the measured position and dopplers of points in the first few scans, whether the doppler and displacement parameters satisfy an initialization constraint. When the initialization constraint is not satisfied, the radar system flags the respective cluster with an initialization flag, and adaptively uses the measured position and doppler of scanned points to determine the gating size for the next scan, instead of using a fixed gate size. When the initialization flag of the same cluster across a few consecutive scans satisfies a combination logic, the radar system determines that the tracking enters into the association stage, e.g., the radar system formally generates a track for the target points along a series of scans.
Opening claim text (preview).
What is claimed is: 1. A method of adaptive gating for tracking a target over multiple sensor data scans, the method comprising: obtaining, by a sensor unit associated with a vehicle, first sensor data relating to at least one target point captured at a first time using a first gating size; determining, from the first sensor data, a first movement parameter associated with the at least one target point; adaptively determining a second gating size based at least in part on the first movement parameter, including computing a Doppler change and a displacement for the target point between a first location of a current time step and a prior location from a previous time step to determine a tracking initialization condition that controls whether tracking of the target point may enter an association stage from an initialization stage; and obtaining, by the sensor unit, second sensor data captured at a second time using the second gating size. 2. The method of claim 1 , wherein adaptively determining the second gating size includes computing the second gating size using the displacement and the Doppler change, wherein the determining the first movement parameter associated with the one target point comprises: determining a first set of coordinates representing a first location of the one target point at the first time; and determining a first Doppler velocity representing a velocity that the one target point is traveling at the first time. 3. The method of claim 2 , wherein the adaptively determining the second gating size based at least in part on the first movement parameter comprises: retrieving a previously stored set of coordinates representing a prior location of the one target point at a time prior to the first time, and a previously stored Doppler velocity representing a velocity that the one target was traveling at the time prior to the first time; computing the displacement between the first location and the prior location based on the first set of coordinates and the previously stored set of coordinates; computing the Doppler change based on a difference between the first Doppler velocity and the previously stored Doppler velocity; and computing a weighed sum of the displacement and the Doppler change as the second gating size. 4. The method of claim 1 , wherein determining whether tracking enters the association stage includes: determining whether the tracking initialization condition is satisfied based at least in part on the first movement parameter by: comparing the displacement to a sum of a first Doppler velocity weighted by a first pre-defined constant and a second pre-defined constant. 5. The method of claim 3 , further comprising: determining whether the tracking initialization condition is satisfied based at least in part on the first movement parameter by: determining whether the Doppler change is less than or equal to a third pre-defined constant. 6. The method of claim 1 , further comprising: in response to determining that the tracking initialization condition has been satisfied for a series of sensor data captured at a minimum number of consecutive times including the first time, or that the tracking initialization condition has been satisfied for at least a minimum percentage of sensor data captured during a period of time including the first time: determining that the initialization stage is completed; and monitoring the at least one target point starting from the second sensor data to form the track of target points. 7. The method of claim 6 , further comprising: in response to determining that the initialization stage is complete: computing the second gating size based on Kalman filter. 8. The method of claim 7 , wherein the computing the second gating size based on the Kalman filter comprises: generating an elliptical gate based on eccentricity of data points at the first time for capturing the second sensor data. 9. The method of claim 8 , further comprising: terminating the track of target points in response to determining that: observation of a predicted target point has been missed from the generated elliptical gate for at least a minimum number of consecutive times. 10. The method of claim 6 , further comprising: in response to determining that the tracking initialization condition is not satisfied for at least a maximum number of consecutive times, terminating initialization of the track. 11. A system comprising: one or more non-transitory computer-readable storage media embodying instructions; and one or more processors coupled to the storage media and operable to execute the instructions to: obtain, by a sensor unit placed on a vehicle, first sensor data relating to at least one target point captured at a first time using a first gating size, while the vehicle is traveling along a route; determine, from the first sensor data, a first movement parameter associated with the one target point; adaptively determine a second gating size based at least in part on the first movement parameter, including computing a Doppler change and a displacement for the target point between a first location of a current time step and a prior location from a previous time step to determine a tracking initialization condition that controls whether tracking of the target point may enter an association stage from an initialization stage; and obtain, by the sensor unit placed on the vehicle, second sensor data captured at a second time using the second gating size. 12. The system of claim 11 , wherein the one or more processors are operable to execute the instructions to: adaptively determine the second gating size by computing the second gating size using the displacement and the Doppler change, and determine the first movement parameter associated with the one target point by: determining a first set of coordinates representing a first location of the one target point at the first time; and determining a first Doppler velocity representing a velocity that the one target point is traveling at the first time. 13. The system of claim 12 , wherein the one or more processors are operable to execute the instructions to adaptively determine the second gating size based at least in part on the first movement parameter by: retrieving a previously stored set of coordinates representing a prior location of the one target point at a time prior to the first time, and a previously stored Doppler velocity representing a velocity that the one target was traveling at the time prior to the first time; computing the displacement between the first location and the prior location based on the first set of coordinates and the previously stored set of coordinates; computing the Doppler change based on a difference between the first Doppler velocity and the previously stored Doppler velocity; and computing a weighed sum of the displacement and the Doppler change as the second gating size. 14. The system of claim 13 , wherein the one or more processors are operable to execute the instructions to determine whether the tracking initialization condition is satisfied based at least in part on the first movement parameter by: determining whether the displacement is less than or equal to a sum of the first Doppler velocity weighted by a first pre-defined constant and a second pre-defined constant. 15. The system of claim 13 , wherein the one or more processors are operable to execute the instructions to determine whether the tracking initialization condition is satisfied based at least in part on the first movement parameter by: determining whether the Doppler change is les
Related publications grouped by family.
Answers are generated from the same data shown on this page.