IP Library Granted Patent US 10,072,933
Granted Patent B1
US 10,072,933 · App. 15/481,379 · Granted Sep 11, 2018

Decoupling of accelerometer signals

Inventor: Gabriela Surpi (San Diego, CA)
Assignee: Lytx, Inc.
G01C21/165G01S19/47G05B13/024
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,072,933
App. No.
15/481,379
Granted
Sep 11, 2018
Kind
B1
Abstract

A system for decoupling accelerometer signals includes an interface and a processor. The interface is configured to receive accelerometer data and receive coarse behavior data. The processor is configured to determine a coarse acceleration based at least in part on the coarse behavior data, determine a perturbation acceleration using the coarse acceleration and the accelerometer data, and determine an anomalous event based at least in part on the perturbation acceleration.

Claims (38)

1. A system for decoupling accelerometer signals, comprising:

an interface configured to:

receive accelerometer data; and

receive coarse behavior data; and

a processor configured to:

determine a coarse acceleration based at least in part on the coarse behavior data;

determine a perturbation acceleration using the coarse acceleration and the accelerometer data; and

determine an anomalous event based at least in part on the perturbation acceleration.

2. The system of claim 1 , wherein the coarse behavior data comprises GPS data.

3. The system of claim 1 , wherein the coarse behavior data comprises speedometer data.

4. The system of claim 1 , wherein the coarse behavior data comprises gyroscope data.

5. The system of claim 1 , wherein determining the coarse acceleration based at least in part on the coarse behavior data comprises taking a first derivative of the coarse behavior data.

6. The system of claim 1 , wherein determining the coarse acceleration based at least in part on the coarse behavior data comprises taking a second derivative of the coarse behavior data.

7. The system of claim 1 , wherein determining the coarse acceleration based at least in part on the coarse behavior data comprises filtering the coarse behavior data.

8. The system of claim 1 , wherein determining the coarse acceleration based at least in part on the coarse behavior data comprises changing a sample rate of the coarse behavior data.

9. The system of claim 1 , wherein determining the coarse acceleration based at least in part on the coarse behavior data comprises scaling the coarse behavior data.

10. The system of claim 9 , wherein the processor is further configured to determine a scaling factor.

11. The system of claim 1 , wherein determining the coarse acceleration based at least in part on the coarse behavior data comprises aligning the coarse behavior data in a time axis using one or multiple reference points.

12. The system of claim 1 , wherein determining the perturbation acceleration using the coarse acceleration comprises subtracting the coarse acceleration from the accelerometer data.

13. The system of claim 1 , wherein determining the anomalous event based at least in part on the perturbation acceleration comprises determining that a magnitude of the perturbation acceleration crosses an anomaly threshold value.

14. The system of claim 1 , wherein determining the anomalous event based at least in part on the perturbation acceleration comprises analyzing the perturbation acceleration to determine a noisy perturbation component.

15. The system of claim 14 , wherein the processor is further configured to determine an anomaly threshold value based at least in part on the noisy perturbation component.

16. The system of claim 14 , wherein determining the anomalous event based at least in part on the perturbation acceleration comprises subtracting the noisy perturbation component from the perturbation acceleration.

17. The system of claim 1 , wherein determining the anomalous event based at least in part on the perturbation acceleration comprises analyzing the perturbation acceleration using a machine learning model.

18. The system of claim 1 , wherein the accelerometer data and the coarse behavior data comprise forward motion data.

19. The system of claim 1 , wherein the accelerometer data and the coarse behavior data comprise lateral motion data.

20. A method for decoupling accelerometer signals, comprising:

receiving accelerometer data;

receiving coarse behavior data;

determining, using a processor, a coarse acceleration based at least in part on the coarse behavior data;

determining a perturbation acceleration using the coarse acceleration and the accelerometer data; and

determining an anomalous event based at least in part on the perturbation acceleration.

21. A computer program product for decoupling accelerometer signals, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

receiving accelerometer data;

receiving coarse behavior data;

determining a coarse acceleration based at least in part on the coarse behavior data;

determining a perturbation acceleration using the coarse acceleration and the accelerometer data; and

determining an anomalous event based at least in part on the perturbation acceleration.

Assignments (2)
PATENT SECURITY AGREEMENT Recorded Feb 28, 2020
From: LYTX, INC.
To: GUGGENHEIM CREDIT SERVICES, LLC
Reel/Frame 052050/0099 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 12, 2017
From: SURPI, GABRIELA
To: LYTX, INC.
Reel/Frame 042364/0520 →
Cited By (3)
US 12,375,876 US 12,397,785 US 12,444,306