Pattern recognition used to characterize LIDAR window obstruction

Patent metadata

Field	Value
Publication number	US-12019186-B2
Application number	US-202016829125-A
Country	US
Kind code	B2
Filing date	Mar 25, 2020
Priority date	Sep 26, 2017
Publication date	Jun 25, 2024
Grant date	Jun 25, 2024

Abstract

In some embodiments, a LIDAR system may include at least one processor configured to control at least one light source for projecting light toward a field of view and receive from at least one first sensor first signals associated with light projected by the at least one light source and reflected from an object in the field of view, wherein the light impinging on the at least one first sensor is in a form of a light spot having an outer boundary. The processor may further be configured to receive from at least one second sensor second signals associated with light noise, wherein the at least one second sensor is located outside the outer boundary; determine, based on the second signals received from the at least one second sensor, an indicator of a magnitude of the light noise; and determine, based on the indicator the first signals received from the at least one first sensor and, a distance to the object.

First claim

What is claimed is:

1. A LIDAR system for projecting light through a protective window associated with the LIDAR system, the system comprising:
at least one processor configured to:
control at least one LIDAR light source to emit a light pulse;
receive a reflection signal from at least one sensor, wherein the at least one sensor detects the received reflection signal over a period of time, wherein the period of time is longer than a duration of the emitted light pulse, and wherein the received reflection signal includes indications of at least one of: light reflected from the protective window, and light reflected from objects in the field of view and passing through the protective window prior to reaching the at least one sensor;
access stored information characterizing a known internal reflection signal of the LIDAR system, wherein the known internal reflection signal includes information characterizing a known obstruction on or in the protective window;
compare a temporal amplitude profile of the received reflection signal with a temporal amplitude profile of the known internal reflection signal, wherein the temporal amplitude profile of the received reflection signal represents light intensity of the received reflection signal relative to the period of time;
based on the comparison, determine a presence and a type of an obstruction of the protective window; and
output information indicative of the presence and the type of the obstruction.

2. The LIDAR system of claim 1 , wherein the at least one processor is further configured to:
detect, based on the received reflection signal, a particular obstruction pattern at least partially obstructing light passage through the protective window;
access stored information characterizing reference obstruction patterns for at least one of: salt, mud, road grime, snow, rain, dust, bug debris, pollen, and bird droppings;
compare the detected obstruction pattern with the reference obstruction patterns by applying at least one pattern recognition algorithm in order to determine a likely obstruction-pattern match; and
based on the likely match, output information indicative of the match.

3. The LIDAR system of claim 2 , wherein the at least one pattern recognition algorithm includes a temporal pattern analysis of the detected obstruction pattern.

4. The LIDAR system of claim 2 , wherein the at least one pattern recognition algorithm includes a spatial pattern analysis of the detected obstruction pattern.

5. The LIDAR system of claim 2 , wherein the at least one processor is configured to use indications of light reflected from objects in the field of view and passing through the protective window to determine the likely obstruction-pattern match.

6. The LIDAR system of claim 2 , wherein the at least one processor is further configured to detect the particular obstruction pattern by determining from the reflections signals internal reflection parameters associated with different areas of the protective window.

7. The LIDAR system of claim 2 , wherein the at least one processor is further configured to detect the particular obstruction pattern based on differences between signal baseline parameters and internal reflection parameters associated with the area of the protective window.

8. The LIDAR system of claim 2 , wherein the at least one processor is configured to use the indications of light reflected from the protective window to identify at least one obstructed pixel.

9. The LIDAR system of claim 2 , wherein the at least one processor is further configured to detect the particular obstruction pattern based on light detected during a time period between light leaving the at least one light source and reflection impinging on the least one sensor.

10. The LIDAR system of claim 2 , wherein the detected particular obstruction pattern is associated with at least two neighboring instantaneous positions.

11. The LIDAR system of claim 2 , wherein the detected particular obstruction pattern is associated with at least two separated instantaneous positions.

12. The LIDAR system of claim 1 , wherein the at least one processor is further configured to output information that includes a window cleaning request associated with the type of the obstruction of the protective window based on the obstruction-pattern match.

13. The LIDAR system of claim 12 , wherein the at least one processor is further configured to select a cleaning process associated with the type of the obstruction of the protective window, and to output information that includes a window cleaning request associated with the selected cleaning process.

14. The LIDAR system of claim 12 , wherein the at least one processor is further configured to cause a change in light flux projected from the at least one light source based on the type of the obstruction of the protective window.

15. The LIDAR system of claim 12 , wherein the at least one processor is further configured to cause a change in a sensitivity of the at least one sensor based on the type of the obstruction of the protective window.

16. The LIDAR system of claim 1 , wherein a difference between the received reflection signal and the known internal reflection signal is used to determine the presence and the type of the obstruction.

17. The LIDAR system of claim 1 , wherein the at least one LIDAR light source includes a laser ranging emitter.

18. The LIDAR system of claim 1 , wherein at least one LIDAR light source includes a dedicated emitter.

19. The LIDAR system of claim 1 , wherein the at least one sensor includes a ranging detector.

20. The LIDAR system of claim 1 , wherein the at least one sensor includes a dedicated detector.

21. The LIDAR system of claim 1 , wherein the at least one processor is further configured to compare at least one of a timing, an intensity, a polarization, or a spatial profile of the received reflection signal with those of the known internal reflection signal.

22. The LIDAR system of claim 1 , wherein the comparing of the received reflection signal with the known internal reflection signal includes comparing the received reflection signal with one or more threshold parameters, the one or more threshold parameters including one or more of a duration of the known internal reflection signal, a rate of ascend in the temporal amplitude profile of the known internal reflection signal, or a rate of descend in the temporal amplitude profile of the known internal reflection signal.

23. The LIDAR system of claim 1 , wherein the comparing of the received reflection signal with the known internal reflection signal includes determining whether a time period for the received reflection signal to fall below a threshold intensity is longer than a predetermined duration.

24. The LIDAR system of claim 1 , wherein the at least one LIDAR light source is controlled to emit a light pulse, and the comparing of the received reflection signal with the known internal reflection signal includes determining whether an intensity of the received reflection signal exceeds a predetermined threshold within a predetermined time window from the emission of the light pulse.

25. The LIDAR system of claim 1 , wherein the at least one processor is further configured to:
analyze at least one of a timing, an intensity, a polarization, or the temporal amplitude profile of the received reflection signal to distinguish between a reflection from a blockage and a reflection from an

Assignees

• Innoviz Tech Ltd

Inventors

• Osiroff Nir
• Shani Matityahu
• Elooz David
• David Raly Smadar

Classifications

• G01S17/89

  for mapping or imaging · CPC title

• G01S17/06

  Systems determining position data of a target · CPC title

• G01S7/497

  Means for monitoring or calibrating · CPC title

• G01S7/4808

  Evaluating distance, position or velocity data · CPC title

• B60S1/02

  Cleaning windscreens, windows or optical devices {(wind deflectors specially adapted for preventing soiling of windows or windscreens B60J1/2002)} · CPC title