IP Library Granted Patent US 11,783,705
Granted Patent B2
US 11,783,705 · App. 17/304,550 · Granted Oct 10, 2023

Highway exit alert

Inventors: Boaz Mell (Petach Tikva, IL); Adam Harel (Tel Aviv, IL); Igal Raichelgauz (Tel Aviv, IL)
Assignee: AUTOBRAINS TECHNOLOGIES LTD
G08G1/096716G06N20/00G08G1/0137G08G1/096766G08G1/096855
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 11,783,705
App. No.
17/304,550
Granted
Oct 10, 2023
Kind
B2
Abstract

A method for generating the at least one highway exit indicator, the method may include receiving video information and location information obtained during driving sessions of the plurality of vehicles; determining, based on the location information, multiple suspected highway exit events; selecting video information segments, wherein each selected video information segment is acquired before a suspected highway exit event and in timing proximity to the suspected highway exit event; and applying a machine learning process on at least some of the selected video information segments to find the at least one highway exit indicator.

Claims (41)

1. A method for highway exit alert, the method comprises:

receiving by a vehicle computerized system, at least one highway exit indicator that is visible before exiting the highway;

obtaining sensed information regarding an environment of the vehicle;

processing the sensed information, wherein the processing comprises searching a visual highway exit indicator of the at least one highway exit indicator;

determine whether the vehicle is reaching a highway exit; and

generating the highway exit alert when determining that the vehicle is reaching the highway exit;

wherein the at least one highway exit indicator is generated by:

receiving video information and location information obtained during driving sessions of the plurality of vehicles;

determining, based on the location information, multiple suspected highway exit events:

selecting video information segments, wherein each selected video information segment is acquired before a suspected highway exit event and in timing proximity to the suspected highway exit event; and

applying a machine learning process on at least some of the selected video information segments to find the at least one highway exit indicator.

2. The method according to claim 1 comprising generating the at least one highway exit indicator.

3. The method according to claim 1 comprising applying multiple machine learning processes on multiple groups of the selected video information segments, one group per suspected highway exit.

4. The method according to claim 1 comprising applying the machine learning process on selected video information segments associated with more than one highway exit.

5. The method according to claim 1 comprising verifying the multiple suspected highway exit events.

6. The method according to claim 5 wherein the verifying of the multiple suspected highway exit events comprising tracking after a progress of a vehicle, of the plurality of vehicle, during a suspected driving event.

7. The method according to claim 6 wherein the tracking after the progress of the vehicle, of the plurality of vehicle, during the suspected driving event comprises processing images of one or more wheels of the vehicle.

8. The method according to claim 2 comprising associating a distance between the highway exit and the at least one highway exit indicator.

9. The method according to claim 2 wherein the at least one highway exit indicator comprises at least one out of an image information and textual information.

10. The method according to claim 2 comprising determining one or more lane of the highway from which to initiate a highway exit process.

11. A non-transitory computer readable medium for highway exit alert, the non-transitory computer readable medium stores instructions for:

receiving by a vehicle computerized system, at least one highway exit indicator that is visible before exiting the highway;

obtaining sensed information regarding an environment of the vehicle;

processing the sensed information, wherein the processing comprises searching a visual highway exit indicator of the at least one highway exit indicator;

determine whether the vehicle is reaching a highway exit; and

generating the highway exit alert when determining that the vehicle is reaching the highway exit;

wherein the at least one highway exit indicator is generated by:

receiving video information and location information obtained during driving sessions of the plurality of vehicles;

determining, based on the location information, multiple suspected highway exit events;

selecting video information segments, wherein each selected video information segment is acquired before a suspected highway exit event and in timing proximity to the suspected highway exit event; and

applying a machine learning process on at least some of the selected video information segments to find the at least one highway exit indicator.

12. A method for providing at least one highway exit indicator, the method comprises:

obtaining video information and location information obtained during driving sessions of one or more vehicles;

determining, based on the location information and highway exits location information, multiple suspected highway exit events;

selecting video information segments, each selected video information segment is acquired before a suspected highway exit event and in timing proximity to the suspected highway exit event;

obtaining other video information segments that differ from the selected information segments; and

processing at least some of the selected video information segments and at least some of the other video information segments to find the at least one highway exit indicator.

13. The method according to claim 12 wherein the processing comprises applying the machine learning process on at least the least some of the selected video information segments.

14. The method according to claim 12 wherein the processing comprises applying the machine learning process on at least the least some of the selected video information segments and on at least some of the other video information segments.

15. The method according to claim 12 wherein the processing comprises obtaining first occurrence information regarding occurrences of objects within the at least some of the selected video information segments; obtaining second occurrence information regarding occurrences of objects within the at least some of the other video information segments; and determining the at least one highway exit identifier, based on the first occurrence information and the second occurrence information.

16. The method according to claim 12 wherein the obtaining comprises receiving, from a plurality of vehicles, and by an I/O module of a computerized system, the video information and the location information obtained during driving sessions of the plurality of vehicles.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 10, 2023
From: MELL, BOAZ; HAREL, ADAM; RAICHELGAUZ, IGAL
To: CARTICA AI LTD.
Reel/Frame 063279/0627 →
CHANGE OF NAME Recorded Jan 3, 2023
From: CARTICA AI LTD
To: AUTOBRAINS TECHNOLOGIES LTD
Reel/Frame 062266/0553 →
Continuity (2)
Provisional Application 62705977 · Jul 24, 2020
Related Publication 20220028265A1 · Jan 27, 2022