Vision augmented navigation

Patent metadata

Field	Value
Publication number	US-10533869-B2
Application number	US-201715596790-A
Country	US
Kind code	B2
Filing date	May 16, 2017
Priority date	Jun 13, 2013
Publication date	Jan 14, 2020
Grant date	Jan 14, 2020

Abstract

A navigation system may include at least one processing device configured to determine, based on an output of one or more position sensors associated with the navigation system, a current location of at least one component associated with the navigation system and determine a destination location different from the current location. The navigation system may also acquire, from one or more image acquisition devices, a plurality of images representative of an environment of a user of the navigation system and derive, from the plurality of images, visual information associated with at least one object in the environment. The system may also determine one or more instructions for navigating from the current location to the destination location, wherein the one or more instructions include at least one reference to the visual information derived from the plurality of images. The system may also deliver to the user the one or more instructions.

First claim

What is claimed is:

1. A navigation system, comprising:
at least one processing device configured to:
determine, based on an output of one or more position sensors associated with the navigation system, a current location of at least one component associated with the navigation system;
determine a destination location different from the current location;
acquire, from one or more image acquisition devices, while a user of the navigation system is located in an environment and navigating from the current location to the destination location, a plurality of images representative of the environment;
analyze, while the user is navigating from the current location to the destination location, the plurality of images to identify at least one object appearing within a field of view of at least one of the image acquisition devices;
determine, based on the plurality of images, a distance from at least one of the one or more image acquisition devices to the at least one object;
determine, based on the determined distance, one or more instructions for navigating from the current location to the destination location, wherein the one or more instructions include a description based on the determined distance; and
deliver to the user the one or more instructions.

2. The navigation system of claim 1 , wherein the at least one object includes at least one of a vehicle, a building, a sign, a traffic light, a road feature, a structure, or a person.

3. The navigation system of claim 1 , wherein determining the distance from at least one of the one or more image acquisition devices to the at least one object includes calculating a depth map using structure from motion, and wherein the plurality of images includes at least one image captured at a different time from another of the plurality of images.

4. The navigation system of claim 3 , wherein calculating the depth map further includes using information obtained from at least one of a speedometer or the one or more position sensors.

5. The navigation system of claim 3 , wherein calculating the depth map further includes receiving at least a portion of the depth map and updating the received depth map using the plurality of images.

6. The navigation system of claim 1 , wherein determining the distance from at least one of the one or more image acquisition devices to the at least one object includes:
correlating a first area of a first image in the plurality of images with a second area of a second image in the plurality of images;
warping at least one of the first image and the second image using the correlation;
calculating a disparity map between the first image and the second image; and
determining the distance using the disparity map.

7. The navigation system of claim 6 , wherein determining the distance using the disparity map further includes selecting a portion of the disparity map having a disparity within a range of an expected value, wherein the expected value correlates to a target distance.

8. The navigation system of claim 1 , wherein the one or more instructions are delivered audibly to the user.

9. A vehicle, comprising:
one or more position sensors configured to provide an output representative of a position of the vehicle;
one or more image acquisition devices configured to acquire a plurality of images of an environment outside of the vehicle; and
at least one processing device configured to:
determine, based on an output of the one or more position sensors, a current location of at least one component associated with the vehicle;
determine a destination location different from the current location;
acquire, from the one or more image acquisition devices, while a user of the vehicle is located in an environment and navigating from the current location to the destination location, a plurality of images representative of the environment;
analyze, while the user is navigating from the current location to the destination location, the plurality of images to identify at least one object appearing within a field of view of at least one of the image acquisition devices;
determine, based on the plurality of images, a distance from at least one of the one or more image acquisition devices to the at least one object;
determine, based on the determined distance, one or more instructions for navigating from the current location to the destination location, wherein the one or more instructions include a description based on the determined distance; and
deliver to the user the one or more instructions.

10. The vehicle of claim 9 , wherein the at least one object includes at least one of a vehicle, a building, a sign, a traffic light, a road feature, a structure, or a person.

11. The vehicle of claim 9 , wherein determining the distance from at least one of the one or more image acquisition devices to the at least one object includes calculating a depth map using structure from motion, and wherein the plurality of images includes at least one image captured at a different time from another of the plurality of images.

12. The vehicle of claim 11 , further comprising:
a speedometer,
wherein the one or more position sensors include a GPS unit, and
wherein calculating the depth map further includes using information obtained from the speedometer or the GPS unit.

13. The vehicle of claim 11 , wherein calculating the depth map further includes receiving at least a portion of the depth map and updating the received depth map using the plurality of images.

14. The vehicle of claim 9 , wherein determining the distance from at least one of the one or more image acquisition devices to the at least one object includes:
correlating a first area of a first image in the plurality of images with a second area of a second image in the plurality of images;
warping at least one of the first image and the second image using the correlation;
calculating a disparity map between the first image and the second image; and
determining the distance using the disparity map.

15. The vehicle of claim 14 , wherein determining the distance using the disparity map further includes selecting a portion of the disparity map having a disparity within a range of an expected value, wherein the expected value correlates to a target distance.

16. The vehicle of claim 9 , further comprising:
at least one speaker, and
wherein the one or more instructions are delivered audibly to the user using the at least one speaker.

17. A method for navigating a vehicle, comprising:
determining, based on an output of one or more position sensors associated with the navigation system, a current location of at least one component associated with the navigation system;
determining a destination location different from the current location;
acquiring, from one or more image acquisition devices, while a user of the navigation system is located in an environment and navigating from the current location to the destination location, a plurality of images representative of the environment;
analyzing, while the user is navigating from the current location to the destination location, the plurality of images to identify at least one object appearing within a field of view of at least one of the image acquisition devices;
determining, based on the plurality of images, a distance from at least one of the one or more image acquisition devices to the at least one object;
determining, based on the determined distance, one or more instructions for navigating from the current location to the destination location, wherein the one or more instructions include a descrip

Assignees

• Mobileye Vision Technologies Ltd

Inventors

• Stein Gideon

Classifications

• G01C21/3644

  Landmark guidance, e.g. using POIs or conspicuous other objects · CPC title

• G01C21/3602 Primary

  Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera · CPC title