Navigation based on radar-cued visual imaging

Patent metadata

Field	Value
Publication number	US-9664789-B2
Application number	US-201514627178-A
Country	US
Kind code	B2
Filing date	Feb 20, 2015
Priority date	Feb 20, 2014
Publication date	May 30, 2017
Grant date	May 30, 2017

Abstract

A navigation system for a vehicle may include at least one image capture device configured to acquire a plurality of images of an environment of a vehicle and a radar sensor to detect an object in the environment of the vehicle and to provide and output including range information indicative of at least one of a range or range rate between the vehicle and the object. The system may also include at least one processing device programmed to: receive the plurality of images from the at least one image capture device; receive the output from the radar sensor; determine, for each of a plurality of image segments in a first image, from among the plurality of images, and corresponding image segments in a second image, from among the plurality of images, an indicator of optical flow; use range information determined based on the output of the radar sensor together with the indicators of optical flow determined for each of the plurality of image segments in the first image and the corresponding image segments in the second image to calculate for each of a plurality of imaged regions at least one value indicative of a focus of expansion; identify a target object region, including at least a subset of the plurality of imaged regions that share a substantially similar focus of expansion; and cause a system response based on the identified target object region.

First claim

What is claimed is:

1. A navigation system for a vehicle, the system comprising:
at least one image capture device configured to acquire a plurality of images of an environment of a vehicle;
a radar sensor to detect an object in the environment of the vehicle and to provide and output including range information indicative of at least one of a range or range rate between the vehicle and the object; and
at least one processing device programmed to:
receive the plurality of images from the at least one image capture device;
receive the output from the radar sensor;
determine, for each of a plurality of image segments in a first image, from among the plurality of images, and corresponding image segments in a second image, from among the plurality of images, an indicator of optical flow;
determine a value indicative of an expected optical inflation associated with the object in the plurality of images based at least upon the range information from the output of the radar sensor;
determine one or more areas of the second image where the value indicative of an expected optical inflation associated with the object substantially matches the indicator of optical flow;
identify a target object region, including at least a subset of the determined one or more areas of the second image; and
cause a system response based on the identified target object region.

2. The navigation system of claim 1 , wherein the target object region is associated with a common focus of expansion.

3. The navigation system of claim 1 , wherein the at least one processing device is further programmed to determine an angular position of the object relative to the vehicle based on a determined location of the target object region.

4. The navigation system of claim 1 , wherein the at least one processing device is further programmed to determine a location of the object relative to the vehicle based on the identified target object region.

5. The navigation system of claim 1 , wherein the system response includes at least one of braking or a change in current travel direction of the vehicle if the at least one processing device determines that the current travel direction may result in a collision with the object.

6. The navigation system of claim 1 , wherein the system response is a navigational response including braking.

7. The navigation system of claim 1 , wherein the system response is a navigational response including a change in a direction of travel of the vehicle.

8. The navigation system of claim 1 , wherein the at least one processing device is further programmed to identify edges of the object based on the identified target object region.

9. The navigation system of claim 1 , wherein the at least one processing device is further programmed to determine a height of the object based on the identified target object region.

10. The navigation system of claim 1 , wherein the output of the radar sensor includes an indicator of a time to contact between the vehicle and the object.

11. The navigation system of claim 1 , wherein the at least one processing device is configured to account for at least one effect caused by use of a rolling shutter to acquire the plurality of images in determining the indicator of optical flow.

12. The navigation system of claim 1 , wherein the at least one processing device is configured to select an operational mode from among at least a first mode and a second mode, where the first mode is associated with a wider image capture field of view than the second mode, based on the range information from the radar sensor.

13. A vehicle comprising a navigation system, the navigation system comprising:
at least one image capture device configured to acquire a plurality of images of an environment of the vehicle;
a radar sensor to detect an object in the environment of the vehicle and to provide and output including range information indicative of at least one of a range or range rate between the vehicle and the object; and
at least one processing device programmed to:
receive the plurality of images from the at least one image capture device;
receive the output from the radar sensor;
determine, for each of a plurality of image segments in a first image, from among the plurality of images, and corresponding image segments in a second image, from among the plurality of images, an indicator of optical flow;
determine a value indicative of an expected optical inflation associated with the object in the plurality of images based at least upon the range information in the output of the radar sensor;
determine one or more areas of the second image where the value indicative of an expected optical inflation associated with the object substantially matches the indicator of optical flow;
identify a target object region, including at least a subset of the determined one or more areas of the second image; and
cause a system response based on the identified target object region.

14. The vehicle of claim 13 , wherein the at least one processing device is further programmed to determine an angular position of the object relative to the vehicle based on a determined location of the target object region.

15. The vehicle of claim 13 , wherein the at least one processing device is further programmed to determine a location of the object relative to the vehicle based on the identified target object region.

16. The vehicle of claim 13 , wherein the system response includes at least one of braking or a change in current travel direction of the vehicle if the at least one processing device determines that the current travel direction may result in a collision with the object.

17. The vehicle of claim 13 , wherein the at least one processing device is further programmed to identify edges of the object based on the identified target object region.

18. The vehicle of claim 13 , wherein the at least one processing device is further programmed to determine a height of the object based on the identified target object region.

19. The vehicle of claim 13 , wherein the output of the radar sensor includes an indicator of a time to contact between the vehicle and the object.

20. The vehicle of claim 13 , wherein the processing device is further configured to identify a light source in at least one of the plurality of images, determine whether the light source is a traffic light based on the indicator of optical flow and the output of the radar sensor, and cause automatic application of brakes of the vehicle if the traffic light is determined to be yellow or red.

21. A method for navigating a vehicle based on radar detection and visual image data, the method comprising:
acquiring a plurality of images of an environment of the vehicle;
detecting an object in the environment of the vehicle using a radar sensor and providing an output of the radar sensor including range information indicative of at least one of a range or range rate between the object and the vehicle;
receiving, at one or more processing devices, the plurality of images from the at least one image capture device and the output from the radar sensor;
determining an indicator of optical flow, for each of a plurality of image segments in a first image, from among the plurality of images, and corresponding image segments in a second image, from among the plurality of images;
identifying a target object region having a substantially common focus of expansion, based the range information provided by the radar sensor and the determined indicators of optical flo

Assignees

• Rosenblum Kevin
• Dagan Erez
• Mobileye Vision Technologies Ltd

Inventors

• Rosenblum Kevin
• Dagan Erez

Classifications

• G01S13/87

  Combinations of radar systems, e.g. primary radar and secondary radar · CPC title

• G01S2013/9322

  using additional data, e.g. driver condition, road state or weather data · CPC title

• G01S2013/93185

  Controlling the brakes · CPC title

• G06T2207/30261

  Obstacle · CPC title

• G01S13/931 Primary

  of land vehicles · CPC title