Use of a Reference Image to Detect a Road Obstacle

1 . A method comprising:

receiving, at a computing device, an image of a road from a camera coupled to a vehicle, wherein the vehicle is navigating a path proximate to the road;

based on a current location of the vehicle, obtaining a reference image, wherein the reference image depicts one or more background objects associated with the road;

aligning the image relative to the reference image;

based on aligning the image relative to the reference image, performing a comparison between the image and the reference image;

based on the comparison, determining one or more foreground objects including at least one of a moving object, an obstacle or a road change; and

controlling the vehicle based on the one or more foreground objects.

2 . The method of claim 1 , wherein the reference image is obtained from a storage.

3 . The method of claim 1 , wherein controlling the vehicle based on the one or more foreground objects comprises at least one of: causing the vehicle to reduce speed, causing the vehicle to change lanes, causing the vehicle to change lanes, or causing the vehicle to follow another vehicle while keeping a predetermined safe distance.

4 . The method of claim 1 , wherein controlling the vehicle based on the one or more foreground objects comprises selecting or modifying a desired control strategy from a plurality of possible control strategies.

5 . The method of claim 4 , wherein the plurality of possible control strategies comprise sets of rules that relate to various driving contexts.

6 . The method of claim 4 , wherein the plurality of possible control strategies comprises a default driving mode and a defensive driving mode, wherein the defensive driving mode comprises at least one of:

controlling the speed of the vehicle so as to follow another vehicle at a predetermined safe distance;

turning-on lights; or

stopping the vehicle.

7 . The method of claim 4 , wherein the plurality of possible control strategies comprise a continuum of driving modes or states based on the difference between the image and the reference image, wherein selecting or modifying the desired control strategy comprises selecting or modifying the desired control strategy so as to cause a smooth transition from a first set of driving rules to a second set of driving rules.

8 . The method of claim 7 , wherein the smooth transition is configured so as to not be perceivable by a passenger in the vehicle.

9 . The method of claim 1 , wherein the computing device is positioned remotely from the vehicle.

10 . The method of claim 1 , wherein the current location of the vehicle is provided to the computing device by a GPS module coupled to the vehicle.

11 . The method of claim 1 , wherein the reference image is obtained based on orientation information of the vehicle.

12 . The method of claim 11 , wherein the orientation information of the vehicle is provided to the computing device by an Inertial Measurement Unit (IMU) coupled to the vehicle.

13 . The method of claim 1 , wherein aligning the image relative to the reference image comprises:

determining, by the computing device, a transform; and

applying the transform to the image.

14 . The method of claim 13 , wherein the transform comprises shifting or rotating pixels of the image.

15 . The method of claim 1 , wherein determining the one or more foreground objects comprises determining a difference between the image and the reference image.

16 . The method of claim 15 , further comprising determining a level of confidence for the difference between the image and the reference image.

17 . The method of claim 16 , wherein the level of confidence is based on an accuracy level assigned to the reference image.

18 . The method of claim 16 , wherein the level of confidence is based on differences in lighting conditions between the image and the reference image.

19 . A computing device comprising:

one or more processors; and

memory containing instructions that when executed by the one or more processors cause the computing device to perform operations comprising:

receiving, an image of a road from a camera coupled to a vehicle, wherein the vehicle is navigating a path proximate to the road;

based on a current location of the vehicle, obtaining a reference image from storage, wherein the reference image depicts one or more background objects associated with the road;

aligning the image relative to the reference image;

based on aligning the image relative to the reference image, performing a comparison between the image and the reference image;

based on the comparison, determining one or more foreground objects including at least one of a moving object, an obstacle or a road change; and

controlling the vehicle based on the one or more foreground objects.

20 . A non-transitory computer-readable medium having stored thereon instructions executable by a computing device to cause the computing device to perform functions, wherein the functions comprise:

receiving, an image of a road from a camera coupled to a vehicle, wherein the vehicle is navigating a path proximate to the road;

based on a current location of the vehicle, obtaining a reference image from storage, wherein the reference image depicts one or more background objects associated with the road;

aligning the image relative to the reference image;

based on aligning the image relative to the reference image, performing a comparison between the image and the reference image;

based on the comparison, determining one or more foreground objects including at least one of a moving object, an obstacle or a road change; and

controlling the vehicle based on the one or more foreground objects.