USE OF ENVIRONMENTAL INFORMATION TO AID IMAGE PROCESSING FOR AUTONOMOUS VEHICLES

• US 20160214605A1
• Filed: 08/19/2015
• Published: 07/28/2016
• Est. Priority Date: 06/24/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Ferguson, David I., Lo, Wan-Yen
• Granted Patent: US 9,387,854 B1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2420/408 Radar; Laser, e.g. lidar
• CPC Class Codes: B60W 2420/54 Audio sensitive means, e.g. ultrasound
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 2554/20 Static objects
• CPC Class Codes: B60W 2554/4029 Pedestrians
• CPC Class Codes: B60W 2554/80 Spatial relation or speed relative to objects
• CPC Class Codes: B60W 30/09 Taking automatic action to avoid collision, e.g. braking and steering
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: B60W 30/16 Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
• CPC Class Codes: B60W 60/0016 of the vehicle or its occupants
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G06F 18/251 of input or preprocessed data
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

An autonomous vehicle may be configured to use environmental information for image processing. The vehicle may be configured to operate in an autonomous mode in an environment and may be operating substantially in a lane of travel of the environment. The vehicle may include a sensor configured to receive image data indicative of the environment. The vehicle may also include a computer system configured to compare environmental information indicative of the lane of travel to the image data so as to determine a portion of the image data that corresponds to the lane of travel of the environment. Based on the portion of the image data that corresponds to the lane of travel of the environment and by disregarding a remaining portion of the image data, the vehicle may determine whether an object is present in the lane, and based on the determination, provide instructions to control the vehicle in the autonomous mode in the environment.

Claims

1. A method comprising:

receiving, using a processor, image data indicative of an environment from at least one sensor of a vehicle, wherein the vehicle is configured to operate in an autonomous mode in the environment, and wherein the vehicle is substantially in a lane of travel of the environment;

comparing the image data to a predetermined image map of a road in the environment indicative of the lane of travel;

based on the comparing, determining a portion of the image data that corresponds to the lane of travel and disregarding a remaining portion of the image data;

performing object detection based on only the determined portion of the image data; and

providing instructions to control the vehicle in the autonomous mode in the environment based on the performed object detection.

2. The method of claim 1, wherein the comparing comprises projecting the predetermined image map onto the image data.

3. The method of claim 1, wherein the predetermined image map indicates at least one of a location of the lane of travel or a boundary of the lane of travel, and

wherein comparing the predetermined image map to the image data further comprises:

comparing the image data to at least one of (i) the location of the lane of travel indicated by the predetermined image map, or (ii) the boundary of the lane of travel indicated by the predetermined image map.

4. The method of claim 1, wherein the portion is a first portion, wherein the lane of travel is a first lane of travel, wherein the predetermined image map of the road in the environment is further indicative of a second lane of travel of the environment, and the method further comprises:

based on the comparing, determining a second portion of the image data that corresponds to the second lane of travel, wherein the second portion of the image data is different than the first portion of the image data, wherein the second lane of travel of the environment is different than the first lane of travel, and wherein the disregarded remaining portion of the image data includes image data other than the first and second portions;

performing additional object detection based on only the first and second portions of the image data; and

providing instructions to control the vehicle in the autonomous mode in the environment based on the performed additional object detection.

5. The method of claim 4, wherein the predetermined image map indicates at least one of a location of the second lane of travel or a boundary of the second lane of travel, and

wherein comparing the predetermined image map to the image data comprises:

comparing the image data to at least one of (i) the location of the second lane of travel indicated by the predetermined image map, or (ii) the boundary of the second lane of travel indicated by the predetermined image map.

6. The method of claim 4, wherein the second lane of travel is adjacent to the first lane of travel.

7. The method of claim 1, wherein the predetermined image map comprises a heading of the vehicle in the environment.

8. The method of claim 1, wherein determining the portion of the image data that corresponds to the lane of travel comprises determining the portion of the image data to be a portion of the image data that includes features that correspond to predetermined features, indicated in the predetermined image map, that are associated with known lane boundaries of the lane of travel.

9. A vehicle comprising:

at least one sensor configured to receive image data indicative of an environment, wherein the vehicle is configured to operate in an autonomous mode in the environment, and wherein the vehicle is substantially in a lane of travel of the environment;

a computer system, wherein the computer system is configured to;

compare the image data to a predetermined image map of a road in the environment indicative of the lane of travel;

based on the comparing, determine a portion of the image data that corresponds to the lane of travel and disregarding a remaining portion of the image data;

perform object detection based on only the determined portion of the image data; and

provide instructions to control the vehicle in the autonomous mode in the environment based on the performed object detection.

10. The vehicle of claim 9, wherein the comparing comprises projecting the predetermined image map onto the image data.

11. The vehicle of claim 9, wherein the predetermined image map indicates at least one of a location of the lane of travel or a boundary of the lane of travel, and

wherein comparing the predetermined image map to the image data further comprises:

comparing the image data to at least one of (i) the location of the lane of travel indicated by the predetermined image map, or (ii) the boundary of the lane of travel indicated by the predetermined image map.

12. The vehicle of claim 9, wherein the portion is a first portion, wherein the lane of travel is a first lane of travel, wherein the predetermined image map of the road in the environment is further indicative of a second lane of travel of the environment, and the computer system is further configured to:

based on the comparing, determine a second portion of the image data that corresponds to the second lane of travel, wherein the second portion of the image data is different than the first portion of the image data, wherein the second lane of travel of the environment is different than the first lane of travel, and wherein the disregarded remaining portion of the image data includes image data other than the first and second portions;

perform additional object detection based on only the first and second portions of the image data; and

provide instructions to control the vehicle in the autonomous mode in the environment based on the performed additional object detection.

13. The vehicle of claim 12, wherein the predetermined image map indicates at least one of a location of the second lane of travel or a boundary of the second lane of travel, and

wherein comparing the predetermined image map to the image data comprises:

comparing the image data to at least one of (i) the location of the second lane of travel indicated by the predetermined image map, or (ii) the boundary of the second lane of travel indicated by the predetermined image map.

14. The vehicle of claim 12, wherein the second lane of travel is adjacent to the first lane of travel.

15. A non-transitory computer readable medium having stored therein instructions that when executed by a computer system in a vehicle, cause the computer system to perform functions comprising:

receiving image data indicative of an environment from at least one sensor of the vehicle, wherein the vehicle is configured to operate in an autonomous mode in the environment, and wherein the vehicle is substantially in a lane of travel of the environment;

comparing the image data to a predetermined image map of a road in the environment indicative of the lane of travel;

based on the comparing, determining a portion of the image data that corresponds to the lane of travel and disregarding a remaining portion of the image data;

performing object detection based on only the determined portion of the image data; and

providing instructions to control the vehicle in the autonomous mode in the environment based on the performed object detection.

16. The non-transitory computer readable medium of claim 15, wherein the comparing comprises projecting the predetermined image map onto the image data.

17. The non-transitory computer readable medium of claim 15, wherein the predetermined image map indicates at least one of a location of the lane of travel or a boundary of the lane of travel, and

wherein comparing the predetermined image map to the image data further comprises:

comparing the image data to at least one of (i) the location of the lane of travel indicated by the predetermined image map, or (ii) the boundary of the lane of travel indicated by the predetermined image map.

18. The non-transitory computer readable medium of claim 15, wherein the predetermined image map comprises a heading of the vehicle in the environment.

19. The non-transitory computer readable medium of claim 15, wherein the portion is a first portion, wherein the lane of travel is a first lane of travel, wherein the predetermined image map of the road in the environment is further indicative of a second lane of travel of the environment adjacent to the first lane of travel, and the instructions are further executable by the computer system in the vehicle to cause the computer system to perform functions comprising:

based on the comparing, determining a second portion of the image data that corresponds to the second lane of travel, wherein the second portion of the image data is different than the first portion of the image data, wherein the second lane of travel of the environment is different than the first lane of travel, and wherein the disregarded remaining portion of the image data includes image data other than the first and second portions;

performing additional object detection based on only the first and second portions of the image data; and

providing instructions to control the vehicle in the autonomous mode in the environment based on the performed additional object detection.

20. The non-transitory computer readable medium of claim 19, wherein the predetermined image map indicates at least one of a location of the second lane of travel or a boundary of the second lane of travel, and

wherein comparing the predetermined image map to the image data comprises:

comparing the image data to at least one of (i) the location of the second lane of travel indicated by the predetermined image map, or (ii) the boundary of the second lane of travel indicated by the predetermined image map.