SYSTEMS AND METHODS FOR BRAKING A VEHICLE BASED ON A DETECTED OBJECT

• US 20150336547A1
• Filed: 05/22/2015
• Published: 11/26/2015
• Est. Priority Date: 05/22/2014
• Status: Active Grant

• Current Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Original Assignee: MobilEye Vision Technologies Ltd. (Intel Corporation)
• Inventors: Dagan, Erez
• Granted Patent: US 9,650,025 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B60T 17/221 Procedure or apparatus for checking or keeping in a correct functioning condition of brake systems hydraulic pressure systems in general F15B19/00, F15B21/04; testing structures or apparatus G01M
• CPC Class Codes: B60T 2201/022 Collision avoidance systems
• CPC Class Codes: B60T 2270/40 Failsafe aspects of brake control systems
• CPC Class Codes: B60T 7/22 initiated by contact of vehicle, e.g. bumper, with an external object, e.g. another vehicle , or by means of contactless obstacle detectors mounted on the vehicle
• CPC Class Codes: B60T 8/171 Detecting parameters used in the regulation; Measuring values used in the regulation
• CPC Class Codes: B60T 8/172 Determining control parameters used in the regulation, e.g. by calculations involving measured or detected parameters B60T8/17551 takes precedence
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 2207/30261 Obstacle
• CPC Class Codes: G06T 7/269 using gradient-based methods
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle
• 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: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005

Abstract

Systems and methods are provided for detecting an object and causing a vehicle to brake based on the detection. In one implementation, an object detecting and braking system for a vehicle includes at least one image capture device configured to acquire a plurality of images of an area including an object in front of the vehicle. The system includes at least one processing device programmed to perform a first image analysis to determine a first estimated time-to-collision of the vehicle with the object, and to perform a second image analysis to determine a second estimated time-to-collision of the vehicle with the object. The processing device is also programmed to calculate a difference between the first estimated time-to-collision and the second estimated time-to-collision, to determine that the difference does not exceed a predetermined threshold, and to cause the vehicle to brake based on the determination that the difference does not exceed the predetermined threshold.

Claims

1. An object detecting and braking system for a vehicle, comprising:

at least one image capture device configured to acquire a plurality of images of an area including an object in front of the vehicle;

a data interface; and

at least one processing device programmed to;

receive the plurality of images via the data interface;

perform a first image analysis based on at least a first image and a second image to determine a first estimated time-to-collision of the vehicle with the object;

perform a second image analysis based on at least a third image and a fourth image to determine a second estimated time-to-collision of the vehicle with the object;

calculate a difference between the first estimated time-to-collision and the second estimated time-to-collision;

determine that the difference does not exceed a predetermined threshold; and

cause the vehicle to brake based on the determination that the difference does not exceed the predetermined threshold.

2. The object detecting and braking system of claim 1, wherein the first image analysis includes:

determining a first size of the object appearing in the first image;

determining a second size of the object appearing in the second image;

determining a change in size of the object based on the first size and the second size; and

determining the first estimated time-to-collision based on the change in size of the object and a predetermined time interval between times of acquisition of the first image and the second image.

3. The object detecting and braking system of claim 1, wherein the second image analysis includes:

obtaining a vector field from at least the third image and fourth image, wherein each point in the vector field is represented by a vector indicating a magnitude and a direction of movement from a first point in the third image to a corresponding second point in the fourth image;

determining a focus of expansion based on the vector field, the focus of expansion being a converging point of vectors in the vector field; and

determining a rate of expansion relative to the focus of expansion for each point in the vector field; and

determining the second estimated time-to-collision based on the rate of expansion and a time interval between times of acquisition of the third image and the fourth image.

4. The object detecting and braking system of claim 3, wherein determining the rate of expansion relative to the focus of expansion includes:

determining a distance from each point in the vector field to the focus of expansion; and

dividing the magnitude by the distance to obtain the rate of expansion for each point in the vector field.

5. The object detecting and braking system of claim 4, wherein the second image analysis includes:

determining a relationship between magnitudes and distances for a plurality of points in the vector field; and

determining that the object represented by the plurality of points is a low time-to-collision upright object based on a determination that the relationship is a linear relationship.

6. The object detecting and braking system of claim 4, wherein the second image analysis includes:

determining a relationship between magnitudes and distances for a plurality of points in the vector field; and

determining that at least a portion of the object is a road surface based on a determination that the relationship is a non-linear relationship.

7. The object detecting and braking system of claim 1, wherein the second image analysis includes:

obtaining a vector field from at least the third image and the fourth image, wherein each point in the vector field is represented by a vector indicating a magnitude and a direction of movement from a first point in the third image to a corresponding second point in the fourth image;

detecting a first focus of expansion that is a first converging point of a first plurality of vectors in the vector field;

detecting a second focus of expansion that is a second converging point of a second plurality of vectors in the vector field; and

determining that the third image and the fourth image include a moving object that moves in a direction that is not parallel to a travel direction of the vehicle.

8. The object detecting and braking system of claim 1, wherein the second image analysis includes:

obtaining a vector field from at least the third image and the fourth image, wherein each point in the vector field is represented by a vector indicating a magnitude and a direction of movement from a first point in the third image to a corresponding second point in the fourth image;

detecting a focus of expansion based on the vector field, the focus of expansion being a converging point of vectors in the vector field; and

determining that the third image and the fourth image represent an environment that is static relative to a road surface on which the vehicle is traveling.

9. The object detecting and braking system of claim 1, wherein the first image used for the first image analysis is different from the third image used for the second image analysis, and wherein the second image used for the first image analysis is different from the fourth image used for the second image analysis.

10. The object detecting and braking system of claim 1, wherein the first image used for the first image analysis is the same as the third image used for the second image analysis, and wherein the second image used for the first image analysis is the same as the fourth image used for the second image analysis.

11. The object detecting and braking system of claim 1, wherein the first image analysis and the second image analysis are independent of each other.

12. The object detecting and braking system of claim 1, wherein the at least one image capture device includes:

a first image sensor configured to capture the first image and the second image to be used in the first image analysis; and

a second image sensor independent of the first image sensor and configured to capture the third image and the fourth image to be used in the second image analysis.

13. A vehicle, comprising:

a body;

at least one image capture device configured to acquire a plurality of images of an area including an object in front of the vehicle;

a data interface; and

at least one processing device programmed to;

receive the plurality of images via the data interface;

perform a first image analysis based on at least a first image and a second image to determine a first estimated time-to-collision of the vehicle with the object;

perform a second image analysis based on at least a third image and a fourth image to determine a second estimated time-to-collision of the vehicle with the object;

calculate a difference between the first estimated time-to-collision and the second estimated time-to-collision;

determine that the difference does not exceed a predetermined threshold; and

cause the vehicle, to brake based on the determination that the difference does not exceed the predetermined threshold.

14. The vehicle of claim. 13, wherein the first image analysis includes:

determining a first size of the object appearing in the first image;

determining a second size of the object appearing in the second image;

determining a change in size of the object based on the first size and the second size; and

determining the first estimated time-to-collision based on the change in size of the object and a predetermined time interval between times of acquisition of the first image and the second image.

15. The vehicle of claim 13, herein the second image analysis includes:

obtaining a vector field from at least the third image and fourth image, wherein each point in the vector field is represented by a vector indicating a magnitude and a direction of movement from a first point in the third image to a corresponding second point in the fourth image;

determining a focus of expansion based on the vector field, the focus of expansion being a converging point of vectors in the vector field; and

determining a rate of expansion relative to the focus of expansion for each point in the vector field; and

determining the second estimated time-to-collision based on the rate of expansion and a time interval between times of acquisition of the third image and the fourth image.

16. The vehicle of claim 15, wherein determining the rate of expansion relative to the focus of expansion includes:

determining a distance from each point in the vector field to the focus of expansion; and

dividing the magnitude by the distance to obtain the rate of expansion for each point in the vector field.

17. The vehicle of claim 16, wherein the second image analysis includes:

determining a relationship between magnitudes and distances for a plurality of points in the vector field; and

determining that the object represented by the plurality of points is a low time-to-collision upright object based on a determination that the relationship is a linear relationship.

18. A method for detecting an object and braking a vehicle, comprising:

acquiring, via at least one image capture device, a plurality of images of an area including an object in front of the vehicle;

receiving, via a processing device, the plurality of images;

performing, via the processing device, a first image analysis based on at least a first image; and

a second image to determine a first estimated time-to-collision of the vehicle with the object;

performing, via the processing device, a second image analysis based on at least a third image and a fourth image to determine a second estimated time-to-collision of the vehicle with the object;

calculating, via the processing device, a difference between the first estimated time-to-collision and the second estimated time-to-collision;

determining, via the processing device, that the difference does not exceed a predetermined threshold; and

causing, via the processing device, the vehicle to brake based on the determination that the difference does not exceed the predetermined threshold.

19. The method of claim 18, wherein the first image analysis includes:

determining a first size of the object appearing in the first image;

determining a second size of the object appearing in the second image;

determining a change in size of the object based on the first size and the second size; and

determining the first estimated time-to-collision based on the change in size of the object and a predetermined time interval between times of acquisition of the first image and the second image.

20. The method of claim 18, wherein the second image analysis includes:

obtaining a vector field from at least the third image and fourth image, wherein each point in the vector field is represented by a vector indicating a magnitude and a direction of movement from a first point in the third image to a corresponding second point in the fourth image;

determining a focus of expansion based on the vector field, the focus of expansion being a converging point of vectors in the vector field; and

determining a rate of expansion relative to the focus of expansion for each point in the vector field; and

determining the second estimated time-to-collision based on the rate of expansion and a time interval between times of acquisition of the third image and the fourth image.

21. A method for assessing an overall system failure rate associated with a braking decisioning system for a vehicle, comprising:

determining, using a processing device, a first failure rate associated with a textural analysis based sub-system, wherein the textural analysis based sub-system is configured to make a decision to brake based on a change in texture between at least two images of an area in front of a vehicle;

determining, using the processing device, a second failure rate associated with a structural analysis based sub-system, wherein the structural analysis based sub-system is configured to make a decision to brake based on optical flow information derived from at least two images of the area in front of the vehicle; and

determining, using the processing device, the overall system failure rate based on the first future rate and the second failure rate.

22. The method of claim 21, wherein determining the overall system failure rate comprises multiplying the first failure rate with the second failure rate to generate the overall system failure rate.