Leading vehicle braking detection

1 . A computer-implemented method, comprising:

processing pixel data of a first digital image and a second digital image of a rear portion of a first vehicle, the first digital image and the second digital image captured by a camera associated with a second vehicle traveling behind the first vehicle;

based on the processed pixel data, for each of the first digital image and the second digital image, automatically:

detecting two laterally spaced rear reference features fixed on the rear portion of the first vehicle and determining, from the first digital image, a first constant distance between the two laterally spaced rear reference features and, from the second digital image, a second constant distance between the two laterally spaced rear reference features; and

detecting a rear bumper of the first vehicle and a road surface and determining a first variable distance between the rear bumper and the road surface in the first digital image and a second variable distance between the rear bumper and the road surface in the second digital image;

determining a first geometric ratio from the first digital image by normalizing the first variable distance using the first constant distance;

determining a second geometric ratio from the second digital image by normalizing the second variable distance using the second constant distance; and

in response to determining that the second geometric ratio is less than the first geometric ratio, detecting, by the second vehicle, a braking action of the first vehicle.

2 . The computer-implemented method of claim 1 , further comprising:

in response to determining that the second geometric ratio is equal to the first geometric ratio, detecting a constant acceleration of the first vehicle.

3 . The computer-implemented method of claim 1 , further comprising:

determining an intensity of the braking action of the first vehicle based on a difference between the first geometric ratio and the second geometric ratio.

4 . The computer-implemented method of claim 1 , wherein the two laterally spaced rear reference features fixed on the rear portion of the first vehicle comprises a set of tail lights of the first vehicle.

5 . The computer-implemented method of claim 1 , wherein determining the first variable distance further comprises:

determining a first perpendicular distance between the rear bumper of the first vehicle and the road surface in the first digital image.

6 . The computer-implemented method of claim 1 , wherein determining the second variable distance further comprises:

determining a second perpendicular distance between the rear bumper of the first vehicle and the road surface in the second digital image.

7 . The computer-implemented method of claim 1 , further comprising:

capturing a first set of sequential digital images of the first vehicle, wherein the first captured set of sequential digital images includes the first digital image of the first vehicle and the second digital image of the first vehicle; and

establishing a geometric ratio range for the first vehicle based on the first captured set of sequential digital images, wherein the established geometric ratio range includes a lower geometric ratio threshold and an upper geometric ratio threshold.

8 . The computer-implemented method of claim 7 , further comprising:

capturing a second set of sequential digital images of the first vehicle;

determining a third geometric ratio associated with the rear portion of the first vehicle from the second captured set of sequential digital images; and

monitoring the third determined geometric ratio to detect whether the third determined geometric ratio falls below the lower geometric ratio threshold of the established geometric ratio range.

9 . The computer-implemented method of claim 8 , further comprising:

in response to detecting that the monitored third determined geometric ratio falls below the lower geometric ratio threshold of the established geometric ratio range, predicting a sudden-brake action of the first vehicle; and

triggering an intervention in the second vehicle behind the first vehicle to prevent a collision between the second vehicle and the first vehicle.

10 . A computer system for brake detection, comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more computer-readable tangible storage media for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:

processing pixel data of a first digital image and a second digital image of a rear portion of a first vehicle, the first digital image and the second digital image captured by a camera associated with a second vehicle traveling behind the first vehicle;

based on the processed pixel data, for each of the first digital image and the second digital image, automatically:

detecting two laterally spaced rear reference features fixed on the rear portion of the first vehicle and determining, from the first digital image, a first constant distance between the two laterally spaced rear reference features and, from the second digital image, a second constant distance between the two laterally spaced rear reference features; and

detecting a rear bumper of the first vehicle and a road surface and determining a first variable distance between the rear bumper and the road surface in the first digital image and a second variable distance between the rear bumper and the road surface in the second digital image;

determining a first geometric ratio from the first digital image by normalizing the first variable distance using the first constant distance;

determining a second geometric ratio from the second digital image by normalizing the second variable distance using the second constant distance; and

in response to determining that the second geometric ratio is less than the first geometric ratio, detecting, by the second vehicle, a braking action of the first vehicle.

11 . The computer system of claim 10 , further comprising:

capturing a first set of sequential digital images of the first vehicle, wherein the first captured set of sequential digital images includes the first digital image of the first vehicle and the second digital image of the first vehicle; and

establishing a geometric ratio range for the first vehicle based on the first captured set of sequential digital images, wherein the established geometric ratio range includes a lower geometric ratio threshold and an upper geometric ratio threshold.

12 . The computer system of claim 11 , further comprising:

capturing a second set of sequential digital images of the first vehicle;

determining a third geometric ratio associated with the rear portion of the first vehicle from the second captured set of sequential digital images; and

monitoring the third determined geometric ratio to detect whether the third determined geometric ratio falls below the lower geometric ratio threshold of the established geometric ratio range.

13 . The computer system of claim 12 , further comprising:

in response to detecting that the monitored third determined geometric ratio falls below the lower geometric ratio threshold of the established geometric ratio range, predicting a sudden-brake action of the first vehicle; and

triggering an intervention in the second vehicle behind the first vehicle to prevent a collision between the second vehicle and the first vehicle.

14 . A computer program product for brake detection, comprising:

one or more computer-readable storage media and program instructions collectively stored on the one or more computer-readable storage media, the program instructions executable by a processor to cause the processor to perform a method comprising:

processing pixel data of a first digital image and a second digital image of a rear portion of a first vehicle, the first digital image and the second digital image captured by a camera associated with a second vehicle traveling behind the first vehicle;

based on the processed pixel data, for each of the first digital image and the second digital image, automatically:

detecting two laterally spaced rear reference features fixed on the rear portion of the first vehicle and determining, from the first digital image, a first constant distance between the two laterally spaced rear reference features and, from the second digital image, a second constant distance between the two laterally spaced rear reference features; and

detecting a rear bumper of the first vehicle and a road surface and determining a first variable distance between the rear bumper and the road surface in the first digital image and a second variable distance between the rear bumper and the road surface in the second digital image;

determining a first geometric ratio from the first digital image by normalizing the first variable distance using the first constant distance;

determining a second geometric ratio from the second digital image by normalizing the second variable distance using the second constant distance; and

in response to determining that the second geometric ratio is less than the first geometric ratio, detecting, by the second vehicle, a braking action of the first vehicle.

15 . The computer program product of claim 14 , further comprising:

capturing a first set of sequential digital images of the first vehicle, wherein the first captured set of sequential digital images includes the first digital image of the first vehicle and the second digital image of the first vehicle; and

establishing a geometric ratio range for the first vehicle based on the first captured set of sequential digital images, wherein the established geometric ratio range includes a lower geometric ratio threshold and an upper geometric ratio threshold.

16 . The computer program product of claim 15 , further comprising:

capturing a second set of sequential digital images of the first vehicle;

determining a third geometric ratio associated with the rear portion of the first vehicle from the second captured set of sequential digital images; and

monitoring the third determined geometric ratio to detect whether the third determined geometric ratio falls below the lower geometric ratio threshold of the established geometric ratio range.

17 . The computer program product of claim 16 , further comprising:

in response to detecting that the monitored third determined geometric ratio falls below the lower geometric ratio threshold of the established geometric ratio range, predicting a sudden-brake action of the first vehicle; and

triggering an intervention in the second vehicle behind the first vehicle to prevent a collision between the second vehicle and the first vehicle.