Vehicle collision warning prevention method using optical flow analysis

• US 9,834,139 B1
• Filed: 10/20/2016
• Issued: 12/05/2017
• Est. Priority Date: 09/30/2016
• Status: Active Grant

• Current Assignee: PLK Technologies Co., Ltd.
• Original Assignee: PLK Technologies Co., Ltd.
• Inventors: Park, Kwang Il, Lim, Sang Mook, Kim, Jin Hyuck
• Primary Examiner(s): La, Anh V
• Application Number:
  US15/298,651
• Time in Patent Office: 411 Days
• Field of Search: 340435, 340436, 340937, 340903, 340555, 340437, 348148, 348118, 701300, 701301, 180167, 180169
• CPC Class Codes: B60K 2360/167 Vehicle dynamics information
• CPC Class Codes: B60K 2360/176 Camera images
• CPC Class Codes: B60K 2360/177 Augmented reality
• CPC Class Codes: B60K 2360/178 Warnings
• CPC Class Codes: B60K 2360/179 Distances to obstacles or vehicles
• CPC Class Codes: B60K 2360/21 using cameras
• CPC Class Codes: B60K 2370/167 Vehicle dynamics information
• CPC Class Codes: B60K 2370/176 Camera images
• CPC Class Codes: B60K 2370/177 Augmented reality
• CPC Class Codes: B60K 2370/178 Warnings
• CPC Class Codes: B60K 2370/179 Distances to obstacles or vehicles
• CPC Class Codes: B60K 2370/193 for improving awareness
• CPC Class Codes: B60K 2370/21 using cameras
• CPC Class Codes: B60K 35/00 Instruments specially adapted for vehicles; Arrangement of instruments in or on vehicles
• CPC Class Codes: B60K 35/28 characterised by the type of the output information, e.g. video entertainment or vehicle dynamics information; characterised by the purpose of the output information, e.g. for attracting the attention of the driver
• CPC Class Codes: B60Q 5/006 indicating risk of collision between vehicles or with pedestrians
• CPC Class Codes: B60R 2300/30 characterised by the type of image processing
• CPC Class Codes: B60R 2300/8093 for obstacle warning
• CPC Class Codes: G01P 15/00 Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
• CPC Class Codes: G01P 15/18 in two or more dimensions
• CPC Class Codes: G06F 17/11 : for solving equations , e.g. nonlinear equations, general mathematical optimization problems optimization specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06T 2207/10016 : Video; Image sequence
• CPC Class Codes: G06T 2207/10028 : Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30241 : Trajectory
• CPC Class Codes: G06T 2207/30261 : Obstacle
• 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

Abstract

A vehicle collision warning prevention method includes the steps of: (a) extracting a forward video of a vehicle and video recognition information from a video recognition module mounted in a vehicle, and detecting a size change rate of a forward object included in the video recognition information at each frame of the forward video; (b) calculating an average OFCR of a predetermined frame section; (c) determining whether a value obtained by subtracting the average OFCR from a current OFCR is less than a predetermined threshold value; (d) determining that a brake operation signal is generated when it is determined that the value is less than the threshold value; (e) determining whether a collision warning signal is generated within a predetermined time after the step (d); and (f) preventing an output of the collision warning signal when the collision warning signal is generated at the step (e).

Claims

1. A vehicle collision warning prevention method using optical flow analysis, comprising the steps of:

(a) extracting a forward video of a vehicle and video recognition information from a video recognition module mounted in the vehicle, and detecting a size change rate of a forward object included in the video recognition information at each frame of the forward video by an optical flow change rate detection unit;

(b) calculating an average optical flow change rate (OFCR) of a predetermined frame section based on a current point of time by the optical flow change rate detection unit;

(c) determining whether a value obtained by subtracting the average OFCR from a current OFCR is less than a predetermined threshold value by a warning suppression unit;

(d) determining that a brake operation signal is generated when it is determined at the step (c) that the value is less than the threshold value by the warning suppression unit;

(e) determining whether a collision warning signal is generated within a predetermined time after the step (d); and

(f) preventing an output of the collision warning signal when the collision warning signal is generated at the step (e).

2. The vehicle collision warning prevention method of claim 1, wherein the current OFCR is calculated by Equation (1) below, and the average OFCR is calculated by Equation (2) below:

Current OFCR=OP(i)−

OP(i−

1), and 

 

Equation (1);

3. The vehicle collision warning prevention method of claim 1, further comprising the steps of, after the step (c):

(c-1) receiving a moving-direction acceleration signal of the vehicle from an acceleration sensor;

(c-2) calculating integrated acceleration by integrating the received acceleration signal; and

(c-3) determining whether the integrated acceleration calculated at the step (c-2) is less than a predetermined threshold acceleration value by an integrated acceleration calculation unit,

wherein when it is determined at the step (c-3) that the integrated acceleration is less than the threshold value, it is determined at the step (d) that the brake operation signal is generated.

4. The vehicle collision warning prevention method of claim 2, further comprising the steps of, after the step (c):

(c-1) receiving a moving-direction acceleration signal of the vehicle from an acceleration sensor;

(c-2) calculating integrated acceleration by integrating the received acceleration signal; and

(c-3) determining whether the integrated acceleration calculated at the step (c-2) is less than a predetermined threshold acceleration value by an integrated acceleration calculation unit,

wherein when it is determined at the step (c-3) that the integrated acceleration is less than the threshold value, it is determined at the step (d) that the brake operation signal is generated.

5. The vehicle collision warning prevention method of claim 3, further comprising a noise removing step of removing noise of the received acceleration signal using a low pass filter (LPF), after the step (c-1).

6. The vehicle collision warning prevention method of claim 4, further comprising a noise removing step of removing noise of the received acceleration signal using a low pass filter (LPF), after the step (c-1).

7. The vehicle collision warning prevention method of claim 5, wherein in the noise removing step,

the noise is removed by Equation (3):

X_k=α

X_k-1+(1−

α

)x_k,

where X represents an estimated acceleration value, x a represents a current acceleration value, k represent a natural number, and α

represents a constant of 0<

α

<

1.

8. The vehicle collision warning prevention method of claim 6, wherein in the noise removing step,

the noise is removed by Equation (3):

X_k=α

X_k-1+(1−

α

)x_k,

where X represents an estimated acceleration value, x a represents a current acceleration value, k represent a natural number, and α

represents a constant of 0<

α

<

1.

9. The vehicle collision warning prevention method of claim 3, wherein the calculating of the integrated acceleration at the step (c-2) is performed by Equation (4):

Integral acceleration=∫

_T<sup>T+∇

T</sup>A(T)dT,

where T represents time, and A(T) represents the moving-direction acceleration of the vehicle.

10. The vehicle collision warning prevention method of claim 4, wherein the calculating of the integrated acceleration at the step (c-2) is performed by Equation (4):

Integral acceleration=∫

_T<sup>T+∇

T</sup>A(T)dT,

where T represents time, and A(T) represents the moving-direction acceleration of the vehicle.