ACCIDENT AVOIDANCE DURING VEHICLE BACKUP

• US 20090174536A1
• Filed: 01/09/2008
• Published: 07/09/2009
• Est. Priority Date: 01/09/2008
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Rao, Manoharprasad K.
• Granted Patent: US 7,772,991 B2
• Time in Patent Office: Days
• US Class Current: 340/436
• 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

Abstract

In one embodiment, the present invention is directed to a method to operate a host vehicle having a rearview camera vision sensor, and an electronic controller with memory. The method comprises the steps of determining whether the host vehicle is in reverse gear, activating a rearview camera vision sensor on said host vehicle to detect objects, determining host vehicle motion and path of travel, simultaneously determining an inter-frame difference metric and a histogram difference metric of the field of view of said rearview camera, determining a dynamic scene change, determining a collision threat assessment based upon said dynamic scene change, and activating warnings and collision avoidance moves,

Claims

1. A method to operate a host vehicle having a rearview camera vision sensor, and an electronic controller with memory, comprising:

determining whether the host vehicle is in reverse gear;

activating a rearview camera vision sensor on said host vehicle to monitor the camera field of view and detect moving objects;

determining host vehicle motion and path of travel;

simultaneously determining an inter-frame difference metric and a histogram difference metric of the field of view of the said rearview camera;

determining a dynamic scene change;

determining a collision threat assessment based upon said dynamic scene change; and

activating warnings and collision avoidance moves.

2. The method of claim 1, wherein said inter-frame difference metric is determined according to the formula:

$\mathrm{dt}=\sqrt{\left(1/\mathrm{MN}*\underset{\mathrm{ij}}{\sum <br><br>}<br><br>{\left(f_{\mathrm{xy}}<br><br>\left(t\right)-f_{\mathrm{xy}}<br><br>\left(t-1\right)\right)}^2\right)}$

Wherein f_xy(t) is the pixel value at the frame location (x, y);

and M and N are the number of pixels in the x and y directions respectively.

3. The method of claim 1, wherein said inter-frame difference metric is used to detect dynamic scene changes according to the formula:

d_ij=f_ij(t)−

f_ij(t−

1)

Wherein, f_ij(t) is the pixel value at the frame location (ij);

then applying;

$\underset{\mathrm{ij}}{\sum <br><br>}<br><br>d_{\mathrm{ij}}^2\ge <br><br>{\mathrm{\tau <br><br>}}_d$

Where τ

_d≧

0 is taken as an inter-frame dynamic motion threshold.

4. The method of claim 3, wherein said threshold is selected according to the formula:

${\mathrm{\tau <br><br>}}_x=\min +\frac{\max -\min }{3}$

Where min and max are the minimum and maximum values of the inter-frame difference for a frame.

5. The method of claim 1, wherein said histogram difference between frames is determined according to the formula:

$h_t=\left(1/N_b\right)<br><br>\underset{b}{\sum <br><br>}<br><br><br><br>{}^{h}r_b<br><br>\left(t\right)-{}^{h}r_b<br><br>\left(t-1\right)<br><br>$

Wherein;

N_b is the number of bins and

^hr_b(t) is the count in the bin b at the time t.

6. The method of claim 1, wherein said histogram difference metric for dynamic scene changes is determined according to the formula:

$h_t=\left(1/N_b\right)<br><br>\underset{b}{\sum <br><br>}<br><br><br><br>{}^{h}r_b<br><br>\left(t\right)-{}^{h}r_b<br><br>\left(t-1\right)<br><br>\ge <br><br>{\mathrm{\tau <br><br>}}_h$

Wherein, τ

_h is an appropriate threshold.

7. The method of claim 1, wherein said warnings and collision avoidance moves include automatically applying vehicle brakes, flashing lights, and providing audio signals to warn by-standers.

8. The method of claim 1, wherein said warnings and collision avoidance moves further include providing haptic, audio and visual warning signals to the vehicle operator.