Vehicle collision warning system and method

• US 9,139,133 B2
• Filed: 05/31/2012
• Issued: 09/22/2015
• Est. Priority Date: 05/31/2012
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Eng, Donald, Weigert, Norman J., Chau, Jarvis
• Primary Examiner(s): Perungavoor, Sath V
• Assistant Examiner(s): Young, Patricia I
• Application Number:
  US13/485,291
• Publication Number:
  US 20130321628A1
• Time in Patent Office: 1,209 Days
• Field of Search: 348/148, 348/E07.085, 701/36, 701/301, 382/103, 382/107, 340/436
• US Class Current: 1/1
• CPC Class Codes: B60R 1/00 Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
• CPC Class Codes: B60R 1/24 in front of the vehicle
• CPC Class Codes: B60R 1/31 providing stereoscopic vision
• CPC Class Codes: B60R 2300/307 virtually distinguishing relevant parts of a scene from the background of the scene
• CPC Class Codes: B60R 2300/8093 for obstacle warning
• CPC Class Codes: G08G 1/165 for passive traffic, e.g. including static obstacles, trees
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes

Abstract

A vehicle collision warning system and method that alerts a driver of an impending collision by displaying enhanced video of an upcoming road segment, where the enhanced video includes an in-path object that is highlighted so that it stands apart. In one exemplary embodiment, the system and method receive video of an upcoming road segment from a forward-looking vision system, obtain certain collision data for an in-path object, and then use the video and the collision data to provide enhanced video to a visual display that is seen by the driver. The enhanced video may include an in-path object that is highlighted according to the collision data (e.g., highlighted with a color-coded scheme where the in-path object changes color based on time-to-collision data) so that it stands apart from the rest of the upcoming road segment.

Claims

1. A collision warning system for a vehicle, comprising:

a vision system being mounted on the vehicle, the vision system provides color video of an upcoming road segment that includes at least one in-path object;

a control module being coupled to the vision system, the control module receives the color video from the vision system and provides enhanced video of the upcoming road segment that includes the in-path object, wherein the in-path object is highlighted in color according to collision data by graying out a background of the color video so that the in-path object stands apart from the rest of the upcoming road segment which is in black and white; and

a color heads-up display (HUD) being coupled to the control module, the color heads-up display (HUD) receives the enhanced video from the control module and displays the enhanced video to a driver on a windshield of the vehicle, wherein the enhanced video that is displayed on the color heads-up display (HUD) includes the in-path object in color set against the rest of the upcoming road segment in black and white so as to create a contrast that acts as an intuitive warning to the driver.

2. The collision warning system of claim 1, wherein the vision system is a forward-looking stereo vision system and includes a plurality of video cameras, the vision system provides real-time video of the upcoming road segment.

3. The collision warning system of claim 1, wherein the control module receives both the video and the collision data from the vision system.

4. The collision warning system of claim 1, wherein the control module receives the video from the vision system and the collision data from at least one object-detecting sensor that is separate from the vision system.

5. The collision warning system of claim 4, wherein the object-detecting sensor is an infrared (IR) sensor that is directed at the upcoming road segment and provides time-to-collision data for the in-path object.

6. The collision warning system of claim 1, wherein the control module provides enhanced video of the upcoming road segment that includes the in-path object highlighted with a color that changes according to the collision data so that it becomes more noticeable to the driver as the vehicle gets closer to the in-path object.

7. A method of operating a collision warning system for a vehicle, comprising the steps of:

(a) receiving color video from a vision system, the color video is of an upcoming road segment and includes a plurality of pixels associated with an in-path object;

(b) receiving collision data from one or more object detecting sensors, the collision data pertains to the in-path object and is used in conjunction with the color video to determine time-to-collision values for the plurality of pixels associated with the in-path object;

(c) using the color video and the collision data to generate enhanced video, the enhanced video is of the upcoming road segment and includes the in-path object which is highlighted in color for at least some of the plurality of pixels associated with the in-path object according to the time-to-collision values and the remaining pixels of the upcoming road segment that are not associated with the in-path object are grayed out so as to be in black and white; and

(d) providing the enhanced video to a visual display and displaying the enhanced video with the in-path object in color set against the remaining pixels in black and white.

8. The method of claim 7, wherein step (a) further comprises continuously receiving video on a real-time basis so that the video streams from the vision system.

9. The method of claim 7, wherein step (a) further comprises intermittently receiving video on an event basis so that the video is provided from the vision system only when the in-path object is detected.

10. The method of claim 7, wherein step (c) further comprises filtering out a plurality of pixels in the video that are not associated with the in-path object.

11. The method of claim 10, wherein step (c) further comprises determining a priority level for the plurality of pixels in the video that are associated with the in-path object, and the priority level is based on the time to-collision values.

12. The method of claim of claim 11, wherein step (c) further comprises selecting between a first priority level with a first range of time-to-collision values, a second priority level with a second range of time-to-collision values, and a third priority level with a third range of time-to-collision values.

13. The method of claim 11, where step (c) further comprises highlighting the plurality of pixels in the video that are associated with the in-path object with a certain color that is selected according to a priority level.

14. The method of claim 13, wherein step (c) further comprises removing the plurality of pixels in the video that are not associated with the in-path object so that they are not displayed in the enhanced video.

15. The method of claim 7, wherein step (d) further comprises providing the enhanced video to a head-up display (HUD) so that the in-path object is highlighted and stands apart from the rest of the upcoming road segment.

16. The method of claim 7, wherein step (d) further comprises providing enhanced video to the visual display that includes multiple in-path objects, where each in-path object is highlighted according to a priority scheme that is based on time-to-collision data.

17. A method of operating a collision warning system for a vehicle, comprising the steps of:

(a) receiving color video from a vision system, the color video is of an upcoming road segment and includes a plurality of pixels associated with an in-path object;

(b) receiving collision data from one or more object detecting sensors, the collision data pertains to the in-path object and is used in conjunction with the color video to determine time-to-collision values for the plurality of pixels associated with the in-path object;

(c) using the color video and the collision data to generate enhanced video, the enhanced video is of the upcoming road segment and includes the in-path object which is highlighted in color for at least some of the plurality of pixels associated with the in-path object according to the time-to-collision values and the remaining pixels of the upcoming road segment that are not associated with the in-path object are removed; and

(d) providing the enhanced video to a visual display and displaying the enhanced video with the in-path object in color and the remaining pixels of the upcoming road segment removed.