Obstacle determination system and method implemented through utilizing bird's-eye-view images

• US 20110026771A1
• Filed: 10/06/2009
• Published: 02/03/2011
• Est. Priority Date: 07/31/2009
• Status: Active Grant

• Current Assignee: Automotive Research & Testing Center
• Original Assignee: Automotive Research & Testing Center
• Inventors: Hsu, Tzu-Chien, Chen, Chia-Tseng
• Granted Patent: US 8,315,433 B2
• Time in Patent Office: Days
• US Class Current: 382/104
• 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 technology of determining obstacles around a vehicle through utilizing bird'"'"'s-eye-view images; wherein, a plurality of image fetching devices disposed in various positions of said vehicle fetch a plurality of images around said vehicle, said images of two adjacent regions contain at least an overlapped region; an image processor transforms said images into said respective independent bird'"'"'s-eye-view images; and an obstacle detection unit compares said overlapped region in said independent bird'"'"'s-eye-view images of two adjacent regions, so as to obtain their correlations, and existence of said obstacle is determined based on said correlations. Moreover, a correspondence table is set up containing a set of space transformation information based on vehicle driving condition information. Therefore, a surrounding bird'"'"'s-eye-view image of an appropriate visual angle can be produced quickly and a position of said obstacle is marked on said surrounding bird'"'"'s-eye-view image.

Claims

1. An obstacle determination system implemented through utilizing bird'"'"'s-eye-view images, comprising:

a plurality of image fetching devices, installed on a vehicle and that are used to obtain a plurality of images around said vehicle;

an image processor, used to convert said images respectively into a plurality of independent bird'"'"'s-eye-view images, wherein, said independent bird'"'"'s-eye-view images of two adjacent regions contain said image of an overlapped region; and

an obstacle detection unit, used to compare correlation of said overlapped regions in said independent bird'"'"'s-eye-view images of said two adjacent regions, and determine existence of an obstacle based on said correlation.

2. The obstacle determination system implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 1, further comprising:

a vehicle signal fetching device, used to fetch a steering-wheel-turning-angle signal, a vehicle speed signal, or a gear shifting signal, said image processor is used to transform and obtain a surrounding bird'"'"'s-eye-view image based on signals fetched by said vehicle signal fetching device, a virtual visual angle of said surrounding bird'"'"'s-eye-view image can be varied based on variations of said steering-wheel-turning-angle signal of said vehicle.

3. The obstacle determination system implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 2, wherein

said image processor further includes a plurality of correspondence tables, said correspondence tables are used to perform image distortion correction, image perspective transformation, and images stitching, thus obtaining said transformed surrounding bird'"'"'s-eye-view image.

4. The obstacle determination system implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 2, wherein

said image processor further includes a plurality of correspondence tables, that contain space transformation information relating to said steering-wheel-turning angle of said vehicle and a position of said image fetching device.

5. The obstacle determination system implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 2, further comprising:

a displayer, electrically connected to said image processor, said displayer is used to output said surrounding bird'"'"'s-eye-view image, and mark a position of said obstacle in said surrounding bird'"'"'s-eye-view image.

6. The obstacle determination system implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 5, wherein

said displayer is used to display vehicle driving assistance lines or parking assistance lines around said vehicle.

7. The obstacle determination system implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 1, wherein

said obstacle detection unit is used to divide said overlapped region in said independent bird'"'"'s-eye-view images of said two adjacent regions into a plurality of sub-regions, calculate and obtain a correlation coefficient of said sub-region of said overlapped regions in said independent bird'"'"'s-eye-view images of said two adjacent regions, and determine if said obstacle exists in said sub-region based on said correlation coefficient, hereby obtaining a distance between said vehicle and said obstacle.

8. The obstacle determination system implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 7, wherein

a formula of calculating said correlation coefficient is as follows:

9. The obstacle determination system implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 7, further comprising:

an alarm device, such as a light-emitting-diode (LED), a buzzer or a loudspeaker, and that is used to send out alarm signals in reminding a driver to pay attention to said obstacle.

10. The obstacle determination system implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 1, wherein

said image fetching device can be a charge-coupled-display (CCD) camera or a composite metal-oxide-semiconductor (CMOS) camera.

11. An obstacle determination method implemented through utilizing bird'"'"'s-eye-view images, comprising the following steps:

fetching vehicle signals of a vehicle, selecting a corresponding correspondence table, and fetching a plurality of images around said vehicle, producing a surrounding bird'"'"'s-eye-view image based on said correspondence table, wherein, said image of two adjacent regions contain an overlapped region;

transforming said images respectively into a plurality of independent bird'"'"'s-eye-view images;

determining correlation of said overlapped region in said independent bird'"'"'s-eye-view images of two adjacent regions;

determining if an obstacle exists in said overlapped region; and

if said obstacle does exist in said overlapped region, then marking said obstacle in said surrounding bird'"'"'s-eye-view image.

12. The obstacle determination method implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 11, wherein

a virtual viewpoint of said surrounding bird'"'"'s-eye-view image can be varied according to a steering-wheel-turning-angle signal.

13. The obstacle determination method implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 11, wherein

said step of determining said correlation of said overlapped regions in said independent bird'"'"'s-eye-view images of said two adjacent regions further includes a step of:

dividing said overlapped region in said independent bird'"'"'s-eye-view images of said two adjacent regions into a plurality of sub-regions, and calculating a correlation coefficient for said sub-regions of said overlapped region in said independent bird'"'"'s-eye-view images of said two adjacent regions, and determining if said obstacle exists in said sub-region as based on said correlation coefficient, hereby obtaining a distance between said vehicle and said obstacle.

14. The obstacle determination method implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 13, wherein

a formula of calculating said correlation coefficient is as follows:

15. The obstacle determination method implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 11, wherein

said correspondence table contains space transformation information set up as based on said vehicle signal and a position of said image fetching device.

16. The obstacle determination method implemented through utilizing bird'"'"'s-eye-view images as claimed in claim 11, wherein

said vehicle signal includes:

a steering-wheel-turning-angle signal, a gear-shift signal, or a vehicle speed signal.