Self-adaptive image-based obstacle detection method
US8934669B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 7, 2012 |
| Grant date | Jan 13, 2015 |
| Priority date | — |
| Expiry date | Aug 10, 2033 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V20/588
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A self-adaptive image-based obstacle detection method comprises steps: capturing an original image; transforming the original image to an HSV color space, and retrieving a hue component (H) and a saturation component (S) of the HSV color space to form an HS-based image; dividing the HS-based image into image blocks; selecting one image block as a background block; using an obstacle recognition equation to determine whether each of the image blocks is similar to the background block; if no, deleting the image block; if yes, preserving the image block to form a binary obstacle image; and overlaying the binary obstacle image on the original image to filter out the background and obtain an initial ambit of an obstacle image. Then, three orderly movement flow equations are used to determine whether it is an obstacle.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.