| 摘要 |
A system for image processing is provided. The system includes a region of interest (ROI) module receiving video from a camera and detects a ROI(s) in a first image. A lookup table generates a value responsive to a block type for a first vanishing point (VP). A labeling module identifies a point “p” most close to the first VP, a point “q” most remote to the first VP and a length “h” between “p” and “q” in each ROI(s), and generates information on p, q and h. Another lookup table generates information on p′, q′ and h′, wherein p′ is a point most close to a second VP, q′ is a point most remote to the second VP and h′ is a length between p′ and q′ in ROI(s) in the second image. A transforming module transforms ROI(s) in the first image into an ROI in the second image. |
