Method, apparatus and system for processing a display from a surround view camera solution
First Claim
Patent Images
1. A multi-camera image processing method, comprising:
- performing geometric alignment to produce a geometric output, wherein performing the geometric alignment includes;
performing perspective correction on each of a plurality of frames;
performing corner detection in overlapping areas to find regions of interest;
filtering corner data to locate corners;
calculating a descriptor for each of the corners;
matching corners from two cameras using scores;
finding perspective matrices for each of the frames for minimizing distances between matched features; and
creating a geometric lookup table that encodes fisheye lens distortion correction and perspective transformation information, the method further comprising;
performing photometric alignment to produce a photometric output and a blending output;
using the geometric output and the photometric output for performing a synthesis function for at least one of blending and stitching images obtained from the two cameras; and
displaying an image obtained from the synthesis function.
1 Assignment
0 Petitions
Accused Products
Abstract
A method, apparatus and a system multi-camera image processing method. The method includes performing geometric alignment to produce a geometric output, performing photometric alignment to produce a photometric output and blending output, using data from the geometric alignment and the photometric alignment for performing synthesis function for at least one of blending and stitching images from the multi-cameras, and displaying an image from the synthesis function.
23 Citations
16 Claims
-
1. A multi-camera image processing method, comprising:
-
performing geometric alignment to produce a geometric output, wherein performing the geometric alignment includes; performing perspective correction on each of a plurality of frames; performing corner detection in overlapping areas to find regions of interest; filtering corner data to locate corners; calculating a descriptor for each of the corners; matching corners from two cameras using scores; finding perspective matrices for each of the frames for minimizing distances between matched features; and creating a geometric lookup table that encodes fisheye lens distortion correction and perspective transformation information, the method further comprising; performing photometric alignment to produce a photometric output and a blending output; using the geometric output and the photometric output for performing a synthesis function for at least one of blending and stitching images obtained from the two cameras; and displaying an image obtained from the synthesis function. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. An image processing system, comprising:
-
a memory; and a processor coupled to the memory, the processor configured to; perform geometric alignment to produce a geometric output; perform perspective correction on each of a plurality of frames; perform corner detection in overlapping areas to find regions of interest; filter corner data to locate corners; calculate a descriptor for each of the corners; match the corners from two cameras using scores; find perspective matrices for each of the frames for minimizing distances between matched features; create a geometric lookup table that encodes fisheye lens distortion correction and perspective transformation information; perform photometric alignment to produce a photometric output and blending output; use the geometric output and the photometric output for performing a synthesis function for at least one of blending and stitching images obtained from the two cameras; and display an image obtained from the synthesis function. - View Dependent Claims (10, 11, 12, 13, 14, 16)
-
-
15. The image processing system of claim, wherein an output of the photometric lookup table has 255 entries for 8-bit data input.
Specification