Method and apparatus for fusing images from an array of cameras

A non-transitory computer readable medium with executable computer instruction, when executed, performs a method for fusing images from an array of cameras, comprising:

• retrieving input images from an array of cameras;
• selecting at least one camera from the array of cameras as a reference camera;
• estimating misalignment between the retrieved input images from the at least one reference camera and the retrieved input images from the other cameras in the array of cameras;
• estimating misalignment parameters between the at least one reference camera and the other cameras in the array of cameras;
• estimating local disparity between the reference camera image data and the other cameras in the array of cameras based on the estimated misalignment parameters;
• using the estimated misalignment parameters and the estimated disparity values, mapping the image data into a reference camera grid, wherein the retrieved input image data from the other cameras in the array of cameras is fused in the reference camera grid utilizing fractional offsets from integer coordinates;
• and
• producing an output image grid on the reference camera grid and interpolate output pixels using processed data for producing a high-resolution image.

An image fusing system, comprising:

• a memory;
• and
• a digital processor configured to perform an image fusing method by:
• retrieving input images from an array of cameras;
• selecting at least one camera from the array of cameras as a reference camera;
• estimating misalignment between the retrieved input images from the at least one reference camera and the retrieved input images from the other cameras in the array of cameras;
• estimating misalignment parameters between the at least one reference camera and the other cameras in the array of cameras;
• estimating local disparity between the reference camera image data and the other cameras in the array of cameras based on the estimated misalignment parameters;
• using the estimated misalignment parameters and the estimated disparity values, mapping the image data into a reference camera grid, wherein the retrieved input image data from the other cameras in the array of cameras is fused in the reference camera grid utilizing fractional offsets from integer coordinates;
• and
• producing an output image grid on the reference camera grid and interpolate output pixels using processed data for producing a high-resolution image.