Sri International

Sarnoff Corporation

Chao Zhang

Gooitzen Sieman Van Der Wal

Peter Jeffrey Burt

Wenyi Zhao

James Russell Bergen

Wenyl Zhao

A computer implemented method for fusing images taken by a plurality of cameras is disclosed, comprising the steps of: receiving a plurality of images of the same scene taken by the plurality of cameras; generating Laplacian pyramid images for each source image of the plurality of images; applying contrast normalization to the Laplacian pyramids images; performing pixel-level fusion on the Laplacian pyramid images based on a local salience measure that reduces aliasing artifacts to produce one salience-selected Laplacian pyramid image for each pyramid level; and combining the salience-selected Laplacian pyramid images into a fused image. Applying contrast normalization further comprises, for each Laplacian image at a given level: obtaining an energy image from the Laplacian image; determining a gain factor that is based on at least the energy image and a target contrast; and multiplying the Laplacian image by a gain factor to produce a normalized Laplacian image.

Multi-scale adaptive fusion with contrast normalization

Multi-scale multi-camera adaptive fusion with contrast normalization

A scene-based non-uniformity correction method super-resolution for eliminating fixed pattern noise in a video having a plurality of input images is disclosed, comprising the steps of warping each of the plurality of images with respect to a reference image to obtain a warped set of images; performing one of averaging and deblurring on the warped set of images to obtain an initial estimate of a reference true scene frame; warping the initial estimate of the reference true scene frame with respect to each of the plurality of images to obtain a set of estimated true signal images; performing a least square fit algorithm to estimate a gain image and an offset image given the set of estimated true signal images; applying the estimated gain image and estimated offset image to the plurality of images to obtain a clean set of images; and applying a super-resolution algorithm to the clean set of images to obtain a higher resolution version of the reference true scene frame.

Scene-based non-uniformity correction and enhancement method using super-resolution

A scene-based non-uniformity correction method employing local constant statistics for eliminating fixed pattern noise in a video comprising a plurality of images is disclosed, comprising the steps of providing an initial gain image, an initial offset image, a predetermined pyramid level, and a filter of a predetermined level; setting one of the plurality of input images to the current image; calculating a temporary true scene image for the current image based on the initial gain image and the initial offset image; accumulating a temporal mean image and a temporal standard deviation image based on the calculated temporary true scene image; setting another of the plurality of images to the current image and repeating the setting, calculating, and accumulating steps until substantially all of the images of the plurality of images have been processed, otherwise further perform the steps of calculating a Gaussian mean image based on the accumulated temporal mean and calculating a Gaussian gain image based on the accumulated temporal standard deviation image; spectrum shaping the Gaussian mean image and the Gaussian gain image based on the predetermined pyramid level and the filter of a predetermined level; multiplying the spectrum shaped Gaussian gain image by the initial gain image to obtain a final gain image; and multiplying the spectrum shaped Gaussian mean image by the initial gain image and add the initial offset image to obtain a final offset image.

Scene-based non-uniformity correction method using local constant statistics

A method and apparatus for reducing noise in at least one frame in an image sequence is disclosed. A minimum function is applied to the at least one frame to produce a plurality of minimum values. A mask is generated in accordance with the plurality of minimum values. The mask is applied to reduce the noise in the at least one frame. In one embodiment, impulse noise is reduced. In another embodiment wideband non-linear noise is reduced.

Growing community of inventors

Belle Mead, NJ, United States of America

Chao Zhang