Equinox Corporation

Diego A Socolinsky

Lawrence B Wolff

Christopher K Eveland

Joshua D Neuheisel

Andrea Selinger

A methodology and apparatus is described that registers images outputted by at least two video camera sensors that are not necessarily bore-sighted nor co-located together. Preferably this can be performed in real-time at least at video rate. The two video camera sensors can be either of similar or two different modalities (e.g., one can be intensified visible, while the other can be thermal infrared) each possibly with a different field-of-view. The methodology and apparatus take advantage of a combination of Inertial Measurement Units (IMUs) information and image registration between the two camera sensors from computational image processing. In one preferred embodiment, the system uses a rifle mounted weapon sight camera sensor and a helmet mounted sensor camera. The aim point of the weapon sight camera sensor (e.g., typically at the image center) zeroed to the true rifle aim point is digitally overlayed as a reticle on the video image from the helmet sensor, displayed on a head mounted display (HMD). In another embodiment pixel-level image fusion is displayed across the overlapping field-of-view of the rifle mounted camera sensor weapon sight with the helmet mounted camera image.

Method and apparatus for dynamic image registration

A methodology for forming a composite color image fusion from a set of N gray level images takes advantage of the natural decomposition of color spaces into 2-D chromaticity planes and 1-D intensity. This is applied to the color fusion of thermal infrared and reflective domain (e.g., visible) images whereby chromaticity representation of this fusion is invariant to changes in reflective illumination.

Color invariant image fusion of visible and thermal infrared video

A methodology and apparatus is described that incorporates the use of thermal infrared imaging into a complete end-to-end face recognition system. Since thermal infrared primarily images emissive phenomenology there are advantages over video imaging in the reflective domain (e.g., visible, near-infrared) for face recognition, particularly with respect to image invariance in the presence of varying illumination incident on the subject. On the other hand video cameras in the reflective domain provide important image detail not apparent in thermal infrared imagery. Fusion of thermal infrared imagery with reflective domain (e.g., visible, near-infrared) imagery provides even further advantages. Embodiments of such systems that incorporate thermal infrared imaging for automatic face recognition are important for access control, verification, identification, and surveillance and monitoring.

Method and apparatus for using thermal infrared for face recognition

A method is presented for the treatment and visualization of local contrast in n-dimensional multispectral images, which directly applies to n-dimensional multisensor images as well. A 2&times;2 matrix called the contrast form is defined comprised of the first derivatives of the n-dimenional image function with respect to the image plane, and a local metric defined on n-dimensional photometric space. The largest eigenvector of this 2&times;2 contrast form encodes the inherent local contrast at each point on the image plane. It is shown how a scalar intensity function defined on n-dimensional photometric space is used to select a preferred orientation for this eigenvector at each image point in the n-dimensional image defining the contrast vector field for an n-dimensional image. A grey level visualization of local n-dimensional image contrast is produced by the greylevel image intensity function such that the sum of the square difference between the components of the gradient vector of this intensity function and the components of the contrast vector field is minimized across the image plane. This is achieved by solving the corresponding Euler-Lagrange equations for this variational problem. An m-dimensional image, 1<m<n, visualization of n-dimensional data is produced by an m-dimensional image function such that the sum of the square difference between the components of the contrast form of this m-dimensional image and the components of the contrast form for the n-dimensional image is minimized across the image plane.

Growing community of inventors

Baltimore, MD, United States of America

Diego A Socolinsky