Abstract: Techniques are provided for image-based estimation of the orientation of an airborne platform. A methodology implementing the techniques according to an embodiment includes rotating an image, provided by a camera on the platform, by a selected rotation angle. The method also includes computing an intensity gradient image based on the rotated image. The method further includes extracting a left quarter segment and a right quarter segment of the intensity gradient image. The method further includes flipping one of the extracted segments about a vertical axis through that segment and comparing the non-flipped segment to the flipped segment to generate a matching score. The comparison may be based on a correlation between the flipped segment and the non-flipped segment. The process may be repeated for additional rotation angles and the rotation angle associated with the highest matching score is selected as the estimated orientation angle of the platform.

Abstract: Techniques are provided for image-based estimation of the orientation of an airborne platform. A methodology implementing the techniques according to an embodiment includes rotating an image, provided by a camera on the platform, by a selected rotation angle. The method also includes computing an intensity gradient image based on the rotated image. The method further includes extracting a left quarter segment and a right quarter segment of the intensity gradient image. The method further includes flipping one of the extracted segments about a vertical axis through that segment and comparing the non-flipped segment to the flipped segment to generate a matching score. The comparison may be based on a correlation between the flipped segment and the non-flipped segment. The process may be repeated for additional rotation angles and the rotation angle associated with the highest matching score is selected as the estimated orientation angle of the platform.

Abstract: An image registration system and method for matching images having fundamentally different characteristics. One exemplary feature of the system and method includes the use of an enhanced phase correlation method combined with a coarse sensor model to hypothesize and match a custom match metric to determine a best solution. The system and method may be operated on a non-transitory computer-readable medium storing a plurality of instructions which when executed by one or more processors causes the one or more processors to perform the image registration method utilizing the enhanced phase correlation.

Abstract: An image registration system and method for matching images having fundamentally different characteristics. One exemplary feature of the system and method includes the use of an enhanced phase correlation method combined with a coarse sensor model to hypothesize and match a custom match metric to determine a best solution. The system and method may be operated on a non-transitory computer-readable medium storing a plurality of instructions which when executed by one or more processors causes the one or more processors to perform the image registration method utilizing the enhanced phase correlation.