Abstract: Video mosaicing is commonly used to increase the visual field of view by pasting together many video frames. The invention provides for image mosaicing for general camera motion, including forward camera motion and zoom. After computing the motion between the images in a sequence, strips are selected from individual frames such that the strips are approximately perpendicular to the optical flow. The strips are warped such that the optical flow becomes parallel, and are pasted to a panoramic mosaic. The warping transformation on the strips, which results in making the optical flow to be parallel, can be modeled by an oblique projection of the image onto a cylindrical surface whose central axis is the trajectory of the camera. In addition, this invention uses view interpolation to generate dense intermediate views between original video frames, such that these intermediate views are used to overcome effects of motion parallax when creating panoramic mosaics.

Abstract: A stereoscopic image arrangement includes at least one stereoscopic data source, at least one utilization device and a distribution channel. The at least one stereoscopic data source records images from which a stereoscopic image set can be generated. The utilization device is provided to facilitate viewing, printing, or otherwise utilizing the stereoscopic image set. The distribution channel facilitates transferring information between the stereoscopic data source and the utilization device, the information including the images as recorded by the stereoscopic data source or the stereoscopic image set itself. A number of stereoscopic data sources of diverse configurations are disclosed, including fixed and moving mirrors, prisms, and lenses, which may be used in the stereoscopic data source in the stereoscopic image arrangement.

Abstract: A method of generating a mosaic from a plurality of camera images of a scene acquired by a camera moving relative to the scene, the method comprising: associating with each camera image a value of at least one variable so that the variable is a substantially a linear function of a spatial coordinate that defines the locations of the camera at which it acquires the images by requiring that a coordinate of pixels in the camera images that image a same feature in the scene is substantially a linear function of the variable; and generating the mosaic responsive to the at least one variable.

Abstract: A system for generating a stereoscopic panoramic image pair having left and right panoramic mosaic images for use in facilitating stereoscopic viewing of a panoramic scene, the system comprising a panoramic image generator and a strip separation value generation module. The panoramic image generator is configured to mosaic together respective left and right image strips from respective ones of a plurality of images to form the respective left and right panoramic images. The panoramic image generator is configured to use strip separation values for the respective images to determine the separation of the respective left and right image strips in generating the respective left and right panoramic images. The strip separation value generation module is configured to generate, for respective ones of said images, the strip separation values so as to provide at least one selected disparity for objects in the panoramic scene.

Abstract: A stereoscopic image arrangement includes at least one stereoscopic data source, at least one utilization device and a distribution channel. The at least one stereoscopic data source records images from which a stereoscopic image set can be generated. The utilization device is provided to facilitate viewing, printing, or otherwise utilizing the stereoscopic image set. The distribution channel facilitates transferring information between the stereoscopic data source and the utilization device, the information including the images as recorded by the stereoscopic data source or the stereoscopic image set itself. A number of stereoscopic data sources of diverse configurations are disclosed, including fixed and moving mirrors, prisms, and lenses, which may be used in the stereoscopic data source in the stereoscopic image arrangement.

Abstract: Various camera arrangements are disclosed comprising a camera and an optical element. The camera is configured to record an image defined by light rays directed thereto. The optical element is configured to deflect rays from a scene to the camera for recording thereby. The optical element is further configured to deflect the rays such that, if the rays were undeflected, the rays would instead be tangent to a viewing device of predetermined shape, such as a circle. Optical elements may be in the form of curved mirrors or lenses. The camera arrangements are configured to record images in the form of left or right panoramic images of a stereo panoramic image pair, and several stereo panoramic camera arrangements are described, including one or more camera arrangements, for contemporaneously recording both left or right panoramic images of a stereo panoramic image pair.

Abstract: A recognition system which obtains and analyzes images of at least one object in a scene comprising a wide field of view (WFOV) imager which is used to capture an image of the scene and to locate the object and a narrow field of view (NFOV) imager which is responsive to the location information provided by the WFOV imager and which is used to capture an image of the object, the image of the object having a higher resolution than the image captured by the WFOV imager is disclosed. In one embodiment, a system that obtains and analyzes images of the irises of eyes of a human or animal in an image with little or no active involvement by the human or animal is disclosed.

Abstract: A super-resolution enhanced image generating system is described for generating a super-resolution-enhanced image from an image of a scene, identified as image g0, comprising a base image and at least one other image gi, the system comprising an initial super-resolution enhanced image generator, an image projector module and a super-resolution enhanced image estimate update generator module. The initial super-resolution enhanced image generator module is configured to use the image g0 to generate a super-resolution enhanced image estimate. The image projector module is configured to selectively use a warping, a blurring and/or a decimation operator associated with the image gi to generate a projected super-resolution enhanced image estimate. The super-resolution enhanced image estimate update generator module is configured to use the input image gi and the super-resolution enhanced image estimate to generate an updated super-resolution enhanced image estimate.

Abstract: Systems are disclosed for generating left and right panoramic mosaic images for use in facilitating panoramic stereoscopic viewing of a scene, and for displaying stereoscopic panoramic images to a viewer. The left and right panoramic image generators generate the left and right panoramic mosaic images from a series of images recorded or otherwise generated corresponding to respective angular or other positions, each image having a respective left and right image portion, and mosaics portions of those images together to form the respective left and right panoramic images. The display system displays a stereoscopic panoramic image to a viewer by displaying left and right panoramic images such that each is viewed by a respective one of the viewer's eyes.

Abstract: A method for automated computerized audio visual dubbing of a movie comprises (i) generating a three-dimensional head model of an actor in a movie, the head model being representative of specific facial features of the actor, and (ii) generating a three-dimensional head model of a dubber making target sounds for the actor, the dubber head model being representative of specific facial features of the dubber, as the target sounds are made. The method also comprises modifying at least a portion of the specific facial features of the actor head model according to the dubber head model such that the actor appears to be producing target sounds made by the dubber.

Abstract: Video mosaicing is commonly used to increase the visual field of view by pasting together many video frames. The invention provides for image mosaicing for general camera motion, including forward camera motion and zoom. After computing the motion between the images in a sequence, strips are selected from individual frames such that the strips are approximately perpendicular to the optical flow. The strips are warped such that the optical flow becomes parallel, and are pasted to a panoramic mosaic. The warping transformation on the strips, which results in making the optical flow to be parallel, can be modeled by an oblique projection of the image onto a cylindrical surface whose central axis is the trajectory of the camera. In addition, this invention uses view interpolation to generate dense intermediate views between original video frames, such that these intermediate views are used to overcome effects of motion parallax when creating panoramic mosaics.

Abstract: A method for combining a sequence of two-dimensional images of a scene to construct a panoramic mosaic of the scene has a sequence of images acquired by a camera with relative motion to the scene. The relative motion gives rise to an optical flow between the images. The images are warped so that the optical flow becomes substantially parallel to a direction in which the mosaic is constructed and pasted so that the sequence of the images is continuous for the scene to construct the panoramic mosaic of the scene. For this, the images are projected onto a three-dimensional cylinder having a major axis that approximates the path of an optical center of the camera. The combination of the images is achieved by translating the projected two-dimensional images substantially along the cylindrical surface of the three-dimensional cylinder.

Abstract: A method using computer software for automatic audio visual dubbing (5) using an efficient computerized automatic method for audio visual dubbing of movies by computerized image copying of the characteristic features of the lip movements of the dubber onto the mouth area of the original speaker. The invention uses a method of vicinity-searching, three-dimensional head modeling of the original speaker (3), and texture mapping (10) technique to produce new images which correspond to the dubbed sound track: The invention thus overcomes the well known disadvantage of the correlation problems between lip movement in an original movie and the sound track of the dubbed movie.

Abstract: A super-resolution-enhanced mosaic image generating system is provided for generating a super-resolution-enhanced mosaic image from a plurality of image frames, each image frame being associated with image data representative of an image of a portion of a scene. The mosaic image generating system comprises a mosaic image generator and a super-resolution generator. The mosaic image generator uses the image data from the image frames to generate mosaic image data representing a mosaic image. The super-resolution generator uses the mosaic image data and the image data from the image frames to generate the super-resolution-enhanced mosaic image. In that process, the super-resolution generator divides the mosaic image into a plurality of patches, each patch associated with at least one image frame, and performs a super-resolution operation in connection with the patch and image frames associated therewith to generate the super-resolution-enhanced mosaic image.

Abstract: A system is described for generating a stereoscopic panoramic image pair comprising left and right panoramic mosaic images for use in facilitating stereoscopic viewing of a panoramic scene, the system comprising a panoramic image generator and a strip separation value generation module. The panoramic image generator is configured to mosaic together respective left and right image strips from respective ones of a plurality of images to form the respective left and right panoramic images. The panoramic image generator is configured to use strip separation values for the respective images to determine the separation of the respective left and right image strips in generating the respective left and right panoramic images. The strip separation value generation module is configured to generate, for respective ones of said images, the strip separation values so as to provide at least one selected disparity for objects in the panoramic scene.

Abstract: Various camera arrangements are disclosed comprising a camera and an optical element. The camera is configured to record an image defined by light rays directed thereto. The optical element is configured to deflect rays from a scene to the camera for recording thereby. The optical element is further configured to deflect the rays such that, if the rays were undeflected, the rays would instead be tangent to a viewing device of predetermined shape, such as a circle. Optical elements may be in the form of curved mirrors or lenses. The camera arrangements are configured to record images in the form of left or right panoramic images of a stereo panoramic image pair, and several stereo panoramic camera arrangements are described, including one or more camera arrangements, for contemporaneously recording both left or right panoramic images of a stereo panoramic image pair.

Abstract: A method of constructing an image mosaic comprising the steps of selecting source images, aligning the source images, selecting source segments, enhancing the images, and merging the images to form the image mosaic is disclosed. An apparatus for constructing an image mosaic comprising means for selecting source images, means for aligning the source images, means for selecting source image segments, means for enhancing the images, and means for merging the images to form the image mosaic is also disclosed. The process may be performed automatically by the system or may be guided interactively by a human operator. Applications include the construction of photographic quality prints form video and digital camera images.

Abstract: A method for indexing video sequences relative to a reference model. A system implementing the method includes an (optional) image pre-processor that produces the reference model or is provided the reference model. The pre-processor is then provided input image data such as a video sequence containing a series of frames of a particular scene. The pre-processor performs a transformation to align the images within the video sequence with the reference model. The pre-processor then stores the transformation, the reference model and the image data within a mass storage device such as a hard disk drive. Subsequently, the system provides access to the information stored within the mass storage device through a user interface. The user may recall and position on a computer screen the reference model, select a particular point within the reference model, and request that the system produce all of the image data that contains that particular point within the reference model.

Abstract: An iterative process, implemented by a feedback loop, responds to all the image data in the respective analysis regions of three consecutive frames of a motion picture, to provide, after a plurality of cycles of operation thereof, an accurate estimation of the motion of either one or both of two differently moving patterns defined by the image data of these respective analysis regions. The analysis region of each frame is preferably large, and may occupy the entire frame area of a frame. The type of differently moving patterns include (1) separation by a motion bounty, (2) overlapping transparent surface in motion, (3) "picket fence" motion (4) masking of a small and/or low-contrast pattern by a dominant pattern, and (5) two-component aperture effects. Also, the operation of this iterative process inherently accurately estimates the motion of image data defining a single moving pattern.