Abstract: A method and apparatus for reducing motion judder in a 3D input source are disclosed. The 3D input source is separated into left and right images. Motion vectors for the left and right images are calculated. Frame rate conversion is performed on the left and right images, to produce motion compensated left and right images. The left and right images and the motion compensated left and right images are reordered for display. Alternatively, the motion estimation and motion compensation can be performed on the 3D input source, and the input image and the motion compensated image can then be separated into respective left and right images. The method and apparatus can be adapted to perform 2D to 3D conversion by extracting a 2D input source into left and right 3D images and performing motion estimation and motion compensation.

Abstract: An endoscope with a stereoscopic optical channel is held and positioned by a robotic surgical system. A capture unit captures (1) a visible first image and (2) a visible second image combined with a fluorescence second image from the light. An intelligent image processing system receives (1) the visible first image and (2) the visible second image combined with the fluorescence second image and generates at least one fluorescence image of a stereoscopic pair of fluorescence images and a visible second image. An augmented stereoscopic display system outputs a real-time stereoscopic image including a three-dimensional presentation including in one eye, a blend of the at least one fluorescence image of a stereoscopic pair of fluorescence images and one of the visible first and second images; and in the other eye, the other of the visible first and second images.

Abstract: A vehicle environment recognition apparatus includes stereo-image taking means for outputting a reference image of the surroundings of a subject vehicle, stereo matching means for correlating a parallax with each pixel block in the reference image by stereo matching, preceding-vehicle detecting means for detecting a preceding vehicle from the reference image on the basis of the parallax or the like, and smear determining means for searching a pixel column vertically extending in the reference image for brightnesses of pixels, the pixel column including a pixel block having a parallax less than or equal to a long-distance parallax threshold value corresponding to the long distance including infinity, and determining that a smear occurs when a ratio of the number of pixels having brightnesses more than or equal to a predetermined brightness to the total number of pixels in the pixel column is more than or equal to a predetermined ratio.

Abstract: A method, medium, and system generating a depth map of a video image are provided. The depth map generating method extracts the ground of a video image other than an object from the video image, classifies the video image as a long shot image or a non-long shot image based on a distribution value of the extracted ground, calculates a depth value gradually varied along a predetermined direction of the extracted ground when the video image corresponds to the long shot image and calculates a depth value based on the object when the video image corresponds to the non-long shot image. Accordingly, a sense of space and perspective can be effectively given to even a long shot image in which the ground occupies a large part of the image and a stereoscopic image recognizable by a viewer can be generated even if rapid object change is made between scenes in a video image.

Abstract: Provided is a method and apparatus for generating a multi-view image data stream, the method including: recording multi-view image data onto the multi-view image data stream; recording onto the multi-view image data stream a multi-view image parameter recording parameter indicating whether a multi-view image parameter with regard to the multi-view image data is to be recorded onto the multi-view image data stream; and determining whether the multi-view image parameter is to be recorded onto the multi-view image data stream based on a value of the multi-view image data parameter recording parameter.

Abstract: A stereo camera comprises at least one image sensor; a first surface configured to direct a first view of an area to the at least one image sensor, the first view comprising an approximately 360 degree view of the area; and a second surface configured to direct a second view of the area to the at least one image sensor, the second view comprising an approximately 360 degree view of the area; wherein the at least one image sensor is configured to capture the first and second views in at least one image.

Abstract: The invention relates to stereo projection systems for displaying stereopaired images on mirror-spherical or parabolic screens and for collectively watching a stereo effect without using stereo spectacles. Said invention makes it possible to continuously dynamically superimpose the projections of the left and right picture frames of a steropair with the user's left and right eyes, respectively. Such impositions are carried out simultaneously and independently for each viewer.

Abstract: A system and method locate a central groove in a document such as a book, magazine, or catalog. In one implementation, scores are generated for points in a three-dimensional image that defines a surface of the document. The scores quantify a likelihood that a particular point is in the groove. The groove is then detected based on the scores. For example, lines may be fitted through the points and a value calculated for the lines based on the scores. The line corresponding to the highest calculated value may be selected as the line that defines the groove.

Abstract: A system includes a stereoscopic camera to generate images of a document, such as a book, that can be converted to a three-dimensional contour of the document. A second camera take a two-dimensional image of the document. A model is generated that defines a mapping between the three-dimensional contour of the document and a two-dimensional flattened (de-warped) version of the document. The model may be applied to the two-dimensional image taken by the second camera to compensate for warping in the image.

Abstract: An image management method which creates and records two or more real images and two or more thumbnail images from two or more images by viewpoints photographed by two or more image pickup devices corresponding to the viewpoints, wherein the real images include a stereoscopic image including the images by viewpoints, a common image range cut from the images by viewpoints and a whole image synthesized from the images by viewpoints, and the thumbnail images include two or more thumbnail images y each viewpoint corresponding to each of images by viewpoints, a 3D thumbnail image corresponding to the stereoscopic image, and a whole thumbnail image corresponding to the whole image.

Abstract: The invention discloses a method and system thereof for displaying a stereoscopic image including left-eye image data and right-eye image data. The invention utilizes persistence of vision to process the stereoscopic image based on display frequency, such that different images can be displayed at different time but on the same line of a screen. Accordingly, when the stereoscopic image is being displayed, the vertical resolution can be enhanced, and discontinuity of frames can be eliminated.