Abstract: Briefly, in accordance with one embodiment of the invention, a method of reducing shadows and/or noise in a digital image includes the following. A noise floor for the digital image is estimated. A threshold level for a difference image of the digital image and a background image is determined based, at least in part, on the noise floor estimate. The digital image is modified based, at least in part, on the determined threshold level and the difference image.

Abstract: Simultaneous tracking of multiple objects in a sequence of video frames captured by multiple cameras may be accomplished by extracting a foreground elements from a background in a frame, segmenting objects from the foreground surface, tracking objects within the frame, globally tracking positions of objects over time across multiple frames, fusing track data of objects obtained from multiple cameras to infer object positions, and resolving conflicts to estimate most likely object positions over time. Embodiments of the present invention improve substantially over existing trackers by including a technique for extraction of the region of interest that corresponds to a playing field, a technique for segmenting players from the field under varying illuminations, a template matching criteria that does not rely on specific shapes or color coherency of objects but on connected component properties, and techniques for reasoning about occlusions and consolidating tracking data from multiple cameras.

Abstract: A virtual reality system surveys a real-world environment, generates 3D data that defines the real-world environment, renders a virtual 3D environment using the 3D data, retrieves a virtual object from a database comprised of pre-stored virtual objects, renders the virtual object in the virtual 3D environment, and re-positions the virtual object in the virtual 3D environment.

Abstract: Passively tracking a user's eye gaze while the user is browsing a web page and modifying the presentation of the web page to the user based on the tracked gaze. By combining historical information about a user's direction of gaze on individual cached web pages, a browser may be enabled to represent regions of a web page that have been previously glanced at by the user in a modified manner. For example, sections of a web page that a user has previously read or viewed may be represented in a changed form, such as in a different color, brightness, or contrast, for example. In one embodiment, the portions of the web page previously viewed by the user may be represented as “grayed out” so as to be unobtrusive.

Abstract: Portable virtual reality is disclosed. A digital camera captures an input video stream comprising video frames that carry information about a surrounding environment limited by a field of view of the camera. The input video stream is processed by a handheld computer coupled to the camera. Parameters that define a rendered scene of a virtual environment are adjusted based upon motion parameters extracted from the input video stream by the handheld computer during the processing.

Abstract: Camera driven virtual workspace management is disclosed. A digital camera captures an input video stream comprising images of a surrounding environment limited by a field of view of the camera. The input video stream is processed by a handheld computer coupled to the camera. Parameters that define a partial view of a virtual workspace are redefined based upon motion analysis of the input video stream performed by the handheld computer during the processing.

Abstract: A method comprises, for a plurality of interpolated pixels in an interpolated video frame, classifying an interpolated pixel of the plurality as one of stationary, moving, covered, and uncovered, and then setting components of the interpolated pixel to components of a previous pixel from a previous video frame, the previous pixel corresponding to the interpolated pixel in the video frame. If the interpolated pixel is uncovered, components of the interpolated pixel are set to components of a current pixel from a current video frame if the interpolated pixel is uncovered, the current pixel corresponding to the interpolated pixel in the video frame. If the interpolated pixel is moving, the interpolated pixel is set to a function of the current pixel and the previous pixel.

Abstract: A source model in combination with an interest structure is provided to generate a quantization value for use in encoding a video signal. The interest structure is generated from a region of interest manually identified by a user viewing the video on an interactive user display or automatically by a system which recognizes the regions of interest automatically. The region of interest in the video signal is encoded using a quantization value calculated from the interest structure in combination with the source model, and the region of interest is encoded at a higher resolution level than surrounding regions.

Abstract: Interpolation of a new frame between a previous frame and a current frame of a video stream by motion compensated frame rate upsampling. The interpolation method includes identifying nodes and edges of objects such as triangles present in the previous frame, constructing a superimposed triangular mesh based on the identified nodes and edges, estimating displacement such nodes in the superimposed triangular mesh from the previous frame with respect to the current frame, and rendering the new frame based on the estimated displacement of nodes. Additionally, pixels of the previous frame and the current frame may be classified according to whether a pixel's value has changed from the previous frame to the current frame. This classification may be used during rendering to reduce overall processing time. Pixel-based forward motion estimation may be used to estimate motion of pixels between the previous frame and the current frame and the estimated motion may be used in estimating node displacement.

Abstract: A method for processing image data includes quantizing a region in a frame with an initial quantizer level. It is determined whether an amount of bits required for encoding the region after quantizing the region with the initial quantizer level is within a bit allocation budget. The region is re-quantized if the amount of bits is not within the bit allocation budget.

Abstract: A method comprises, for a plurality of interpolated pixels in an interpolated video frame, classifying an interpolated pixel of the plurality as one of stationary, moving, covered, and uncovered, and then setting components of the interpolated pixel to components of a previous pixel from a previous video frame, the previous pixel corresponding to the interpolated pixel in the video frame. If the interpolated pixel is uncovered, components of the interpolated pixel are set to components of a current pixel from a current video frame if the interpolated pixel is uncovered, the current pixel corresponding to the interpolated pixel in the video frame. If the interpolated pixel is moving, the interpolated pixel is set to a function of the current pixel and the previous pixel.