Microsoft Technology Licensing, LLC

General Electric Company

Geoffrey Cross

Antonio Criminisi

Andrew Blake

Vladimir Kolmogorov

Carsten Curt Eckard Rother

Peter Henry Tu

Segmentation of foreground from background layers in an image may be provided by a segmentation process which may be based on one or more factors including motion, color, contrast, and the like. Color, motion, and optionally contrast information may be probabilistically fused to infer foreground and/or background layers accurately and efficiently. A likelihood of motion vs. non-motion may be automatically learned from training data and then fused with a contrast-sensitive color model. Segmentation may then be solved efficiently by an optimization algorithm such as a graph cut. Motion events in image sequences may be detected without explicit velocity computation.

Image segmentation of foreground from background layers

Real-time segmentation of foreground from background layers in binocular video sequences may be provided by a segmentation process which may be based on one or more factors including likelihoods for stereo-matching, color, and optionally contrast, which may be fused to infer foreground and/or background layers accurately and efficiently. In one example, the stereo image may be segmented into foreground, background, and/or occluded regions using stereo disparities. The stereo-match likelihood may be fused with a contrast sensitive color model that is initialized or learned from training data. Segmentation may then be solved by an optimization algorithm such as dynamic programming or graph cut. In a second example, the stereo-match likelihood may be marginalized over foreground and background hypotheses, and fused with a contrast-sensitive color model that is initialized or learned from training data. Segmentation may then be solved by an optimization algorithm such as a binary graph cut.

Stereo image segmentation

Segmentation of foreground from background layers in an image may be provided by a segmentation process which may be based on one or more factors including motion, color, contrast, and the like. Color, motion, and optionally contrast information may be probabilistically fused to infer foreground and/or background layers accurately and efficiently. A likelihood of motion vs. non-motion may be automatically learned from training data and then fused with a contrast-sensitive color model. Segmentation may then be solved efficiently by an optimization algorithm such as a graph cut.

Images of the same scene from multiple cameras may be use to generate a stereo disparity map. At least a portion of the stereo disparity map may be compared to a kernel image to detect and/or determine the location of an object in the disparity map. The kernel image is an array of pixel values which represent the stereo disparity of an object to be located, more particularly, the kernel image indicates the 3-dimensional surface shape of the object to be located from a point of view. The disparity map containing the located object may be process to manipulate the display of the stereo-based image and/or an input image. For example, the display of the image may be cropped and/or zoomed, areas of the image that are not the located object may be modified, an object such as an emoticon or smart-emoticon may be virtually inserted into the three dimensions of the image and may interact with the object, the location of the object in the image may localize further searches, presence of the located object in the image may indicate selected storing of the image and/or image indexing, and/or the located object in the image may be used as a non-standard input device to a computing system.

Stereo-based image processing

A method of determining the leading edge (E) of a turbine blade or airfoil (P). The object is mounted in a desired position and backlit using a light source (S). The object and its leading edge are viewed using one or more cameras (I) which are positioned on the opposite side of the part. When illuminated, the object blocks a portion of the light from the source and the occluded portion of the light defines an outline (T) of the object including its leading edge. An image of the object is obtained and the part is then moved to other positions at which additional images are obtained. The images are processed using a space carving algorithm to ascertain the contour of the leading edge of the object. This allows accurate measurements of the leading edge to be made for using in determining acceptability of the part.

Growing community of inventors

Oxford, United Kingdom

Geoffrey Cross