Abstract: Techniques are provided for segmentation of objects in video frames. A methodology implementing the techniques according to an embodiment includes receiving image frames, including an initial reference frame, and receiving a mask to outline a region in the reference frame that contains the object to be segmented. The method also includes calculating Gaussian mixture models associated with both the masked region and a background region external to the masked region. The method further includes segmenting the object from a current frame based on a modelling of the pixels within an active area of the current frame as a Markov Random Field of nodes for cost minimization. The costs are based in part on the Gaussian mixture models. The active area is based on the segmentation of a previous frame and on an estimation of optical flow between the previous frame and the current frame.

Abstract: Image scene labeling with 3D image data. A plurality of pixels of an image frame may be label based at least on a function of pixel color and a pixel depth over the spatial positions within the image frame. A graph-cut technique may be utilized to optimize a data cost and neighborhood cost in which at least the data cost function includes a component that is a dependent on a depth associated with a given pixel in the frame. In some embodiments, in the MRF formulation pixels are adaptively merged into pixel groups based on the constructed data cost(s) and neighborhood cost(s). These pixel groups are then made nodes in the directed graphs. In some embodiments, a hierarchical expansion is performed, with the hierarchy set up within the label space.

Abstract: Image scene labeling with 3D image data. A plurality of pixels of an image frame may be label based at least on a function of pixel color and a pixel depth over the spatial positions within the image frame. A graph-cut technique may be utilized to optimize a data cost and neighborhood cost in which at least the data cost function includes a component that is a dependent on a depth associated with a given pixel in the frame. In some embodiments, in the MRF formulation pixels are adaptively merged into pixel groups based on the constructed data cost(s) and neighborhood cost(s). These pixel groups are then made nodes in the directed graphs. In some embodiments, a hierarchical expansion is performed, with the hierarchy set up within the label space.

Abstract: Techniques are provided for segmentation of objects, in videos comprising a sequence of color and depth image frames. A methodology implementing the techniques according to an embodiment includes receiving image frames, including an initial reference frame, and receiving a mask to outline a region in the reference frame that contains the object to be segmented. The method also includes calculating Gaussian mixture models associated with both the masked region and a background region external to the masked region. The method further includes segmenting the object from a current frame based on a modelling of the pixels within an active area of the current frame as a Markov Random Field of nodes for cost minimization. The costs are based in part on the Gaussian mixture models. The active area is based on the segmentation of a previous frame and on an estimation of optical flow between the previous frame and the current frame.