A segmentation system (100) for segmenting a first image feature (214) in a first video image from an adjacent second image feature (216) in the first video image on basis of motion and on an image property like color or luminance. The segmentation system (100) comprises; a block-based motion estimator (102) for estimating motion vectors (218-230) for blocks of pixels; a motion segmentation unit (104) for segmenting the first video image into a first group of connected blocks of pixels (204) and a second group of connected blocks of pixels (206) on basis of the motion vectors (218-230) of the respective blocks of pixels; and a pixel-based segmentation unit (106) for segmenting the first image feature (214) from the second image feature (214) by means of a pixel-based segmentation of a portion of the blocks of pixels of the first and second group of connected blocks of pixels (214 and 216), on basis of the respective values of the image property.

A digital image segmentation method and device is provided. The method includes the steps of grouping an image stream into a plurality of continuous frame groups, setting one arbitrary frame as an I frame and the others as P frames in each group, segmenting the I frame into a plurality of regions, and segmenting the P frames by obtaining motion vectors, using motion prediction, of the segmented I frame regions, respectively, with respect to each of the P frames, by moving the segmented I frame regions by the respective motion vectors, and by setting the moved I frame regions as segmented P frame regions. Accordingly, the segmentation of the I frame is applied to the P frame segmentation, and a conventional segmentation process consuming excessive time with respect to all frames does not need to be performed. Thus, rapid segmentation can be performed.

In a video signal processing method, video signal parts are labeled (L) as non-matchable parts (N-M) if reliable motion or depth information (d1, d2) cannot be obtained for such parts (N-M), motion or depth information (d1, d2) is generated for the video signal (V), and motion or depth information (d1, d2) is produced for the non-matchable parts (N-M) of the video signal (V) from the motion or depth information generated for the video signal (V).

A mechanism for improving connectivity processing of computer axial tomography and magnetic resonance images by a fast, stack independent, iterative method first designates a pixel of an object material of interest in an image as a seed pixel. The mechanism then performs connectivity processing by starting at the seed pixel and evaluating the next forward direct neighbor pixel to determine if it is within the object material of interest. If the direct neighbor pixel is within the object, the direct neighbor pixel is marked as a new seed pixel and the connectivity mechanism evaluates the next forward direct neighbor pixel, continuing in a left-to-right and top-to-bottom fashion. Once forward processing of all pixels is complete, and if at least one pixel has been identified as a new seed pixel, the connectivity mechanism evaluates, in a backward progression, unevaluated pixel within the image, beginning at the lower right-most pixel in the image and proceeding through the pixels in a right-to-left, bottom-to-top fashion.

The disclosed method provides a new resolution of the aperture problem, which is one of the basic problems present in motion estimation technology. The method constitutes a resolution of this problem by means of adaptive transfer to smaller blocks. The approach consists of adaptive partitioning of the picture with the use of quadratic trees. If an aperture problem is detected in the block, then the block partitions with the help of quadratic trees into smaller blocks. The partitioning continues until either the aperture problem is resolved or the smallest size block is reached. Through the use of this method, the aperture problem is successfully resolved without substantial loss in the degree of compression.