Abstract: The method discloses a method of segmenting an image. The method firstly (304) allocates pixels as seeds in areas of an image as a function of the luminance of the pixels and the size of those areas. The method then grows (306) regions from said seeds so as to segment the image into a number of regions. The method considers a number of pixels that border the growing regions and the pixel that is most similar in luminance to a region it borders is appended (528) to that region. The method then updates (528) the luminance of the appended region. The method continues until there are no more pixels bordering the growing regions. The method then encodes the segmented image (106). It does this by splitting (604) the image into a number of rectangular sub-images in a quadtree manner until each rectangular sub-image comprises a segmented image forming the dominant portion of the sub-image. The method then merges (606) rectangular sub-images which have a common dominant portion and share a common edge.

Abstract: The method discloses a method of segmenting moving objects and determining their motion from video data. The method generates (104) a motion vector field by comparing the current frame of video data with the previous frame, where a motion vector is determined for each pixel of the current frame. The method then generates (106) a motion parameter field by sliding a window over the motion vector field of the current frame, and determining a set of motion parameters for each pixel based on a motion model of the motion vector field. The method then distributes (108) seeds throughout the motion parameter field so that fewer seeds are allocated to those areas of the motion parameter field having homogeneous motion parameter sets. The method then grows (110) regions from said seeds so as to segment the motion parameter field into a number of regions.