Efficient use of parallelism in intermediate level vision tasks

The primary task of intermediate level vision (ILV) is to take the output of low level vision, which is typically a subset of pixels from the original image array, and to generate a representation of image content which is appropriate for symbolic manipulations at a higher level. These tasks, e.g. boundary detection, various types of segmentation or the computation of attributes of image components, involve operations on individual pixels, sets of pixels with a common label or on entities extracted from the raw pixel data, such as orientation of lines or distance between pairs of parallel lines. A class of tasks which operate on individual pixels or sets of pixels is described, problems which are raised in parallel implementations of this class of tasks are considered, and solutions are suggested