Two-dimensional Scene Research Articles

Adaptive Bayesian Classification of Spatial Data

Abstract A two-dimensional scene is analyzed statistically by superimposing on it a rectangular grid and studying each square picture element (pixel) as one unit of the entire picture. With each pixel we want to associate one of K labels, but the label must be determined. Labels may be related to one another spatially, reflecting an underlying pattern in the scene. There is a noisy observation vector associated with each pixel, and these vectors are used contextually to classify the pixels; that is, to determine their labels in an effort to reconstruct the true scene. The discretized picture and the K labels constitute a lattice structure. We assume there is prior information available to assist in the reconstruction. The adaptive Bayesian classification (ABC) procedure proposed is iterative. It starts with a formal predictive contextual Bayesian classification of the entire map, then proceeds by adaptively reclassifying all of the labels in the map at each iteration using an empirical Bayesian updating algorithm. The ABC algorithm provides an approximation to a local maximum for the joint posterior classification probability of all pixels in the map. The procedure attempts to improve on other such iterative procedures by reestimating parameters and reclassifying pixels by conditioning initially on prior information via the predictive Bayesian paradigm. It is “adaptive Bayesian” in that its initial reconstruction stage is formal Bayesian, and it also uses a Bayes theorem-type argument for updating the data at each iteration. Applications include image processing of remotely sensed satellite data, photon emission tomography, and computer vision.

A unifying approach to iconic indexing for 2-D and 3-D scenes

Several iconic indexes for representing three-dimensional scenes are presented. The approach extends previous work in iconic indexing of two-dimensional scenes in a unified manner. Good characteristics for iconic indexes are also pointed out. OPP2 and OPP3, two-dimensional iconic indexes for three-dimensional scenes, are introduced. The problem of ambiguity in the OPP2 and OPP3 representations of three-dimensional scenes is studied in detail and a class of images for which they are unambiguous is identified. The Genstring, a linear iconic index which can be used to represent two-, three-, or higher-dimensional scenes, is introduced. It provides a compact, unambiguous representation of a three-dimensional scene. The Genstring takes advantage of previous work, thus providing fast pattern matching for higher-dimensional scenes. In fact, the pattern matching algorithm given for k-dimensional scenes is as fast as that previously given for two-dimensional scenes. >

Shortest paths without a map

We study several versions of the shortest-path problem when the map is not known in advance, but is specified dynamically. We are seeking dynamic decision rules that optimize the worst-case ratio of the distance covered to the length of the (statically) optimal path. We describe optimal decision rules for two cases: layered graphs of width two, and two-dimensional scenes with unit square obstacles. The optimal rules turn out to be intuitive, common-sense heuristics. For slightly more general graphs and scenes, we show that no bounded ratio is possible. We also show that the computational problem of devising a strategy that achieves a given worst-case ratio to the optimum path in a graph with unknown parameters is a universal two-person game, and thus PSPACE-complete, whereas optimizing the expected ratio is #P-hard.

Design Options For Optically Restructuring Damaged Image Detectors

Engineering guidelines are presented for selecting and implementing a method to optically restructure a damaged detector. Under certain conditions, undamaged areas of a detector can be coalesced to maintain recording continuity of a two-dimensional object scene with minimal loss of total detector area. This goal can be achieved by using relay lenses in specific arrangements and in some cases by locating a biprism or a coherent fiber bundle near an image surface. Optical correction and performance are identified with the parameters of detector and damage sizes.

Path-planning strategies for a point mobile automaton moving amidst unknown obstacles of arbitrary shape

The problem of path planning for an automaton moving in a two-dimensional scene filled with unknown obstacles is considered. The automaton is presented as a point; obstacles can be of an arbitrary shape, with continuous boundaries and of finite size; no restriction on the size of the scene is imposed. The information available to the automaton is limited to its own current coordinates and those of the target position. Also, when the automaton hits an obstacle, this fact is detected by the automaton's “tactile sensor.” This information is shown to be sufficient for reaching the target or concluding in finite time that the target cannot be reached. A worst-case lower bound on the length of paths generated by any algorithm operating within the framework of the accepted model is developed; the bound is expressed in terms of the perimeters of the obstacles met by the automaton in the scene. Algorithms that guarantee reaching the target (if the target is reachable), and tests for target reachability are presented. The efficiency of the algorithms is studied, and worst-case upper bounds on the length of generated paths are produced.

The perception of coherent motion in two-dimensional patterns (abstract only)

When one looks at a two-dimensional scene of moving objects, one can usually assign a velocity to each point in that scene with little effort. This suggests that some early visual processes are able to generate a two-dimensional velocity map using fast parallel computations. But it is not obvious how this should be done, and we are currently trying to understand how the human visual system does it.

Background Suppression And Tracking With A Staring Mosaic Sensor

This paper presents theoretical analysis for a staring mosaic infrared sensor with representative examples of data processing from a computer simulation. The analysis treats (1 ) generation of synthetic two-dimensional scenes with specified cloud geometry and desired statistical characteristics, (2) processing of frames of data from two-dimensional scenes to represent temporal, spatial, and multispectral filtering, and (3) thresholding and examination of processed scenes to implement track association. The temporal filtering includes multiple differencing, statistically optimal nonrecursive filtering, and recursive filtering. Methods are presented for reducing the computation load when calculating the optimal coefficients in spatial and multispectral filtering. The track association uses thresholding and examination to eliminate stationary objects and facilitate track assembly. For visual display, the two-dimensional scenes and the processed frames are output with a forty-eight level gray scale.

A parallel-serial recognition cone system for perception: some test results

This paper presents some results of tests of specific “recognition cone” systems for probabilistic parallel-serial recognition and description of two-dimensional scenes of objects. SIMULA and FORTRAN encoded systems were given particular sets of transforms, and examined for their ability to handle scenes that contain (1) letters, (2) “place-settings” of several pieces of silverware and china and (3) a “real-world” outdoor scene, in color. The same parallel-serial flow through structured layers of variable-resolution probabilistic transforms serves to detect edges, find features, characterize, recognize and describe, without any sharp dividing lines between different types of processes. Thus, a wide variety of diverse sources of information contextually interact, in a relatively simple and general way.