Martin A. Fischler

Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

A new paradigm, Random Sample Consensus (RANSAC), for fitting a model to experimental data is introduced. RANSAC is capable of interpreting/smoothing data containing a significant percentage of gross errors, and is thus ideally suited for applications in automated image analysis where interpretation is based on the data provided by error-prone feature detectors. A major portion of this paper describes the application of RANSAC to the Location Determination Problem (LDP): Given an image depicting a set of landmarks with known locations, determine that point in space from which the image was obtained. In response to a RANSAC requirement, new results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form. These results provide the basis for an automatic system that can solve the LDP under difficult viewing

Detection of roads and linear structures in low-resolution aerial imagery using a multisource knowledge integration technique☆

This paper describes a computer-based approach to the problem of detecting and precisely delineating roads, and similar “line-like” structures, appearing in low-resolution aerial imagery. The approach is based on a new paradigm for combining local information from multiple, and possibly incommensurate, sources, including various line and edge detection operators, map knowledge about the likely path of roads through an image, and generic knowledge about roads (e.g., connectivity, curvature, and width constraints). The final interpretation of the scene is achieved by using either a graph search or dynamic programming technique to optimize a global figure of merit. Implementation details and experimental results are included.

Outdoor Mapping and Navigation Using Stereo Vision

We consider the problem of autonomous navigation in an unstructured outdoor environment. The goal is for a small outdoor robot to come into a new area, learn about and map its environment, and move to a given goal at modest speeds (1 m/s). This problem is especially difficult in outdoor, off-road environments, where tall grass, shadows, deadfall, and other obstacles predominate. Not surprisingly, the biggest challenge is acquiring and using a reliable map of the new area. Although work in outdoor navigation has preferentially used laser rangefinders [14,2,6], we use stereo vision as the main sensor. Vision sensors allow us to use more distant objects as landmarks for navigation, and to learn and use color and texture models of the environment, in looking further ahead than is possible with range sensors alone.

Context-based vision: recognizing objects using information from both 2D and 3D imagery

Results from an ongoing project concerned with recognizing objects in complex scene domains, especially in the domain that includes the natural outdoor world, are described. Traditional machine recognition paradigms assume either that all objects of interest are definable by a relatively small number of explicit shape models or that all objects of interest have characteristic, locally measurable features. The failure of both assumptions has a dramatic impact on the form of an acceptable architecture for an object recognition system. In this work, the use of the contextual information is a central issue, and a system is explicitly designed to identify and use context as an integral part of recognition that eliminates the traditional dependence on stored geometric models and universal image partitioning algorithms. This paradigm combines the results of many simple procedures that analyze monochrome, color, stereo, or 3D range images. Interpreting the results along with relevant contextual knowledge makes it possible to achieve a reliable recognition result, even when using imperfect visual procedures. Initial experimentation with the system on ground-level outdoor imagery has demonstrated competence beyond what is attainable with other vision systems. >

An optimization-based approach to the interpretation of single line drawings as 3D wire frames

Line drawings provide an effective means of communication about the geometry of 3D objects. An understanding of how to duplicate the way humans interpret line drawings is extremely important in enabling man-machine communication with respect to images, diagrams, and spatial constructs. In particular, such an understanding could be used to provide the human with the capability to create a line-drawing sketch of a polyhedral object that the machine can automatically convert into the intended 3D model.A recently published paper (Marill 1991) presented a simple optimization procedure supposedly able to duplicate human judgment in recovering the 3D “wire frame” geometry of objects depicted in line drawings. Marill provided some impressive examples, but no theoretical justification for his approach. Here, we introduce our own work by first critically examining Marills algorithm. We provide an explanation for why Marills algorithm was able to perform as well as it did on the examples he presented, discuss its weaknesses, and show very simple examples where it fails. We then provide an algorithm that improves on Marills results. In particular, we show that an effective objective function must favor both symmetry and planarity-Marill deals only with the symmetry issue. By modifying Marills objective function to explicitly favor planar-faced solutions, and by using a more competent optimization technique, we were able to demonstrate significantly improved performance in all of the examples Marill provided and those additional ones we constructed ourselves. Finally, we examine some questions relevant to the implications of this work for understanding the human ability to interpret line drawings.

Perceptual Organization and Curve Partitioning

In this paper we offer a critical evaluation of the partitioning (perceptual organization) problem, noting the extent to which it has distinct formulations and parameterizations. We show that most partitioning techniques can be characterized as variations of four distinct paradigms, and argue that any effective technique must satisfy two general principles. We give concrete substance to our general discussion by introducing new partitioning techniques for planar geometric curves, and present experimental results demonstrating their effectiveness.

Locating perceptually salient points on planar curves

This paper describes the underlying ideas and algorithmic details of a computer program that performs at a human level of competence for a significant subset of the curve partitioning task. It extends and rounds out the technique and philosophical approach originally presented by Fischler and Bolles (1986). In particular, it provides a unified strategy for selecting and dealing with interactions between salient points, even when these points are salient at different scales of resolution. Experimental results are presented involving on the order of 1000 real and synthetically generated images. >

An iconic transform for sketch completion and shape abstraction

Abstract This paper shows how a simple label propagation technique, in conjunction with some novel ideas about how labels can be applied to an image to express semantic knowledge, leads to the simplifi ation of a number of diverse and difficult image analysis tasks (e.g., sketch completion and shape abstraction). A single algorithmic technique, based on skeleton and distance transform concepts, is applied to appropriately labeled images to obtain the desired results. A key point is that the initial semantic labeling is not required at every location in the image, but only at those few critical locations where significant changes or discontinuities occur.

Scene modeling: A structural basis for image description

Abstract Conventional statistical approaches to image modeling are fundamentally limited because they take no account of the underlying physical structure of the scene nor of the image formation process. The image features being modeled are frequently artifacts of viewpoint and illumination that have no intrinsic significance for higher-level interpretation. This paper argues for a structural approach to modeling that explicitly relates image appearance to the scene characteristics from which it arose. After establishing the necessity for structural modeling in image analysis, a specific representation for scene structure is proposed and then a possible computational paradigm for recovering this description from an image is described.

Describing and abstracting pictorial structures

Abstract As part of a research program concerned with the nature of descriptive representations of photographic material, it was necessary to obtain answers to questions concerned with the state-of-the-art in indexing and describing pictorial data. In addition to a discussion of the nature and use of pictorial description, three main classes of formal description are surveyed and evaluated: the grammar-based approach, which uses a set of rules to describe the arrangement and relationships among the picture primitives; the descriptor-based approach, which captures the content of the picture by using a number of terms or phrases; and the procedure-based approach, in which a system (possibly grammar-based) capable of generating a large number of descriptions, is coupled to a high-level control mechanism which selects procedures and order of procedures so as to produce only a single desired description.