Single Two-dimensional Image Research Articles

Techniques for segmenting image curves into meaningful descriptions

This paper describes an approach to the detection of straight lines and circular arcs in images. The algorithm uses a measure based on significance proposed by D. G. Lowe (Three-dimensional object recognition from single two-dimensional images, Artificial Intelligence 31, 355–395 (1987)). Edge points are processed to produce a description combining lines and arcs. No thresholds are required for either (1) fitting the best lines and arcs to the data or (2) choosing between the best line and arc fits as the most appropriate description. Results are presented demonstrating the performance on complex images.

Recognizing solid objects by alignment with an image

In this paper we consider the problem of recognizing solid objects from a single two-dimensional image of a three-dimensional scene. We develop a new method for computing a transformation from a three-dimensional model coordinate frame to the two-dimensional image coordinate frame, using three pairs of model and image points. We show that this transformation always exists for three noncollinear points, and is unique up to a reflective ambiguity. The solution method is closed-form and only involves second-order equations. We have implemented a recognition system that uses this transformation method to determine possible alignments of a model with an image. Each of these hypothesized matches is verified by comparing the entire edge contours of the aligned object with the image edges. Using the entire edge contours for verification, rather than a few local feature points, reduces the chance of finding false matches. The system has been tested on partly occluded objects in highly cluttered scenes.

Three-dimensional object recognition from single two-dimensional images

A computer vision system has been implemented that can recognize three-dimensional objects from unknown viewpoints in single gray-scale images. Unlike most other approaches, the recognition is accomplished without any attempt to reconstruct depth information bottom-up from the visual input. Instead, three other mechanisms are used that can bridge the gap between the two-dimensional image and knowledge of three-dimensional objects. First, a process of perceptual organization is used to form groupings and structures in the image that are likely to be invariant over a wide range of viewpoints. Second, a probabilistic ranking method is used to reduce the size of the search space during model-based matching. Finally, a process of spatial correspondence brings the projections of three-dimensional models into direct correspondence with the image by solving for unknown viewpoint and model parameters. A high level of robustness in the presence of occlusion and missing data can be achieved through full application of a viewpoint consistency constraint. It is argued that similar mechanisms and constraints form the basis for recognition in human vision.

One-Eyed Stereo: A General Approach to Modeling 3-D Scene Geometry

A single two-dimensional image is an ambiguous representation of the three-dimensional world¿many different scenes could have produced the same image¿yet the human visual system is ex-tremely successful at recovering a qualitatively correct depth model from this type of representation. Workers in the field of computational vision have devised a number of distinct schemes that attempt to emulate this human capability; these schemes are collectively known as ``shape from...'' methods (e.g., shape from shading, shape from texture, or shape from contour). In this paper we contend that the distinct assumptions made in each of these schemes is tantamount to providing a second (virtual) image of the original scene, and that each of these approaches can be translated into a conventional stereo formalism. In particular, we show that it is frequently possible to structure the problem as one of recovering depth from a stereo pair consisting of the supplied perspective image (the original image) and an hypothesized orthographic image (the virtual image). We present a new algorithm of the form required to accomplish this type of stereo reconstruction task.

High-speed three-dimensional X-ray computed tomography: The dynamic spatial reconstructor

Most X-ray CT scanners require a few seconds to produce a single two-dimensional (2-D) image of a cross section of the body. The accuracy of full three-dimensional (3-D) images of the body synthesized from a contiguous set of 2-D images produced by sequential CT scanning of adjacent body slices is limited by 1) slice-to-slice registration (positioning of patient); 2) slice thickness; and 3) motion, both voluntary and involuntary, which occurs during the total time required to scan all slices. Therefore, this method is inadequate for true dynamic 3-D imaging of moving organs like the heart, lungs, and circulation. To circumvent these problems, the Dynamic Spatial Reconstructor (DSR) was designed by the Biodynamics Research Unit at the Mayo Clinic to provide synchronous volume imaging, that is stop-action (1/100 s), high-repetition rate (up to 60/s), simultaneous scanning of many parallel thin cross sections (up to 240, each 0.45 mm thick, 0.9 mm apart) spanning the entire anatomic extent of the bodily organ(s)of interest. These capabilities are achieved by using multiple X-ray sources and multiple 2-D fluoroscopic video camera assemblies on a continually rotating gantry. Desired tradeoffs between temporal, spatial, and density resolution can be achieved by retrospective selection and processing of appropriate subsets of the total data recorded during a continuous DSR scan sequence.