A space-sweep approach to true multi-image matching

Published 1 January 1996

Robert T. Collins

DOI10.1109/cvpr.1996.517097

Citations606

TL;DR

A new space-sweep approach to true multi-image matching is presented that simultaneously determines 2D feature correspondences and the 3D positions of feature points in the scene.

Abstract

The problem of determining feature correspondences across multiple views is considered. The term "true multi-image" matching is introduced to describe techniques that make full and efficient use of the geometric relationships between multiple images and the scene. A true multi-image technique must generalize to any number of images, be of linear algorithmic complexity in the number of images, and use all the images in an equal manner. A new space-sweep approach to true multi-image matching is presented that simultaneously determines 2D feature correspondences and the 3D positions of feature points in the scene. The method is illustrated on a seven-image matching example from the aerial image domain.

Keywords

Computer ScienceEngineering

IEEE Transactions on Pattern Analysis and Machine IntelligenceA Computational Approach to Edge Detection

29,107 Citations1986John Canny

There is a natural uncertainty principle between detection and localization performance, which are the two main goals, and with this principle a single operator shape is derived which is optimal at any scale.

IEEE Transactions on Pattern Analysis and Machine IntelligenceA multiple-baseline stereo

938 Citations1993Masatoshi Okutomi, Takeo Kanade

A space-sweep approach to true multi-image matching

606 Citations1996Robert T. Collins

A new space-sweep approach to true multi-image matching is presented that simultaneously determines 2D feature correspondences and the 3D positions of feature points in the scene.

International Journal of Computer VisionObject-centered surface reconstruction: Combining multi-image stereo and shading

246 Citations1995Pascal Fua, Y.G. Leclerc

It is argued that an object-centered representation is most appropriate for this purpose because it naturally accommodates multiple sources of data, multiple images (including motion sequences of a rigid object), and self-occlusions.

View PDF

Development of a video-rate stereo machine

229 Citations2002Takeo Kanade, Hiroshi KANO +3 more

A video-rate stereo machine has been developed at CMU with the capability of generating a dense range map, aligned with an intensity image, at the video rate, with high throughput and high precision.

Matching constraints and the joint image

193 Citations2002Bill Triggs

The geometry of multi image perspective projection and the matching constraints that this induces on image measurements are studied and their complex algebraic interdependency is captured by quadratic structural simplicity constraints on the Grassmannian.

View PDF

Direct recovery of shape from multiple views: a parallax based approach

165 Citations2002Raman Kumar, P. Anandan +1 more

The authors exploit the above theorem to infer 3D height information from oblique aerial 2D images and develop methods to infer height information under the following three conditions: focal length and image center are both known, only the focal length is known, and both are unknown.

Lecture notes in computer scienceTrilinearity in visual recognition by alignment

158 Citations1994Amnon Shashua

The trilinearity result is shown to be of much practical use in visual recognition by alignment — yielding a direct method superior to the conventional epipolar line intersection method.

View PDF

Complete scene structure from four point correspondences

52 Citations2002Steven M. Seitz, Charles R. Dyer

An efficient recursive algorithm is described that uses a unified framework for point and line features and is immune to outliers and feature drift, two weaknesses of existing structure from motion techniques.

Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE<title>RADIUS: the government viewpoint</title>

6 Citations1992Donald J. Gerson

The Office of Research and Development, with major involvement and support from the Defense Advanced Research Projects Agency (DARPA), has begun a highly applications- oriented project intended to provide image understanding technology in a fully and semi- automated support system of human-machine interface interactive tools to the photo interpreter and imagery analyst.