Integrated 3D analysis of flight image sequences

Abstract

This paper is concerned with three-dimensional (3D) analysis of images showing 3D motion of an observer relative to a scene. It presents an approach to recovering 3D motion and structure parameters from multiple features present in a monocular image sequence such as points, regions, lines, texture gradient and vanishing line. For concreteness, the paper focuses on flight images of a planar, textured surface. In this paper, a linear integrated estimation method using two views is developed. Then, for robust estimation, a nonlinear integrated estimation method using multiple frames is presented. The integration of information in these diverse features is carried out using minimization of image errors. To reduce computation, a sequential-batch method is used to compute motion and structure. Performance is evaluated through simulations and experiments with a real image sequence digitized from a commercially available laserdisc of films taken from flying aircrafts.

The support of Defense Advanced Research Projects Agency and the National Science Foundation under grant IRI-89-02728 is gratefully acknowledged.

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.