Зарегистрироваться
Восстановить пароль
FAQ по входу

Burger W., Bhanu B. Qualitative Motion Understanding

  • Файл формата pdf
  • размером 5,57 МБ
  • Добавлен пользователем
  • Отредактирован
Burger W., Bhanu B. Qualitative Motion Understanding
Springer, 1992. — 220.
Mobile robots operating in real-world, outdoor scenarios depend on dynamic scene understanding for detecting and avoiding obstacles, recognizing landmarks, acquiring models, and for detecting and tracking moving objects. Motion understanding has been an active research area for more than a decade to solve some of these problems. However, it still remains one of the more difficult and challenging areas of computer vision research.
Most of the previous work on motion analysis has used one of two techniques. The first technique employs numeric methods for the reconstruction of 3-D motion and scene structure from perspective 2-D image sequences. The structure and motion of a rigid object are computed simultaneously by solving systems of linear or nonlinear equations. This technique has been reported to be noise sensitive even when more than two frames are used. The second technique relies on the characteristic expansion patterns experienced by a moving observer. The basic idea is that, when a camera moves forward along a straight line in space, every point in the image seems to diverge from a single point, called the focus of expansion (FOE), and each image point's rate of expansion depends on the point's location in the field-of-view and the distance between the robot and the point.
This book describes a qualitative approach to dynamic scene and motion analysis, called DRIVE (Dynamic Reasoning from Integrated Visual Evidence). The DRIVE system addresses the problems of (a) estimating the robot's egomotion, (b) reconstructing the observed 3-D scene structure, and (c) evaluating the motion of individual objects from a sequence of monocular images. The approach is based on the FOE-concept but it takes a somewhat unconventional route. The DRIVE system uses a qualitative scene model and a fuzzy focus of expansion to estimate robot motion from visual cues, to detect and track moving objects, and to construct and maintain a global dynamic reference model.
Introduction
Framework for Qualitative Motion Understanding
Effects of Camera Motion
Decomposing Image Motion
The Fuzzy Foe
Reasoning About Structure and Motion
The Qualitative Scene Model
Examples
Summary
  • Чтобы скачать этот файл зарегистрируйтесь и/или войдите на сайт используя форму сверху.
  • Регистрация