Object Detection Using Model-based Prediction and Motion Parallax

Abstract

When a visual observer moves forward, the projections of the objects in the scene will move over the visual image. If an object extends vertically from the ground, its image will move differently from the immediate background. This difference is called motion parallax [1, 2]. Much work in automatic visual navigation and obstacle detection has been concerned with computing motion fields or more or less complete 3-D information about the scene [3–5]. These approaches, in general, assume a very unconstrained environment and motion. If the environment is constrained, for example, motion occurs on a planar road, then this information can be exploited to give more direct solutions to, for example, obstacle detection [6]. Figure 6.1 shows superposed the images from two successive times for an observer translating relative to a planar road. The arrows show the displacement field, that is, the transformation of the image points between the successive time points.