Coarse-to-fine adaptive masks for appearance matching of occluded scenes |
| |
Authors: | JL Edwards H Murase |
| |
Affiliation: | (1) Media Information Recognition Research Group, NTT Basic Research Labs, Atsugi-shi, Kanagawa 243-01, Japan; e-mail: {jledward,murase}@eye.brl.ntt.jp , JP |
| |
Abstract: | In this paper, we discuss an appearance-matching approach to the difficult problem of interpreting color scenes containing
occluded objects. We have explored the use of an iterative, coarse-to-fine sum-squared-error method that uses information
from hypothesized occlusion events to perform run-time modification of scene-to-template similarity measures. These adjustments
are performed by using a binary mask to adaptively exclude regions of the template image from the squared-error computation.
At each iteration higher resolution scene data as well as information derived from the occluding interactions between multiple
object hypotheses are used to adjust these masks. We present results which demonstrate that such a technique is reasonably
robust over a large database of color test scenes containing objects at a variety of scales, and tolerates minor 3D object
rotations and global illumination variations.
Received: 21 November 1996 / Accepted: 14 October 1997 |
| |
Keywords: | :Object recognition – Occlusion – Appearance matching – Image similarity metrics – Coarse-to-fine search |
本文献已被 SpringerLink 等数据库收录! |
|