MULTISCALE APPROACHES TO MOVING TARGET DETECTION IN IMAGE SEQUENCES

被引：5

作者：

ALLEN, TG ^{[1
]}

LUETTGEN, MR ^{[1
]}

WILLSKY, AS ^{[1
]}

机构：

[1] MIT,CAMBRIDGE,MA 02139

来源：

OPTICAL ENGINEERING | 1994年 / 33卷 / 07期

关键词：

ADAPTIVE WAVELET TRANSFORMS; MULTISCALE ESTIMATION; AUTOMATIC TARGET DETECTION; TRACKING; OPTICAL FLOW;

D O I：

10.1117/12.172255

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

We discuss a novel multiscale approach to the detection of moving objects in a sequence of images. The approach is based in part on a multiframe generalization of an optical flow estimation algorithm previously developed by two of the authors. This algorithm provides an extremely efficient multiscale method for estimating optical flow in an image sequence and allows for the temporal accumulation of motion information. Moving objects in a sequence correspond to discontinuities in the true optical flow and, as a result, the residual image associated with the estimated optical flow can be used as a basis for detecting these objects. We propose an approach to detection based on morphological processing of the residual image, and illustrate its potential on real data.

引用

页码：2248 / 2254

页数：7

共 17 条

[1] MODELING AND ESTIMATION OF MULTIRESOLUTION STOCHASTIC-PROCESSES [J].