文章基本信息

标题：A Combined Estimation-Deformation Model for Area Detection: Application to Topographic Area Feature Update
本地全文：下载
作者：Sylvie Jodouin ; Layachi Bentabet ; Djemel Ziou 等
期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2002
卷号：XXXIV Part 3 A
页码：181-186
出版社：Copernicus Publications
摘要：This paper presents a fully a ut oma t ed approach for area detection based on multi-spectral images and features from a topographicdatabase. The vectors residing in the database are refined using active contours (snakes) according to updated information providedby t he multi-spectral images. The conventional methods of defining the external energy of the snake based on statistical measuresor gradient-based boundary finding are often corrupted by p oor image quality. Here a method to integrate the two approaches isproposed using an estimation of the maximum a posteriori (MAP) segmentation in an effort to form a unified approach that isrobust to noise and poor edges. We further propose to improve the accur acy of the resulting boundary l oca tion an update of thesnake topology. A number of experiments are performed on both synthetic and LANDSAT 7 images to evaluate the approach
关键词：active contour; ; multispectral boundary fi nding; region-based segmentation; MAP; change detection; topographic ; databases update; Raster and vector information; integration