SEMI-AUTOMATIC ALGORITHM FOR CONSTRUCTING THE CONTOUR OF AREA OBJECTS ON MULTISPECTRAL SATELLITE IMAGE

Author:

NEDZVEDZ A.1,QING Bu2,BELOTSERKOVSKY A.3

Affiliation:

1. Belarusian State University

2. Nanjing Research Institute of Electronics Engineering

3. United Institute of Informatics Problems of the National Academy of Sciences of Belarus

Abstract

This article formalizes the problem of semi-automatic construction of the contour of area objects from satellite multispectral images and presents a solution algorithm using PCA and Dijkstra's algorithm. The emphasis of the article is on optimizing PCA using annual matrices for images of the same class, as well as optimizing the Dijkstra algorithm using dynamic programming methods. The contour is considered as the boundary of an object, which can be used for its segmentation and classification. The semi-automatic contour accepts reference points specified by the operator. The formalization of the algorithm is completed.

Publisher

Polotsk State University

Reference15 articles.

1. Sojfer, V. A. (2003). Metody komp'juternoj obrabotki izobrazhenij. Moscow: FIZMATLIT. (In Russ.).

2. Furman, Ja. A., Jur'ev, A. N., & Janshin, V. V. (1992). Cifrovye metody obrabotki i raspoznavanija binarnyh izobrazhenij. Krasnojarsk: Izd-vo Krasnojar. un-ta. (In Russ.).

3. Vershinina, V. V., Palamar', I. N. (2002). Organizacija bazy znanij semanticheskoj seti na osnove XML-formata. In IV VNTK «Informacionnye tehnologii v nauke, proektirovanii i proizvodstve» (23). N. Novgorod: MVVO ATN RF. (In Russ.).

4. Ognev, I. V., Sidorova, N. A. (2007). Obrabotka izobrazhenij metodami matematicheskoj morfologii v associativnoj oscilljatornoj srede. Tehnicheskie nauki. Informatika i vychislitel'naja tehnika, (4), 87–98. (In Russ.).

5. Fisenko, V. T., Fisenko, T. Ju. (2008). Komp'juternaja obrabotka i raspoznavanie izobrazhenij. St. Petersburg: SPbGU ITMO. (In Russ.).

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3