【摘要】：數(shù)據(jù)場(chǎng)通過(guò)模擬物理場(chǎng)中對(duì)象間的相互作用,來(lái)描述數(shù)據(jù)對(duì)象間的相互作用關(guān)系。數(shù)據(jù)場(chǎng)中的勢(shì)值高低反映對(duì)象間相關(guān)程度,故在遙感影像中可用數(shù)據(jù)場(chǎng)來(lái)刻畫(huà)像元間的空間相關(guān)性特征。提出了一種基于數(shù)據(jù)場(chǎng)和密度聚類的高分辨率居民區(qū)有效提取的方法。首先,利用數(shù)據(jù)場(chǎng)計(jì)算遙感影像的勢(shì)值特征圖像;然后,對(duì)勢(shì)值圖像進(jìn)行分水嶺分割,提取分割所得對(duì)象塊的形心;最后,對(duì)形心進(jìn)行基于密度的聚類,從而實(shí)現(xiàn)居民區(qū)提取。實(shí)驗(yàn)結(jié)果表明,基于此方法進(jìn)行高分辨率遙感影像的居民區(qū)提取相對(duì)于傳統(tǒng)方法具有更好的魯棒性和高效性。
[Abstract]:The data field describes the interaction between data objects by simulating the interaction between objects in the physical field. The potential values in the data field reflect the degree of correlation between objects, so the spatial correlation characteristics between pixels can be described in remote sensing images. A high resolution neighborhood extraction method based on data field and density clustering is proposed. Firstly, the potential feature image of remote sensing image is calculated by using the data field; then, the potential value image is segmented by watershed, and the centroid of the object block is extracted. Finally, the centroid is clustered based on density to realize the extraction of residential area. The experimental results show that the proposed method is more robust and efficient than the traditional method in the extraction of residential areas from high-resolution remote sensing images.
【作者單位】： 武漢大學(xué)遙感信息工程學(xué)院;地球空間信息技術(shù)協(xié)同創(chuàng)新中心;
【基金】：國(guó)家重點(diǎn)基礎(chǔ)研究發(fā)展計(jì)劃(973)項(xiàng)目“高分辨率遙感影像的目標(biāo)特征描述與數(shù)學(xué)建�！�(編號(hào):2012CB719903) 重慶市國(guó)土房管局科技計(jì)劃項(xiàng)目“基于圖像識(shí)別技術(shù)的國(guó)家高分辨率遙感數(shù)據(jù)分析應(yīng)用方法研究”(編號(hào):CQGT-KJ-2014032)共同資助
【分類號(hào)】：TP751

【相似文獻(xiàn)】

相關(guān)期刊論文 前1條

1 馬建文,劉素紅,馬超飛;遙感多維空間數(shù)據(jù)場(chǎng)特征的角度分析與應(yīng)用[J];遙感學(xué)報(bào);2001年01期

，

本文編號(hào)：2304354