基于SIFT和非參貝葉斯的高分辨率遙感影像地物識(shí)別算法
發(fā)布時(shí)間：2019-01-05 03:06
【摘要】：地物識(shí)別是遙感圖像處理領(lǐng)域中的一個(gè)重要問(wèn)題。隨著遙感技術(shù)的發(fā)展,高分辨率遙感影像中攜帶有大量相似的具有尺度不變特征的地物,傳統(tǒng)的地物識(shí)別方法難以適應(yīng)這一發(fā)展,亟需對(duì)其進(jìn)行改進(jìn)。針對(duì)高分遙感影像,在SIFT(Scale-invariant Feature Transform)算法的基礎(chǔ)上進(jìn)行改進(jìn)并得出一種快速精準(zhǔn)的地物識(shí)別算法DBSIFT(Double Backward SIFT),實(shí)現(xiàn)了相似地物多對(duì)一的模式識(shí)別。DBSIFT在原算法的基礎(chǔ)上構(gòu)造了二重差金字塔,利用DP(Dirichlet Process)識(shí)別出相似地物并對(duì)其進(jìn)行分割。在幾何與算數(shù)關(guān)系上,選取9個(gè)指標(biāo)對(duì)分割精度進(jìn)行評(píng)價(jià)。實(shí)驗(yàn)中,使用該方法得到的地物能夠被準(zhǔn)確識(shí)別,且分割效果良好,說(shuō)明了該算法的有效性。
[Abstract]:Ground object recognition is an important problem in the field of remote sensing image processing. With the development of remote sensing technology, high resolution remote sensing images carry a large number of similar features with scale invariant features, the traditional method of ground object recognition is difficult to adapt to this development, it is urgent to improve it. Based on SIFT (Scale-invariant Feature Transform) algorithm), a fast and accurate ground object recognition algorithm, DBSIFT (Double Backward SIFT), is developed for high score remote sensing images. DBSIFT constructs the pyramid of double difference based on the original algorithm and uses DP (Dirichlet Process) to recognize and segment the similar ground objects. In the relation between geometry and arithmetic, nine indexes are selected to evaluate the segmentation accuracy. In the experiment, the ground objects obtained by this method can be accurately identified and the segmentation effect is good, which shows the effectiveness of the algorithm.
【作者單位】： 山西大學(xué)計(jì)算機(jī)與信息技術(shù)學(xué)院;山西大學(xué)計(jì)算智能與中文信息處理教育部重點(diǎn)實(shí)驗(yàn)室;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(41101440) 山西省青年科技基金資助項(xiàng)目(2012021015-1)資助
【分類號(hào)】：TP751
本文編號(hào)：2401178
[Abstract]:Ground object recognition is an important problem in the field of remote sensing image processing. With the development of remote sensing technology, high resolution remote sensing images carry a large number of similar features with scale invariant features, the traditional method of ground object recognition is difficult to adapt to this development, it is urgent to improve it. Based on SIFT (Scale-invariant Feature Transform) algorithm), a fast and accurate ground object recognition algorithm, DBSIFT (Double Backward SIFT), is developed for high score remote sensing images. DBSIFT constructs the pyramid of double difference based on the original algorithm and uses DP (Dirichlet Process) to recognize and segment the similar ground objects. In the relation between geometry and arithmetic, nine indexes are selected to evaluate the segmentation accuracy. In the experiment, the ground objects obtained by this method can be accurately identified and the segmentation effect is good, which shows the effectiveness of the algorithm.
【作者單位】： 山西大學(xué)計(jì)算機(jī)與信息技術(shù)學(xué)院;山西大學(xué)計(jì)算智能與中文信息處理教育部重點(diǎn)實(shí)驗(yàn)室;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(41101440) 山西省青年科技基金資助項(xiàng)目(2012021015-1)資助
【分類號(hào)】：TP751
【參考文獻(xiàn)】
相關(guān)期刊論文 前3條
1 葛盼盼;陳強(qiáng);顧一禾;;基于Harris角點(diǎn)和SURF特征的遙感圖像匹配算法[J];計(jì)算機(jī)應(yīng)用研究;2014年07期
2 陳夢(mèng)婷;閆冬梅;王剛;;基于Harris角點(diǎn)和SIFT描述符的高分辨率遙感影像匹配算法[J];中國(guó)圖象圖形學(xué)報(bào);2012年11期
3 張林;劉輝;;Dirichlet過(guò)程混合模型的聚類算法[J];中國(guó)礦業(yè)大學(xué)學(xué)報(bào);2012年01期
【相似文獻(xiàn)】
相關(guān)期刊論文 前3條
1 龔建周;陳健飛;劉彥隨;;基于E0-1 Hyperion影像地物識(shí)別與分類不同方法的效果比較[J];應(yīng)用基礎(chǔ)與工程科學(xué)學(xué)報(bào);2013年03期
2 劉行華;胡寶新;張淵智;;地物理解的現(xiàn)狀、設(shè)想與展望[J];遙感信息;1992年04期
3 ;[J];;年期
相關(guān)碩士學(xué)位論文 前1條
1 李益;基于光譜/空間聯(lián)合特征的遙感影像地物提取技術(shù)研究[D];解放軍信息工程大學(xué);2012年
，本文編號(hào)：2401178
本文鏈接：http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2401178.html
最近更新
教材專著
