基于SIFT和非參貝葉斯的高分辨率遙感影像地物識別算法
發(fā)布時間：2019-01-05 03:06
【摘要】：地物識別是遙感圖像處理領(lǐng)域中的一個重要問題。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)的地物識別方法難以適應(yīng)這一發(fā)展,亟需對其進行改進。針對高分遙感影像,在SIFT(Scale-invariant Feature Transform)算法的基礎(chǔ)上進行改進并得出一種快速精準的地物識別算法DBSIFT(Double Backward SIFT),實現(xiàn)了相似地物多對一的模式識別。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)識別出相似地物并對其進行分割。在幾何與算數(shù)關(guān)系上,選取9個指標(biāo)對分割精度進行評價。實驗中,使用該方法得到的地物能夠被準確識別,且分割效果良好,說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)計算機與信息技術(shù)學(xué)院;山西大學(xué)計算智能與中文信息處理教育部重點實驗室;
【基金】：國家自然科學(xué)基金資助項目(41101440) 山西省青年科技基金資助項目(2012021015-1)資助
【分類號】：TP751
本文編號：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)計算機與信息技術(shù)學(xué)院;山西大學(xué)計算智能與中文信息處理教育部重點實驗室;
【基金】：國家自然科學(xué)基金資助項目(41101440) 山西省青年科技基金資助項目(2012021015-1)資助
【分類號】：TP751
【參考文獻】
相關(guān)期刊論文 前3條
1 葛盼盼;陳強;顧一禾;;基于Harris角點和SURF特征的遙感圖像匹配算法[J];計算機應(yīng)用研究;2014年07期
2 陳夢婷;閆冬梅;王剛;;基于Harris角點和SIFT描述符的高分辨率遙感影像匹配算法[J];中國圖象圖形學(xué)報;2012年11期
3 張林;劉輝;;Dirichlet過程混合模型的聚類算法[J];中國礦業(yè)大學(xué)學(xué)報;2012年01期
【相似文獻】
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;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：2401178
本文鏈接：http://www.sikaile.net/kejilunwen/zidonghuakongzhilunwen/2401178.html
最近更新
教材專著
