引入上下文信息的可見光遙感圖像目標(biāo)檢測與識別方法研究
發(fā)布時間：2018-08-12 11:59
【摘要】：可見光遙感圖像的目標(biāo)檢測與識別是遙感技術(shù)中的重要內(nèi)容。由于受多種成像因素的影響,目標(biāo)特征常常存在顯著的變化,這使檢測識別的難度大大增加。有效利用上下文信息可以提升目標(biāo)檢測識別的效率和性能。本文針對引入多層次上下文信息的可見光遙感圖像目標(biāo)檢測與識別方面開展了如下工作:在緊鄰背景相對穩(wěn)定場景的目標(biāo)檢測研究中,針對存在與真實(shí)目標(biāo)具有相似特性的虛警干擾問題,提出了一種引入鄰域上下文信息的檢測框架。在該框架中,提出了梯度方向二進(jìn)制模式描述子來表征目標(biāo)的鄰域上下文信息,由于該描述子不需要由碼本學(xué)習(xí)進(jìn)行特征量化,因此在特征提取方面顯著提升了效率,并將該描述子嵌入空間金字塔匹配模型,提高了目標(biāo)檢測性能。在場景變化的目標(biāo)檢測研究中,提出了一種引入目標(biāo)上下文信息的檢測框架。針對目標(biāo)上下文關(guān)系存在著同一種上下文約束關(guān)系發(fā)生在不同類別目標(biāo)與候選目標(biāo)之間、不同的上下文約束關(guān)系發(fā)生在同類別目標(biāo)與候選目標(biāo)之間的現(xiàn)象,我們設(shè)計基于詞匯的目標(biāo)上下文表述,再組合使用概率潛在語義分析模型來解決這一問題。在目標(biāo)類別識別研究中,針對特征提取環(huán)節(jié)存在誤差的問題,提出了一種引入內(nèi)部上下文信息的識別框架,它首先提取目標(biāo)的稀疏顯著特征,再結(jié)合目標(biāo)內(nèi)部空間區(qū)域信息進(jìn)行特征表述,最后進(jìn)行分類識別。該方法增強(qiáng)了特征表述的穩(wěn)健性,從而提升了識別性能。在遙感圖像的地物分類研究中,針對同類地物目標(biāo)光譜特性變化大、形狀和紋理特征分布復(fù)雜的問題,提出了一種引入多種上下文信息的地物分類框架。它首先為了獲取良好的分割對象,提出了一種基于圖模型的層次化分割方法獲取對象并用于初始分類,然后提出了一種具有旋轉(zhuǎn)不變性的鄰域上下文表述用于優(yōu)化初始分類結(jié)果,最后利用馬爾可夫隨機(jī)場(Markov Random Field,MRF)模型引入鄰域?qū)ο蟮南嚓P(guān)性約束得到最終分類結(jié)果。該方法采用分層遞進(jìn)的策略逐步引入不同上下文信息,克服了直接使用MRF模型時對初始分類結(jié)果依賴性較大的問題。
[Abstract]:Target detection and recognition of visible remote sensing image is an important content in remote sensing technology. Because of the influence of many imaging factors, the target features often change significantly, which makes the detection and recognition more difficult. Using context information effectively can improve the efficiency and performance of target detection and recognition. In this paper, the target detection and recognition of visible light remote sensing images with multi-level context information are studied as follows: in the research of target detection in the relative stable scene adjacent to the background, In order to solve the problem of false alarm interference which is similar to the real target, a detection framework based on neighborhood context information is proposed. In this framework, a gradient direction binary pattern descriptor is proposed to represent the neighborhood context information of the target. Because the descriptor does not need to be quantized by codebook learning, it improves the efficiency of feature extraction significantly. The description is embedded into the space pyramid matching model to improve the performance of target detection. In the research of scene change target detection, a detection framework is proposed to introduce target context information. There is a phenomenon that the same kind of context constraints occur between different categories of targets and candidate targets, and different contextual constraints occur between the same category targets and candidate targets. We design target context representation based on vocabulary and combine probabilistic latent semantic analysis model to solve this problem. In the research of target category recognition, aiming at the problem of error in feature extraction, a recognition framework with internal context information is proposed, which firstly extracts sparse salient features of target. Combined with the spatial region information of the target, the feature is expressed, and the classification and recognition are carried out at last. This method enhances the robustness of feature representation and improves the recognition performance. In the research of ground object classification of remote sensing image, a new classification framework is proposed to solve the problem that the spectral characteristics of similar objects vary greatly and the distribution of shape and texture features is complex. In order to obtain good segmentation object, a hierarchical segmentation method based on graph model is proposed to obtain objects and be used for initial classification. Then, a rotation-invariant neighborhood context representation is proposed to optimize the initial classification results. Finally, the Markov random field (Markov Random field MRF model is introduced into the neighborhood object correlation constraints to obtain the final classification results. In this method, the hierarchical progressive strategy is used to introduce different context information step by step, which overcomes the problem of dependence on the initial classification results when the MRF model is used directly.
【學(xué)位授予單位】：國防科學(xué)技術(shù)大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2014
【分類號】：TP751
本文編號：2178991
[Abstract]:Target detection and recognition of visible remote sensing image is an important content in remote sensing technology. Because of the influence of many imaging factors, the target features often change significantly, which makes the detection and recognition more difficult. Using context information effectively can improve the efficiency and performance of target detection and recognition. In this paper, the target detection and recognition of visible light remote sensing images with multi-level context information are studied as follows: in the research of target detection in the relative stable scene adjacent to the background, In order to solve the problem of false alarm interference which is similar to the real target, a detection framework based on neighborhood context information is proposed. In this framework, a gradient direction binary pattern descriptor is proposed to represent the neighborhood context information of the target. Because the descriptor does not need to be quantized by codebook learning, it improves the efficiency of feature extraction significantly. The description is embedded into the space pyramid matching model to improve the performance of target detection. In the research of scene change target detection, a detection framework is proposed to introduce target context information. There is a phenomenon that the same kind of context constraints occur between different categories of targets and candidate targets, and different contextual constraints occur between the same category targets and candidate targets. We design target context representation based on vocabulary and combine probabilistic latent semantic analysis model to solve this problem. In the research of target category recognition, aiming at the problem of error in feature extraction, a recognition framework with internal context information is proposed, which firstly extracts sparse salient features of target. Combined with the spatial region information of the target, the feature is expressed, and the classification and recognition are carried out at last. This method enhances the robustness of feature representation and improves the recognition performance. In the research of ground object classification of remote sensing image, a new classification framework is proposed to solve the problem that the spectral characteristics of similar objects vary greatly and the distribution of shape and texture features is complex. In order to obtain good segmentation object, a hierarchical segmentation method based on graph model is proposed to obtain objects and be used for initial classification. Then, a rotation-invariant neighborhood context representation is proposed to optimize the initial classification results. Finally, the Markov random field (Markov Random field MRF model is introduced into the neighborhood object correlation constraints to obtain the final classification results. In this method, the hierarchical progressive strategy is used to introduce different context information step by step, which overcomes the problem of dependence on the initial classification results when the MRF model is used directly.
【學(xué)位授予單位】：國防科學(xué)技術(shù)大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2014
【分類號】：TP751
【相似文獻(xiàn)】
相關(guān)期刊論文 前8條
1 楊凱;姜宏旭;;基于失真敏感性的可見光遙感圖像壓縮補(bǔ)償[J];中國空間科學(xué)技術(shù);2012年04期
2 劉曉沐;季艷;萬壽紅;;單源可見光遙感圖像中的水域識別[J];儀器儀表學(xué)報;2006年S3期
3 趙敏;張榮;尹東;王奎;;一種新的可見光遙感圖像云判別算法[J];遙感技術(shù)與應(yīng)用;2012年01期
4 趙英海;吳秀清;聞凌云;徐守時;;可見光遙感圖像中艦船目標(biāo)檢測方法[J];光電工程;2008年08期
5 李智勇;董世永;楊效軍;;衛(wèi)星可見光遙感圖像異常原因分析方法初探[J];航天返回與遙感;2009年01期
6 產(chǎn)曉冰;周川杰;呂原;;基于應(yīng)用的可見光遙感圖像質(zhì)量評價方法研究[J];無線電工程;2013年11期
7 陳克;尹東;馬婧;張開華;;基于層次反應(yīng)型agent的可見光遙感圖像陰影提取[J];中國科學(xué)技術(shù)大學(xué)學(xué)報;2009年08期
8 ;[J];;年期
相關(guān)會議論文 前1條
1 晏磊;童慶禧;;可見光遙感作業(yè)新途徑——以中國貴州無人機(jī)超低空遙感試驗(yàn)為例[A];中國感光學(xué)會第七次全國會員代表大會暨學(xué)術(shù)年會和第七屆青年學(xué)術(shù)交流會論文摘要集[C];2006年
相關(guān)博士學(xué)位論文 前3條
1 郭軍;引入上下文信息的可見光遙感圖像目標(biāo)檢測與識別方法研究[D];國防科學(xué)技術(shù)大學(xué);2014年
2 陳雁;可見光遙感圖像分割與提取研究[D];中國科學(xué)技術(shù)大學(xué);2010年
3 廉藺;紅外與可見光遙感圖像自動配準(zhǔn)算法研究[D];國防科學(xué)技術(shù)大學(xué);2013年
相關(guān)碩士學(xué)位論文 前2條
1 于鵬;高分辨率可見光遙感圖像艦船目標(biāo)識別方法研究[D];吉林大學(xué);2011年
2 陳榮;西洋水域水深可見光遙感反演研究[D];南京師范大學(xué);2008年
，本文編號：2178991
本文鏈接：http://www.wukwdryxk.cn/guanlilunwen/gongchengguanli/2178991.html
最近更新
教材專著
