基于背景字典構(gòu)造的稀疏表示高光譜目標(biāo)檢測
2022年電子技術(shù)應(yīng)用第1期
陶 洋,林飛鵬,楊 雯,翁 善
重慶郵電大學(xué) 通信與信息工程學(xué)院,重慶400065
摘要: 針對(duì)現(xiàn)有基于稀疏表示的目標(biāo)檢測算法采用同心雙窗口構(gòu)建背景字典的過程中,目標(biāo)像元將會(huì)對(duì)背景字典產(chǎn)生干擾的問題,提出基于背景字典構(gòu)造的稀疏表示高光譜目標(biāo)檢測算法。該算法將高光譜圖像分解成低秩背景和稀疏目標(biāo),引入目標(biāo)字典作為稀疏目標(biāo)的先驗(yàn)信息,更好地分離目標(biāo)和背景,構(gòu)建純凈背景字典。通過在4個(gè)公開高光譜圖像數(shù)據(jù)集上仿真分析,證明所提出的算法具有出色的檢測性能。
中圖分類號(hào): TN10
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.211420
中文引用格式: 陶洋,林飛鵬,楊雯,等. 基于背景字典構(gòu)造的稀疏表示高光譜目標(biāo)檢測[J].電子技術(shù)應(yīng)用,2022,48(1):124-128.
英文引用格式: Tao Yang,Lin Feipeng,Yang Wen,et al. Background dictionary construction-based sparse representation hyperspectral target detection[J]. Application of Electronic Technique,2022,48(1):124-128.
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.211420
中文引用格式: 陶洋,林飛鵬,楊雯,等. 基于背景字典構(gòu)造的稀疏表示高光譜目標(biāo)檢測[J].電子技術(shù)應(yīng)用,2022,48(1):124-128.
英文引用格式: Tao Yang,Lin Feipeng,Yang Wen,et al. Background dictionary construction-based sparse representation hyperspectral target detection[J]. Application of Electronic Technique,2022,48(1):124-128.
Background dictionary construction-based sparse representation hyperspectral target detection
Tao Yang,Lin Feipeng,Yang Wen,Weng Shan
School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications, Chongqing 400065,China
Abstract: Aiming at the existing target detection algorithms based on sparse representation, in the process of building the background dictionary with concentric double windows, the target pixels will interfere with the background dictionary. A sparse representation hyperspectral target detection algorithm based on background dictionary is proposed. The algorithm decomposes the hyperspectral image into low rank background and sparse target, and introduces the target dictionary as the prior information of sparse target, which can separate the target and background better and construct a pure background dictionary. Simulation results on four public hyperspectral image datasets show that the proposed algorithm has excellent detection performance.
Key words : hyperspectral image;sparse representation;binary-class;target dictionary;low-rank
0 引言
高光譜圖像目標(biāo)檢測是一個(gè)典型的二分類問題,目的是將圖像中的每個(gè)像素標(biāo)記為目標(biāo)或背景[1],被廣泛應(yīng)用于軍事、農(nóng)業(yè)、礦物等領(lǐng)域[2]。
經(jīng)典的目標(biāo)檢測算法包括約束能量最小化(Constrained Energy Minimization,CEM)[3]、自適應(yīng)一致余弦估計(jì)(Adaptive Coherence Estimator,ACE)[4]。但是經(jīng)典算法有效性都依賴于對(duì)統(tǒng)計(jì)模型的假設(shè),現(xiàn)實(shí)場景中不能保證一定成立。近些年來,稀疏表示在高光譜領(lǐng)域也得到了很好的發(fā)展,研究人員相繼提出了基于稀疏表示(Sparse Representation for Target Detection,STD)[5]以及基于二元假設(shè)稀疏表示的目標(biāo)檢測(Sparse Representation-Based Binary Hypothesis,SRBBH)[6]。最近,有人提出了一種基于單頻譜驅(qū)動(dòng)的二分類稀疏表示檢測器[7]。
本文詳細(xì)內(nèi)容請(qǐng)下載:http://theprogrammingfactory.com/resource/share/2000003922。
作者信息:
陶 洋,林飛鵬,楊 雯,翁 善
(重慶郵電大學(xué) 通信與信息工程學(xué)院,重慶400065)
此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。