本文選題：稀疏表示 + 匹配追蹤�。� 參考：《西安電子科技大學(xué)》2014年碩士論文

【摘要】：作為壓縮感知理論的研究核心之一，對(duì)冗余字典下信號(hào)稀疏表示理論的研究越來(lái)越受到人們的重視，該方法的核心是為了在變換域上，利用盡可能少的原子的線性組合來(lái)逼近原始信號(hào)，通過(guò)得到為數(shù)不多的非零信息來(lái)揭示信號(hào)的本質(zhì)特性，從而使對(duì)信號(hào)的處理變得高效而又簡(jiǎn)單。本文基于稀疏表示的相關(guān)理論，重點(diǎn)研究了基于匹配追蹤思想的信號(hào)重構(gòu)與分類(lèi)算法。 基于稀疏表示的圖像重構(gòu)中，介紹了經(jīng)典的匹配追蹤類(lèi)算法，詳細(xì)地分述了各算法的思路、流程及特點(diǎn)，并針對(duì)原有的SAMP算法存在的兩點(diǎn)缺陷，即初始迭代步長(zhǎng)難以確定和耗時(shí)較多的問(wèn)題進(jìn)行改進(jìn)，提出了稀疏度自適應(yīng)貪婪(SAGP)算法。通過(guò)一維稀疏信號(hào)和二維真實(shí)圖像的重構(gòu)實(shí)驗(yàn)，驗(yàn)證了SAGP算法重構(gòu)效果優(yōu)于SAMP算法的同時(shí)，也保持了時(shí)間的優(yōu)越性。 基于稀疏表示的分類(lèi)中，針對(duì)CSSOMP算法中異類(lèi)原子集間存在交集的問(wèn)題，進(jìn)一步優(yōu)化了MCSSOMP算法，并增加了大量實(shí)驗(yàn)。MCSSOMP算法采用約束原子集間相互獨(dú)立的策略，能夠減少異類(lèi)信號(hào)間的共性因素，強(qiáng)化信號(hào)間的區(qū)分度。標(biāo)準(zhǔn)圖像庫(kù)和實(shí)測(cè)雷達(dá)信號(hào)集上的大量實(shí)驗(yàn)，從多個(gè)角度驗(yàn)證了改善后的算法在提升分類(lèi)效果方面具有良好的表現(xiàn)，，特別是在噪聲和遮擋較為嚴(yán)重情況下，仍有較強(qiáng)的魯棒性。 基于字典更新思想的分類(lèi)中，針對(duì)LC-KSVD算法在字典初始化時(shí)過(guò)于側(cè)重局部信息，而非從全局考慮的問(wèn)題，提出了MLC-KSVD算法。該方法在初始化時(shí)采用分類(lèi)SOMP算法的策略，即每類(lèi)信號(hào)挑選共同的原子集，而異類(lèi)信號(hào)選取不同的原子集，使改進(jìn)后的算法能更適于分類(lèi)識(shí)別。各種圖像數(shù)據(jù)庫(kù)和實(shí)測(cè)雷達(dá)數(shù)據(jù)集上的實(shí)驗(yàn)，證實(shí)了所提算法在多種信號(hào)分類(lèi)識(shí)別中的有效性。
[Abstract]:As one of the core of compressed sensing theory, the research on sparse representation theory of signals in redundant dictionaries has been paid more and more attention. The core of this method is in the transform domain. The linear combination of as few atoms as possible is used to approximate the original signal, and the essential characteristics of the signal are revealed by obtaining a few non-zero information, which makes the signal processing more efficient and simple. Based on the theory of sparse representation, this paper focuses on the algorithm of signal reconstruction and classification based on the idea of matching and tracking. In image reconstruction based on sparse representation, the classical matching and tracing algorithms are introduced, the ideas, flow and characteristics of each algorithm are described in detail, and the two defects of the original SAMP algorithm are pointed out. That is, the initial iteration step size is difficult to determine and time-consuming to improve, a sparse adaptive greedy SAGP-based algorithm is proposed. Through the experiments of one dimensional sparse signal and two dimensional real image reconstruction, it is proved that the reconstruction effect of SAGP algorithm is better than that of SAMP algorithm, while maintaining the superiority of time. In the classification based on sparse representation, aiming at the problem of intersecting among different atomic sets in CSSOMP algorithm, this paper further optimizes the MCSSOMP algorithm, and adds a lot of experiments. MCSSOMP algorithm adopts the strategy of independent between constrained atomic sets. It can reduce the common factors among heterogeneous signals and strengthen the differentiation between signals. A large number of experiments on the standard image database and the measured radar signal set show that the improved algorithm has a good performance in improving the classification performance from several angles, especially in the case of serious noise and occlusion, there is still strong robustness. In the classification based on the idea of dictionary updating, the MLC-KSVD algorithm is proposed to solve the problem that the LC-KSVD algorithm emphasizes the local information rather than the global consideration when initializing the dictionary. In this method, the strategy of classifying SOMP algorithm is adopted in initialization, that is, each kind of signal selects a common atomic set, while a different class signal selects different atomic sets, which makes the improved algorithm more suitable for classification and recognition. Experiments on various image databases and measured radar datasets show that the proposed algorithm is effective in the classification and recognition of various signals.
【學(xué)位授予單位】：西安電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：TN911.7

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 曹靜杰;王彥飛;楊長(zhǎng)春;;地震數(shù)據(jù)壓縮重構(gòu)的正則化與零范數(shù)稀疏最優(yōu)化方法[J];地球物理學(xué)報(bào);2012年02期

2 石光明;劉丹華;高大化;劉哲;林杰;王良君;;壓縮感知理論及其研究進(jìn)展[J];電子學(xué)報(bào);2009年05期

3 楊成;馮巍;馮輝;楊濤;胡波;;一種壓縮采樣中的稀疏度自適應(yīng)子空間追蹤算法[J];電子學(xué)報(bào);2010年08期

4 焦李成;楊淑媛;劉芳;侯彪;;壓縮感知回顧與展望[J];電子學(xué)報(bào);2011年07期

5 謝曉春;張?jiān)迫A;;基于壓縮感知的二維雷達(dá)成像算法[J];電子與信息學(xué)報(bào);2010年05期

6 劉亞新;趙瑞珍;胡紹海;姜春暉;;用于壓縮感知信號(hào)重建的正則化自適應(yīng)匹配追蹤算法[J];電子與信息學(xué)報(bào);2010年11期

7 何艷敏;甘濤;陳武凡;;基于稀疏表示的兩級(jí)圖像去噪[J];電子與信息學(xué)報(bào);2012年09期

8 王海濤;王俊;;基于壓縮感知的無(wú)源雷達(dá)超分辨DOA估計(jì)[J];電子與信息學(xué)報(bào);2013年04期

9 王磊;姬紅兵;史亞;;基于模糊函數(shù)特征優(yōu)化的雷達(dá)輻射源個(gè)體識(shí)別[J];紅外與毫米波學(xué)報(bào);2011年01期

10 王磊;史亞;姬紅兵;;基于多集典型相關(guān)分析的雷達(dá)輻射源指紋識(shí)別[J];西安電子科技大學(xué)學(xué)報(bào);2013年02期

本文編號(hào)：1780093