基于低秩結(jié)構(gòu)提取的高光譜圖像壓縮表示

唐中奇; 付光遠(yuǎn); 陳進(jìn); 張利

doi:10.11999/JEIT150906

基于低秩結(jié)構(gòu)提取的高光譜圖像壓縮表示

doi: 10.11999/JEIT150906

2.
(第二炮兵工程大學(xué)信息工程系西安 710025) ②(清華大學(xué)電子工程系北京 100084) ③(北京市遙感信息研究所北京 100192)

基金項(xiàng)目:

國家自然科學(xué)基金(61132007, 61202332, 61503405)，國家自然科學(xué)青年基金(61403397)，中國博士后科學(xué)基金(2012M521905)，陜西省自然科學(xué)基礎(chǔ)研究計(jì)劃項(xiàng)目(2015JM6313)

計(jì)量
- 文章訪問數(shù): 1484
- HTML全文瀏覽量: 116
- PDF下載量: 386
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2015-07-30
- 修回日期: 2015-12-31
- 刊出日期: 2016-05-19

Low-rank Structure Based Hyperspectral Compression Representation

2.
(Xi&rsquo

Funds:

The National Natural Science Foundation of China (61132007, 61202332, 61503405), The National Natural Science Foundation for Young Scientists of China (61403397), China Postdoctoral Science Foundation (2012M521905), Natural Science Foundation of Shaanxi Province, China (2015JM6313)

摘要

摘要: 為實(shí)現(xiàn)高效、精準(zhǔn)的高光譜圖像分類，該文利用低秩矩陣恢復(fù)從原始數(shù)據(jù)中提取低維特征，實(shí)現(xiàn)高光譜圖像的壓縮表示。針對高光譜應(yīng)用的特殊性，該文算法基于結(jié)構(gòu)相似性度量(Structural Similarity Index Measurement, SSIM)對矩陣恢復(fù)過程提出了信噪分離約束，有助于選擇更優(yōu)的模型參數(shù)，增強(qiáng)表示的準(zhǔn)確性。實(shí)驗(yàn)證明，相比現(xiàn)有相關(guān)方法，該文算法能夠有效去除高光譜圖像中的噪聲，表示結(jié)果更為魯棒；在僅使用低維特征時(shí)，仍能達(dá)到較高的分類精度。
- 高光譜圖像分類 /
- 壓縮表示 /
- 低秩矩陣恢復(fù)
Abstract: A method which makes use of structure information abstracted from hyperspectral data via low-rank matrix recovery for hyperspectral image classification is proposed in this paper. The principle of maximizing structure information based on Structural Similarity Index Measurement (SSIM) is proposed to restrain the process of matrix recovery as well, which facilitates the separation of the signal and the noise. The experiments show that the proposed algorithm can effectively eliminate the non-linear noise in hyperspectral image and abstract the low-rank characteristics of hyperspectral image, which achieves better performance in classification.
- Hyperspectral image classification /
- Compression representation /
- Low-rank matrix recovery

HTML全文

參考文獻(xiàn)(20)

吳倩, 張榮, 徐大衛(wèi). 基于稀疏表示的高光譜數(shù)據(jù)壓縮算法[J]. 電子與信息學(xué)報(bào), 2015, 37(1): 78-84. doi: 10.11999/ JEIT140214.

WU Qian, ZHANG Rong, and XU Dawei. Hyperspectral data compression based on sparse representation[J]. Journal of Electronics Information Technology, 2015, 37(1): 78-84. doi: 10.11999/JEIT140214.

CAMPS-VALLS G, TUIA D, BRUZZONE L, et al. Advances in hyperspectral image classification[J]. IEEE Signal Processing Magazine, 2014, 21(4): 45-54. doi: 10.1109/MSP. 2013.2279179.

賈應(yīng)彪, 馮燕, 王忠良, 等. 基于譜間結(jié)構(gòu)相似先驗(yàn)的高光譜壓縮感知重構(gòu)[J]. 電子與信息學(xué)報(bào), 2014, 36(6): 1406-1412. doi: 10.3724/SP.J.1146.2013.01132.

JIA Yingbiao, FENG Yan, WANG Zhongliang, et al. Hyperspectral compressive sensing recovery via spectrum structure similarity[J]. Journal of Electronics Information Technology, 2014, 36(6): 1406-1412. doi: 10.3724/SP.J.1146. 2013.01132.

BIOUCAS-DIAS J, PLAZA A, CAMPS-VALLS G, et al. Hyperspectral remote sensing data analysis and future challenges[J]. IEEE Remote Sensing Magazine, 2013, 1(2): 6-36. doi: 10.1109/MGRS.2013.2244672.

粘永健, 辛勤, 湯毅, 等. 基于多波段預(yù)測的高光譜圖像分布式無損壓縮[J]. 光學(xué)精密工程, 2012, 20(4): 906-912. doi: 10.3788/OPE.20122004.0906.

NIAN Yongjian, XIN Qin, TANG Yi, et al. Distributed lossless compression of hyperspectral images based on multi-band prediction[J]. Optics and Precision Engineering, 2012, 20(4): 906-912. doi: 10.3788/OPE.20122004.0906.

唐中奇, 付光遠(yuǎn), 陳進(jìn), 等. 基于多尺度分割的高光譜圖像稀疏表示與分類[J]. 光學(xué)精密工程, 2015, 23(9): 2708-2714. doi: 10.3788/OPE.20152309.2708.

TANG Zhongqi, FU Guangyuan, CHEN Jin, et al. Multiscale segmentation-based sparse coding for hyperspectral image classification[J]. Optics and Precision Engineering, 2015, 23(9): 2708-2714. doi: 10.3788/OPE.20152309.2708.

ZHOU Yicong, PENG Jiangtao, and CHEN C L P. Dimension reduction using spatial and spectral regularized local discriminant embedding for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(2): 1082-1095. doi: 10.1109/TGRS. 2014.2333539.

LIAO W, PIZURICA A, SCHEUNDERS P, et al. Semi- supervised local discriminant analysis for feature extraction in hyperspectral images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(1): 184-198. doi: 10.1109/ TGRS.2012.2200106.

CARIOU C, CHEHDI K, and MOAN S L. An unsupervised band reduction method for hyperspectral remote sensing[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(3): 565-569. doi: 10.1109/LGRS.2010.2091673.

XUE Zhaohui, LI Jun, CHENG Liang, et al. Spectral-spatial classification of hyperspectral data via morphological component analysis-based image separation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(1): 70-84. doi: 10.1109/TGRS.2014.2318332.

LIU Guangcan, LIN Zhouchen, YAN Shuicheng, et al. Robust recovery of subspace structures by low-rank representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2013, 35(1): 171-184. doi: 10.1109/ TPAMI.2012.88.

CANDS E, LI Xiaodong, MA Yi, et al. Robust principal component analysis?[J]. Journal of the ACM, 2011, 58(3). doi: 10.1145/1970392.1970395.

LIANG Xiao, REN Xiang, ZHANG Zhengdong, et al. Repairing sparse low-rank texture[C]. European Conference on Computer Vision (ECCV), Florence, Italy, 2012. doi: 10.1007/978-3-642-33715-4_35.

JIA Kui, CHAN T H, and MA Yi. Robust and practical face recognition via structured sparsity[C]. European Conference on Computer Vision (ECCV), Florence, Italy, 2012. doi: 10.1007/978-3-642-33765-9_24.

WANG Z and SIMONCELLI E P. An adaptive linear system framework for image distortion analysis[C]. IEEE International Conference Image Processing, Genoa, Italy, 2005, 3: 1160-1163. doi: 10.1007/11889762_19.

LIN Zhouchen, CHEN Minming, WU Leqin, et al. The augmented lagrange multiplier method for exact recovery of corrupted low-rank matrices[R]. University of Illinois at Urbana Champaign (UIUC) Technical Report UILU- ENG-09-2215, 2009. doi: 10.1016/j.jsb.2012.10.010.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)