基于K-均值聚类和传统递归最小二乘法的高光谱图像无损压缩

高放; 孙长建; 邵庆龙; 郭树旭

doi:10.11999/JEIT151439

基于K-均值聚类和传统递归最小二乘法的高光谱图像无损压缩

doi: 10.11999/JEIT151439

基金项目:

国家自然科学基金(41101419)

计量
- 文章访问数: 1897
- HTML全文浏览量: 154
- PDF下载量: 654
- 被引次数: 33
出版历程
- 收稿日期: 2015-12-22
- 修回日期: 2016-04-08
- 刊出日期: 2016-11-19

Lossless Compression of Hyperspectral Images Using K-means Clustering and Conventional Recursive Least-squares Predictor

Funds:

The National Natural Science Foundation of China (41101419)

摘要

摘要: 针对基于预测的高光谱图像无损压缩算法压缩比低的问题，该文将聚类算法与高光谱图像预测压缩算法相结合，提出一种基于K-均值聚类和传统递归最小二乘法的高光谱图像无损压缩算法。首先，对高光谱图像按光谱矢量进行K-均值聚类以提升同类光谱矢量间的相似度。然后，对每一聚类群分别使用传统递归最小二乘法进行预测，消除高光谱图像的空间冗余和谱间冗余。最后，对预测误差图像进行算术编码，完成高光谱图像压缩过程。对AVIRIS 2006高光谱数据进行仿真实验，所提算法对16位校正图像、16位未校正图像和12位未校正图像分别取得了4.63倍，2.82倍和4.77倍的压缩比，优于同类型已报道的各种算法。
- 高光谱图像 /
- 图像压缩 /
- 递归最小二乘法 /
- 聚类
Abstract: To improve the compression ratio of lossless compression scheme based on prediction, a lossless compression scheme for hyperspectral images using K-means Clustering method and Conventional Recursive Least-Squares (C-CRLS) predictor is presented in this paper. The proposed scheme first clusters the spectral data into clusters according to their spectra using the famous K-means clustering method. Then, the proposed scheme calculates the preliminary estimates to form the input vector of the conventional recursive least-squares predictor. Finally, after prediction, the prediction residuals are sent to the arithmetic coder. Experiments on the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) 2006 hyperspectral images show that the proposed scheme yields an average compression ratio of 4.63, 2.82, and 4.77 on the 16-bit calibrated images, the 16-bit uncalibrated images, and the 12-bit uncalibrated images, respectively. Experimental results demonstrate that the proposed scheme outperforms other current state-of-the-art schemes for hyperspectral images that have been previously reported.
- Hyperspectral images /
- Image compression /
- Recursive least-squares /
- Clustering

HTML全文

参考文献(23)

MIELIKAINEN J. Lossless compression of hyperspectral images using lookup tables[J]. IEEE Signal Processing Letters, 2006, 13(3): 157-160. doi: 10.1109/LSP.2005.862604.

HUANG B and SRIRAJA Y. Lossless compression of hyperspectral imagery via lookup tables with predictor selection[C]. Conference on Image and Signal Processing for Remote Sensing XII, Stockholm, Sweden, 2006: 63650L.1- 63650L.8. doi: 10.1117/12.690659.

MIELIKAINEN J and TOIVANEN P. Lossless compression of hyperspectral images using a quantized index to lookup tables[J]. IEEE Geoscience and Remote Sensing Letters, 2008, 5(3): 474-478. doi: 10.1109/LGRS.2008.917598.

KLIMESH K. Low-complexity adaptive lossless compression of hyperspectral imagery[C]. Conference on Satellite Data Compression, Communications, and Archiving II, San Diego, USA, 2006: 63000N-1-63000N-9. doi: 10.1117/12.682624.

LIN Chengchen and HWANG Yintsung. An efficient lossless compression scheme for hyperspectral images using two-stage prediction[J]. IEEE Geoscience and Remote Sensing Letters, 2010, 7(3): 558-562. doi: 10.1109/LGRS.2010.2041630.

SONG Jinwei, ZHANG Zhongwei, and CHEN Xiaomin. Lossless compression of hyperspectral imagery via RLS filter[J]. Electronics Letters, 2013, 49(16): 992-993. doi: 10.1049/el.2013.1315.

ABRARDO A, BARNI M, MAGLI E, et al. Error-resilient and low-complexity onboard lossless compression of hyperspectral images by means of distributed source coding[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(4): 1892-1904. doi: 10.1109/TGRS.2009.2033470.

RIZZO F, CARPENTIERI B, MOTTA G, et al. Low- complexity lossless compression of hyperspectral imagery via linear prediction[J]. IEEE Signal Processing Letters, 2005, 12(2): 138-141. doi: 10.1109/LSP.2004.840907(410).

MAGLI E. Multiband lossless compression of hyperspectral images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(4): 1168-1178. doi: 10.1109/TGRS. 2008.2009316.

MIELIKAINEN J and TOIVANEN P. Clustered DPCM for the lossless compression of hyperspectral images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2003, 41(12): 2943-2946. doi: 10.1109/TGRS.2003.820885.

AIAZZI B, ALPARONE L, BARONTI S, et al. Crisp and fuzzy adaptive spectral predictions for lossless and near-lossless compression of hyperspectral imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2007, 4(4): 532-536. doi: 10.1109/LGRS.2007.900695.

WU Jiaji, KONG Wanqiu, MIELIKAINEN J, et al. Lossless compression of hyperspectral imagery via clustered differential pulse code modulation with removal of local spectral outliers[J]. IEEE Signal Processing Letters, 2015, 22(12): 2194-2198. doi: 10.1109/LSP.2015.2443913.

ULKU I and TOREYIN B U. Sparse representations for online-learning-based hyperspectral image compression[J]. Applied Optics, 2015, 54(29): 8625-8631. doi: 10.1364/AO.54.008625.

WANG Lei, BAI Jing, WU Jiaji, et al. Hyperspectral image compression based on lapped transform and Tucker decomposition[J]. Signal Processing: Image Communication, 2015, 36: 63-69. doi: 10.1016/j.image.2015.06.002.

BEERTEN J, BLANES I, and SERRA-SAGRISTA J. A fully embedded two-stage coder for hyperspectral near-lossless compression[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(8): 1775-1779. doi: 10.1109/LGRS.2015.2425548.

LEE C, YOUN S, JEONG T, et al. Hybrid compression of hyperspectral images based on PCA with pre-encoding discriminant information[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(7): 1491-1495. doi: 10.1109/LGRS. 2015.2409897.

ZHAO Chunhui, LI Xiaohui, REN Jinchang, et al. A novel framework for object-based coding and compression of hyperspectral imagery[J]. Chinese Journal of Electronics, 2015, 24(2): 300-305. doi: 10.1049/cje.2015.04.012.

NIAN Yongjian, HE Mi, and WAN Jianwei. Lossless and near-lossless compression of hyperspectral images based on distributed source coding[J]. Journal of Visual Communication and Image Representation, 2015, 28: 113-119. doi: 10.1016/j.jvcir.2014.06.008.

ZHANG Lefei, ZHANG Liangpei, TAO Dacheng, et al. Compression of hyperspectral remote sensing images by tensor approach[J]. Neurocomputing, 2015, 147(1): 358-363. doi: 10.1016/j.neucom.2014.06.052.

HUANG Bingchao, NIAN Yongjian, and WAN Jianwei. Distributed lossless compression algorithm for hyperspectral images based on classification[J]. Spectroscopy Letters, 2015, 48(7): 528-535. doi: 10.1080/00387010.2014.920888.

JAIN A K. Data clustering: 50 years beyond k-means[C]. 19th International Conference on Pattern Recognition, Tampa, USA, 2010: 651-666.

DINIZ P S R. Adaptive Filtering: Algorithms and Practical Implementation[M]. New York, Springer, 2012: 195-227.

MOFFAT A, NEAL R, and WITTEN I H. Arithmetic coding revisited[C]. Data Compression Conference, Snowbird, USA, 1995: 202-211.

施引文献

期刊类型引用(16)

1.	王蕾，张恒璟，高小明，邢晨，马海超. 一种高光谱遥感影像无损压缩方法与应用. 测绘通报. 2023(08): 120-125 . 百度学术
2.	巫钟兴，丁忠安，夏桃芳，朱子旭，王雅平. 基于交互时长的通信协议应用诊断与优化方法. 电测与仪表. 2022(07): 122-128 . 百度学术
3.	丁绪东，杨东润，刘慧，赵星凯，张迎，孙梅. 数据驱动的蒸发器在线建模方法. 计算机与现代化. 2022(11): 22-31 . 百度学术
4.	杨丽平，胡红莉，朱福全. 基于多波段预测的高光谱图像快速无损压缩算法. 价值工程. 2022(32): 142-144 . 百度学术
5.	郑铁，薛长斌，宋金伟. 利用格型递归最小二乘滤波器组的高光谱图像压缩. 光学精密工程. 2021(04): 896-905 . 百度学术
6.	苏令华，王平，马志强，张茜. 基于光谱线性分解的高光谱图像高效压缩. 太赫兹科学与电子信息学报. 2021(06): 1075-1080 . 百度学术
7.	朱福全，王华军，杨丽平，李昌国. 自适应波段选择与最佳预测顺序的高光谱图像无损压缩. 光学精密工程. 2020(07): 1609-1617 . 百度学术
8.	刘霞，吴珊. 动态视频采集中多光谱图像无损压缩. 激光杂志. 2020(08): 87-90 . 百度学术
9.	蒋媛，魏瑞，卢超. 深度学习网络的激光光谱图像压缩研究. 激光杂志. 2020(12): 176-180 . 百度学术
10.	韩宾，张红红，江虹，丁一. 基于方位信息的改进LZW前缀编码方案. 计算机科学. 2019(08): 157-162 . 百度学术
11.	孙会强，吕佳，吴秀敏. 基于最小二乘法的人脸素描卡通图像算法. 现代电子技术. 2019(18): 143-146 . 百度学术
12.	徐金甫，刘露，李伟，王周闯，杨宇航. 一种基于阵列配置加速比模型的无损压缩算法. 电子与信息学报. 2018(06): 1492-1498 . 本站查看
13.	肖儿良，冯杰，简献忠. KSVDSAMP自适应稀疏算法在电能质量信号重构中的应用. 电子测量技术. 2018(19): 100-105 . 百度学术
14.	陈善学，张燕琪. 基于自适应波段聚类主成分分析和反向传播神经网络的高光谱图像压缩. 电子与信息学报. 2018(10): 2478-2483 . 本站查看
15.	张海涛，曹博甫，刘万军. 多波段和查找表预测值校正的高光谱图像压缩. 激光与红外. 2017(09): 1181-1185 . 百度学术
16.	张治远. 基于三维图像的运动员起跑动作误差预测仿真. 计算机仿真. 2017(08): 412-416 . 百度学术