Please wait a minute...
img

官方微信

遥感技术与应用  2004, Vol. 19 Issue (1): 42-46    DOI: 10.11873/j.issn.1004-0323.2004.1.42
技术方法     
基于神经网络的多光谱遥感图像无损压缩
冯 燕,何明一,魏 江
(西北工业大学电子信息学院,陕西西安 710072)
Lossless Compression of Multispectral Remote SensingImage Based on Neural Network
FENG Yan, HE Ming-yi, WEI Jiang
(Institute of Electronic Information,Northwestern Polytechnical University,Xi'an710072,China)
 全文: PDF 
摘要:

分析并改进了利用自组织特征映射(SOFM)神经网络设计码书的方法,提出了一种基于改进SOFM算法设计码书的矢量量化和分类谱间预测相结合的多光谱图像无损压缩方法。该方法对光谱信息进行矢量量化,根据分类信息生成残差图像以去除数据的空间相关性,构造分类谱间预测器去除数据的谱间结构和统计相关性。对机载64波段多光谱遥感图像的试验结果表明,该方法无论是对训练集内图像还是训练集外图像,均取得了较好的压缩效果,平均无损压缩比达到3.2以上。

关键词: 多光谱遥感图像无损压缩SOFM神经网络矢量量化分类谱间预测    
Abstract:

The algorithm of self-organizing feature mapping neural network is analyzed and improved. Anew method based on SOFM codebook design for lossless compression of multispectral image is developed.This method combines vector quantization and classified prediction technique. At first, the multispectralimages are transformed to quantization form. Then, residual images are produced and predicted accordingto classified map. The method removes the intra-band spatial redundancy and the inter-band structural andstatistic redundancy, so the better compression results can be obtained. The experimental results by usingpractical 64-band multispectral images have shown that the lossless compression ratio achieved by themethod is not less than 3.2, better than LBG method.

Key words: Multispectral remote sensing image    Lossless compression    SOFM neural network    Vectorquantization    Classified prediction
收稿日期: 2003-10-13 出版日期: 2011-12-26
:  TP 751    
基金资助:

国家973计划资助项目和陕西省自然科学基金项目。

作者简介: 冯燕(1963-),女,陕西西安人,副教授,在职博士生,主要研究方向为数字信号处理、神经网络和数据压缩。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

冯燕,何明一,魏江. 基于神经网络的多光谱遥感图像无损压缩[J]. 遥感技术与应用, 2004, 19(1): 42-46.

FENG Yan, HE Ming-yi, WEI Jiang. Lossless Compression of Multispectral Remote SensingImage Based on Neural Network. Remote Sensing Technology and Application, 2004, 19(1): 42-46.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2004.1.42        http://www.rsta.ac.cn/CN/Y2004/V19/I1/42

〔1〕 Kaarna A. Integer PCA and Wavelet Transforms for LosslessCompression of Multispectral Image〔A〕. Proc IGARSS' 01〔C〕.2001.1853~1855.〔2〕 Wang J F, Zhang K, Tang S. Spectral and Spatial Decorrelation of Landsat-TM Data for Lossless Compression〔J〕.IEEE Trans Geosci Remote Sensing, 1995, 33(5): 1277~1285.〔3〕 Memon N D, Sayood K, Nagliras S S. Lossless Compressionof Multispectral Image Data〔J〕. IEEE Trans Geosci RemoteSensing, 1994, 32(2): 282~289.〔4〕 倪林.基于地物反射特性的多波段遥感图像无损压缩方法〔J〕.遥感技术与应用,1999,12(4): 53~58.〔5〕 毛克彪,覃志豪,张万昌.一个基于SOFM网络模型的遥感图像分类方法〔J〕.遥感技术与应用,2003,18(6):399~403.〔6〕 陆哲明,孙圣和.基于自组织特征映射神经网络的矢量量化〔J〕.中国图像图形学报,2000,10(10):846~851.

[1] 况军, 罗建书, 向露. 基于自适应预测的高光谱遥感图像无损压缩算法[J]. 遥感技术与应用, 2007, 22(6): 739-742.
[2] 毋立芳,张晓玲,沈兰荪. 整型小波变换应用于遥感图像无损压缩[J]. 遥感技术与应用, 2000, 15(3): 175-178.
[3] 倪林. 基于地物反射特性的多波段遥感图像无损压缩方法[J]. 遥感技术与应用, 1999, 14(4): 53-58.