利用高光谱图像具有较强谱间相关性的特点,本文提出了一种基于2D/3D混合自适应预测的高光谱图像无损压缩方法,首先根据相关系数计算波段预测顺序,通过局部纹理分析进行二维空间预测,采用基于神经网络模型的自适应预测方法进行三维预测,然后利用预测波段与当前波段间邻域块的相关性对二维预测和三维预测的结果进行校正,对预测残差采用基于上下文模型的Golomb编码.实验结果表明,应用于四种不同遥感器所获取的图像,该方法都能够有效的去除高光谱图像的空间和谱间相关性,与无损压缩国际标准JPEG-LS和3D-APA算法相比,压缩后的平均比特率均有明显降低.
Using the significant spectral correlation within the hyperspectral images, we present a lossless compression algorithm in this paper. The method includes four key steps : ( 1 ) band ordering according to spectral correlation coefficient; (2) 2-D and 3-D hybrid adaptive prediction based on local texture and neural networks, respectively ;3) hybrid prediction based on the correlation of neighborhood;4) context-based Golomb coding. Experimental results show that this method can remove the spatial and spectral redundancy efficiently and outperforms JPEG-LS and 3D-APA on average bit rate obviously.