基于分布式信源编码和感兴趣区域编码的干涉多光谱图像压缩(英文)

An Improved Distributed Source Coding and ROI Coding-Based Interferometric Multi-Spectral Image Compression Alogrithm

基于干涉多光谱图像特点和应用环境要求,提出一种基于分布式信源编码和感兴趣区域编码的干涉多光谱图像压缩算法。编码端通过关键帧预测出边信息帧,然后联合估计的边信息帧和插值分布的概率模型在编码端进行比特平面码率估计,最后采用基于率失真提升的感兴趣区域编码,调整图像不同区域的率失真斜率来进行更合理的码率分配。实验结果表明,该算法比传统算法更好地保护了多光谱图像的光谱信息。在不同压缩比的情况下,这种编码方式在干涉多光谱图像压缩系统中可获得较好的效果,算法复杂度低。

Considering the interferometric multi-spectral image characteristics and requirements for application environment,a new distributed source coding,ROI coding-based interferometric multi-spectral image compression algorithm is proposed.Owning to the apparent shift features in the image series,side information frames are predicted by key frames in the encoder.And then a code rate estimate algorithm is proposed to estimate the code rate of each bitplane in combination with the estimated side information frame and laplacian distribution of difference in the encoder.Finally,a rate-distortion lifting procedure based ROI coding algorithm is adopted for code rate allocation to protect the spectral information.The experimental results indicate that the performance of the proposed algorithm in spectral domain outperforms the conventional algorithms.Under the condition of different compression ratios,the algorithm can get a good effect in the multispectral image coding system,and efficiently reduces the cost of computation.