State-of-the-art lossy compression of Martian images via the CMA-ES evolution strategy

Brendan Babb, Frank Moore, Shawn Aldridge, Michael R. Peterson, Amir Said, Onur G. Guleryuz, Robert L. Stevenson
2012 Visual Information Processing and Communication III  
The research described in this paper uses the CMA-ES evolution strategy to optimize matched forward and inverse transform pairs for the compression and reconstruction of images transmitted from Mars rovers under conditions subject to quantization error. Our best transforms outperform both the integer and floating-point implementations of the 2/6 wavelet, substantially reducing error in reconstructed images without allowing increases in compressed file size. This result establishes a new
more » ... -the-art for the lossy compression of images transmitted over the deep-space channel.
doi:10.1117/12.912162 dblp:conf/vipc/BabbMAP12 fatcat:sz7sgorfzvff3dfimb37hqonie