Saliency Driven Imagery Preprocessing for Efficient Compression -- Industrial Paper

TL;DR

This paper introduces a saliency-driven preprocessing method for satellite imagery that enhances compression efficiency by focusing encoding on important regions using variable smoothing based on saliency maps.

Contribution

It presents a novel preprocessing technique that leverages saliency maps to optimize satellite image compression with traditional lossy standards.

Findings

Improved compression efficiency on satellite images.

Effective focus on regions of interest reduces data size.

Compatible with existing lossy compression standards.

Abstract

The compression of satellite imagery remains an important research area as hundreds of terabytes of images are collected every day, which drives up storage and bandwidth costs. Although progress has been made in increasing the resolution of these satellite images, many downstream tasks are only interested in small regions of any given image. These areas of interest vary by task but, once known, can be used to optimize how information within the image is encoded. Whereas standard image encoding methods, even those optimized for remote sensing, work on the whole image equally, there are emerging methods that can be guided by saliency maps to focus on important areas. In this work we show how imagery preprocessing techniques driven by saliency maps can be used with traditional lossy compression coding standards to create variable rate image compression within a single large satellite image. Specifically, we use variable sized smoothing kernels that map to different quantized saliency levels to process imagery pixels in order to optimize downstream compression and encoding schemes.