Optimal Use of Multi-spectral Satellite Data with Convolutional Neural Networks
This work addresses the challenge of optimizing multi-spectral data usage in CNNs for satellite imagery analysis, which is incremental as it builds on existing methods with specific improvements for domain-specific applications.
The paper tackled the problem of applying Convolutional Neural Networks to multi-spectral satellite images for semantic segmentation of agricultural vegetation, showing that using all available bands improves test accuracy and that Bayesian optimization for band selection further boosts performance.
The analysis of satellite imagery will prove a crucial tool in the pursuit of sustainable development. While Convolutional Neural Networks (CNNs) have made large gains in natural image analysis, their application to multi-spectral satellite images (wherein input images have a large number of channels) remains relatively unexplored. In this paper, we compare different methods of leveraging multi-band information with CNNs, demonstrating the performance of all compared methods on the task of semantic segmentation of agricultural vegetation (vineyards). We show that standard industry practice of using bands selected by a domain expert leads to a significantly worse test accuracy than the other methods compared. Specifically, we compare: using bands specified by an expert; using all available bands; learning attention maps over the input bands; and leveraging Bayesian optimisation to dictate band choice. We show that simply using all available band information already increases test time performance, and show that the Bayesian optimisation, first applied to band selection in this work, can be used to further boost accuracy.