Leveraging Convolutional and Graph Networks for an Unsupervised Remote Sensing Labelling Tool
This addresses the cost and expertise bottleneck in remote sensing data preparation, though it appears incremental as it builds on existing segmentation and neural network techniques.
The paper tackles the problem of time-consuming manual labeling of remote sensing imagery by developing an unsupervised pipeline that automatically finds and labels geographical areas with similar context and content in Sentinel-2 satellite imagery. The result is a tool that reduces labeling outliers, enables granular labeling, and forms rotationally invariant semantic relationships.
Machine learning for remote sensing imaging relies on up-to-date and accurate labels for model training and testing. Labelling remote sensing imagery is time and cost intensive, requiring expert analysis. Previous labelling tools rely on pre-labelled data for training in order to label new unseen data. In this work, we define an unsupervised pipeline for finding and labelling geographical areas of similar context and content within Sentinel-2 satellite imagery. Our approach removes limitations of previous methods by utilising segmentation with convolutional and graph neural networks to encode a more robust feature space for image comparison. Unlike previous approaches we segment the image into homogeneous regions of pixels that are grouped based on colour and spatial similarity. Graph neural networks are used to aggregate information about the surrounding segments enabling the feature representation to encode the local neighbourhood whilst preserving its own local information. This reduces outliers in the labelling tool, allows users to label at a granular level, and allows a rotationally invariant semantic relationship at the image level to be formed within the encoding space.