Hedgementation = Hedgerow Segmentation: A Remote Sensing Benchmark
2026-06-22 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionMachine Learning
AI summaryⓘ
The authors created Hedgementation, a new test to see how well computer models can find hedgerows—small tree lines—in large satellite images of France. They combined different types of satellite data and real-world maps of hedgerows to make this test. They checked how well three different computer models worked when finding hedgerows far away from where they were trained and in different climates, which is harder. Their test works with models that learn from labeled data and those that learn on their own. They also shared their code so others can try it out.
hedgerow mappingremote sensingmachine learningbenchmark datasetspatial resolutionsupervised learningself-supervised learningclimatic zonesgeneralizationground truth labels
Authors
Nathan Senyard, Salem Hamdani, Astrid Zhang, Derek Wang, Evan Shelhamer, Mathias Lécuyer, Joséphine Gantois
Abstract
We propose Hedgementation: a new benchmark to evaluate machine learning models for hedgerow mapping from remote sensing data at country scale and 10m$^2$ spatial resolution. We combine and harmonize multiple remote sensing data products and ground truth labels sourced from a hedgerow inventory in France. We measure the ability of three baseline models to generalize across spatial distance, and across climatic zones, a more explicitly challenging task. Our benchmark tests both supervised and self-supervised learning approaches for remote sensing, applied to tracking fine-scale features of high agricultural importance. The code to reproduce the benchmark and baselines results is available at https://github.com/hedgementation/hedgementation.