The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B3-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2020, 1009–1016, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-1009-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B3-2020, 1009–1016, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-1009-2020

  21 Aug 2020

21 Aug 2020

A DEEP LEARNING ARCHITECTURE FOR BATCH-MODE FULLY AUTOMATED FIELD BOUNDARY DETECTION

L. Meyer1, F. Lemarchand1, and P. Sidiropoulos1,2 L. Meyer et al.
  • 1Hummingbird Technologies Ltd
  • 2University College London, UK

Keywords: field boundary detection, image segmentation, image instantiation, deep learning, earth observation

Abstract. The accurate split of large areas of land into discrete fields is a crucial step for several agriculture-related remote sensing pipelines. This work aims to fully automate this tedious and resource-demanding process using a state-of-the-art deep learning algorithm with only a single Sentinel-2 image as input. The Mask R-CNN, which has forged its success upon instance segmentation for objects from everyday life, is adapted for the field boundary detection problem. Such model automatically generates closed geometries without any heavy post-processing. When tested with satellite imagery from Denmark, this tailored model correctly predicts field boundaries with an overall accuracy of 0.79. Besides, it demonstrates a robust knowledge generalisation with positive results over different geographies, as it gets an overall accuracy of 0.71 when used over areas in France.