DeepVerge: Classification of roadside verge biodiversity and conservation potential

Andrew Perrett, Harry Pollard, Charlie Barnes, Mark Schofield, Lan Qie, Petra Bosilj, James M. Brown

Abstract: Highlights•A system for remote surveying of UK roadside verges was developed.•Street-view imagery was used to train a deep learning classifier.•The model can identify roadside verges with high conservation potential.•The automated system reduces the need for manual field surveys.