Large-scale road detection in forested mountainous areas using airborne topographic lidar data

This paper addresses the problem of road detection and characterization in forested environments over large scales (>1000 km2). For that purpose, an efficient pipeline is proposed, which assumes that main forest roads can be modeled as planar elongated features in the road direction with relief variation in orthogonal direction. DTMs are the only input and no complex 3D point cloud processing methods are involved. First, a restricted but carefully designed set of morphological features is defined as input for a supervised Random Forest classification of potential road patches. Then, a graph is built over these candidate regions: vertices are selected using stochastic geometry tools and edges are created in order to fill gaps in the DTM created by vegetation occlusion. The graph is pruned using morphological criteria derived from the input road model. Finally, once the road is located in 2D, its width and slope are retrieved using an object-based image analysis. We demonstrate that our road model is valid for most forest roads and that roads are correctly retrieved (>80%) with few erroneously detected pathways (10-15%) using fully automatic methods. The full pipeline takes less than 2 min per km2 and higher planimetric accuracy than 2D existing topographic databases are achieved. Compared to these databases, additional roads can be detected with the ability of lidar sensors to penetrate the understory. In case of very dense vegetation and insufficient relief in the DTM, gaps may exist in the results resulting in local incompleteness (∼15%).