Jan Bjerketvedt
Research Scientist
Abstract
RoadSens is a platform designed to expedite the digitalization process of forest roads, a cornerstone of efficient forest operations and management. We incorporate stereo-vision spatial mapping and deep-learning image segmentation to extract, measure, and analyze various geometric features of the roads. The features are precisely georeferenced by fusing post-processing results of an integrated global navigation satellite system (GNSS) module and odometric localization data obtained from the stereo camera. The first version of RoadSens, RSv1, provides measurements of longitudinal slope, horizontal/vertical radius of curvature and various cross-sectional parameters, e.g., visible road width, centerline/midpoint positions, left and right sidefall slopes, and the depth and distance of visible ditches from the road’s edges. The potential of RSv1 is demonstrated and validated through its application to two road segments in southern Norway. The results highlight a promising performance. The trained image segmentation model detects the road surface with the precision and recall values of 96.8 and 81.9 , respectively. The measurements of visible road width indicate sub-decimeter level inter-consistency and 0.38 m median accuracy. The cross-section profiles over the road surface show 0.87 correlation and 9.8 cm root mean squared error (RMSE) against ground truth. The RSv1’s georeferenced road midpoints exhibit an overall accuracy of 21.6 cm in horizontal direction. The GNSS height measurements, which are used to derive longitudinal slope and vertical curvature exhibit an average error of 5.7 cm compared to ground truth. The study also identifies and discusses the limitations and issues of RSv1, which provide useful insights into the challenges in future versions.
Abstract
No abstract has been registered
Abstract
Recent decades have seen increased temperatures and precipitation in the Nordic countries with long-term projections for reduced frost duration and depth. The consequence of these trends has been a gradual shift of delivery volumes to the frost-free season, requiring more agile management to exploit suitable weather conditions. Bearing capacity and trafficability are dependent on soil moisture state and in this context two satellite missions offer potenially useful information on soil moisture levels; NASA’s SMAP (Soil Moisture Active Passive) and ESA’s Sentinel-1. The goal of this pilot study was to quantify the performance of such satellite-based soil moisture variables for modeling forest road bearing capacity (e-module) during the frost-free season. The study was based on post-transport registrations of 103 forest road segments on the coastal and interior side of the Scandinavian mountain range. The analysis focused on roads of three types of surface deposits. Weekly SMAP soil moisture values better explained the variation in road e-module than soil water index (SWI) derived from Sentinel-1. Soil Water Index (SWI), however, reflected the weather conditions typical for operations on the respective surface deposit types. Regression analysis using (i) SMAP-based soil dryness index and (ii) its interaction with surface deposit types, together with (iii) the ratio between a combined SMAP_SWI dryness index and segment-specific depth to water (DTW) explained over 70% of the variation in road e-module. The results indicate a future potential to monitor road trafficability over large supply areas on a weekly level, given further refinement of study methods and variables for improved prediction.
