USING UNMANNED AERIAL VEHICLES IN RECOGNIZING TERRAIN ANOMALIES ENCOUNTERED IN THE GAS PIPELINE RIGHT-OF-WAY (ROW)

Abstract

The objective of the undertaken research was to characterize and evaluate the impact of weather and lighting conditions on recording terrain anomalies in the photographs obtained during a UAV photogrammetric flight. The present work describes the use and capabilities of the UAV in the mapping of photo acquisition conditions similar to those performed during inspection flights with the use of a manned helicopter equipped with a hyperspectral camera, in the target range of visible light. The research was conducted in the southern part of Poland (between Gliwice and Katowice), where 7 routes were selected, differing from one another in terms of terrain anomalies (buildings, types of land areas, vehicles, vegetation). In the studies, which involved photogrammetric flights performed using a UAV, different seasons and times of day as well as changes in light intensity were taken into account. The flight specification was based on the main parameters with the following assumptions: taking only perpendicular (nadir) RGB photographs, flight altitude 120 m AGL, strip width 160 m, GSD ≤0.04 m and overlap ≥83%. The analysis of the photographic material obtained made it possible to correct the catalog of anomalies defined previously, since the recognition of some objects is very difficult, being usually below the orthophotomap resolution. When making and evaluating orthophotomaps, problems with mapping the shape of objects near the edges of the frame were found. When a 12 mm lens is used, these distortions are significant. It was decided that for the purpose of generating training data from orthophotomaps, only the fragments containing objects which shape would be mapped in accordance with the real one would be used. Thus, the effective width of orthophotomaps obtained from simulated flights will be approximately 100 m.