Ground Feature Oriented Path Planning for Unmanned Aerial Vehicle Mapping

Unmanned aerial vehicles (UAVs) are being used to take roles that were previously performed by traditional manned aircraft, such as remote sensing and photogrammetry. The standard path planning for UAV mapping is mainly executed by adopting the lawnmower mode. However, some situations that have sparse or repetitive features are problematic to map with this technique, given that orthoimage stitching relies heavily on the number and quality of image tie points. Traditional path planning can result in some unregistered images due to a lack of tie points. This paper proposes a ground feature oriented path-planning method for UAV mapping. The method first estimates the distribution of the ground feature points from a lower-resolution image. Then, image footprints are selected by applying a three-step optimization. The flight path for the UAV is then generated by solving the grouped traveling salesman problem. This approach ensures the georegistration of images during orthoimage stitching while maximizing the orthoimage coverage. Two cases, including a simulation and a real-world case, together with standard path-planning modes with different overlaps, are selected to evaluate the proposed method. The results show that the proposed method covers the same area with the smallest number of images. The model excludes problematic areas from the scanning path to generate a more efficient processing dataset.