Abstract
A georeferenced orthophoto built from aerial images is the basic resource for various of remote sensing applications. As traditional low flight altitude aerial photographic survey is hard to handle large areas, higher altitude brings better survey efficiency, and a telephoto camera is required to maintain the resolution. Since existed structure from motion (SfM) methods are not suitable to process the low field-of-view images with high altitude, this article presents a novel georeferenced orthophoto stitching solution for telephoto images, which contain both translation and rotation movements. A mission planning strategy is designed to guarantee the consistent quality, according to the flight plan and camera intrinsic parameters. The potential matching topology is obtained by projecting images to the prior ground plan,e and overlap scores are estimated for neighbors query, followed with a feature-based keypoint matching. The ground plane and camera poses are optimized by joint considering feature matches, GPS and gimbal rotation information, while the final orthophoto is fused with a fast exposure leveling and weighted multiband-blending algorithm. The experiments show that our system is able to output novel quality orthophoto with high robustness, and we shared a trial version of our algorithm. 1
Highlights
AND RELATED WORKSNowadays, satellite and aerial remote sensing are popular used in different applications such as city surveillance, power line inspection, forest fire monitoring and agricultural management
As image resolution is limited by sensors, a lower field-of-view telephoto camera is generally used in high flight height, which brings challenge for existing reconstruction systems
Many works have been conducted to do image mosaicking in recent years, this section collects and analyzes the existing related algorithms that are applicable to the Unmanned Aerial Vehicles (UAVs) aerial orthoimage generation, and summarizes as follows: Structure from Motion (SfM) based, simultaneous localization and mapping (SLAM) based, and 2D Mosaicing based aerial orthoimage generation methods
Summary
Satellite and aerial remote sensing are popular used in different applications such as city surveillance , power line inspection, forest fire monitoring and agricultural management. As image resolution is limited by sensors, a lower field-of-view telephoto camera is generally used in high flight height, which brings challenge for existing reconstruction systems. With the rapid development in the field of Unmanned Aerial Vehicles (UAVs) and photogrammetry, almost any briefly trained user can safely plan and execute flight missions with high autonomy This trend already democratised aerial imagery and led to numerous softwares for processing and evaluation of acquired aerial data, such as Pix4DMapper [2], Agisoft Metashape [3] and DroneDeploy [4]. Since existed methods are not suitable to process low field-of-view images with high altitude. This paper aims to present a complete solution to mosaic georeferenced orthophoto efficiently with a high altitude rocking telephoto camera. To evaluate the effectiveness of our solution, we share a public NPU HighStitch Dataset with extremely low overlap and field-of-view images
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
