In recent years, hyperspectral images are gaining popularity in various applications, including anomaly detection, target classification, search and rescue operations, and many others. However, due to the presence of vegetation and buildings, some additional processing steps are needed in order to obtain DTM from DSM. Near infrared (NIR) together with color imagers have been used in recent years to generate DSM. Due to availability of low-cost drones, stereo imaging has been gaining popularity. It is well known that LiDAR and radar equipment are expensive. The obtained DTM is in general satisfactory even though the point density may not be very dense as compared to optical stereo imaging approach. In recent years, people have started to use LiDAR to generate DTM. The process is time-consuming, tedious, and prone to human errors. The oldest method is to do this manually by measuring the terrain elevations of some selected points of a given area. Objective evaluation results indicate that some inpainting methods perform better than others. The DTM from United States Geological Survey (USGS) was used as the ground truth. A dataset with DSM and hyperspectral data near the U. That is, for buildings and trees, we remove those pixels from the DSM and then apply inpainting techniques to reconstruct the terrain pixels in those areas.
In this chapter, we assume the land cover types have been classified and we focus on the use of image inpainting algorithms for DTM generation. Normally, the process of extracting DTM involves a land cover classification followed by a trimming step that removes the elevation due to trees and buildings. Although digital surface model (DSM) obtained by radar or LiDAR can provide a general idea of the terrain, the presence of trees, buildings, etc. However, in urban and sub-urban areas, the terrain may be covered by trees and man-made structures.
In some applications such as construction planning and land surveying, an accurate digital terrain model (DTM) is essential.
0 kommentar(er)
