With point cloud generation we create height information from the UAV images after stitching. Point clouds generated from UAV images are essentially elevation data (i.e., each point is a triplet (x,y,z) where z denotes elevation). High density point clouds are automatically generated through image matching (Rosnell and Honkavaara, 2012). The success of image matching, and subsequent generation of the dense point could, depends on factors such as visual content and overlap. Large overlaps and high visual content will lead to better results than smaller overlaps and low visual content. Once image stitching has been completed, dense point cloud can be generated. Once image stitching has been completed, a dense point cloud can be generated (Figures 5.10 and 5.11).
The generation of the point cloud is the most computationally intensive step in processing UAV images. One needs a computer with high performance specs to process a (usually large) number of images.
For an area of 0.47 km2, and 97 photos, the generation of a dense point cloud took approximately 45 min for a computer with these CPU specs: Intel(R) Core(TM) i5-3340MCPU @2.70GHz, RAM: 16GB, GPU: Intel(R) HD Graphics 4000 (Driver: 18.104.22.16896). In desktop computers, CUDA GPU devices are advisable to improve the processing power of the PC.
In case where such a high specs computer is not available, it may be advisable to perform this task overnight while remotely monitoring progress (e.g., monitoring your workstation at work with your laptop at home). Performing this overnight ensures that all the computer resources are dedicated to the operation thus leading to lower failure chances. One has to ensure a continuous power supply, though!
Cleaning the generated point cloud is an important step to improve the resulting ortho-image, especially in areas with drastic changes in height, such as fences, trees and buildings. This can be achieved manually when an analyst scrutinizes the generated point cloud and deletes points that are outliers to the terrain shape. Low overlap areas outside the planned area need more cleaning work to obtain a good DSM. For easier viewing and editing of the point cloud, a 3D mesh can be generated with the same processing software (e.g., in Pix4D) (figure 5.11). This mesh is formed by connecting the points in the generated cloud. After this cleaning, the project can be re-matched and improved.