Abstract
When performing structural inspection, the generation of three-dimensional (3D) point clouds is a common resource. Those are usually generated from photogrammetry or through laser scan techniques. However, a significant drawback for complete inspection is the presence of covering vegetation, hiding possible structural problems, and making difficult the acquisition of proper object surfaces in order to provide a reliable diagnostic. Therefore, this research’s main contribution is developing an effective vegetation removal methodology through the use of a deep learning structure that is capable of identifying and extracting covering vegetation in 3D point clouds. The proposed approach uses pre and post-processing filtering stages that take advantage of colored point clouds, if they are available, or operate independently. The results showed high classification accuracy and good effectiveness when compared with similar methods in the literature. After this step, if color is available, then a color filter is applied, enhancing the results obtained. Besides, the results are analyzed in light of real Structure From Motion (SFM) reconstruction data, which further validates the proposed method. This research also presented a colored point cloud library of bushes built for the work used by other studies in the field.
Highlights
Many techniques can be applied in order to monitor different aspects of the terrain when inspecting large structures
This work aims to reduce this effect by removing the vegetation that is present in the 3D reconstruction
The proposed methodology applies a combination of deep learning with a windowing processing in order to accurately determine the presence and position of vegetation that needs to be removed
Summary
Many techniques can be applied in order to monitor different aspects of the terrain when inspecting large structures. Photogrammetry is a widely used method, due to its flexibility, cost-effectiveness, and accuracy [1] This technique can be applied in many different cases, such as presented in Barazzetti et al [2], and it can be combined with other technologies to improve the results. Works of Khaloo et al [5] and Pinto et al [6] showed a potential use of UAV along with photogrammetry to perform large structures’ inspection. This kind of process generates point clouds with acurracy
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
