Figure 6. (a) The blue points represent the mapped paint damages found in the drone images captured in one drone flight. A CAD model moved to the same position as the geo-referenced coordinate system is used (b) The paint damages have been divided into 7 different clusters. The surface area for the clusters is presented together with image numbers. The image number makes it possible to find the images that have paint damages that contributed to the paint damage points in the cluster. (c) The blue points represent the paint damages mapped to the reconstructed 3D model.
The mapping method where the paint damage pixels are projected along surface normals is, as stated above, more accurate than the closest point on the TP method. The former method is needed when the paint damage is contained in a small area. The closest point approach would require a very high mesh resolution of the TP. Figure 7 shows an example where the paint damage has a small surface area. Figure 7 (a) shows the content of the bounding box calculated using the YOLO algorithm. The paint damage has a light yellow color and is placed near the center of the bounding box. Figure 7 (b) shows the output of the color threshold segmentation algorithm. The result of mapping the black paint damage pixels to the TP is presented in Figure 8 (a).