Since our input models are raw and unstructured 3D point clouds,
the very first step of our pipeline must identify some structured
evidence of the architectural shape of interest. A natural choice for
buildings primarily composed of planar elements is to use planar
patches, as done in many previous approaches [21,16,17]. The use of
3D patches, as opposed to, e.g., 2D line projections [20,18], is wellsuited for our occlusions-based pruning algorithm. We perform patch
growing on a per-scan basis, so that every patch contains points that
belong to a same laser range scan. This way, when looking for
potential occluders of a patch, we can restrict the search to the
patches extracted from that same scan.
We extract patches using a simple region growing process based
on normal deviation and plane offset. Like Chauve et al. [16] we
have found this scheme to work well; more robust and elaborate
methods [25] were not needed in our application. Since a correct
choice of the seed points is very important, we start the growing
from the points that have most planar and low-noise neighborhoods. The quality of a candidate seed is evaluated by fitting a plane
to its k nearest neighbors with the Least-Median-of-Squares (LMS)
algorithm [4] and by then computing the sum of the residuals.
For the next steps we need a simplified patch representation,
and we found that an oriented bounding box (OBB) gives us
reasonable trade-off between simplicity and shape approximation
quality. The OBB is aligned with the two main principal components of the xy-plane projection of the patch and gives a good fit
for structures like long and thin walls that are not aligned with the
main axes (see also Fig. 3).
Since our input models are raw and unstructured 3D point clouds,the very first step of our pipeline must identify some structuredevidence of the architectural shape of interest. A natural choice forbuildings primarily composed of planar elements is to use planarpatches, as done in many previous approaches [21,16,17]. The use of3D patches, as opposed to, e.g., 2D line projections [20,18], is wellsuited for our occlusions-based pruning algorithm. We perform patchgrowing on a per-scan basis, so that every patch contains points thatbelong to a same laser range scan. This way, when looking forpotential occluders of a patch, we can restrict the search to thepatches extracted from that same scan.We extract patches using a simple region growing process basedon normal deviation and plane offset. Like Chauve et al. [16] wehave found this scheme to work well; more robust and elaboratemethods [25] were not needed in our application. Since a correctchoice of the seed points is very important, we start the growingfrom the points that have most planar and low-noise neighborhoods. The quality of a candidate seed is evaluated by fitting a planeto its k nearest neighbors with the Least-Median-of-Squares (LMS)algorithm [4] and by then computing the sum of the residuals.For the next steps we need a simplified patch representation,and we found that an oriented bounding box (OBB) gives usreasonable trade-off between simplicity and shape approximationquality. The OBB is aligned with the two main principal components of the xy-plane projection of the patch and gives a good fitfor structures like long and thin walls that are not aligned with themain axes (see also Fig. 3).
การแปล กรุณารอสักครู่..