no code implementations • 24 Sep 2021 • Meida Chen, Andrew Feng, Yu Hou, Kyle McCullough, Pratusha Bhuvana Prasad, Lucio Soibelman
For ground material segmentation, we utilized an existing convolutional neural network architecture (i. e., 3DMV) which was originally designed for segmenting RGB-D sensed indoor data.
no code implementations • Journal of Computing in Civil Engineering 2020 • Meida Chen, Andrew Feng, Kyle McCullough, Pratusha Bhuvana Prasad, Ryan McAlinden, Lucio Soibelman
In this paper, we introduce a model ensembling framework for segmenting a 3D photogrammetry point cloud into top-level terrain elements (i. e., ground, human-made objects, and vegetation).
no code implementations • 21 Aug 2020 • Meida Chen, Andrew Feng, Kyle McCullough, Pratusha Bhuvana Prasad, Ryan McAlinden, Lucio Soibelman
At I/ITSEC 2019, the authors presented a fully-automated workflow to segment 3D photogrammetric point-clouds/meshes and extract object information, including individual tree locations and ground materials (Chen et al., 2019).
no code implementations • 21 Aug 2020 • Meida Chen, Andrew Feng, Kyle McCullough, Pratusha Bhuvana Prasad, Ryan McAlinden, Lucio Soibelman
This paper discusses the next steps in extending our designed data segmentation framework for segmenting 3D city data.
no code implementations • 9 Aug 2020 • Meida Chen, Andrew Feng, Kyle McCullough, Pratusha Bhuvana Prasad, Ryan McAlinden, Lucio Soibelman, Mike Enloe
The results showed that 3D mesh trees could be replaced with geo-typical 3D tree models using the extracted individual tree locations.