English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

At I/ITSEC 2019, the authors presented a fully-automated workflow to segment3D photogrammetric point-clouds/meshes and extract object information,including individual tree locations and ground materials (Chen et al., 2019).The ultimate goal is to create realistic virtual environments and provide thenecessary information for simulation. We tested the generalizability of thepreviously proposed framework using a database created under the U.S. Army'sOne World Terrain (OWT) project with a variety of landscapes (i.e., variousbuildings styles, types of vegetation, and urban density) and different dataqualities (i.e., flight altitudes and overlap between images). Although thedatabase is considerably larger than existing databases, it remains unknownwhether deep-learning algorithms have truly achieved their full potential interms of accuracy, as sizable data sets for training and validation arecurrently lacking. Obtaining large annotated 3D point-cloud databases istime-consuming and labor-intensive, not only from a data annotation perspectivein which the data must be manually labeled by well-trained personnel, but alsofrom a raw data collection and processing perspective. Furthermore, it isgenerally difficult for segmentation models to differentiate objects, such asbuildings and tree masses, and these types of scenarios do not always exist inthe collected data set. Thus, the objective of this study is to investigateusing synthetic photogrammetric data to substitute real-world data in trainingdeep-learning algorithms. We have investigated methods for generating syntheticUAV-based photogrammetric data to provide a sufficiently sized database fortraining a deep-learning algorithm with the ability to enlarge the data sizefor scenarios in which deep-learning models have difficulties.

Generating synthetic photogrammetric data for training deep learning based 3D point cloud segmentation models