Feature extraction
Feature extraction
part of the Knowledge extraction theme from CEGIS
Feature extraction is the process of extracting features of interest from geospatial data using specialized approaches.
Extracted features are later used to generate informative datasets, which can be further utilized for classification or prediction.
Deep learning (DL) technology is now widely used for feature extraction from geospatial data.
Initial research for feature extraction implementation
Current cartographic processes, such as generalization and feature extraction, pose fundamental hurdles to The National Map implementation.
This proposed research will begin an investigation of the problem of feature extraction from available image and map database sources to help establish a framework for the implementation of The National Map.
The research approach is to build a knowledge base of 20 specific features for inclusion in The National Map and develop a table of probabilities for the extraction of those features from current image sources.
Expected products from this research include a knowledge base framework and implementation for supporting feature representation and extraction for The National Map, and a specific knowledge base of 20 features with associated tables of extraction probabilities. The knowledge base will be expandable to include other features and image sources.
Publications
You will find here a sampling of publications. More are available and are being published throughout the year.
Check back often or view our custom search for more!
-
Automated deep learning-based point cloud classification on USGS 3DEP lidar data using transformer
The goal of the U.S. Geological Survey’s (USGS) 3D Elevation Program (3DEP) is to facilitate the acquisition of nationwide lidar data. Although data meet USGS lidar specifications, some point cloud tiles include noisy and incorrectly classified points. The enhanced accuracy of classified point clouds can improve support for many downstream applications such as hydrologic analysis, urban...AuthorsJung-Kuan (Ernie) Liu, Rongjun Qin, Shuang SongEvaluation of classified ground points from National Agriculture Imagery program photogrammetrically derived point clouds
Studies have shown that digital surface models and point clouds generated by the United States Department of Agriculture’s National Agriculture Imagery Program (NAIP) can measure basic forest parameters such as canopy height. However, all measured forest parameters from these studies are evaluated using the differences between NAIP digital surface models (DSMs) and available lidar...AuthorsJung-Kuan (Ernie) Liu, Samantha Arundel, Ethan J. ShaversRemote sensing-based 3D assessment of landslides: A review of the data, methods, and applications
Remote sensing (RS) techniques are essential for studying hazardous landslide events because they capture information and monitor sites at scale. They enable analyzing causes and impacts of ongoing events for disaster management. There has been a plethora of work in the literature mostly discussing (1) applications to detect, monitor, and predict landslides using various instruments and...AuthorsHessah Albanwan, Rongjun Qin, Jung-Kuan (Ernie) LiuGeoAI for spatial image processing
The development of digital image processing, as a subset of digital signal processing, depended upon the maturity of photography and image science, introduction of computers, discovery and advancement of digital recording devices, and the capture of digital images. In addition, government and industry applications in the Earth and medical sciences were paramount to the growth of the...AuthorsSamantha Arundel, Kevin G McKeehan, Wenwen Li, Zhining GuTransferring deep learning models for hydrographic feature extraction from IfSAR data in Alaska
The National Hydrography Dataset (NHD) managed by the U.S. Geological Survey (USGS) is being updated with higher-quality feature representations through efforts that derive hydrography from 3DEP HR elevation datasets. Deriving hydrography from elevation through traditional flow routing and interactive methods is a complex, time-consuming process that must be tailored for different...AuthorsLarry V. Stanislawski, Nattapon Jaroenchai, Shaowen Wang, Ethan J. Shavers, Alexander Duffy, Philip T. Thiem, Zhe Jiang, Adam Camerer
CEGIS science themes
Theme topics home
Knowledge extraction
Deep learning (DL)
Feature extraction
Terrain features
Hydrographic feature extraction
3DEP Feature extraction and conflation
You will find here a sampling of publications. More are available and are being published throughout the year.
Check back often or view our custom search for more!
All Feature extraction publications
All Knowledge extraction publications
All CEGIS publications
Automated deep learning-based point cloud classification on USGS 3DEP lidar data using transformer
Evaluation of classified ground points from National Agriculture Imagery program photogrammetrically derived point clouds
Remote sensing-based 3D assessment of landslides: A review of the data, methods, and applications
GeoAI for spatial image processing
Transferring deep learning models for hydrographic feature extraction from IfSAR data in Alaska
CEGIS - Denver, Colorado

CEGIS - Rolla, Missouri

Samantha T Arundel, PhD
Research Director
Senior Science Advisor
Ethan Shavers, PhD
CEGIS Section Chief/ Supervisory Geographer
Jung kuan (Ernie) Liu
Physical Research Scientist
Feature extraction is the process of extracting features of interest from geospatial data using specialized approaches.
Extracted features are later used to generate informative datasets, which can be further utilized for classification or prediction.
Deep learning (DL) technology is now widely used for feature extraction from geospatial data.
Initial research for feature extraction implementation
Current cartographic processes, such as generalization and feature extraction, pose fundamental hurdles to The National Map implementation.
This proposed research will begin an investigation of the problem of feature extraction from available image and map database sources to help establish a framework for the implementation of The National Map.
The research approach is to build a knowledge base of 20 specific features for inclusion in The National Map and develop a table of probabilities for the extraction of those features from current image sources.
Expected products from this research include a knowledge base framework and implementation for supporting feature representation and extraction for The National Map, and a specific knowledge base of 20 features with associated tables of extraction probabilities. The knowledge base will be expandable to include other features and image sources.
Publications
You will find here a sampling of publications. More are available and are being published throughout the year.
Check back often or view our custom search for more!
-
Automated deep learning-based point cloud classification on USGS 3DEP lidar data using transformer
The goal of the U.S. Geological Survey’s (USGS) 3D Elevation Program (3DEP) is to facilitate the acquisition of nationwide lidar data. Although data meet USGS lidar specifications, some point cloud tiles include noisy and incorrectly classified points. The enhanced accuracy of classified point clouds can improve support for many downstream applications such as hydrologic analysis, urban...AuthorsJung-Kuan (Ernie) Liu, Rongjun Qin, Shuang SongEvaluation of classified ground points from National Agriculture Imagery program photogrammetrically derived point clouds
Studies have shown that digital surface models and point clouds generated by the United States Department of Agriculture’s National Agriculture Imagery Program (NAIP) can measure basic forest parameters such as canopy height. However, all measured forest parameters from these studies are evaluated using the differences between NAIP digital surface models (DSMs) and available lidar...AuthorsJung-Kuan (Ernie) Liu, Samantha Arundel, Ethan J. ShaversRemote sensing-based 3D assessment of landslides: A review of the data, methods, and applications
Remote sensing (RS) techniques are essential for studying hazardous landslide events because they capture information and monitor sites at scale. They enable analyzing causes and impacts of ongoing events for disaster management. There has been a plethora of work in the literature mostly discussing (1) applications to detect, monitor, and predict landslides using various instruments and...AuthorsHessah Albanwan, Rongjun Qin, Jung-Kuan (Ernie) LiuGeoAI for spatial image processing
The development of digital image processing, as a subset of digital signal processing, depended upon the maturity of photography and image science, introduction of computers, discovery and advancement of digital recording devices, and the capture of digital images. In addition, government and industry applications in the Earth and medical sciences were paramount to the growth of the...AuthorsSamantha Arundel, Kevin G McKeehan, Wenwen Li, Zhining GuTransferring deep learning models for hydrographic feature extraction from IfSAR data in Alaska
The National Hydrography Dataset (NHD) managed by the U.S. Geological Survey (USGS) is being updated with higher-quality feature representations through efforts that derive hydrography from 3DEP HR elevation datasets. Deriving hydrography from elevation through traditional flow routing and interactive methods is a complex, time-consuming process that must be tailored for different...AuthorsLarry V. Stanislawski, Nattapon Jaroenchai, Shaowen Wang, Ethan J. Shavers, Alexander Duffy, Philip T. Thiem, Zhe Jiang, Adam Camerer
CEGIS science themes
Theme topics home
Knowledge extraction
Deep learning (DL)
Feature extraction
Terrain features
Hydrographic feature extraction
3DEP Feature extraction and conflation
You will find here a sampling of publications. More are available and are being published throughout the year.
Check back often or view our custom search for more!
All Feature extraction publications
All Knowledge extraction publications
All CEGIS publications
Automated deep learning-based point cloud classification on USGS 3DEP lidar data using transformer
Evaluation of classified ground points from National Agriculture Imagery program photogrammetrically derived point clouds
Remote sensing-based 3D assessment of landslides: A review of the data, methods, and applications
GeoAI for spatial image processing
Transferring deep learning models for hydrographic feature extraction from IfSAR data in Alaska
CEGIS - Denver, Colorado

CEGIS - Rolla, Missouri
