Kyle Landolt
Kyle is a geographer in the Geospatial Sciences and Technologies branch at the Upper Midwest Environmental Sciences Center. His current work uses geospatial statistics and machine learning techniques to process aerial imagery for natural resource management.
Research Interests:
- Data Management
- Open Source Software
- Geographic Information Systems
- Machine Learning
- Cartography
Education and Certifications
M.S., Geography, The University of Tennessee, Knoxville, 2016
B.S., Ecological Restoration, Texas A&M University, 2014
Science and Products
Deep Learning for Automated Detection and Classification of Waterfowl, Seabirds, and other Wildlife from Digital Aerial Imagery
The U.S. Geological Survey Upper Midwest Environmental Sciences Center is developing deep learning algorithms and tools for the automatic detection, enumeration, classification, and annotation of seabirds and other marine wildlife from digital aerial imagery — advancing cutting-edge research in collaboration with the Bureau of Ocean Energy Management (BOEM), the U.S. Fish and Wildlife Service (FWS...
Images and annotations to automate the classification of avian species
This dataset is a collection of cropped avian images that pair with species identification annotation values.
Aerial thermal imagery of the Central Platte River Valley and bounding box annotations of sandhill cranes
Aerial thermal imagery was collected over the Central Platte River Valley, Nebraska, USA. Bounding box annotations were manually created for the purpose of machine learning tasks to automate the detection of sandhill cranes. Mosaicking of the thermal imagery was complete to assemble the individual images into a single, geo-referenced image.
Challenges and solutions for automated avian recognition in aerial imagery
Remote aerial sensing provides a non-invasive, large geographical-scale technology for avian monitoring, but the manual processing of images limits its development and applications. Artificial Intelligence (AI) methods can be used to mitigate this manual image processing requirement. The implementation of AI methods, however, has several challenges: (1) imbalanced (i.e., long-tailed) data distribu
Authors
Zhonqgi Miao, Stella X Yu, Kyle Lawrence Landolt, Mark D. Koneff, Timothy White, Luke J. Fara, Enrika Hlavacek, Bradley A. Pickens, Travis J. Harrison, Wayne M. Getz
Automating sandhill crane counts from nocturnal thermal aerial imagery using deep learning
Population monitoring is essential to management and conservation efforts for migratory birds, but traditional low-altitude aerial surveys with human observers are plagued by individual observer bias and risk to flight crews. Aerial surveys that use remote sensing can reduce bias and risk, but manual counting of wildlife in imagery is laborious and may be cost-prohibitive. Therefore, automated met
Authors
Emilio Luz-Ricca, Kyle Lawrence Landolt, Bradley A. Pickens, Mark D. Koneff
Science and Products
- Science
Deep Learning for Automated Detection and Classification of Waterfowl, Seabirds, and other Wildlife from Digital Aerial Imagery
The U.S. Geological Survey Upper Midwest Environmental Sciences Center is developing deep learning algorithms and tools for the automatic detection, enumeration, classification, and annotation of seabirds and other marine wildlife from digital aerial imagery — advancing cutting-edge research in collaboration with the Bureau of Ocean Energy Management (BOEM), the U.S. Fish and Wildlife Service (FWS... - Data
Images and annotations to automate the classification of avian species
This dataset is a collection of cropped avian images that pair with species identification annotation values.Aerial thermal imagery of the Central Platte River Valley and bounding box annotations of sandhill cranes
Aerial thermal imagery was collected over the Central Platte River Valley, Nebraska, USA. Bounding box annotations were manually created for the purpose of machine learning tasks to automate the detection of sandhill cranes. Mosaicking of the thermal imagery was complete to assemble the individual images into a single, geo-referenced image. - Publications
Challenges and solutions for automated avian recognition in aerial imagery
Remote aerial sensing provides a non-invasive, large geographical-scale technology for avian monitoring, but the manual processing of images limits its development and applications. Artificial Intelligence (AI) methods can be used to mitigate this manual image processing requirement. The implementation of AI methods, however, has several challenges: (1) imbalanced (i.e., long-tailed) data distribuAuthorsZhonqgi Miao, Stella X Yu, Kyle Lawrence Landolt, Mark D. Koneff, Timothy White, Luke J. Fara, Enrika Hlavacek, Bradley A. Pickens, Travis J. Harrison, Wayne M. GetzAutomating sandhill crane counts from nocturnal thermal aerial imagery using deep learning
Population monitoring is essential to management and conservation efforts for migratory birds, but traditional low-altitude aerial surveys with human observers are plagued by individual observer bias and risk to flight crews. Aerial surveys that use remote sensing can reduce bias and risk, but manual counting of wildlife in imagery is laborious and may be cost-prohibitive. Therefore, automated metAuthorsEmilio Luz-Ricca, Kyle Lawrence Landolt, Bradley A. Pickens, Mark D. Koneff