J
James T. Dietrich
Researcher at University of Northern Iowa
Publications - 17
Citations - 1665
James T. Dietrich is an academic researcher from University of Northern Iowa. The author has contributed to research in topics: Photogrammetry & Structure from motion. The author has an hindex of 9, co-authored 17 publications receiving 1389 citations. Previous affiliations of James T. Dietrich include Dartmouth College & University of Oregon.
Papers
More filters
Journal ArticleDOI
Topographic structure from motion: a new development in photogrammetric measurement
Mark A. Fonstad,James T. Dietrich,Brittany C. Courville,Jennifer L. R. Jensen,Patrice Carbonneau +4 more
TL;DR: This test shows that SfM and low-altitude platforms can produce point clouds with point densities comparable with airborne LiDAR, with horizontal and vertical precision in the centimeter range, and with very low capital and labor costs and low expertise levels.
Journal ArticleDOI
Bathymetric Structure-from-Motion: extracting shallow stream bathymetry from multi-view stereo photogrammetry
TL;DR: In this article, a multi-camera refraction correction method was proposed to improve the accuracy of bathymetric data for a variety of river, coastal, and estuary systems.
Journal ArticleDOI
Cost-effective non-metric photogrammetry from consumer-grade sUAS: implications for direct georeferencing of structure from motion photogrammetry
TL;DR: It is argued that direct georeferencing and low-cost sUAS are capable of producing reliable topography products without recourse to expensive survey equipment and could transform survey practices in both academic and commercial disciplines.
Journal ArticleDOI
Riverscape mapping with helicopter-based Structure-from-Motion photogrammetry
TL;DR: In this paper, the authors employed a helicopter-mounted digital SLR camera and Structure-from-Motion (SfM) photogrammetry to bridge the gap between smaller scale aerial surveys from platforms like small unmanned aerial systems and larger scale commercial aerial photography or airborne LiDAR collections.
Journal ArticleDOI
Adopting deep learning methods for airborne RGB fluvial scene classification.
Patrice Carbonneau,Stephen J. Dugdale,Toby P. Breckon,James T. Dietrich,Mark A. Fonstad,Hitoshi Miyamoto,Amy Woodget +6 more
TL;DR: Deep learning can predict land-cover classifications for rivers not used in training and demonstrates the potential to train a generalised open-source deep learning model for airborne river surveys suitable for most rivers ‘out of the box’.