Assessing the accuracy of georeferenced landcover data derived from oblique imagery using machine learning

Simple item page
dc.contributor.authorTricker, James
dc.contributor.authorWright, Claire
dc.contributor.authorRose, Spencer
dc.contributor.authorRhemtulla, Jeanine M.
dc.contributor.authorLantz, Trevor C.
dc.contributor.authorHiggs, Eric
dc.date.accessioned2025-03-26T19:41:19Z
dc.date.available2025-03-26T19:41:19Z
dc.date.issued2024
dc.description.abstractRepeat photography offers distinctive insights into ecological change, with ground-based oblique photographs often predating early aerial images by decades. However, the oblique angle of the photographs presents challenges for extracting and analyzing ecological information using traditional remote sensing approaches. Several innovative methods have been developed for analyzing repeat photographs, but none offer a comprehensive end-to-end workflow incorporating image classification and georeferencing to produce quantifiable landcover data. In this paper, we provide an overview of two new tools, an automated deep learning classifier and intuitive georeferencing tool, and describe how they are used to derive landcover data from 19 images associated with the Mountain Legacy Project, a research team that works with the world's largest collection of systematic high-resolution historic mountain photographs. We then combined these data to produce a contemporary landcover map for a study area in Jasper National Park, Canada. We assessed georeferencing accuracy by calculating the root-mean-square error and mean displacement for a subset of the images, which was 4.6 and 3.7 m, respectively. Overall classification accuracy of the landcover map produced from oblique images was 68%, which was comparable to landcover data produced from aerial imagery using a conventional classification method. The new workflow advances the use of repeat photographs for yielding quantitative landcover data. It has several advantages over existing methods including the ability to produce quick and consistent image classifications with little human input, and accurately georeference and combine these data to generate landcover maps for large areas.
dc.description.reviewstatusReviewed
dc.description.scholarlevelFaculty
dc.description.sponsorshipAnd we thank Jasper National Park, fRI Research, Mitacs Accelerate, Lorene Kennedy Environmental Studies PhD Award, Lorene Kennedy Field Research Award, and SSHRC for supporting this research.
dc.identifier.citationTricker, J., Wright, C., Rose, S., Rhemtulla, J., Lantz, T., & Higgs, E. (2024). Assessing the accuracy of georeferenced landcover data derived from oblique imagery using machine learning. Remote Sensing in Ecology and Conservation, 10(3), 401–415. https://doi.org/10.1002/rse2.379
dc.identifier.urihttps://doi.org/10.1002/rse2.379
dc.identifier.urihttps://hdl.handle.net/1828/21689
dc.language.isoen
dc.publisherRemote Sensing in Ecology and Conservation
dc.rightsCC BY-NC 4.0
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0
dc.subjectaccuracy assessment
dc.subjectlandcover classification
dc.subjectmachine learning
dc.subjectMountain Legacy Project
dc.subjectoblique photographs
dc.titleAssessing the accuracy of georeferenced landcover data derived from oblique imagery using machine learning
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
tricker_james_RemoteSens.Ecol.Conserv_2024.pdf
Size:
6.28 MB
Format:
Adobe Portable Document Format
Download

Collections

Faculty Publications (Social Sciences)
 
University of Victoria Libraries

We acknowledge and respect the Lək̓ʷəŋən (Songhees and Esquimalt) Peoples on whose territory the university stands, and the Lək̓ʷəŋən and W̱SÁNEĆ Peoples whose historical relationships with the land continue to this day.