Robust and repeatable ruleset development for hierarchical object-based monitoring of revegetation using high spatial and temporal resolution UAS data

T.G. Whiteside, R.E. Bartolo

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

2 Downloads (Pure)

Abstract

The monitoring of mine site rehabilitation, particularly revegetation, involves assessing biophysical parameters over time to determine success or otherwise. Resource and logistical constraints limit the spatial and temporal scale of standard field-based monitoring methods. Unmanned aerial systems (UAS) can provide the capability to acquire optical data with coverage of an entire site at the spatial and temporal scales, suitable for the monitoring of relevant biophysical parameters. UAS data are not without
challenges, such as radiometric variation between flights and sensors, different sun angles and spatial variation between dates. Therefore, a ruleset (a stepwise set of analysis algorithms) is needed that is robust and repeatable across each image regardless of spatial and radiometric variability. This study reports on the development and implementation of such a ruleset. Using a fixed wing unmanned aircraft, colour and near infrared imagery was captured over the Jabiluka mine site, located in the Northern Territory, Australia on 7 dates between April 2014 and October 2015. The imagery was radiometrically and geometrically corrected and 4 band mosaics for each date were created using photogrammetric techniques. Image analysis involved the creation of vegetation indices relevant to the data available, the segmentation of the image to delineate plants from the background and the creation of a hierarchy of objects for analysis that was consistent across all dates. Accuracy assessment showed that the GEOBIA-derived
measures compared well with visual assessments of the imagery. From the analysis, the proportional cover of green plants and number of plant objects per unit area could be calculated. The time series analysis showed that proportional cover across the site varied between dates but gradually increased over time, although there was a high level of plant mortality. In addition, there was natural recruitment of volunteer plants. The same ruleset was applied to the imagery from each date demonstrating that it is robust
enough to be used for further monitoring on the site. In addition, the ruleset in a modified form is currently being used for change analysis using scanned historical aerial photography.
Original languageEnglish
Title of host publicationProceedings of GEOBIA 2016 : Solutions and synergies, 14-16 September 2016, Enschede, Netherlands
EditorsN. Kerle, M. Gerke, S. Lefevre
Place of PublicationEnschede
PublisherUniversity of Twente, Faculty of Geo-Information Science and Earth Observation (ITC)
Number of pages4
ISBN (Print)978-90-365-4201-2
DOIs
Publication statusPublished - 14 Sep 2016
Externally publishedYes
Event6th International Conference on Geographic Object-Based Image Analysis, GEOBIA 2016: Solutions & Synergies - University of Twente Faculty of Geo-Information and Earth Observation (ITC), Enschede, Netherlands
Duration: 14 Sep 201616 Sep 2016
Conference number: 6
https://www.geobia2016.com/

Conference

Conference6th International Conference on Geographic Object-Based Image Analysis, GEOBIA 2016
Abbreviated titleGEOBIA
CountryNetherlands
CityEnschede
Period14/09/1616/09/16
Internet address

Fingerprint

Dive into the research topics of 'Robust and repeatable ruleset development for hierarchical object-based monitoring of revegetation using high spatial and temporal resolution UAS data'. Together they form a unique fingerprint.

Cite this