Spatial Points

A collection of notes on remote sensing, spatial science, and solutions to problems encountered

Using deep learning to detect an indicator arid shrub in ultra-high-resolution UAV imagery

Article link: Using deep learning to detect an indicator arid shrub in ultra-high-resolution UAV imagery

My PhD research is in collaboration with Bush Heritage Australia. The second chapter of my thesis concerns the use of UAV imagery for gathering species-composition information, a component of biodiversity where measurement has typically been restricted to on-ground methods.

I used high resolution UAV imagery and deep-learning-based object detection models to automatically detect pearl bluebush (Maireana sedifolia) in UAV orthomosaics. The aim of the research was to assess the feasibility of this approach for use in monitoring programmes, as well as how detection accuracies were affected by the deep learning models chosen, image resolution, and monitoring site.

Read More

Wrack Off! Drones can help improve our understanding of local seagrass communities

HOW TO SEE SEAGRASS? WITH DRONES!

Seagrass forms an incredibly important ecosystem worldwide, providing a wide range of functions. However, as with many other lifeforms, their health has been threatened by human advancements.

Significant declines of seagrass meadows extent (up to a third of meadows along the Adelaide Metropolitan Coastline) leading up to the early 2000s, has been due to poor waste- and storm-water quality. Significant work has been done to improve water quality being released into the coast, showing significant regrowth over the past 20 years. Assessing the effectiveness of seagrass regeneration requires fast and accurate feedback data. This has been significantly enhanced with the use of up-and-coming monitoring techniques.

Read More

Conference Poster – Using Deep Learning to Detect an Arid Shrub Species in UAV Imagery

Read More

Deep Learning in ArcGIS Pro using your GPU

ArcGIS Pro includes built in tools that allow end-to-end deep learning, all within the Arc interface – from training sample labelling, through model training and final image classification / object detection. This removes the need for coding and installing the correct versions of the required libraries for machine / deep learning in Python.

However, training deep learning models is an extremely processing-heavy task that requires the use of your GPU to even be slightly feasible in terms of processing time.

Although, Deep Learning in ArcGIS Pro is not possible straight out of the box. This post will walk through how to get everything set up, based on my experience with ArcGIS Pro 2.8/2.9 and the graphics cards listed below. Processes / software versions are sure to change in the future, so I will try and keep the instructions as general as possible.

Read More

Some Useful Biodiversity Platforms for Spatial Research

The following are a few useful sites for those undertaking spatial research involving species observational data in Australia primarily. These sites may contain both the observational data as well as tools for analysing this data, with direct access to curated environmental and other data layers.

1. ALA – Atlas of Living Australia (https://www.ala.org.au/)

Provides open access to Australia’s biodiversity data. This site provides a variety of tools and methods to access and analyse Australia’s biodiversity data, including:

Read More

Meet the Team – Alan Stenhouse

My background is in software development and I came to Adelaide to try and apply my skills towards aiding our natural world and helping to conserve our amazing biodiversity. My wife has also been pursuing her PhD in Ecology, studying Malleefowl on the Eyre Peninsula. Both of us studying concurrently has been both highly rewarding and often challenging in many ways!

My PhD research has focussed on developing tools for improving the quality of biodiversity data collected by citizen scientists. I developed two mobile apps for iOS and android devices for The Great Koala Count in South Australia in 2016 and similarly for the Echidna Conservation Science Initiative (echidnaCSI) which began in 2017 and continues today. The echidnaCSI project was one of the 3 finalists for the 2021 Eureka Prize for Innovation in Citizen Science.

Read More

The Fluidity of Monitoring Blue Carbon Ecosystems

What are blue carbon ecosystems and why are they important?

Mangroves, saltmarsh and seagrasses are referred to as blue carbon ecosystems. They are ‘mega’ carbon storers, at 6 to 8 Mg per hectare. This increased carbon storage is where blue carbon ecosystems get their name! When these ecosystems are degraded, much of this carbon is lost and cycled back into the atmosphere and water. Carbon sequestration and conservation of carbon stores can significantly control global warming, and so lots of current research on these ecosystems is focused on how to protect them from degradation. We do this through monitoring possible impacts upon blue carbon systems and we work hard to produce strategies to protect them. This has the added benefit of informing market evaluations of carbon storage. So, the more precise our monitoring, the higher the value of the ecosystem!

Read More

Boolcoomatta – October 2020 and March 2021

Meet The Team – Diego Guevara

Hi there! I’m Diego, a biologist from Peru. I am in the middle of my PhD, working with the Spatial Science Group at the University of Adelaide. I have always been interested in the natural world and tried to explore it as much as I can.

Read More

Page 1 of 4

Powered by WordPress & Theme by Anders Norén