Karen Fagg

Karen Fagg

University of Tasmania, Hobart, Tasmania, Australia

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2018 in Theriogenology
Verified
Journal Article
Closed access
HCHolly R. Cope
Holly R. Cope
CHCarolyn J. Hogg
Carolyn J. Hogg
Karen FaggKaren Fagg
Karen Fagg
OBOlivia Barnard
Olivia Barnard
PWPeter J. White
Peter J. White
CHCatherine Herbert
Catherine Herbert

5 June 2023 in Wildlife Research
Verified
Journal Article
Open access
PDF file
FNFatih Nurçin
Fatih Nurçin
NŞNiyazi Şentürk
Niyazi Şentürk
EIElbrus Imanov
Elbrus Imanov
STSam Thalmann
Sam Thalmann
Karen FaggKaren Fagg
Karen Fagg
Context Artificial intelligence algorithms are beneficial for automating the monitoring of threatened species. Devil facial tumour disease (DFTD) is an endemic disease threatening Australia’s Tasmanian devil. The disease is a cancer that can be transmitted from one devil to another during social interactions. Cameras and trapping techniques have been employed to monitor the spread of the disease in the wild. The use of cameras allows for more frequent monitoring of devils than does trapping, but differentiating wounds from tumours in images is challenging, and this requires time and expertise.Aim The purpose of this work is to develop a computer vision system to assist in the monitoring of DFTD spread.Method We propose a system that involves image segmentation, feature extraction, and classification steps. U-net architecture, global average pooling layer of pre-trained Resnet-18, and support vector machine (SVM) classifiers were employed for these purposes, respectively. In total, 1250 images of 961 healthy and 289 diseased (DFTD) devils were separated into training, validation, and testing sets.Results The proposed algorithm achieved 92.4% classification accuracy for the differentiation of healthy devils from those with DFTD.Conclusion The high classification accuracy means that our method can help field workers with monitoring devils.Implications The proposed approach will allow for more frequent analysis of devils while reducing the workload of field staff. Ultimately, this automation could be expanded to other species for simultaneous monitoring at shorter intervals to facilitate broadened ecological assessments. Context Artificial intelligence algorithms are beneficial for automating the monitoring of threatened species. Devil facial tumour disease (DFTD) is an endemic disease threatening Australia’s Tasmanian devil. The disease is a cancer that can be transmitted from one devil to another during social interactions. Cameras and trapping techniques have been employed to monitor the spread of the disease in the wild. The use of cameras allows for more frequent monitoring of devils than does trapping, but differentiating wounds from tumours in images is challenging, and this requires time and expertise.Aim The purpose of this work is to develop a computer vision system to assist in the monitoring of DFTD spread.Method We propose a system that involves image segmentation, feature extraction, and classification steps. U-net architecture, global average pooling layer of pre-trained Resnet-18, and support vector machine (SVM) classifiers were employed for these purposes, respectively. In total, 1250 images of 961 healthy and 289 diseased (DFTD) devils were separated into training, validation, and testing sets.Results The proposed algorithm achieved 92.4% classification accuracy for the differentiation of healthy devils from those with DFTD.Conclusion The high classification accuracy means that our method can help field workers with monitoring devils.Implications The proposed approach will allow for more frequent analysis of devils while reducing the workload of field staff. Ultimately, this automation could be expanded to other species for simultaneous monitoring at shorter intervals to facilitate broadened ecological assessments.

29 September 2026 in Geomatics
Verified
Journal Article
Open access
PDF file
Karen FaggKaren Fagg
Karen Fagg
SHSteve Harwin
Steve Harwin
Lowland temperate native grasslands are recognised as one of the most threatened vegetation communities in Australia, and even small remnant populations can hold high ecological value. One such site is Township Lagoon Nature Reserve in the Tasmanian Midlands, a key site for the endangered grassland paperdaisy (Leucochrysum albicans subsp. tricolor). Effective monitoring is required to understand population trends, but traditional field survey techniques are labour-intensive. This study evaluated Unpiloted Aerial Vehicle (UAV)-derived red, green and blue (RGB) and multispectral imagery for detecting, segmenting, classifying and estimating the abundance of grassland paperdaisy flowers using object-based image analysis and machine learning classifiers within ESRI ArcGIS Pro software. Imagery collected at 50 m above ground level enabled detection and classification of grassland paperdaisy flowers using Support Vector Machine and Random Tree (RT) algorithms with moderate to substantial levels of agreement. The multispectral RT output produced the highest accuracy (Kappa = 0.767), while workflows incorporating additional vegetation indices and texture measures generally produced lower classification accuracies. Comparison with an independent field counting survey conducted during the same flowering season as UAV capture showed variable agreement among plots, with differences potentially influenced by vegetation structure, plot characteristics, and temporal separation between field and UAV surveys. This study highlights the potential for UAV-based image analysis as a complementary approach for monitoring threatened plant species under operational conservation management conditions.