Karen Fagg
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Karen Fagg has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Carolyn J. Hogg
School of Life and Environmental Sciences, The University of Sydney
1 shared publication - Catherine A. Herbert
School of Life and Environmental Sciences, The University of Sydney, Sydney, NSW 2006, Australia
1 shared publication Elbrus Imanov
Department of Biomedical Engineering Near East University TRNC Mersin 10 99138 Nicosia Turkey
1 shared publication- Fatih Veysel Nurçin
Department of Biomedical Engineering Near East University TRNC Mersin 10 99138 Nicosia Turkey
1 shared publication Holly R. Cope
The University of Sydney, Faculty of Science, SOLES, J.D. Stewart Building B01, Camperdown, 2006, NSW, Australia
1 shared publicationNiyazi Şentürk
Department of Biomedical Engineering, Near East University, TRNC Mersin 10, Nicosia 99138, Turkey
1 shared publication
Latest Publications
- Open Access
Evaluating UAV-Based Object Classification Workflows for Detecting the Endangered Tasmanian Grassland Paperdaisy Flower (Leucochrysum albicans subsp. tricolor)
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.
Open AccessEvaluating UAV-Based Object Classification Workflows for Detecting the Endangered Tasmanian Grassland Paperdaisy Flower (Leucochrysum albicans subsp. tricolor)
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.
- Open Access
- 5 June 2023
- Published by CSIRO Publishing in Wildlife Research
- Vol. 51 (1)
Automated Tasmanian devil segmentation and devil facial tumour disease classification
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.
- 5 June 2023
- Published by CSIRO Publishing in Wildlife Research
- Vol. 51 (1)
Open AccessAutomated Tasmanian devil segmentation and devil facial tumour disease classification
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.
- 1 February 2018
- Published by Elsevier in Theriogenology
- Vol. 107, 134-141
Effects of deslorelin implants on reproduction and feeding behavior in Tasmanian devils (Sarcophilus harrisii) housed in free-range enclosures
- 1 February 2018
- Published by Elsevier in Theriogenology
- Vol. 107, 134-141
Effects of deslorelin implants on reproduction and feeding behavior in Tasmanian devils (Sarcophilus harrisii) housed in free-range enclosures