Nicholas Rollings
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
Nicholas Rollings has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Edward Zimudzi
Department of Computer Science, University of Botswana, Gaborone, Botswana
2 shared publications - Ashik Rubaiyat
Burckhardt Institute, Tropical Silviculture and Forest Ecology, Faculty of Forest Sciences and Forest Ecology, University of Göttingen, Germany
1 shared publication C. Macgregor
ASchool of Environmental and Rural Science, University of New England, Armidale, NSW 2351, Australia
1 shared publicationChristian Omlin
School of Computing, College of Science Engineering and Technology, University of South Africa, Pretoria, South Africa
1 shared publicationChristian W. Omlin
School of Computing, University of South Africa, Florida, South Africa
1 shared publicationDavid Aitchison
School of Engineering and Physics, University of the South Pacific (USP), Suva 19128, Fiji
1 shared publication
Latest Publications
- 8 September 2023
- Published by National Inquiry Services Center (NISC) in Southern Forests: a Journal of Forest Science
- Vol. 85 (3-4) , 142-151
Tree diversity, vegetation structure and management of mangrove systems on Viti Levu, Fiji Islands
- 8 September 2023
- Published by National Inquiry Services Center (NISC) in Southern Forests: a Journal of Forest Science
- Vol. 85 (3-4) , 142-151
Tree diversity, vegetation structure and management of mangrove systems on Viti Levu, Fiji Islands
- 19 June 2019
- Published by Taylor & Francis in Journal of Spatial Science
- Vol. 66 (2) , 195-212
Remote sensing of mangroves using unmanned aerial vehicles: current state and future directions
Mapping and identification of mangrove tree species have always played a crucial role in mangrove ecosystem conservation efforts, and several attempts have been made using remote sensing techniques for the acquisition of images and machine learning techniques for image processing with various levels of success. Remote sensing, combined with machine learning techniques have demonstrated a high potential to map and identify these ecosystems. In this research, we have conducted a systematic study with the goal of collecting all relevant research on mangrove species mapping and species identification using unmanned aerial vehicles (UAVs). Our objective is to understand current research topics, addressing the methods and techniques used for mangrove image data analysis, research gaps, and the challenges and future directions regarding mangrove species mapping and identification from remote sensing images acquired using UAVs. This will assist future research directions in managing these most threatened and vulnerable mangrove ecosystems.
- 19 June 2019
- Published by Taylor & Francis in Journal of Spatial Science
- Vol. 66 (2) , 195-212
Remote sensing of mangroves using unmanned aerial vehicles: current state and future directions
Mapping and identification of mangrove tree species have always played a crucial role in mangrove ecosystem conservation efforts, and several attempts have been made using remote sensing techniques for the acquisition of images and machine learning techniques for image processing with various levels of success. Remote sensing, combined with machine learning techniques have demonstrated a high potential to map and identify these ecosystems. In this research, we have conducted a systematic study with the goal of collecting all relevant research on mangrove species mapping and species identification using unmanned aerial vehicles (UAVs). Our objective is to understand current research topics, addressing the methods and techniques used for mangrove image data analysis, research gaps, and the challenges and future directions regarding mangrove species mapping and identification from remote sensing images acquired using UAVs. This will assist future research directions in managing these most threatened and vulnerable mangrove ecosystems.
- 22 October 2018
- Published by Taylor & Francis in Geocarto International
- Vol. 34 (14) , 1648-1662
Segmenting mangrove ecosystems drone images using SLIC superpixels
Mangrove ecosystems play a very important ecological role on land–ocean interfaces in tropical regions. These ecosystems comprise of various tree species and aquatic animals, protecting the environment and providing a habitat that supports many living organisms including humans. The identification of image regions in mangrove ecosystems plays a significant role in ecosystem monitoring and conservation. Recent studies have suggested oversegmentation of colour images using superpixels as a solution to the segmentation of image regions. This study used the SLIC superpixel algorithm and k-means clustering to segment images taken from a camera mounted on a drone from a mangrove ecosystem in Fiji. The SLIC superpixel algorithm performed well to demarcate image regions with similar colour and texture information into patches and to use k-means for the segmentation of the whole image. These results lend support to the use of superpixel algorithms for the segmentation of mangrove ecosystems. Understanding how superpixels can be used for the segmentation of drone images will assist conservation efforts in mangrove ecosystems.
- 22 October 2018
- Published by Taylor & Francis in Geocarto International
- Vol. 34 (14) , 1648-1662
Segmenting mangrove ecosystems drone images using SLIC superpixels
Mangrove ecosystems play a very important ecological role on land–ocean interfaces in tropical regions. These ecosystems comprise of various tree species and aquatic animals, protecting the environment and providing a habitat that supports many living organisms including humans. The identification of image regions in mangrove ecosystems plays a significant role in ecosystem monitoring and conservation. Recent studies have suggested oversegmentation of colour images using superpixels as a solution to the segmentation of image regions. This study used the SLIC superpixel algorithm and k-means clustering to segment images taken from a camera mounted on a drone from a mangrove ecosystem in Fiji. The SLIC superpixel algorithm performed well to demarcate image regions with similar colour and texture information into patches and to use k-means for the segmentation of the whole image. These results lend support to the use of superpixel algorithms for the segmentation of mangrove ecosystems. Understanding how superpixels can be used for the segmentation of drone images will assist conservation efforts in mangrove ecosystems.
- 1 May 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
A compact multispectral image capture unit for deployment on drones
The design, implementation and evaluation of a lightweight portable multispectral imaging system for deployment on drones is presented in this paper. The dual cameras used enable concurrent capture of red, green, blue (RGB) and near-infrared (NIR) images using simultaneous triggering. The images are stored in native file generated format. A global positioning system (GPS) connected to the camera's controllers enables geo-tagging of the images via exchangeable image file format (EXIF) metadata. A second-order polynomial has been utilized in order to align and test the RGB and NIR images to attain subpixel accuracy. The system was implemented in the matrix laboratory (MATLAB) and the developed algorithm was verified for accuracy considering different environmental conditions and scenarios.
- 1 May 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
A compact multispectral image capture unit for deployment on drones
The design, implementation and evaluation of a lightweight portable multispectral imaging system for deployment on drones is presented in this paper. The dual cameras used enable concurrent capture of red, green, blue (RGB) and near-infrared (NIR) images using simultaneous triggering. The images are stored in native file generated format. A global positioning system (GPS) connected to the camera's controllers enables geo-tagging of the images via exchangeable image file format (EXIF) metadata. A second-order polynomial has been utilized in order to align and test the RGB and NIR images to attain subpixel accuracy. The system was implemented in the matrix laboratory (MATLAB) and the developed algorithm was verified for accuracy considering different environmental conditions and scenarios.
- 1 July 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21614393,p. 1-8
Application of cooperative neuro-evolution of Elman recurrent networks for a two-dimensional cyclone track prediction for the south pacific region
This paper presents a two-dimensional time series prediction approach for cyclone track prediction using cooperative neuro-evolution of Elman recurrent networks in the South Pacific region. The latitude and longitude of tracks of cyclone lifetime is taken into consideration for past three decades to build a robust forecasting system. The proposed method performs one step ahead prediction of the cyclone position which is essentially a two-dimensional time series prediction problem. The results show that the Elman recurrent network is able to achieve very good accuracy in terms of prediction of the tracks which can be used as means of taking precautionary measures.
- 1 July 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21614393,p. 1-8
Application of cooperative neuro-evolution of Elman recurrent networks for a two-dimensional cyclone track prediction for the south pacific region
This paper presents a two-dimensional time series prediction approach for cyclone track prediction using cooperative neuro-evolution of Elman recurrent networks in the South Pacific region. The latitude and longitude of tracks of cyclone lifetime is taken into consideration for past three decades to build a robust forecasting system. The proposed method performs one step ahead prediction of the cyclone position which is essentially a two-dimensional time series prediction problem. The results show that the Elman recurrent network is able to achieve very good accuracy in terms of prediction of the tracks which can be used as means of taking precautionary measures.
- Open Access
- 10 July 2013
- Published by CSIRO Publishing in Animal Production Science
- Vol. 53 (8) , 618-627
Planning for whole-farm systems research at a credible scale: subdividing land into farmlets with equivalent initial conditions
Most research comparing different farming systems has been conducted on relatively uniform plots at small scales made necessary by the desire for sufficient replication of the systems and cost limitations. This paper describes an alternative approach to plan the allocation of land to three unreplicated whole-farm management systems such that each farmlet had equivalent starting conditions and yet was at a scale credible to both livestock producers and researchers. The paddocks of each farmlet were distributed across the landscape in a ‘patchwork quilt’ pattern after six iterations of a mapping exercise using a Geographic Information System. Allocation of paddocks took into account those variables of the landscape and natural resource capacity that were not able to be altered. An important benefit of the procedure was that it ensured that the farmlets were co-located with contiguous paddock boundaries so that all farmlets experienced the same climatic as well as biophysical conditions. An electromagnetic survey was conducted of the entire property and used in conjunction with a detailed soils map in order to classify areas into soil conductivity groupings. Equivalent areas of each soil type were allocated across the three farmlets. Similarly, land was distributed according to its topography so that no farmlet would be compromised by being allocated more low lying, flood-prone land than any other farmlet. The third factor used to allocate land to each farmlet was the prior fertiliser history of the original paddocks. This process ensured that each farmlet was objectively allocated equivalent areas of soil type, topography and fertiliser history thus avoiding initial bias among the farmlets. After the plan for all paddocks of each farmlet was finalised, new paddock boundaries were drawn and where necessary, fencing was removed, modified and added, along with re-arranged watering points. The farmlet treatments commenced in July 2000 when the first pasture establishment and differential fertiliser applications were carried out. Evidence from the electromagnetic survey and the Landsat imagery confirmed that the distribution of hydrologic soil conductivity and vegetation greenness were similar between all farmlets just before the commencement of the experiment.
- 10 July 2013
- Published by CSIRO Publishing in Animal Production Science
- Vol. 53 (8) , 618-627
Open AccessPlanning for whole-farm systems research at a credible scale: subdividing land into farmlets with equivalent initial conditions
Most research comparing different farming systems has been conducted on relatively uniform plots at small scales made necessary by the desire for sufficient replication of the systems and cost limitations. This paper describes an alternative approach to plan the allocation of land to three unreplicated whole-farm management systems such that each farmlet had equivalent starting conditions and yet was at a scale credible to both livestock producers and researchers. The paddocks of each farmlet were distributed across the landscape in a ‘patchwork quilt’ pattern after six iterations of a mapping exercise using a Geographic Information System. Allocation of paddocks took into account those variables of the landscape and natural resource capacity that were not able to be altered. An important benefit of the procedure was that it ensured that the farmlets were co-located with contiguous paddock boundaries so that all farmlets experienced the same climatic as well as biophysical conditions. An electromagnetic survey was conducted of the entire property and used in conjunction with a detailed soils map in order to classify areas into soil conductivity groupings. Equivalent areas of each soil type were allocated across the three farmlets. Similarly, land was distributed according to its topography so that no farmlet would be compromised by being allocated more low lying, flood-prone land than any other farmlet. The third factor used to allocate land to each farmlet was the prior fertiliser history of the original paddocks. This process ensured that each farmlet was objectively allocated equivalent areas of soil type, topography and fertiliser history thus avoiding initial bias among the farmlets. After the plan for all paddocks of each farmlet was finalised, new paddock boundaries were drawn and where necessary, fencing was removed, modified and added, along with re-arranged watering points. The farmlet treatments commenced in July 2000 when the first pasture establishment and differential fertiliser applications were carried out. Evidence from the electromagnetic survey and the Landsat imagery confirmed that the distribution of hydrologic soil conductivity and vegetation greenness were similar between all farmlets just before the commencement of the experiment.