ORCID Profile
0000-0002-4342-3682
Current Organisation
Queensland University of Technology (QUT)
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Environmental Monitoring | Photogrammetry and Remote Sensing | Aircraft Performance and Flight Control Systems | Aerospace Engineering | Control Systems, Robotics and Automation | Environmental Engineering not elsewhere classified | Conservation and Biodiversity | Interdisciplinary Engineering not elsewhere classified | Atmospheric Sciences | Structural Engineering | Environmental Engineering | Civil Engineering | Geomatic Engineering | Climate Change Processes | Global Change Biology | Other Biological Sciences | Environmental Management | Atmospheric Sciences not elsewhere classified |
Ecosystem Assessment and Management at Regional or Larger Scales | Ecosystem Assessment and Management of Urban and Industrial Environments | Air Quality not elsewhere classified | Air Safety | Environmental Health | Effects of Climate Change and Variability on Antarctic and Sub-Antarctic Environments (excl. Social Impacts) | Ecosystem Assessment and Management of Antarctic and Sub-Antarctic Environments | Residential Construction Design | Commercial Construction Design | Ground Transport not elsewhere classified | Expanding Knowledge in Technology | Environmental Policy, Legislation and Standards not elsewhere classified | Natural Hazards in Forest and Woodlands Environments | Expanding Knowledge in the Environmental Sciences | Flora, Fauna and Biodiversity at Regional or Larger Scales
Publisher: IEEE
Date: 06-03-2021
Publisher: IEEE
Date: 05-2014
Publisher: IEEE
Date: 06-03-2021
Publisher: IEEE
Date: 03-2016
Publisher: IEEE
Date: 03-2016
Publisher: MDPI AG
Date: 07-08-2020
DOI: 10.3390/S20164420
Abstract: The use of UAVs for remote sensing is increasing. In this paper, we demonstrate a method for evaluating and selecting suitable hardware to be used for deployment of algorithms for UAV-based remote sensing under considerations of Size, Weight, Power, and Computational constraints. These constraints hinder the deployment of rapidly evolving computer vision and robotics algorithms on UAVs, because they require intricate knowledge about the system and architecture to allow for effective implementation. We propose integrating computational monitoring techniques—profiling—with an industry standard specifying software quality—ISO 25000—and fusing both in a decision-making model—the analytic hierarchy process—to provide an informed decision basis for deploying embedded systems in the context of UAV-based remote sensing. One software package is combined in three software–hardware alternatives, which are profiled in hardware-in-the-loop simulations. Three objectives are used as inputs for the decision-making process. A Monte Carlo simulation provides insights into which decision-making parameters lead to which preferred alternative. Results indicate that local weights significantly influence the preference of an alternative. The approach enables relating complex parameters, leading to informed decisions about which hardware is deemed suitable for deployment in which case.
Publisher: American Institute of Aeronautics and Astronautics
Date: 08-01-2007
DOI: 10.2514/6.2007-36
Publisher: IEEE
Date: 03-2020
Publisher: MDPI AG
Date: 30-07-2023
DOI: 10.3390/RS15153802
Abstract: Coordinating multiple unmanned aerial vehicles (UAVs) for the purposes of target finding or surveying points of interest in large, complex, and partially observable environments remains an area of exploration. This work proposes a modeling approach and software framework for multi-UAV search and target finding within large, complex, and partially observable environments. Mapping and path-solving is carried out by an extended NanoMap library the global planning problem is defined as a decentralized partially observable Markov decision process and solved using an online model-based solver, and the local control problem is defined as two separate partially observable Markov decision processes that are solved using deep reinforcement learning. Simulated testing demonstrates that the proposed framework enables multiple UAVs to search and target-find within large, complex, and partially observable environments.
Publisher: IEEE
Date: 09-2020
Publisher: IEEE
Date: 05-2013
Publisher: MDPI AG
Date: 12-08-2015
DOI: 10.3390/S150819667
Publisher: IEEE
Date: 03-2017
Publisher: IEEE
Date: 03-2020
Publisher: IEEE
Date: 03-2017
Publisher: MDPI AG
Date: 02-12-2022
Abstract: Autonomous Unmanned Aerial Vehicles (UAV) for planetary exploration missions require increased onboard mission-planning and decision-making capabilities to access full operational potential in remote environments (e.g., Antarctica, Mars or Titan). However, the uncertainty introduced by the environment and the limitation of available sensors has presented challenges for planning such missions. Partially Observable Markov Decision Processes (POMDPs) are commonly used to enable decision-making and mission-planning processes that account for environmental, perceptional (extrinsic) and actuation (intrinsics) uncertainty. Here, we propose the UAV4PE framework, a testing framework for autonomous UAV missions using POMDP formulations. This framework integrates modular components for simulation, emulation, UAV guidance, navigation and mission planning. State-of-the-art tools such as python, C++, ROS, PX4 and JuliaPOMDP are employed by the framework, and we used python data-science libraries for the analysis of the experimental results. The source code and the experiment data are included in the UAV4PE framework. The POMDP formulation proposed here was able to plan and command a UAV-based planetary exploration mission in simulation, emulation and real-world experiments. The experiments evaluated key indicators such as the mission success rate, the surface area explored and the number of commands (actions) executed. We also discuss future work aimed at improving the UAV4PE framework, and the autonomous UAV mission planning formulation for planetary exploration.
Publisher: Elsevier BV
Date: 04-2022
Publisher: Elsevier BV
Date: 04-2011
Publisher: MDPI AG
Date: 02-11-2022
DOI: 10.3390/AGRICULTURE12111838
Abstract: Parthenium weed (Parthenium hysterophorus L. (Asteraceae)), native to the Americas, is in the top 100 most invasive plant species in the world. In Australia, it is an annual weed (herb/shrub) of national significance, especially in the state of Queensland where it has infested both agricultural and conservation lands, including riparian corridors. Effective control strategies for this weed (pasture management, biological control, and herbicide usage) require populations to be detected and mapped. However, the mapping is made difficult due to varying nature of the infested landscapes (e.g., uneven terrain). This paper proposes a novel method to detect and map parthenium populations in simulated pastoral environments using Red-Green-Blue (RGB) and/or hyperspectral imagery aided by artificial intelligence. Two datasets were collected in a control environment using a series of parthenium and naturally co-occurring, non-parthenium (monocot) plants. RGB images were processed with a YOLOv4 Convolutional Neural Network (CNN) implementation, achieving an overall accuracy of 95% for detection, and 86% for classification of flowering and non-flowering stages of the weed. An XGBoost classifier was used for the pixel classification of the hyperspectral dataset—achieving a classification accuracy of 99% for each parthenium weed growth stage class all materials received a discernible colour mask. When parthenium and non-parthenium plants were artificially combined in various permutations, the pixel classification accuracy was 99% for each parthenium and non-parthenium class, again with all materials receiving an accurate and discernible colour mask. Performance metrics indicate that our proposed processing pipeline can be used in the preliminary design of parthenium weed detection strategies, and can be extended for automated processing of collected RGB and hyperspectral airborne unmanned aerial vehicle (UAV) data. The findings also demonstrate the potential for images collected in a controlled, glasshouse environment to be used in the preliminary design of invasive weed detection strategies in the field.
Publisher: IEEE
Date: 10-2012
Publisher: IEEE
Date: 03-2016
Publisher: IEEE
Date: 03-2016
Publisher: IEEE
Date: 05-2014
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2007
Publisher: Elsevier BV
Date: 11-2017
DOI: 10.1016/J.ENVPOL.2017.06.033
Abstract: A quantitative assessment of the vertical profile of traffic pollution, specifically particle number concentration (PNC), in an open space adjacent to a motorway was possible for the first time, to the knowledge of the authors, using an Unmanned Aerial Vehicle (UAV) system. Until now, traffic pollution has only been measured at ground level while the vertical distribution, is limited to studies conducted from buildings or fixed towers and balloons. This new UAV system demonstrated that the PNC s led during the period form 10 a.m. to 4 p.m., outside the rush hours with a constant traffic flow, increased from a concentration of 2 × 10
Publisher: MDPI AG
Date: 16-10-2020
DOI: 10.3390/RS12203386
Abstract: Response efforts in emergency applications such as border protection, humanitarian relief and disaster monitoring have improved with the use of Unmanned Aerial Vehicles (UAVs), which provide a flexibly deployed eye in the sky. These efforts have been further improved with advances in autonomous behaviours such as obstacle avoidance, take-off, landing, hovering and waypoint flight modes. However, most UAVs lack autonomous decision making for navigating in complex environments. This limitation creates a reliance on ground control stations to UAVs and, therefore, on their communication systems. The challenge is even more complex in indoor flight operations, where the strength of the Global Navigation Satellite System (GNSS) signals is absent or weak and compromises aircraft behaviour. This paper proposes a UAV framework for autonomous navigation to address uncertainty and partial observability from imperfect sensor readings in cluttered indoor scenarios. The framework design allocates the computing processes onboard the flight controller and companion computer of the UAV, allowing it to explore dangerous indoor areas without the supervision and physical presence of the human operator. The system is illustrated under a Search and Rescue (SAR) scenario to detect and locate victims inside a simulated office building. The navigation problem is modelled as a Partially Observable Markov Decision Process (POMDP) and solved in real time through the Augmented Belief Trees (ABT) algorithm. Data is collected using Hardware in the Loop (HIL) simulations and real flight tests. Experimental results show the robustness of the proposed framework to detect victims at various levels of location uncertainty. The proposed system ensures personal safety by letting the UAV to explore dangerous environments without the intervention of the human operator.
Publisher: IEEE
Date: 03-2017
Publisher: MDPI AG
Date: 14-02-2017
DOI: 10.3390/S17020343
Publisher: MDPI AG
Date: 03-12-2022
DOI: 10.3390/RS14236137
Abstract: White leaf disease (WLD) is an economically significant disease in the sugarcane industry. This work applied remote sensing techniques based on unmanned aerial vehicles (UAVs) and deep learning (DL) to detect WLD in sugarcane fields at the Gal-Oya Plantation, Sri Lanka. The established methodology to detect WLD consists of UAV red, green, and blue (RGB) image acquisition, the pre-processing of the dataset, labelling, DL model tuning, and prediction. This study evaluated the performance of the existing DL models such as YOLOv5, YOLOR, DETR, and Faster R-CNN to recognize WLD in sugarcane crops. The experimental results indicate that the YOLOv5 network outperformed the other selected models, achieving a precision, recall, mean average precision@0.50 (mAP@0.50), and mean average precision@0.95 (mAP@0.95) metrics of 95%, 92%, 93%, and 79%, respectively. In contrast, DETR exhibited the weakest detection performance, achieving metrics values of 77%, 69%, 77%, and 41% for precision, recall, mAP@0.50, and mAP@0.95, respectively. YOLOv5 is selected as the recommended architecture to detect WLD using the UAV data not only because of its performance, but this was also determined because of its size (14 MB), which was the smallest one among the selected models. The proposed methodology provides technical guidelines to researchers and farmers for conduct the accurate detection and treatment of WLD in the sugarcane fields.
Publisher: IEEE
Date: 06-2018
Publisher: Public Library of Science (PLoS)
Date: 11-12-2019
Publisher: IEEE
Date: 03-2020
Publisher: MDPI AG
Date: 16-02-2018
DOI: 10.3390/S18020605
Abstract: The monitoring of invasive grasses and vegetation in remote areas is challenging, costly, and on the ground sometimes dangerous. Satellite and manned aircraft surveys can assist but their use may be limited due to the ground s ling resolution or cloud cover. Straightforward and accurate surveillance methods are needed to quantify rates of grass invasion, offer appropriate vegetation tracking reports, and apply optimal control methods. This paper presents a pipeline process to detect and generate a pixel-wise segmentation of invasive grasses, using buffel grass (Cenchrus ciliaris) and spinifex (Triodia sp.) as ex les. The process integrates unmanned aerial vehicles (UAVs) also commonly known as drones, high-resolution red, green, blue colour model (RGB) cameras, and a data processing approach based on machine learning algorithms. The methods are illustrated with data acquired in Cape Range National Park, Western Australia (WA), Australia, orthorectified in Agisoft Photoscan Pro, and processed in Python programming language, scikit-learn, and eXtreme Gradient Boosting (XGBoost) libraries. In total, 342,626 s les were extracted from the obtained data set and labelled into six classes. Segmentation results provided an in idual detection rate of 97% for buffel grass and 96% for spinifex, with a global multiclass pixel-wise detection rate of 97%. Obtained results were robust against illumination changes, object rotation, occlusion, background cluttering, and floral density variation.
Publisher: Elsevier BV
Date: 05-2012
Publisher: MDPI AG
Date: 30-10-2022
DOI: 10.3390/RS14215463
Abstract: Encoding sensor data into a map is a problem that must be undertaken by any robotic agent operating in unknown or uncertain environments, and real-time updates are crucial to safe planning and control. Most modern robotic sensors produce some form of depth data or point cloud information that is only useful to the agent after being processed into the appropriate data structure, oftentimes an occupancy map. However, as the quality of sensor technology improves, so does the magnitude of the input data, which can creates a problem when trying to construct occupancy maps in real-time. Populating such an occupancy map using these dense point clouds can quickly become an expensive process, and many robotic agents have limited onboard computational bandwidth and memory. This results in delayed map updates and reduced operational performance in dynamic environments where real-time information is crucial for safe operation. However, while many modern robotic agents are still relatively limited by the power of onboard central processing units (CPUs), many platforms are gaining access to onboard graphics processing units (GPUs), and these resources remain underutilised with respect to the problem of occupancy mapping. We propose a novel probabilistic mapping solution that leverages a combination of OpenVDB, NanoVDB, and Nvidia’s Compute Unified Device Architecture (CUDA) to encode dense point clouds into OpenVDB data structures, leveraging the parallel compute strength of GPUs to provide significant speed advantages and further free up resources for tasks that cannot as easily be performed in parallel. An evaluation of our solution is provided, with performance benchmarks provided for both a laptop and a low power single board computer with onboard GPU. Similar performance improvements should be accessible on any system with access to a CUDA-compatible GPU. Additionally, our library provides the means to simulate one or more sensors on an agent operating within a randomly generated 3D-grid environment and create a live map for the purposes of evaluating planning and control techniques and for training agents via deep reinforcement learning. We also provide interface packages for the Robotic Operating System (ROS1) and the Robotic Operating System 2 (ROS2), and a ROS2 visualisation (RVIZ2) plugin for the underlying OpenVDB data structure.
Publisher: Elsevier BV
Date: 11-2018
Publisher: IEEE
Date: 03-2016
Publisher: IEEE
Date: 08-2018
Publisher: Wiley
Date: 17-11-2015
DOI: 10.1002/ROB.21641
Publisher: IEEE
Date: 03-2016
Publisher: IEEE
Date: 03-2019
Publisher: Springer Science and Business Media LLC
Date: 09-09-2011
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2011
Publisher: IEEE
Date: 06-03-2021
Publisher: MDPI AG
Date: 14-01-2016
DOI: 10.3390/S16010097
Publisher: Informa UK Limited
Date: 17-09-2023
Publisher: Cambridge University Press (CUP)
Date: 10-2006
DOI: 10.1017/S0001924000001524
Abstract: Unmanned aerial vehicle (UAV) design tends to focus on sensors, payload and navigation systems, as these are the most expensive components. One area that is often overlooked in UAV design is airframe and aerodynamic shape optimisation. As for manned aircraft, optimisation is important in order to extend the operational envelope and efficiency of these vehicles. A traditional approach to optimisation is to use gradient-based techniques. These techniques are effective when applied to specific problems and within a specified range. These methods are efficient for finding optimal global solutions if the objective functions and constraints are differentiable. If a broader application of the optimiser is desired, or when the complexity of the problem arises because it is multi-modal, involves approximation, is non-differentiable, or involves multiple objectives and physics, as it is often the case in aerodynamic optimisation, more robust and alternative numerical tools are required. Emerging techniques such as evolutionary algorithms (EAs) have been shown to be robust as they require no derivatives or gradients of the objective function, have the capability of finding globally optimum solutions among many local optima, are easily executed in parallel, and can be adapted to arbitrary solver codes without major modifications. In this paper, the formulation and application of a evolutionary technique for aerofoil shape optimisation is described. Initially, the paper presents an introduction to the features of the method and a short discussion on multi-objective optimisation. The method is first illustrated on its application to mathematical test cases. Then it is applied to representative test cases related to aerofoil design. Results indicate the ability of the method for finding optimal solutions and capturing Pareto optimal fronts.
Publisher: SAGE Publications
Date: 18-07-2011
Abstract: This study investigates the application of two advanced optimization methods for solving active flow control (AFC) device shape design problem and compares their optimization efficiency in terms of computational cost and design quality. The first optimization method uses hierarchical asynchronous parallel multi-objective evolutionary algorithm and the second uses hybridized evolutionary algorithm with Nash-Game strategies (Hybrid-Game). Both optimization methods are based on a canonical evolution strategy and incorporate the concepts of parallel computing and asynchronous evaluation. One type of AFC device named shock control bump (SCB) is considered and applied to a natural laminar flow (NLF) aerofoil. The concept of SCB is used to decelerate supersonic flow on suction ressure side of transonic aerofoil that leads to a delay of shock occurrence. Such active flow technique reduces total drag at transonic speeds which is of special interest to commercial aircraft. Numerical results show that the Hybrid-Game helps an EA to accelerate optimization process. From the practical point of view, applying a SCB on the suction and pressure sides significantly reduces transonic total drag and improves lift-to-drag ( L/ D) value when compared to the baseline design.
Publisher: Elsevier BV
Date: 2014
Publisher: Elsevier
Date: 1996
Publisher: IOP Publishing
Date: 06-2010
Publisher: IEEE
Date: 03-2020
Publisher: IEEE
Date: 03-2020
Publisher: IEEE
Date: 05-2013
Publisher: IEEE
Date: 10-2016
Publisher: MDPI AG
Date: 21-12-2016
DOI: 10.3390/S16122202
Publisher: IEEE
Date: 09-2020
Publisher: MDPI AG
Date: 03-01-2020
DOI: 10.3390/S20010272
Abstract: Small unmanned aerial systems (UASs) now have advanced waypoint-based navigation capabilities, which enable them to collect surveillance, wildlife ecology and air quality data in new ways. The ability to remotely sense and find a set of targets and descend and hover close to each target for an action is desirable in many applications, including inspection, search and rescue and spot spraying in agriculture. This paper proposes a robust framework for vision-based ground target finding and action using the high-level decision-making approach of Observe, Orient, Decide and Act (OODA). The proposed framework was implemented as a modular software system using the robotic operating system (ROS). The framework can be effectively deployed in different applications where single or multiple target detection and action is needed. The accuracy and precision of camera-based target position estimation from a low-cost UAS is not adequate for the task due to errors and uncertainties in low-cost sensors, sensor drift and target detection errors. External disturbances such as wind also pose further challenges. The implemented framework was tested using two different test cases. Overall, the results show that the proposed framework is robust to localization and target detection errors and able to perform the task.
Publisher: IEEE
Date: 05-2011
Publisher: IEEE
Date: 03-2015
Publisher: Copernicus GmbH
Date: 31-01-2019
Abstract: Abstract. This research demonstrates the use of an unmanned aerial vehicle (UAV) to characterize the gaseous (CO2) and particle (10–500 nm) emissions of a ship at sea. The field study was part of the research voyage “The Great Barrier Reef as a significant source of climatically relevant aerosol particles” on board the RV Investigator around the Australian Great Barrier Reef. Measurements of the RV Investigator exhaust plume were carried out while the ship was operating at sea, at a steady engine load of 30 %. The UAV system was flown autonomously using several different programmed paths. These incorporated different altitudes and distances behind the ship in order to investigate the optimal position to capture the ship plume. Five flights were performed, providing a total of 27 horizontal transects perpendicular to the ship exhaust plume. Results show that the most appropriate altitude and distance to effectively capture the plume was 25 m a.s.l. and 20 m downwind. Particle number emission factors (EFPNs) were calculated in terms of number of particles emitted (no.) per weight of fuel consumed (kgfuel). Fuel consumption was calculated using the simultaneous measurements of plume CO2 concentration. The calculated EFPN was 7.6±1.4×1015no. kgfuel-1 which is in line with those reported in the literature for ship emissions ranging from 0.2 to 6.2×1016 no. kgfuel-1. This UAV system successfully assessed ship emissions to derive EFPN under real world conditions. This is significant as it provides a novel, relatively inexpensive and accessible way to assess ship EFPN at sea.
Publisher: Elsevier BV
Date: 08-2011
Publisher: Wiley
Date: 12-10-2011
DOI: 10.1002/ROB.20417
Publisher: IEEE
Date: 11-2013
Publisher: Springer Science and Business Media LLC
Date: 04-10-2017
Publisher: IEEE
Date: 03-2019
Publisher: IEEE
Date: 09-2020
Publisher: IEEE
Date: 03-2015
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: MDPI AG
Date: 22-03-2018
DOI: 10.3390/S18040944
Publisher: IEEE
Date: 09-2020
Publisher: IEEE
Date: 09-2020
Publisher: MDPI AG
Date: 28-08-2015
DOI: 10.3390/S150921537
Publisher: Elsevier BV
Date: 06-2008
Publisher: ASMEDC
Date: 2009
Abstract: This paper presents the application of advanced optimization techniques to Unmanned Aerial Systems (UAS) Mission Path Planning System (MPPS) using Multi-Objective Evolutionary Algorithms (MOEAs). Two types of multi-objective optimizers are compared the MOEA Non-dominated Sorting Genetic Algorithms II (NSGA-II) and a Hybrid Game strategy are implemented to produce a set of optimal collision-free trajectories in three-dimensional environment. The resulting trajectories on a three-dimension terrain are collision-free and are represented by using Be´zier spline curves from start position to target and then target to start position or different position with altitude constraints. The efficiency of the two optimization methods is compared in terms of computational cost and design quality. Numerical results show the benefits of adding a Hybrid-Game strategy to a MOEA and for a MPPS.
Publisher: IEEE
Date: 03-2019
Publisher: WORLD SCIENTIFIC
Date: 07-2010
Publisher: IOP Publishing
Date: 06-2010
Publisher: Springer International Publishing
Date: 2015
Publisher: American Institute of Aeronautics and Astronautics (AIAA)
Date: 2008
DOI: 10.2514/1.30842
Publisher: IEEE
Date: 03-2017
Publisher: MDPI AG
Date: 09-2022
Abstract: Sugarcane white leaf phytoplasma (white leaf disease) in sugarcane crops is caused by a phytoplasma transmitted by leafhopper vectors. White leaf disease (WLD) occurs predominantly in some Asian countries and is a devastating global threat to sugarcane industries, especially Sri Lanka. Therefore, a feasible and an effective approach to precisely monitoring WLD infection is important, especially at the early pre-visual stage. This work presents the first approach on the preliminary detection of sugarcane WLD by using high-resolution multispectral sensors mounted on small unmanned aerial vehicles (UAVs) and supervised machine learning classifiers. The detection pipeline discussed in this paper was validated in a sugarcane field located in Gal-Oya Plantation, Hingurana, Sri Lanka. The pixelwise segmented s les were classified as ground, shadow, healthy plant, early symptom, and severe symptom. Four ML algorithms, namely XGBoost (XGB), random forest (RF), decision tree (DT), and K-nearest neighbors (KNN), were implemented along with different python libraries, vegetation indices (VIs), and five spectral bands to detect the WLD in the sugarcane field. The accuracy rate of 94% was attained in the XGB, RF, and KNN to detect WLD in the field. The top three vegetation indices (VIs) for separating healthy and infected sugarcane crops are modified soil-adjusted vegetation index (MSAVI), normalized difference vegetation index (NDVI), and excess green (ExG) in XGB, RF, and DT, while the best spectral band is red in XGB and RF and green in DT. The results revealed that this technology provides a dependable, more direct, cost-effective, and quick method for detecting WLD.
Publisher: Springer Netherlands
Date: 2009
Publisher: MDPI AG
Date: 17-03-2023
DOI: 10.3390/RS15061633
Abstract: Hawkweeds (Pilosella spp.) have become a severe and rapidly invading weed in pasture lands and forest meadows of New Zealand. Detection of hawkweed infestations is essential for eradication and resource management at private and government levels. This study explores the potential of machine learning (ML) algorithms for detecting mouse-ear hawkweed (Pilosella officinarum) foliage and flowers from Unmanned Aerial Vehicle (UAV)-acquired multispectral (MS) images at various spatial resolutions. The performances of different ML algorithms, namely eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Random Forest (RF), and K-nearest neighbours (KNN), were analysed in their capacity to detect hawkweed foliage and flowers using MS imagery. The imagery was obtained at numerous spatial resolutions from a highly infested study site located in the McKenzie Region of the South Island of New Zealand in January 2021. The spatial resolution of 0.65 cm ixel (acquired at a flying height of 15 m above ground level) produced the highest overall testing and validation accuracy of 100% using the RF, KNN, and XGB models for detecting hawkweed flowers. In hawkweed foliage detection at the same resolution, the RF and XGB models achieved highest testing accuracy of 97%, while other models (KNN and SVM) achieved an overall model testing accuracy of 96% and 72%, respectively. The XGB model achieved the highest overall validation accuracy of 98%, while the other models (RF, KNN, and SVM) produced validation accuracies of 97%, 97%, and 80%, respectively. This proposed methodology may facilitate non-invasive detection efforts of mouse-ear hawkweed flowers and foliage in other naturalised areas, enabling land managers to optimise the use of UAV remote sensing technologies for better resource allocation.
Publisher: Elsevier BV
Date: 06-2008
Publisher: ASME International
Date: 16-06-2010
DOI: 10.1115/1.4001336
Abstract: This paper presents the application of advanced optimization techniques to unmanned aerial system mission path planning system (MPPS) using multi-objective evolutionary algorithms (MOEAs). Two types of multi-objective optimizers are compared the MOEA nondominated sorting genetic algorithm II and a hybrid-game strategy are implemented to produce a set of optimal collision-free trajectories in a three-dimensional environment. The resulting trajectories on a three-dimensional terrain are collision-free and are represented by using Bézier spline curves from start position to target and then target to start position or different positions with altitude constraints. The efficiency of the two optimization methods is compared in terms of computational cost and design quality. Numerical results show the benefits of adding a hybrid-game strategy to a MOEA and for a MPPS.
Publisher: MDPI AG
Date: 08-11-2021
DOI: 10.3390/RS13214481
Abstract: Recent advances in autonomy of unmanned aerial vehicles (UAVs) have increased their use in remote sensing applications, such as precision agriculture, biosecurity, disaster monitoring, and surveillance. However, onboard UAV cognition capabilities for understanding and interacting in environments with imprecise or partial observations, for objects of interest within complex scenes, are limited, and have not yet been fully investigated. This limitation of onboard decision-making under uncertainty has delegated the motion planning strategy in complex environments to human pilots, which rely on communication subsystems and real-time telemetry from ground control stations. This paper presents a UAV-based autonomous motion planning and object finding system under uncertainty and partial observability in outdoor environments. The proposed system architecture follows a modular design, which allocates most of the computationally intensive tasks to a companion computer onboard the UAV to achieve high-fidelity results in simulated environments. We demonstrate the system with a search and rescue (SAR) case study, where a lost person (victim) in bushland needs to be found using a sub-2 kg quadrotor UAV. The navigation problem is mathematically formulated as a partially observable Markov decision process (POMDP). A motion strategy (or policy) is obtained once a POMDP is solved mid-flight and in real time using augmented belief trees (ABT) and the TAPIR toolkit. The system’s performance was assessed using three flight modes: (1) mission mode, which follows a survey plan and used here as the baseline motion planner (2) offboard mode, which runs the POMDP-based planner across the flying area and (3) hybrid mode, which combines mission and offboard modes for improved coverage in outdoor scenarios. Results suggest the increased cognitive power added by the proposed motion planner and flight modes allow UAVs to collect more accurate victim coordinates compared to the baseline planner. Adding the proposed system to UAVs results in improved robustness against potential false positive readings of detected objects caused by data noise, inaccurate detections, and elevated complexity to navigate in time-critical applications, such as SAR.
Publisher: Elsevier BV
Date: 12-2021
Publisher: IEEE
Date: 09-2008
Publisher: IEEE
Date: 03-2018
Publisher: MDPI AG
Date: 17-12-2017
DOI: 10.3390/S17122929
Abstract: In this paper, a system that uses an algorithm for target detection and navigation and a multirotor Unmanned Aerial Vehicle (UAV) for finding a ground target and inspecting it closely is presented. The system can also be used for accurate and safe delivery of payloads or spot spraying applications in site-specific crop management. A downward-looking camera attached to a multirotor is used to find the target on the ground. The UAV descends to the target and hovers above the target for a few seconds to inspect the target. A high-level decision algorithm based on an OODA (observe, orient, decide, and act) loop was developed as a solution to address the problem. Navigation of the UAV was achieved by continuously sending local position messages to the autopilot via Mavros. The proposed system performed hovering above the target in three different stages: locate, descend, and hover. The system was tested in multiple trials, in simulations and outdoor tests, from heights of 10 m to 40 m. Results show that the system is highly reliable and robust to sensor errors, drift, and external disturbance.
Publisher: Elsevier BV
Date: 2016
Publisher: MDPI AG
Date: 12-07-2016
DOI: 10.3390/S16071072
Publisher: IEEE
Date: 03-2019
Publisher: IEEE
Date: 06-2018
Publisher: MDPI AG
Date: 24-09-2017
DOI: 10.3390/S17102196
Publisher: MDPI AG
Date: 17-01-2018
DOI: 10.3390/S18010260
Publisher: MDPI AG
Date: 10-05-2016
DOI: 10.3390/S16050666
Publisher: MDPI AG
Date: 25-02-2022
DOI: 10.3390/RS14051140
Abstract: The use of satellite-based Remote Sensing (RS) is a well-developed field of research. RS techniques have been successfully utilized to evaluate the chlorophyll content for the monitoring of sugarcane crops. This research provides a new framework for inferring the chlorophyll content in sugarcane crops at the canopy level using unmanned aerial vehicles (UAVs) and spectral vegetation indices processed with multiple machine learning algorithms. Studies were conducted in a sugarcane field located in Sugarcane Research Institute (SRI, Uda Walawe, Sri Lanka), with various fertilizer applications over the entire growing season from 2020 to 2021. An UAV with multispectral camera was used to collect the aerial images to generate the vegetation indices. Ground measurements of leaf chlorophyll were used as indications for fertilizer status in the sugarcane field. Different machine learning (ML) algorithms were used ground-truthing data of chlorophyll content and spectral vegetation indices to forecast sugarcane chlorophyll content. Several machine learning algorithms such as MLR, RF, DT, SVR, XGB, KNN and ANN were applied in two ways: before feature selection (BFS) by training the algorithms with all twenty-four (24) vegetation indices with five (05) spectral bands and after feature selection (AFS) by training algorithms with fifteen (15) vegetation indices. All the algorithms with both BFS and AFS methods were compared with an estimated coefficient of determination (R2) and root mean square error (RMSE). Spectral indices such as RVI and DVI were shown to be the most reliable indices for estimating chlorophyll content in sugarcane fields, with coefficients of determination (R2) of 0.94 and 0.93, respectively. XGB model shows the highest validation score (R2) and lowest RMSE in both methods of BFS (0.96 and 0.14) and AFS (0.98 and 0.78), respectively. However, KNN and SVR algorithms show the lowest validation accuracy than other models. According to the results, the AFS validation score is higher than BFS in MLR, SVR, XGB and KNN. Even though, validation score of the ANN model is decreased in AFS. The findings demonstrated that the use of multispectral UAV could be utilized to estimate chlorophyll content and measure crop health status over a larger sugarcane field. This methodology will aid in real-time crop nutrition management in sugarcane plantations by reducing the need for conventional measurement of sugarcane chlorophyll content.
Publisher: IEEE
Date: 06-2018
Publisher: American Institute of Aeronautics and Astronautics (AIAA)
Date: 05-2011
DOI: 10.2514/1.C031237
Publisher: Elsevier BV
Date: 2021
Publisher: Elsevier BV
Date: 10-2009
Publisher: MDPI AG
Date: 21-08-2020
DOI: 10.3390/S20174739
Abstract: The problem of multi-agent remote sensing for the purposes of finding survivors or surveying points of interest in GPS-denied and partially observable environments remains a challenge. This paper presents a framework for multi-agent target-finding using a combination of online POMDP based planning and Deep Reinforcement Learning based control. The framework is implemented considering planning and control as two separate problems. The planning problem is defined as a decentralised multi-agent graph search problem and is solved using a modern online POMDP solver. The control problem is defined as a local continuous-environment exploration problem and is solved using modern Deep Reinforcement Learning techniques. The proposed framework combines the solution to both of these problems and testing shows that it enables multiple agents to find a target within large, simulated test environments in the presence of unknown obstacles and obstructions. The proposed approach could also be extended or adapted to a number of time sensitive remote-sensing problems, from searching for multiple survivors during a disaster to surveying points of interest in a hazardous environment by adjusting the in idual model definitions.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2013
Publisher: Informa UK Limited
Date: 10-2007
Publisher: MDPI
Date: 05-03-2018
Publisher: MDPI AG
Date: 11-02-2015
DOI: 10.3390/S150204072
Publisher: IEEE
Date: 03-2018
Publisher: IEEE
Date: 06-2012
Publisher: MDPI AG
Date: 25-06-2018
DOI: 10.3390/S18072026
Publisher: IEEE
Date: 09-2015
Publisher: IEEE
Date: 15-06-2021
Publisher: Springer Science and Business Media LLC
Date: 04-09-2023
Publisher: Informa UK Limited
Date: 2020
Start Date: 2018
End Date: 2020
Funder: Australian Research Council
View Funded ActivityStart Date: 2018
End Date: 2018
Funder: Australian Research Council
View Funded ActivityStart Date: 2020
End Date: 2022
Funder: Australian Research Council
View Funded ActivityStart Date: 2019
End Date: 2021
Funder: Australian Research Council
View Funded ActivityStart Date: 2016
End Date: 2018
Funder: Australian Research Council
View Funded ActivityStart Date: 07-2020
End Date: 12-2023
Amount: $360,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 12-2019
End Date: 12-2023
Amount: $889,797.00
Funder: Australian Research Council
View Funded ActivityStart Date: 10-2022
End Date: 09-2025
Amount: $360,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 05-2018
End Date: 06-2023
Amount: $362,734.00
Funder: Australian Research Council
View Funded ActivityStart Date: 03-2018
End Date: 12-2019
Amount: $159,450.00
Funder: Australian Research Council
View Funded ActivityStart Date: 04-2017
End Date: 04-2020
Amount: $445,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 06-2021
End Date: 06-2030
Amount: $36,000,000.00
Funder: Australian Research Council
View Funded Activity