Anomaly detection aims to identify the data samples that do not conform to a known normal (regular) behavior. As the definition of an anomaly is often ambiguous, unsupervised and semi-supervised deep learning (DL) algorithms that primarily use unlabeled datasets to model normal (regular) behaviors, are popularly studied in this context. The unmanned aerial system (UAS) can use contextual anomaly detection algorithms to identify interesting objects of concern in applications like search and rescue, disaster management, public security etc. This thesis presents a novel multi-stage framework that supports detection of frames with unknown anomalies, localization of anomalies in the detected frames, and validation of detected frames for incremental semi-supervised learning, with the help of a human operator. The proposed architecture is tested on two new datasets collected for a UAV-based system. In order to detect and localize anomalies, it is important to both model the normal data distribution accurately as well as formulate powerful discriminant (anomaly scoring) techniques. We implement a generative adversarial network (GAN)-based anomaly detection architecture to study the effect of loss terms and regularization on the modeling of normal (regular) data and arrive at the most effective anomaly scoring method for the given application. Following this, we use incremental semi-supervised learning techniques that utilize a small set of labeled data (obtained through validation from a human operator), with large unlabeled datasets to improve the knowledge-base of the anomaly detection system. / Master of Science / Anomaly detection aims to identify the data samples that do not conform to a known normal (regular) behavior. As the definition of an anomaly is often ambiguous, most techniques use unlabeled datasets, to model normal (regular) behaviors. The availability of large unlabeled datasets combined with novel applications in various domains, has led to an increasing interest in the study of anomaly detection. In particular, the unmanned aerial system (UAS) can use contextual anomaly detection algorithms to identify interesting objects of concern in applications like search and rescue (SAR), disaster management, public security etc. This thesis presents a novel multi-stage framework that supports detection and localization of unknown anomalies, as well as the validation of detected anomalies, for incremental learning, with the help of a human operator. The proposed architecture is tested on two new datasets collected for a UAV-based system. In order to detect and localize anomalies, it is important to both model the normal data distribution accurately and formulate powerful discriminant (anomaly scoring) techniques. To this end, we study the state-of-the-art generative adversarial networks (GAN)-based anomaly detection algorithms for modeling of normal (regular) behavior and formulate effective anomaly detection scores. We also propose techniques to incrementally learn the new normal data as well as anomalies, using the validation provided by a human operator. This framework is introduced with the aim to support temporally critical applications that involve human search and rescue, particularly in disaster management.

he digital revolution in the latter part of the twentieth century has resulted in the increased use and development of Cyber-Physical Systems. Two of which are Unmanned Aerial Systems (UAS) and Integrated Vehicle Health Management (IVHM). Both are relatively new areas of interest to academia, military, and commercial organisations. Designing IVHM for a UAS is no easy task – the complexity inherent in UAS, with projects involving multiple partners/organisations; multiple stakeholders are also interested in the IVHM. IVHM needs to justify itself throughout the life of the UAS, and the lack of established knowledge makes it hard to know where to start. The establishment and analysis of requirements for IVHM on UAS is known to be important and costly – and for IVHM a complex one. There are multiple stakeholders to satisfy and ultimately the needs of the customer, all demanding different things from the IVHM, and with limited resources they need to be prioritised. There are also many hindrances to this: differences in language between stakeholders, customers failing to see the benefits, scheduling conflicts, no operational data. The contribution to knowledge in this thesis is the IVHM Requirements Deployment (IVHM-RD) – a method for a designer of UAS IVHM to build a tool which can consolidate and evaluate the various stakeholder’s requirements. When the tool is subsequently populated with knowledge from individual Subject Matter Experts (SMEs), it provides a prioritised set of IVHM requirements. The IVHM-RD has been tested on two design cases and generalised for the use with other designs. Analysis of the process has been conducted and in addition the results of the design cases have been analysed in three ways: how the results relate to each design case, comparison between the two cases, and how much the relationships between requirements are understood. A validation exercise has also been conducted to establish the legitimacy of the IVHM-RD process. This research is likely to have an impact on the elicitation and analysis of IVHM requirements for UAS – and the wider design process of IVHM. The IVHM-RD process should also prove of use to designers of IVHM on other assets. The populations of the design cases also provide information which could be useful to other designer and future research.

Unmanned aerial vehicles (UAVs) have been used increasingly over the past few years. Special Forces of various countries utilise these systems successfully in war zones such as Afghanistan. The biggest advantage is rapid information gathering without endangering human lives. The South African National Defence Force (SANDF) also identified the need for local short range aerial reconnaissance and information gathering. A detailed literature survey identified various international players involved in the development of small hand-launch UAV systems. Unfortunately, these overseas systems are too expensive for the SANDF. A new system had to be developed locally to comply with the unique requirements, and budget, of the SANDF. The survey of existing systems provided valuable input to the detailed user requirement statement (URS) for the new South African development. The next step was to build a prototype using off-the-shelf components. Although this aircraft flew and produced good video images, it turned out to be unreliable. The prototype UAV was then replaced with a standard type model aircraft, purchased from Micropilot. Some modifications were needed to ensure better compliance with the URS. Laboratory and field tests proved that the aircraft can be applied for aerial images, within range of 10 km from the ground control station (GCS). The major limitation is that it can only fly for 40 minutes. Furthermore, the airframe is not robust, needing repairs after only 15 flights. Although the system has shortcomings, it has already been used successfully. It is expected that improved battery technologies and sturdier light-weight materials will further help to improve the system beyond user specifications. / Thesis (MIng (Electrical Engineering))--North-West University, Potchefstroom Campus, 2010.

Unmanned aerial vehicles (UAVs) have been used increasingly over the past few years. Special Forces of various countries utilise these systems successfully in war zones such as Afghanistan. The biggest advantage is rapid information gathering without endangering human lives. The South African National Defence Force (SANDF) also identified the need for local short range aerial reconnaissance and information gathering. A detailed literature survey identified various international players involved in the development of small hand-launch UAV systems. Unfortunately, these overseas systems are too expensive for the SANDF. A new system had to be developed locally to comply with the unique requirements, and budget, of the SANDF. The survey of existing systems provided valuable input to the detailed user requirement statement (URS) for the new South African development. The next step was to build a prototype using off-the-shelf components. Although this aircraft flew and produced good video images, it turned out to be unreliable. The prototype UAV was then replaced with a standard type model aircraft, purchased from Micropilot. Some modifications were needed to ensure better compliance with the URS. Laboratory and field tests proved that the aircraft can be applied for aerial images, within range of 10 km from the ground control station (GCS). The major limitation is that it can only fly for 40 minutes. Furthermore, the airframe is not robust, needing repairs after only 15 flights. Although the system has shortcomings, it has already been used successfully. It is expected that improved battery technologies and sturdier light-weight materials will further help to improve the system beyond user specifications. / Thesis (MIng (Electrical Engineering))--North-West University, Potchefstroom Campus, 2010.

<p>The presented work quantifies the impacts of inundated land area (ILA) on streamflow and crop development in the Upper Midwest, which is experiencing a changing climate with observed increases in temperature and precipitation. Quantitative information is needed to understand how upland and downstream stakeholders are impacted by ILA; yet the temporal and spatial extent of ILA and the impact of water storage on flood propagation is poorly understood. Excess water in low gradient agricultural landscapes resulting in ILA can have opposing impacts. The ILA can negatively impact crop development causing financial loss from a reduction or total loss in yield while conversely, ILA can also benefit downstream stakeholders by preventing flood damage from the temporary surface storage that slows water movement into channels. This research evaluates the effects of ILA on streamflow and crop development by leveraging the utility of remotely sensed observations and models.</p><p> </p><p>The influence of ILA on streamflow is investigated in the Red River basin, a predominantly agricultural basin with a history of damaging flood events. An inundation depth-area (IDA) parameterization was developed to parameterize the ILA in a hydrologic model, the Variable Infiltration Capacity (VIC) model, using remotely sensed observations from the MODIS Near Real-Time Global Flood Mapping product and discharge data. The IDA parameterization was developed in a subcatchment of the Red River basin and compared with simulation scenarios that did and did not represent ILA. The model performance of simulated discharge and ILA were evaluated, where the IDA parameterization outperformed the control scenarios. In addition, the simulation results using the IDA parameterization were able to explain the dominant runoff generation mechanism during the winter-spring and summer-fall seasons. The IDA parameterization was extended to the Red River basin to analyze the effects of ILA on the timing and magnitude of peak flow events where observed discharge revealed an increasing trend and magnitude of summer peak flow events. The results also showed that the occurrence of peak flow events is shifting from unimodal to bimodal structure, where peak flow events are dominant in the spring and summer seasons. By simulating ILA in the VIC model, the shift in occurrence of peak flow events and magnitude are better represented compared to simulations not representing ILA.</p><p> </p><p>The impacts of ILA on crop development are investigated on soybean fields in west-central Indiana using proximal remote sensing from unmanned aerial systems (UASs). Models sensitive to ILA were developed from the in-situ and UAS data at the plot scale to estimate biomass and percent of expected yield between the R4-R6 stages at the field scale. Low estimates of biomass and percent of expected yield were associated with mapped observations of ILA. The estimated biomass and percent of expected yield were useful early indicators to identify soybean impacted by excess water at the field scale. The models were applied to satellite imagery to quantify the impacts of ILA on soybean development over larger areas and multiple years. The estimated biomass and percent of expected yield correlated well with the observed data, where low model estimates were also associated with mapped observations of ILA and periods of excessive rainfall. The results of the work link the impacts of ILA on streamflow and crop development, and why it is important to quantify both in a changing climate. By representing ILA in hydrologic models, we can improve simulated streamflow and ILA and represent dominant physical process that influence hydrologic responses and represent shift and seasonal occurrence of peak flow events. In the summer season, where there is an increased occurrence of peak flow events, it is important to understand the impacts of ILA on crop development. By quantifying the impacts of ILA on soybean development we can analyze the spatiotemporal impacts of excess water on soybean development and provide stakeholders with early assessments of expected yield which can help improvement management decisions.</p>

Forage quality is a principal factor in managing both herbivores and the landscapes they use. Nutrition varies across the landscape, and in turn, so do the distributions of these populations. With the rise of remote sensing technologies (i.e. satellites, unmanned aerial vehicles, and multi/hyperspectral sensors), comes the ability to index forage health and nutrition swiftly. However, no methodology has been developed which allows managers to use unmanned aerial systems to the fullest capacity. The following methodologies produce compelling evidence for predicting forage quality metrics (such as fiber, carbohydrates, and digestibility) using 5 measured bands of reflectance (Blue, Green, Red, Red Edge, and NIR), 3 derived vegetation indices (NDVI, EVI and VARI), and a variety of environmental factors (i.e. time and sun angles) in a LASSO framework. Fiber content, carbohydrates, and digestibility showed promising model performance in terms of goodness-of-fit (R2= 0.624, 0.637, and 0.639 respectively).