Browsing by Author "Bird, John P."

Now showing 1 - 20 of 20
  • Thumbnail Image
    Agricultural Crop Monitoring with Computer Vision
    Burns, James Ian (Virginia Tech, 2014-09-25)
    Precision agriculture allows farmers to efficiently use their resources with site-specific applications. The current work looks to computer vision for the data collection method necessary for such a smart field, including cameras sensitive to visual (430-650~nm), near infrared (NIR,750-900~nm), shortwave infrared (SWIR,950-1700~nm), and longwave infrared (LWIR,7500-16000~nm) light. Three areas are considered in the study: image segmentation, multispectral image registration, and the feature tracking of a stressed plant. The accuracy of several image segmentation methods are compared. Basic thresholding on pixel intensities and vegetation indices result in accuracies below 75% . Neural networks (NNs) and support vector machines (SVMs) label correctly at 89% and 79%, respectively, when given only visual information, and final accuracies of 97% when the near infrared is added. The point matching methods of Scale Invariant Feature Transform (SIFT) and Edge Orient Histogram (EOH) are compared for accuracy. EOH improves the matching accuracy, but ultimately not enough for the current work. In order to track the image features of a stressed plant, a set of basil and catmint seedlings are grown and placed under drought and hypoxia conditions. Trends are shown in the average pixel values over the lives of the plants and with the vegetation indices, especially that of Marchant and NIR. Lastly, trends are seen in the image textures of the plants through use of textons.
  • Thumbnail Image
    Automatic Esophageal Intubation Detection Using Giant Magneto Resistance Sensors
    Alson, Bradley Jacob (Virginia Tech, 2015-09-09)
    This thesis will cover the principle, design, and construction of an automatic esophageal intubation detector. This device uses a giant magneto recitative sensor to and a magnetized stylet to automatically measure the position of an ET tube in a person's throat. This method is less subjective than currently used methods such as end tidal CO2, as it does not rely on user interpretation of data or physiological state of the patient. The device developed during this project was tested on an anatomical mockup, a porcine airway model, and an intubation training dummy. In all three tests, the device performed well, accurately indicating tracheal intubation when the tube was placed in the trachea. Only one instance of a false positive indication of tracheal intubation was recorded and this occurred in an atypical and avoidable situation. As of now, the device functions in non-obese adult male patients, but plans are in place to increase usability for the entire population.
  • Thumbnail Image
    A Computer Vision Tool For Use in Horticultural Research
    Thoreson, Marcus Alexander (Virginia Tech, 2017-02-13)
    With growing concerns about global food supply and environmental impacts of modern agriculture, we are seeing an increased demand for more horticultural research. While research into plant genetics has seen an increased throughput from recent technological advancements, plant phenotypic research throughput has lagged behind. Improvements in open-source image processing software and image capture hardware have created an opportunity for the development of more competitively-priced, faster data-acquisition tools. These tools could be used to collect measurements of plants' phenotype on a much larger scale without sacrificing data quality. This paper demonstrates the feasibility of creating such a tool. The resulting design utilized stereo vision and image processes in the OpenCV project to measure a representative collection of observable plant traits like leaflet length or plant height. After the stereo camera was assembled and calibrated, visual and stereo images of potato plant canopies and tubers(potatoes) were collected. By processing the visual data, the meaningful regions of the image (the canopy, the leaflets, and the tubers) were identified. The same regions in the stereo images were used to determine plant physical geometry, from which the desired plant measurements were extracted. Using this approach, the tool had an average accuracy of 0.15 inches with respect to distance measurements. Additionally, the tool detected vegetation, tubers, and leaves with average Dice indices of 0.98, 0.84, and 0.75 respectively. To compare the tool's utility to that of traditional implements, a study was conducted on a population of 27 potato plants belonging to 9 separate genotypes. Both newly developed and traditional measurement techniques were used to collect measurements of a variety of the plants' characteristics. A multiple linear regression of the plant characteristics on the plants' genetic data showed that the measurements collected by hand were generally better correlated with genetic characteristics than those collected using the developed tool; the average adjusted coefficient of determination for hand-measurements was 0.77, while that of the tool-measurements was 0.66. Though the aggregation of this platform's results is unsatisfactory, this work has demonstrated that such an alternative to traditional data-collection tools is certainly attainable.
  • Thumbnail Image
    Conceptual Design of a Battery Pack for Use in a Mobile Hybridized Power Generation System
    Hamm Jr, David Wesley (Virginia Tech, 2013-10-11)
    Mobile generation platforms are very common among both military and civilian applications. However, in military applications getting fuel to the front lines can come at a very high cost. This cost is both financial, costing upwards of hundreds of dollars a gallon, and human, with resupply convoys being the leading cause of casualties in today's warfront. Diesel generators operate much more efficiently at higher loads, rather than the lower loads that the systems normally operate at. To improve fuel efficiency, a hybridized generator system is proposed. This system combines a standard generator with a large rechargeable battery pack. The addition of the battery pack allows for several unique power scenarios to occur through power generation. The battery pack functions to provide an efficient storage capability for the system. During times of excess load, the battery and generator work together. This allows for algorithms to manage the generator set to operate at peak efficiency while addressing load spikes. A system like this has been theoretically designed and a simulation has been developed to determine the impact over a standard system. Actual load cycle information from military sources has been used to evaluate the concept. The results of the simulation show increase efficiency, in the low load scenarios, to more than double the standard generator efficiency.
  • Thumbnail Image
    The data processing to detect correlated movement of Cerebral Palsy patient in early phase
    Pyon, Okmin (Virginia Tech, 2016-02-03)
    The early diagnosis of CP (Cerebral Palsy) in infants is important for developing meaningful interventions. One of the major symptoms of the CP is lack of the coordinated movements of a baby. The bilateral coordinated movement (BCM) is that a baby shows in the early development stage. Each limb movement shows various ranges of speed and angle with fluency in a normal infant. When a baby has CP the movements are cramped and more synchronized. A quantitative method is needed to diagnose the BCM. Data is collected from 3-axis accelerometers, which are connected, to each limb of the baby. Signal processing the collected data using short time Fourier transforms, along with the formation of time-dependent transfer functions and the coherence property is the key to the diagnostic approach. Combinations of each limb's movement and their relationship can represent the correlated movement. Data collected from a normal baby is used to develop the technique for identifying the fidgety movement. Time histories and the resulting diagnostic tool are presented to show the regions of the described movement. The evaluation of the transduction approach and the analysis is discussed in detail. The application of the quantitative tool for the early diagnosis of CP offers clinicians the opportunity to provide interventions that may reduce the debilitating impact this condition has on children. Tools such as this can also be used to assess motor development in infants and lead to the identification and early intervention for other conditions.
  • Thumbnail Image
    Design and Optimization of a Mobile Hybrid Electric System to Reduce Fuel Consumption
    Del Barga, Christopher (Virginia Tech, 2015-05-29)
    The high costs and high risks of transporting fuel to combat zones make fuel conservation a dire need for the US military. A towable hybrid electric system can help relieve these issues by replacing less fuel efficient standalone diesel generators to deliver power to company encampments. Currently, standalone generators are sized to meet peak demand, even though peak demand only occurs during short intervals each day. The average daily demand is much less, meaning generators will be running inefficiently most of the day. In this thesis, a simulation is created to help determine an optimal system design given a load profile, size and weight constraints, and relocation schedule. This simulation is validated using test data from an existing system. After validation, many hybrid energy components are considered for use in the simulation. The combination of components that yields the lowest fuel consumption is used for the optimal design of the system. After determining the optimal design, a few design parameters are varied to analyze their effect on fuel consumption. The model presented in this thesis agrees with the test data to 7% of the measured fuel consumption. Sixteen system configurations are run through the simulation and their results are compared. The most fuel efficient system is the system that uses a 3.8kW diesel engine generator with a 307.2V, maximum capacity LiFeMgPO? battery pack. This system is estimated to consume 21% less fuel than a stand-alone generator, and up to 28% less when solar power is available.
  • Thumbnail Image
    Fabrication and Characterization of Carbon Nanocomposite Photopolymers via Projection Stereolithography
    Campaigne, Earl Andrew III (Virginia Tech, 2014-08-19)
    Projection Stereolithography (PSL) is an Additive Manufacturing process that digitally patterns light to selectively expose and layer photopolymer into three dimensional objects. Nanomaterials within the photopolymer are therefore embedded inside fabricated objects. Adding varying concentrations of multi-walled carbon nanotubes (MWCNT) to the photopolymer may allow for the engineering of an objects tensile strength and electric conductivity. This research has two goals (i) the fabrication of three-dimensional structures using PSL and (ii) the material characterization of nanocomposite photopolymers. A morphological matrix design tool was developed and used to categorically analyze published PSL systems. These results were used to justifying design tradeoffs during the design and fabricate of a new PSL system. The developed system has 300μm resolution, 45mm x 25mm fabrication area, 0.23mW/cm2 intensity, and 76.2mm per hour vertical build rate. Nanocomposite materials were created by mixing Objet VeroClear FullCure 810 photopolymer with 0.1, 0.2, and 0.5 weight percent MWCNT using non-localized bath sonication. The curing properties of these nanocomposite mixtures were characterized; adding 0.1 weight-percent MWCNT increases the critical exposure by 10.7% and decreases the depth of penetration by 40.1%. The material strength of these nanocomposites were quantified through tensile testing; adding 0.1 weight-percent MWCNT decreases the tensile stress by 45.89%, the tensile strain by 33.33%, and the elastic modulus by 28.01%. Higher concentrations always had exaggerated effects. Electrical conductivity is only measurable for the 0.5 weight-percent nanocomposite with a 8k/mm resistance. The 0.1 weight-percent nanocomposite was used in the PSL system to fabricate a three-dimensional nanocomposite structure.
  • Thumbnail Image
    High Resolution Imaging Ground Penetrating Radar Design and Simulation
    Saunders, Charles Phillip II (Virginia Tech, 2014-05-06)
    This paper describes the design and simulation of a microwave band, high resolution imaging ground penetrating radar. A conceptual explanation is given on the mechanics of wave-based imaging, followed by the governing radar equations. The performance specifications for the imaging system are given as inputs to the radar equations, which output the full system specifications. Those specifications are entered into a MATLAB simulation, and the simulation results are discussed with respect to both the mechanics and the desired performance. Finally, this paper discusses limitations of the design, both with the simulations and anticipated issues if the device is fully realized.
  • Thumbnail Image
    IRIS: Intelligent Roadway Image Segmentation
    Brown, Ryan Charles (Virginia Tech, 2014-06-23)
    The problem of roadway navigation and obstacle avoidance for unmanned ground vehicles has typically needed very expensive sensing to operate properly. To reduce the cost of sensing, it is proposed that an algorithm be developed that uses a single visual camera to image the roadway, determine where the lane of travel is in the image, and segment that lane. The algorithm would need to be as accurate as current lane finding algorithms as well as faster than a standard k- means segmentation across the entire image. This algorithm, named IRIS, was developed and tested on several sets of roadway images. The algorithm was tested for its accuracy and speed, and was found to be better than 86% accurate across all data sets for an optimal choice of algorithm parameters. IRIS was also found to be faster than a k-means segmentation across the entire image. IRIS was found to be adequate for fulfilling the design goals for the algorithm. IRIS is a feasible system for lane identification and segmentation, but it is not currently a viable system. More work to increase the speed of the algorithm and the accuracy of lane detection and to extend the inherent lane model to more complex road types is needed. IRIS represents a significant step forward in the single camera roadway perception field.
  • Thumbnail Image
    Machine Learning Techniques for Gesture Recognition
    Caceres, Carlos Antonio (Virginia Tech, 2014-10-13)
    Classification of human movement is a large field of interest to Human-Machine Interface researchers. The reason for this lies in the large emphasis humans place on gestures while communicating with each other and while interacting with machines. Such gestures can be digitized in a number of ways, including both passive methods, such as cameras, and active methods, such as wearable sensors. While passive methods might be the ideal, they are not always feasible, especially when dealing in unstructured environments. Instead, wearable sensors have gained interest as a method of gesture classification, especially in the upper limbs. Lower arm movements are made up of a combination of multiple electrical signals known as Motor Unit Action Potentials (MUAPs). These signals can be recorded from surface electrodes placed on the surface of the skin, and used for prosthetic control, sign language recognition, human machine interface, and a myriad of other applications. In order to move a step closer to these goal applications, this thesis compares three different machine learning tools, which include Hidden Markov Models (HMMs), Support Vector Machines (SVMs), and Dynamic Time Warping (DTW), to recognize a number of different gestures classes. It further contrasts the applicability of these tools to noisy data in the form of the Ninapro dataset, a benchmarking tool put forth by a conglomerate of universities. Using this dataset as a basis, this work paves a path for the analysis required to optimize each of the three classifiers. Ultimately, care is taken to compare the three classifiers for their utility against noisy data, and a comparison is made against classification results put forth by other researchers in the field. The outcome of this work is 90+ % recognition of individual gestures from the Ninapro dataset whilst using two of the three distinct classifiers. Comparison against previous works by other researchers shows these results to outperform all other thus far. Through further work with these tools, an end user might control a robotic or prosthetic arm, or translate sign language, or perhaps simply interact with a computer.
  • Thumbnail Image
    Mixed Modes of Autonomy for Scalable Communication and Control of Multi-Robot Systems
    Bird, John P. (Virginia Tech, 2011-09-26)
    Multi-robot systems (MRS) offer many performance benefits over single robots for tasks that can be completed by one robot. They offer potential redundancies to the system to improve robustness and allow tasks to be completed in parallel. These benefits, however, can be quickly offset by losses in productivity from diminishing returns caused by interference between robots and communication problems. This dissertation developed and evaluated MRS control architectures to solve the dynamic multi-robot autonomous routing problem. Dynamic multi-robot autonomous routing requires robots to complete a trip from their initial location at the time of task allocation to an assigned destination. The primary concern for the control architectures was how well the communication requirements and overall system performance scaled as the number of robots in the MRS got larger. The primary metrics for evaluation of the controller were the effective robot usage rate and the bandwidth usage. This dissertation evaluated several different approaches to solving dynamic multi-robot autonomous routing. The first three methods were based off of common MRS coordination approaches from previous research. These three control architectures with distributed control without communication (a swarm-like method), distributed control with communication, and centralized control. An additional architecture was developed to solve the problem in a way that scales better as the number of robots increase. This architecture, mixed mode autonomy, combines the strengths of distributed control with communication and centralized control. Like distributed control with communication, mixed mode autonomy's performance degrades gracefully with communication failures and is not dependent on a single controller. Like centralized control, there is oversight from a central controller to ensure repeatable high performance of the system. Each of the controllers other than distributed control without communication is based on building world models to facilitate coordination of the routes. A second variant of mixed mode autonomy was developed to allow robots to share parts of their world models with their peers when their models were incomplete or outdated. The system performance was evaluated for three example applications that represent different cases of dynamic multi-robot autonomous routing. These example applications were the automation of open pit mines, container terminals, and warehouses. The effective robot usage rates for mixed mode autonomy were generally significantly higher than the other controllers with a higher numbers of robots. The bandwidth usage was also much lower. These performance trends were also observed across a wide range of operating conditions for dynamic multi-robot autonomous routing. The original contributions from this work were the development of a new MRS control architecture, development of system model for the dynamic multi-robot autonomous routing problem, and identification of the tradeoffs for MRS design for the dynamic multi-robot autonomous routing problem.
  • Thumbnail Image
    Model of the Air System Transients in a Fuel Cell Vehicle
    Bird, John P. (Virginia Tech, 2002-01-30)
    This thesis describes a procedure to measure the transient effects in a fuel cell air delivery system. These methods were applied to model the 20 kW automotive fuel cell system that was used in Animul H2, a fuel cell-battery hybrid sedan developed by a group of engineering students at Virginia Tech. The air delivery system included the air compressor, the drive motor for the compressor, the motor controller, and any plumbing between the fuel cell inlet and the compressor outlet. The procedure was to collect data from a series of tests of the air delivery system with no load (zero outlet pressure) and at several loads. The air compressor speed, outlet pressure, and motor controller current were measured in response to a variety of speed requests. This data was fit to transfer functions relating the compressor speed, outlet pressure, or motor controller current to the speed request. The fits were found using a least squares optimization technique. After the experimental model was developed, it was augmented with an analytical model of the rest of the fuel cell system. The mass flow of the air was determined from the air compressor speed and outlet pressure with the compressor map. The fuel cell current was found by assuming a constant stoichiometric ratio. The power out of the fuel cell was calculated from the fuel cell current and the pressure with the polarization curve. The model of the fuel cell system was implemented in Matlab/Simulink. Several open and closed loop simulations were run to test the functionality of the fuel cell system model. The gross and net powers of the fuel cell system were found as a function of the compressor operating speed. The time it took for the system to come up to power as a function of idle speed was also found. A PID controller was implemented to allow the system to track a reference power request. The key contributions of this work were to develop a method to test the air delivery system to determine the dynamics of the system, to develop a model based on these tests and some analytical knowledge of fuel cells, and to use the model to simulate the operation and control of a fuel cell system.
  • Thumbnail Image
    Online Aerial Terrain Mapping for Ground Robot Navigation
    Peterson, John; Chaudhry, Haseeb; Abdelatty, Karim; Bird, John P.; Kochersberger, Kevin B. (MDPI, 2018-02-20)
    This work presents a collaborative unmanned aerial and ground vehicle system which utilizes the aerial vehicle’s overhead view to inform the ground vehicle’s path planning in real time. The aerial vehicle acquires imagery which is assembled into a orthomosaic and then classified. These terrain classes are used to estimate relative navigation costs for the ground vehicle so energy-efficient paths may be generated and then executed. The two vehicles are registered in a common coordinate frame using a real-time kinematic global positioning system (RTK GPS) and all image processing is performed onboard the unmanned aerial vehicle, which minimizes the data exchanged between the vehicles. This paper describes the architecture of the system and quantifies the registration errors between the vehicles.
  • Thumbnail Image
    An Optical Resection Local Positioning System for an Autonomous Agriculture Vehicle
    Murray, Kevin Hugh (Virginia Tech, 2012-09-28)
    Obtaining accurate and precise position information is critical in precision and autonomous agriculture. Systems accurate to the centimeter-level are available, but may be prohibitively expensive for relatively small farms and tasks that involve multiple vehicles. Optical resection is proposed as a potentially more cost-effective and scalable positioning system for such cases. The proposed system involves the placement of optical beacons at known locations throughout the environment and the use of cameras on the vehicle to detect the apparent angles between beacons. The position of the vehicle can be calculated with resection when three or four beacons are identified. In addition, the system provides precise orientation information, so a separate inertial measurement unit is not required. The system is seen as potentially cost-effective by taking advantage of the precision and low cost of digital image sensors. Whereas the components in other positioning systems tend to be more specialized, the widespread consumer demand for inexpensive and high quality cameras has allowed for billions of dollars of research and development to be spread across billions of image sensors.
  • Thumbnail Image
    Sensor Fused Scene Reconstruction and Surface Inspection
    Moodie, Daniel Thien-An (Virginia Tech, 2014-04-17)
    Optical three dimensional (3D) mapping routines are used in inspection robots to detect faults by creating 3D reconstructions of environments. To detect surface faults, sub millimeter depth resolution is required to determine minute differences caused by coating loss and pitting. Sensors that can detect these small depth differences cannot quickly create contextual maps of large environments. To solve the 3D mapping problem, a sensor fused approach is proposed that can gather contextual information about large environments with one depth sensor and a SLAM routine; while local surface defects can be measured with an actuated optical profilometer. The depth sensor uses a modified Kinect Fusion to create a contextual map of the environment. A custom actuated optical profilometer is created and then calibrated. The two systems are then registered to each other to place local surface scans from the profilometer into a scene context created by Kinect Fusion. The resulting system can create a contextual map of large scale features (0.4 m) with less than 10% error while the optical profilometer can create surface reconstructions with sub millimeter resolution. The combination of the two allows for the detection and quantification of surface faults with the profilometer placed in a contextual reconstruction.
  • Thumbnail Image
    Techniques in Kalman Filtering for Autonomous Vehicle Navigation
    Jones, Philip Andrew (Virginia Tech, 2015-05-05)
    This thesis examines the design and implementation of the navigation solution for an autonomous ground vehicle suited with global position system (GPS) receivers, an inertial measurement unit (IMU), and wheel speed sensors (WSS) using the framework of Kalman filtering (KF). To demonstrate the flexibility of the KF several methods are explored and implemented such as constraints, multi-rate data, and cascading filters to augment the measurement matrix of a main filter. GPS and IMU navigation are discussed, along with common errors and disadvantages of each type of navigation system. It is shown that the coupling of sensors, constraints, and self-alignment techniques provide an accurate solution to the navigation problem for an autonomous vehicle. Filter divergence is discussed during times when the states are unobservable. Post processed data is analyzed to demonstrate performance under several test cases, such as GPS outage, and the effect that the initial calibration and alignment has on the accuracy of the solution.
  • Thumbnail Image
    Text Localization for Unmanned Ground Vehicles
    Kirchhoff, Allan Richard (Virginia Tech, 2014-10-16)
    Unmanned ground vehicles (UGVs) are increasingly being used for civilian and military applications. Passive sensing, such as visible cameras, are being used for navigation and object detection. An additional object of interest in many environments is text. Text information can supplement the autonomy of unmanned ground vehicles. Text most often appears in the environment in the form of road signs and storefront signs. Road hazard information, unmapped route detours and traffic information are available to human drivers through road signs. Premade road maps lack these traffic details, but with text localization the vehicle could fill the information gaps. Leading text localization algorithms achieve ~60% accuracy; however, practical applications are cited to require at least 80% accuracy [49]. The goal of this thesis is to test existing text localization algorithms against challenging scenes, identify the best candidate and optimize it for scenes a UGV would encounter. Promising text localization methods were tested against a custom dataset created to best represent scenes a UGV would encounter. The dataset includes road signs and storefront signs against complex background. The methods tested were adaptive thresholding, the stroke filter and the stroke width transform. A temporal tracking proof of concept was also tested. It tracked text through a series of frames in order to reduce false positives. Best results were obtained using the stroke width transform with temporal tracking which achieved an accuracy of 79%. That level of performance approaches requirements for use in practical applications. Without temporal tracking the stroke width transform yielded an accuracy of 46%. The runtime was 8.9 seconds per image, which is 44.5 times slower than necessary for real-time object tracking. Converting the MATLAB code to C++ and running the text localization on a GPU could provide the necessary speedup.
  • Thumbnail Image
    Underwater Robotic Propulsors Inspired by Jetting Jellyfish
    Marut, Kenneth Joseph (Virginia Tech, 2014-06-04)
    Underwater surveillance missions both for defense and civilian applications are continually demanding the need for unmanned underwater vehicles or UUVs. Unmanned vehicles are needed to meet the logistical requirements for operation over long distances, greater depths, long duration, and harsh conditions. In order to design UUVs that not only satisfy these needs but are also adaptive and efficient, there has been increasing interest in taking inspiration from nature. These biomimetic/bio-inspired UUVs are expected to provide significant improvement over the conventional propeller based vehicles by taking advantage of flexible bodies and smart actuation. In this thesis, jetting jellyfish were utilized as the inspiration to understand the fundamentals of this new form of propulsion and subsequently translate the understanding onto the engineered platform to validate the hypothesis and construct robust models. Jetting jellyfish species are generally smaller in dimensions than rowing jellyfish, consume lower energy for transport, and exhibit higher proficiency. In the second chapter, a bio-inspired stationary jet propulsion mechanism that utilizes an iris diaphragm actuation system was developed. Detailed discussion is provided on the design methodology and factors playing the leading role in controlling the vortex formation. The propulsion mechanism was intended to mimic the morphological and deformation features of Sarsia sp. jellyfish that measures approximately 1 cm in diameter. The performance of experimental model was analyzed and modeled to elucidate the role of structure and fluid displacement. Utilizing the results from Chapter 2, a free-swimming jellyfish-inspired robot (named JetPRo) was developed (also utilizing an iris diaphragm) in Chapter 3 and characterized for relevant propulsive metrics. A combination of theoretical modeling and experimental analysis was used to optimize the JetPRo's gait for maximum steady-state swimming velocity. Next, an attempt was made towards creating a free-swimming jetting robot (named JP2) using a guided cable mechanism to achieve the desired actuation and improve the propulsion while simplifying the drive mechanism. Using JP2 robotic model, a systematic set of experiments were conducted and the results were used to refine the theory. Based upon the comprehensive computational analysis, an optimized swimming gait was predicted and then validated. A modular robot inspired by siphonophores was developed and initial efforts were made in laying down the foundation for understanding of this complex locomotion mechanism. Siphonophores are colonial organisms consisting of several jetting bodies attached to a central stem. An experimental model was developed mimicking the multimodal swimming propulsion utilized by Siphonophores. Several swimming gaits inspired by the natural animal were replicated and the preliminary performance of the experimental model was quantified. Using these results, an analysis is presented towards further improving the design and assembly of a siphonophore-inspired robot.
  • Thumbnail Image
    Unmanned Aerial System for Monitoring Crop Status
    Rogers, Donald Ray III (Virginia Tech, 2014-01-11)
    As the cost of unmanned aerial systems (UAS) and their sensing payloads decrease the practical applications for such systems have begun expanding rapidly. Couple the decreased cost of UAS with the need for increased crop yields under minimal applications of agrochemicals, and the immense potential for UAS in commercial agriculture becomes immediately apparent. What the agriculture community needs is a cost effective method for the field-wide monitoring of crops in order to determine the precise application of fertilizers and pesticides to reduce their use and prevent environmental pollution. To that end, this thesis presents an unmanned aerial system aimed at monitoring a crop's status. The system presented uses a Yamaha RMAX unmanned helicopter, operated by Virginia Tech']s Unmanned Systems Lab (USL), as the base platform. Integrated with helicopter is a dual-band multispectral camera that simultaneously captures images in the visible and near-infrared (NIR) spectrums. The UAS is flown over a quarter acre corn crop undergoing a fertilizer rate study of two hybrids. Images gathered by the camera are post-processed to form a Normalized Difference Vegetative Index (NDVI) image. The NDVI images are used to detect the most nutrient deficient corn of the study with a 5% margin of error. Average NDVI calculated from the images correlates well to measured grain yield and accurately identifies when one hybrid reaches its yield plateau. A secondary test flight over a late-season tobacco field illustrates the system's capabilities to identify blocks of highly stressed crops. Finally, a method for segmenting bleached tobacco leaves from green leaves is presented, and the segmentation results are able to provide a reasonable estimation of the bleached tobacco content per image.
  • Thumbnail Image
    Wrist Worn Device to Aid the Elderly to Age in Place
    Scott, Latonya Rochelle (Virginia Tech, 2014-10-15)
    The elderly population is increasing at a rapid rate each year, and with the increase in the elderly population there is a need for better medical assistance and devices. The greatest problem this demographic is facing is the ability to age in place. More elderly people are being placed in nursing homes, assisted living homes, moving in with relatives due to disabilities or fear of disabilities caused by a life threaten event such as heart disease, stroke, falling/fainting, or uncontrolled glucose levels. Falling is the number one leading cause of deaths, injuries and incapacity in the elderly. Stroke is the 3rd leading cause of death in the U.S; it is the 2nd leading cause worldwide. Rapid change in glucose levels is another leading cause of disabilities and deaths. Heart disease is the 2nd leading cause of death in the elderly. These life threatening events can be prevented and if treated early enough can allow the person to have a full recovery and continue to age in place. A device was proposed that could monitor these four life threatening events: heart disease, stroke, falling/fainting and changes in glucose levels. This device will monitor the user continuously. Research was conducted to see what other products are on the market and how they detect these events and how reliable they are for the user. A literature review was performed to understand what other people are doing to solve the aging in place problem. Using this and needs assessment of the elderly, the system architecture for the wrist worn device was designed along with a testing plan and procedure. More research needs to be done in certain areas to better improve solutions and technology in the area aging in place of the elderly. Before this device can bridge some of the gaps between the current issues and the solution the device will have to be tested for several things such as its ability to differentiate between stimulated falling/fainting and fall like activities such as sitting then lying. The orientation and position will be tested to see if the device can actually tell where the person is located. The device will have to be tested against well-known devices and see if it gives similar precise and accurate readings in real time.