Folk wisdom on the subject of human knowledge holds that it is “better to know nothing than to know what ain’t so1”. In some circumstances that precept may be particularly important. If the negative consequences of false knowledge are sufficiently severe, we may be willing to forgo the benefits of knowing some facts to avoid the dangers of believing “facts” that are incorrect. This is the foundation of the “innocent until proven guilty” system of justice. According to English jurist William Blackstone, “it is better that ten guilty persons escape than that one innocent suffer2”. Similar principles apply wherever it is especially harmful to act upon false beliefs. If we wish to employ machine learning as an aid to human judgment, it may in some cases be advisable to insist upon near-certainty from the machine’s reported results. One way of working towards this goal is to use an ensemble of different agents. If their results are consistent with each other, we can have greater confidence in their overall reliability. We can also set a threshold value for the average confidence of the agents themselves. This paper explores the decision-making process for developing an ensemble of classifiers, and evaluates the results in the context of an example set. This set is appropriately categorized by a hierarchical structure, which permits less-specific judgments to be made if confidence falls below our predetermined threshold. We examine the tradeoffs to be made when setting parameters, and discuss aligning them with overarching requirements.
Hardware assisted operating systems have their origins in microprogramming from the early 1970’s. In 2014, Renesas marketed a hardware based operating system in the R-IN32M microprocessor. It is time for cybersecurity to consider the security benefits of moving hypervisor and OS features into hardware. A trusted computing base architecture using a hardware state machine separation kernel is the future of cybersecurity. In this paper, we will research a hardware state machine as the trusted computing base. A traditional operating system provides security for applications software. We are interested in a state machine monitor to secure the execution of instructions and provide separation kernel features.
KEYWORDS: Roads, Genetic algorithms, Video, Sensors, Monte Carlo methods, Hyperspectral imaging, Detection and tracking algorithms, Distance measurement, Kinematics, Feedback control
Hyperspectral imagery (HSI) data has proven useful for discriminating targets, however the relatively slow speed at
which HSI data is gathered for an entire frame reduces the usefulness of fusing this information with grayscale video. A
new sensor under development has the ability to provide HSI data for a limited number of pixels while providing
grayscale video for the remainder of the pixels. The HSI data is co-registered with the grayscale video and is available
for each frame. This paper explores the exploitation of this new sensor for target tracking. The primary challenge of
exploiting this new sensor is to determine where the gathering of HSI data will be the most useful. We wish to optimize
the selection of pixels for which we will gather HSI data. We refer to this as spatial sampling. It is proposed that
spatial sampling be solved using a utility function where pixels receive a value based on their nearness to a target of
interest (TOI). The TOIs are determined from the tracking algorithm providing a close coupling of the tracking and the
sensor control. The relative importance or weighting of the different types of TOI will be accomplished by a genetic
algorithm. Tracking performance of the spatially sampled tracker is compared to both tracking with no HSI data and
although physically unrealizable, tracking with complete HSI data to demonstrate its effectiveness within the upper and
lower bounds.
Video tracking is used in military operations and homeland defense. Multiple cameras are mounted on an airplane that flies in a circle and points to a central location. The images are pre-registered and a single large image is sent to a ground station at the rate of a frame per second. The first step needed for tracking is measurements. The video undergoes additional registration and processing to produce multi-frame motion detections. These measurements are passed to the tracking algorithm. Tracking through an urban environment has its own unique challenges. Targets frequently cross paths, go behind one another, and go behind buildings or into shadowed areas. Additional challenges include Move-Stop-Move, parallax, and track association with highly similar targets. These challenges need to be overcome with up to a thousand vehicles, so processing speed is crucial. The project is Open-Source to aid in overcoming these technical challenges. Alternative trackers (IMM, MHT), features, association methods, track-initiation and deletion (M/N or LU), state variables, or other specialized routines (for Move-Stop-Move, parallax, etc.) will be tried and analyzed with representative data. By keeping it Open-Source, any ideas to improve the system can be easily implemented and analyzed. This paper presents current findings and state of the project.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.