Publications

Abstract not provided.

Images are often not the optimal data form to perform machine learning tasks such as scene classification. Compressive classification can reduce the size, weight, and power of a system by selecting the minimum information while maximizing classification accuracy.In this work we present designs and simulations of prism arrays which realize sensing matrices using a monolithic element. The sensing matrix is optimized using a neural network architecture to maximize classification accuracy of the MNIST dataset while considering the blurring caused by the size of each prism. Simulated optical hardware performance for a range of prism sizes are reported.

Unmanned aircraft systems (UASs) have grown significantly within the private sector with ease of acquisition and platform capabilities far outstretching what previously existed. Where once the operation of these platforms was limited to skilled individuals, increased computational power, manufacturing techniques, and increased autonomy allows inexperienced individuals to skillfully maneuver these devices. With this rise in consumer use of UAS comes an increased security concern regarding their use for malicious intent.The focus area of counter UAS (CUAS) remains a challenging space due to a small cross-sectioned UAS's ability to move in all three dimensions, attain very high speeds, carry payloads of notable weight, and avoid standard delay techniques.We examine frequency analysis of pixel fluctuation over time to exploit the temporal frequency signature present in UAS imagery. This signature allows for lower pixels-on-target detection [1]. The methodology also acts as a method of assessment due to the distinct frequency signatures of UAS when examined against the standard nuisance alarms such as birds. The temporal frequency analysis (TFA) method demonstrates a UAS detection and assessment method. In this paper we discuss signal processing and Fourier filter optimization methodologies that increase UAS contrast.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Alternative architectures for imaging devices which fuse the optical design with an algorithmic component enable inexpensive sensing systems optimized for specific classification tasks. Leveraging past work in task-specific compressive devices, this work seeks to improve upon previous designs of optical and algorithmic elements. We achieve this through use of genetic algorithms to enforce conditions upon the optimization phase of a computational imaging system. Through enforcement of binary sampling or discrete-valued outputs of a system measurement matrix, it is possible to simplify optical hardware design while achieving high task-specific performance.

Many optical systems are used for specific tasks such as classification. Of these systems, the majority are designed to maximize image quality for human observers; however, machine learning classification algorithms do not require the same data representation used by humans. In this work we investigate compressive optical systems optimized for a specific machine sensing task. Two compressive optical architectures are examined: An array of prisms and neutral density filters where each prism and neutral density filter pair realizes one datum from an optimized compressive sensing matrix, and another architecture using conventional optics to image the aperture onto the detector, a prism array to divide the aperture, and a pixelated attenuation mask in the intermediate image plane. We discuss the design, simulation, and tradeoffs of these compressive imaging systems built for compressed classification of the MNSIT data set. To evaluate the tradeoffs of the two architectures, we present radiometric and raytrace models for each system. Additionally, we investigate the impact of system aberrations on classification accuracy of the system. We compare the performance of these systems over a range of compression. Classification performance, radiometric throughput, and optical design manufacturability are discussed.

Many optical systems are used for specific tasks such as classification. Of these systems, the majority are designed to maximize image quality for human observers; however, machine learning classification algorithms do not require the same data representation used by humans. In this work we investigate compressive optical systems optimized for a specific machine sensing task. Two compressive optical architectures are examined: An array of prisms and neutral density filters where each prism and neutral density filter pair realizes one datum from an optimized compressive sensing matrix, and another architecture using conventional optics to image the aperture onto the detector, a prism array to divide the aperture, and a pixelated attenuation mask in the intermediate image plane. We discuss the design, simulation, and tradeoffs of these compressive imaging systems built for compressed classification of the MNSIT data set. To evaluate the tradeoffs of the two architectures, we present radiometric and raytrace models for each system. Additionally, we investigate the impact of system aberrations on classification accuracy of the system. We compare the performance of these systems over a range of compression. Classification performance, radiometric throughput, and optical design manufacturability are discussed.

We investigate the feasibility of additively manufacturing optical components to accomplish task-specific classification in a computational imaging device. We report on the design, fabrication, and characterization of a non-traditional optical element that physically realizes an extremely compressed, optimized sensing matrix. The compression is achieved by designing an optical element that only samples the regions of object space most relevant to the classification algorithms, as determined by machine learning algorithms. The design process for the proposed optical element converts the optimal sensing matrix to a refractive surface composed of a minimized set of non-repeating, unique prisms. The optical elements are 3D printed using a Nanoscribe, which uses two-photon polymerization for high-precision printing. We describe the design of several computational imaging prototype elements. We characterize these components, including surface topography, surface roughness, and angle of prism facets of the as-fabricated elements.

Physical security systems (PSS) and humans are inescapably tied in the current physical security paradigm. Yet, physical security system evaluations often end at the console that displays information to the human. That is, these evaluations do not account for human-in-The-loop factors that can greatly impact performance of the security system, even though methods for doing so are well-established. This paper highlights two examples of methods for evaluating the human component of the current physical security system. One of these methods is qualitative, focusing on the information the human needs to adequately monitor alarms on a physical site. The other of these methods objectively measures the impact of false alarm rates on threat detection. These types of human-centric evaluations are often treated as unnecessary or not cost effective under the belief that human cognition is straightforward and errors can be either trained away or mitigated with technology. These assumptions are not always correct, are often surprising, and can often only be identified with objective assessments of human-system performance. Thus, taking the time to perform human element evaluations can identify unintuitive human-system weaknesses and can provide significant cost savings in the form of mitigating vulnerabilities and reducing costly system patches or retrofits to correct an issue after the system has been deployed.

Nuisance and false alarms are prevalent in modern physical security systems and often overwhelm the alarm station operators. Deep learning has shown progress in detection and classification tasks, however, it has rarely been implemented as a solution to reduce the nuisance and false alarm rates in a physical security systems. Previous work has shown that transfer learning using a convolutional neural network can provide benefit to physical security systems by achieving high accuracy of physical security targets [10]. We leverage this work by coupling the convolutional neural network, which operates on a frame-by-frame basis, with temporal algorithms which evaluate a sequence of such frames (e.g. video analytics). We discuss several alternatives for performing this temporal analysis, in particular Long Short-Term Memory and Liquid State Machine, and demonstrate their respective value on exemplar physical security videos. We also outline an architecture for developing an ensemble learner which leverages the strength of each individual algorithm in its aggregation. The incorporation of these algorithms into physical security systems creates a new paradigm in which we aim to decrease the volume of nuisance and false alarms in order to allow the alarm station operators to focus on the most relevant threats.

Unmanned aircraft system (UAS) technologies have gained immense popularity in the commercial sector and have enabled capabilities that were not available just a short time ago. Once limited to the domain of highly skilled hobbyists or precision military instruments, consumer UAS are now widespread due to increased computational power, manufacturing techniques, and numerous commercial applications. The rise of consumer UAS and the low barrier to entry necessary to utilize these systems provides an increased potential for using a UAS as a delivery platform for malicious intent. This creates a new security concern which must be addressed. The contribution presented in this work is the realization of counter UAS security technology concepts viewed through the traditional security framework and the associated challenges to such a framework.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Abstract not provided.

Advancements in machine learning (ML) and deep learning (DL) have enabled imaging systems to perform complex classification tasks, opening numerous problem domains to solutions driven by high quality imagers coupled with algorithmic elements. However, current ML and DL methods for target classification typically rely upon algorithms applied to data measured by traditional imagers. This design paradigm fails to enable the ML and DL algorithms to influence the sensing device itself, and treats the optimization of the sensor and algorithm as separate sequential elements. Additionally, this current paradigm narrowly investigates traditional images, and therefore traditional imaging hardware, as the primary means of data collection. We investigate alternative architectures for computational imaging systems optimized for specific classification tasks, such as digit classification. This involves a holistic approach to the design of the system from the imaging hardware to algorithms. Techniques to find optimal compressive representations of training data are discussed, and most-useful object-space information is evaluated. Methods to translate task-specific compressed data representations into non-traditional computational imaging hardware are described, followed by simulations of such imaging devices coupled with algorithmic classification using ML and DL techniques. Our approach allows for inexpensive, efficient sensing systems. Reduced storage and bandwidth are achievable as well since data representations are compressed measurements which is especially important for high data volume systems.

Physical unclonable functions (PUFs) are devices which are easily probed but difficult to predict. Optical PUFs have been discussed within the literature, with traditional optical PUFs typically using spatial light modulators, coherent illumination, and scattering volumes; however, these systems can be large, expensive, and difficult to maintain alignment in practical conditions. We propose and demonstrate a new kind of optical PUF based on computational imaging and compressive sensing to address these challenges with traditional optical PUFs. This work describes the design, simulation, and prototyping of this computational optical PUF (COPUF) that utilizes incoherent polychromatic illumination passing through an additively manufactured refracting optical polymer element. We demonstrate the ability to pass information through a COPUF using a variety of sampling methods, including the use of compressive sensing. The sensitivity of the COPUF system is also explored. We explore non-traditional PUF configurations enabled by the COPUF architecture. The double COPUF system, which employees two serially connected COPUFs, is proposed and analyzed as a means to authenticate and communicate between two entities that have previously agreed to communicate. This configuration enables estimation of a message inversion key without the calculation of individual COPUF inversion keys at any point in the PUF life cycle. Our results show that it is possible to construct inexpensive optical PUFs using computational imaging. This could lead to new uses of PUFs in places where electrical PUFs cannot be utilized effectively, as low cost tags and seals, and potentially as authenticating and communicating devices.

There is a desire to detect and assess unmanned aerial systems (UAS) with a high probability of detection and low nuisance alarm rates in numerous fields of security. Currently available solutions rely upon exploiting electronic signals emitted from the UAS. While these methods may enable some degree of security, they fail to address the emerging domain of autonomous UAS that do not transmit or receive information during the course of a mission. We examine frequency analysis of pixel fluctuation over time to exploit the temporal frequency signature present in imagery data of UAS. This signature is present for autonomous or controlled multirotor UAS and allows for lower pixels-on-target detection. The methodology also acts as a method of assessment due to the distinct frequency signatures of UAS when examined against the standard nuisance alarms such as birds or non-UAS electronic signal emitters. The temporal frequency analysis method is paired with machine learning algorithms to demonstrate a UAS detection and assessment method that requires minimal human interaction. The use of the machine learning algorithm allows each necessary human assess to increase the likelihood of autonomous assessment, allowing for increased system performance over time.

Deep learning techniques have demonstrated the ability to perform a variety of object recognition tasks using visible imager data; however, deep learning has not been implemented as a means to autonomously detect and assess targets of interest in a physical security system. We demonstrate the use of transfer learning on a convolutional neural network (CNN) to significantly reduce training time while keeping detection accuracy of physical security relevant targets high. Unlike many detection algorithms employed by video analytics within physical security systems, this method does not rely on temporal data to construct a background scene; targets of interest can halt motion indefinitely and still be detected by the implemented CNN. A key advantage of using deep learning is the ability for a network to improve over time. Periodic retraining can lead to better detection and higher confidence rates. We investigate training data size versus CNN test accuracy using physical security video data. Due to the large number of visible imagers, significant volume of data collected daily, and currently deployed human in the loop ground truth data, physical security systems present a unique environment that is well suited for analysis via CNNs. This could lead to the creation of algorithmic element that reduces human burden and decreases human analyzed nuisance alarms.