Target and Background Signatures X: Traditional Methods and Artificial Intelligence

Deep Learning based architectures such as Convolutional Neural Networks (CNNs) have become quite efficient in recent years at detecting camouflaged objects that would be easily overlooked by a human observer. Consequently, countermeasures have been developed in the form of adversarial attack patterns which can confuse CNNs by causing false classifications while maintaining the original camouflage properties in the visible spectrum. In this paper, we describe the various steps in generating suitable adversarial camouflage patterns based on the Dual Attribute Adversarial Camouflage (DAAC) technique for evading the detection by artificial intelligence as well as human observers which was proposed in [Wang et al. 2021]. The aim here is to develop an efficient camouflage with the added ability to confuse more than a single network without compromising camouflage against human observers. In order to achieve this, two different approaches are suggested and the results of first tests are presented.

Due to the enormous development in the field of artificial intelligence, especially in the area of reconnaissance, detection and recognition, it has become absolutely necessary to think about methods of concealing one's own military units from this new threat. This publication aims to provide an overview of counter ai approaches against enemy reconnaissance, and the possibilities to assess the effectiveness of these methods. It will focus on explainable AI and the camouflaging of key features as well as the possibility of dual attribute adversarial attack camouflage. These are mathematically optimised patterns that drive an AI-based classifier to an incorrect classification or simply suppress the correct classification. We also discuss the robustness of these patterns.

Hiding platforms in plain sight requires camouflage schemes that blend well with the environment in different locations, seasons, and times of day. Inspired by biological systems that continuously adapt their changing environment, this paper presents a new algorithm, the Visible Signatures AI-Generator algorithm (VSAI), for generating camouflage patterns iteratively to reduce visible signatures of objects. The proposed algorithm accepts a set of images from any dynamically changing, cluttered environment. It then generates a customised set of camouflage patterns with colours and textures that are optimised for the environment. We present a novel generative adversarial network, in which a generator with meta-parameters is iteratively trained to produce camouflage patterns. Simultaneously, a generator is trained to differentiate images with or without the inserted camouflage patterns. Unlike the existing methods, the meta-parameters used by our generator are intuitive, explainable, and extendable by the end-users.

Thermal and visible cameras can be characterized by their point spread function (PSF). Various techniques for estimating the PSF based on a simple image of a target object that consists of a random pattern were shown to be effective. Here, we describe a computational pipeline for estimating parametric Gaussian PSFs characterized by their width, height, and orientation, based on binary random pattern targets that are suitable for thermal imaging and easy to manufacture. We evaluate the estimation accuracy based on simulated patterns with varying dot, pitch, and target sizes for different values of the point spread function parameters. Finally, we show experimental examples of acquired on manufactured devices. Our results indicate that the proposed random pattern targets offer a simple and affordable approach to estimating local PSFs.

When using mid-wave infrared imagery for air-to-ground target recognition tasks, challenges such as slow detection, blurred targets, and degraded image quality affect the accuracy of recognition. To address these issues, a two-stage deep learning model is proposed in this thesis. The model utilizes a self-constructed dataset and uses SRN-DeblurNet to de-blur the images. Meanwhile, this paper optimizes YOLO V8 to reduce the computational burden of the model and improve the detection speed by channel pruning and introducing ShuffleNet. In addition, a novel convolution method is proposed in this paper to improve the detection accuracy. Ultimately, the model achieves an average accuracy of 97% in recognizing five ground targets, establishing an efficient embedded deep learning solution for air-to-ground mid-wave infrared target recognition.

Quantum Mechanics has revolutionized not only our understanding of Nature but also, being the foundation of electronics and lasers, virtually all the instruments we use every day. Then again, we have not yet been able to harness the consequences of the most profoundly quantum phenomena such as state superpositions and particle entanglement. The Second Quantum Revolution has the ambition of building novel "quantum machines" able to fully exploit the properties of both microscopic and macroscopic quantum states. Quantum sensors, making use of the phenomenon of entanglement in systems promise to reach the fundamental measurement limits determined by the laws of physics and correspondingly improve the current performance of the sensors by orders of magnitude in terms of precision and accuracy, with important application implications in the scientific, industrial, and commercial fields. They can measure with unprecedented precision a wide class of physical quantities, such as magnetic, electric, and inertial fields, times, frequencies, temperatures and pressures.

In a world of significant technological disruption, Defence’s ability to mitigate future threats is underpinned by a strong science and technology base. I will provide examples of how we are working across UK academia and industry to develop and exploit key sensing and imaging technologies that will deliver future operational advantage to UK forces. Our interests range from understanding fundamental novel optical and quantum phenomena to working in partnership with universities and industrial partners to demonstrate key concepts. I'll provide examples from the area of quantum sensing, where there is a real drive to test prototype technologies in relevant environments on airborne and maritime platforms. At a systems level I'll talk about how MOD is leading the development of architectures like Sapient - a key enabler for future integrated ISTAR systems. As we seek to continually adapt to new opportunities, I'll also talk about emerging themes such as distributed coherent sensing. I’ll close on one of the most important assets for the future of UK defence - a skilled UK workforce which we support through the funding of PhDs, including the recently announced the Sensing, Processing and AI for Defence (SPADS) Centre for Doctoral Training, jointly with EPSRC. Through such collaborations and our work with UK industry we are ensuring the UK armed forces can remain at the cutting edge of science and technology.”

In contrast to full simulation, ‘hybrid’ simulation, in which a virtual target is combined with a real recording of a scene, has been shown to create realistic imagery of targets with sufficient fidelity to assess the visual signature of a target. This method allows one to evaluate different camouflage designs and targets in a variety of backgrounds. Ultimately, the goal is to use a dataset of recorded imagery taken under various (weather) conditions as benchmark for signature analysis for any platform and camouflage pattern. To achieve this, the set of required calibration elements, such as MacBeth Color Checker and probe spheres, should be limited. In this study the extent to which a target coated with a given paint can be predicted from a limited set of painted probe spheres, e.g. differing in colour and/or gloss, is analyzed.

Training object detection algorithms to operate in complex geo-environments remains a significant challenge, necessitating large and diverse datasets not always readily available. Physically generating requisite data can also be cost prohibitive depending on the object(s) and area(s) of interest -– especially in the case of multi-spectral and hyper-spectral imagery. Thus, there is increasing interest in the use of synthetic data to supplement existing physical datasets. To this end, the US Army Engineer Research and Development Center (ERDC) continues to develop a computational tool suite called the VESPA or, the Virtual Environmental Simulation for Physics-based Analysis, to support synthetic multi-spectral and hyper-spectral EO/IR imagery generation. The VESPA consists of integrated (1) scene generation tools, (2) multi-fidelity models (3) data interrogation utilities, and (4) component-level sensor models capable of producing AI/ML ready near- and far-field imagery that is comparable to that produced by real sensors. This study presents an overview of the VESPA, new advances/capabilities, and results from a recent detailed validation and verification study.

Infrared imaging sensors can nowadays be regarded as a viable alternative to radar guidance that is more stealthy and capable of naval target classification, decoy discrimination and aimpoint selection. In view of this, the design of naval platforms, their sensors, weapon systems and counter measure deployment strategies need to be adapted accordingly. For this, tooling capable of simulating engagements by IR guided threats is essential. This paper presents a recently developed physics-based GPU-accelerated model chain that allows to generate realistic and radiometrically correct image sequences representative of those seen by an IR threat having varying levels of intelligence that is approaching a naval vessel. A description of the scientific and computational aspects of the model and modules will be provided along with examples of modelling output.

We will present an assessment of thermal-waveband infrared observation of orbiting satellites for LEO and GEO space-domain awareness. Our methodology includes dynamic orbital boundary conditions and novel thermal/electrical coupled simulation to predict 3D temperature distributions of satellites while incorporating battery cycling, realistic photovoltaic panel efficiency and internal component heating. We provide the SDA/SSA community with a methodology for exploring the detailed thermal-infrared characterization of LEO and GEO satellites. We demonstrate how radiometric infrared satellite signatures can be predicted for space-based remote sensing scenarios, and report the sensitivity of the predicted signatures to various design factors (model inputs).

The growing data availability regarding New Space SAR satellites yields more and more potential for security and defense purposes, in particular classical reconnaissance of systematic threats. So far, a lack of insight regarding the sensor specific object signatures, however, impedes an actual utilization. In this paper, a selection of objects relevant for reconnaissance are explored regarding their signature characteristics in SAR images of New Space satellites. The focus is on temporary tank emplacements, their occupancy status and visibility. With the aid of Open Source information, 3d models of temporary tank emplacements were generated for different states of occupancy. Using the CohRaS SAR simulator of Fraunhofer IOSB these models were then simulated with sensor and acquisition parameters matching those of Capella. Finally, a comparison between simulated signatures and signatures of real SAR imagery, as well as a discussion about the qualitative properties of these signatures will be provided.

The proliferation of Unmanned Aerial Systems (UAS), both commercial-off-the-shelf and homebuilt, is increasingly posing a challenge to the authorities. Law enforcement agencies are confronted with the new task of policing the lower airspace, requiring them to be equipped with effective and appropriate counter-UAS systems for detecting, tracking, identifying (DTI) the offending drone. A number of technologies exists on the market today, using radar, EO/IR, acoustic and RF sensors. Evaluating the performance of these systems is not a trivial tasks, as different nations and entities often have different approaches. The COURAGEOUS project seeks develop evaluation methodologies for counter-UAS systems, leading to a pre-standard. We organized one of three validation trails for this project, implementing a maritime border protection scenario. We invited manufacturers to test their systems against a range of UAS, comparing their DTI data to the flightpath ground truth. These evaluations were not, but rather used to evaluate the usefulness of the evaluation methods developed by the project, allowing us to progress towards developing an EU-wide standard for evaluating DTI technologies.

The complex permittivity of adobe is measured using a coaxial probe system verses frequency and moisture content. Measurements are performed using adobe samples collected from abode bricks. Using the characterization of the adobe material, the application of through-the-wall radar imaging (TWRI) is considered for adobe walls. Matched illumination waveforms are derived, and the effects of optimal transmission waveforms are presented to illustrate the necessity of accurate material characterization for enhancement of TWRI applications. The results presented include simulation of an object located behind an adobe wall as well as experimental measurements taken in an anechoic chamber.