arXiv subjects

Adrian Martin

Publications and source records attributed to Adrian Martin.

10 recordsLinked to original sources

arXiv2026

OmniEye: Efficient Multimodal Forensic Video Intelligence for Law-Enforcement Body-Worn Cameras

We introduce OmniEye, a multimodal video intelligence system for law-enforcement training and review (source code available on request to verified law-enforcement and public-safety agencies). OmniEye ingests body-worn camera footage and perceives every 30-second window jointly across video and audio with one multimodal foundation model. It then stores the model's structured output in an embedded SQLite database with BM25 full-text search. Officers can question the footage through an agent that writes structured queries, retrieves candidate windows, and re-perceives them with the model before it may cite them. The whole system runs on one 16 GB GPU with a 4-bit quantization-aware-trained model, and it also scales to full bf16 precision on a multi-GPU cluster.

cs.ET↗

arXiv2026

The Ultraviolet Spectrograph on ESA's Jupiter Icy Moons Explorer Mission (JUICE-UVS)

The Jupiter Icy Moons Explorer (JUICE) mission, led by ESA, has an Ultraviolet Spectrograph (JUICE-UVS) contributed by NASA and built at Southwest Research Institute. JUICE-UVS is designed to provide a diversity of measurements to further our understanding of the potential habitability of icy ocean worlds at Jupiter and to study Jupiter and the Jovian system as an archetype for gas giants. JUICE-UVS observes photons in the 50-204 nm wavelength range at moderate spectral and spatial resolution along a 7.5 deg slit composed of 7.3 deg x 0.1 deg and 0.2 deg x 0.2 deg contiguous sections. JUICE-UVS performs a comprehensive study of icy satellite atmospheres, plumes, surfaces, and local space environments; Jupiter's atmosphere and aurora; Io and its Io Plasma Torus; and other Jupiter system targets (rings, small moons, etc.) as available. The variety of observational techniques employed include: nadir push-broom imaging, disk scans, limb stares, stellar and solar occultations, Jupiter transit observations, and neutral cloud/plasma torus stares and scans. This paper describes the UVS investigation's science plans, instrument details, concept of operations, and data formats in the context of the JUICE mission's habitability and Jupiter system goals.

astro-ph.EP↗

arXiv2026

Optomechanical Design of the MANTIS SmallSat: An Extreme-, Far- and Near-Ultraviolet Spectrograph for Exoplanet Host Stars

The MANTIS (Monitoring Activity of Nearby sTars with uv Imaging and Spectroscopy) observatory is a compact, multi-instrument small satellite designed for simultaneous extreme- (EUV; 100 - 560 Angstrom), far- (FUV; 1150-1800 Angstrom) and near-ultraviolet/visible (NUV/VIS; 2000-6400 Angstrom) spectroscopy of low-mass stars. The EUV optical system consists of a first-of-its-kind Hettrick-Bowyer grazing incidence telescope contributed by the Italian National Institute for Astrophysics (INAF) feeding an advanced e-beam lithographic etched variable line spacing grating developed at Pennsylvania State University (PSU). The resulting low-resolution spectrum is imaged on an advanced microchannel plate detector with a potassium iodide (KI) photocathode for extremely low background noise, resulting in a limiting sensitivity for MANTIS that exceeds that of the last EUV-sensitive astrophysics point-source spectrograph, the Deep Survey/Spectrometer (DS/S) on EUVE. The FUV and NUV/Optical channels are fed by a compact rectangular telescope that focuses onto a series of point-source apertures. The diverging beam is refocused and the FUV band dispersed by a holographic grating, then folded back onto the same detector as the EUV channel by a toroidal fold mirror. The zero-order light is picked off by a flat NUV grating, with the NUV/Optical spectrum recorded on an e2v CCD 42-10 detector. The MANTIS spacecraft is a custom build that leverages the experience derived from prior University of Colorado - LASP SmallSats for avionics, power, communications, and mechanical structure. MANTIS is projected to be completed in 2027 with an anticipated 2028 launch as an ESPA-class payload on a rideshare opportunity.

astro-ph.IM↗

arXiv2026

Visual Timelines of Police Encounters in Body-Worn Camera Footage: Operational Context and Activity Cataloging for Training and Analysis in OpenBWC

Law enforcement agencies are accumulating vast amounts of body-worn camera (BWC) footage. However, this remains operationally opaque. That is, analysts and trainers still have to invest considerable time watching full-length videos to pinpoint the start of key encounters and identify the points where activity shifts to something more physically intense. We present an approach to process BWC video into a time-aligned sequence of fixed-length 10-second windows, processed and labeled using a privacy-conscious protocol. Each window is labeled with two dimensions of information: (i) the operational context of the window and (ii) the level of motion intensity within the window, with low-evidence labels for windows for which insufficient evidence exists due to darkness, blur or occlusion. We train models to classify windows based on these two axes using frames sampled from each window encoded using CLIP model and aggregated into a window-level representation. We extract dense optical flow statistics for each window to capture motion intensity. On test windows the best context model achieves 78.75% accuracy, and the best-accuracy activity model achieves 88.33%. We also included integrity audits to show the results and how the visual timeline representations support faster incident review and make the officer training workflow more practical.

cs.CV↗

arXiv2026

Ontology for Policing: Conceptual Knowledge Learning for Semantic Understanding and Reasoning in Law Enforcement Reports

Law enforcement reports contain structured fields and written narratives. However, many incident facts that are needed for review, police training, and investigations are in natural language and require manual reading. We propose a framework using symbolic methods for converting narratives into evidence-linked facts. Our objective is to measure the value of narratives to recover incident details only from the unstructured text and build temporal graphs with time cues and domain axioms. We achieve this by redacting personal identifiers, semantic parsing, predicate mapping to ontology, and reasoning. We evaluate the symbolic approach on 450 property crime reports and a short human review. Of the extracted events from the system, 54.1% had a confidence score of at least 0.80 and 93.7% were mapped through the PropBank--VerbNet--WordNet semantic path. 100% agreement was reached on incident initiation, stolen items, and temporal cues and lower agreement for forced entry interpretation.

cs.CL↗

arXiv2026

Inflight performance and future improvements for the INtegral Field Ultraviolet Spectrographic Experiment, the first far ultraviolet integral field spectrograph

Integral field spectroscopy allows for spectral mapping of extended sources in a time efficient manner. An integral field unit (IFU) in the ultraviolet on Habitable Worlds Observatory (HWO) could be used to quickly map extended objects like supernova remnants or galaxies and their surroundings, but there are technical challenges to an ultraviolet IFU. The INtegral Field Ultraviolet Spectrographic Experiment (INFUSE), a sounding rocket project, is the first static configuration far ultraviolet integral field spectrograph. INFUSE features an f/16, 0.49m Cassegrain telescope and a 26-element image slicer feeding 26 replica holographic gratings, with spectra imaged by the largest cross-strip microchannel plate detector flown in space. The first launch of INFUSE occurred from White Sands Missile Range on October 29th, 2023, and demonstrated spectral multiplexing, successfully detecting ionizing gas emission in the XA region of the Cygnus Loop. INFUSE will launch again in fall 2025 to observe NGC 2366, a local analog for Green Pea type galaxies, with several enhancements including a xenon-enhanced lithium fluoride + aluminum coated grating, testing the leading flight coating for HWO for the first time. The INFUSE IFU is designed as a pathfinder for a potential IFU mode on HWO, enabling rapid 3D spectroscopy of extended sources.

astro-ph.IM↗

arXiv2025

Towards AI-Driven Policing: Interdisciplinary Knowledge Discovery from Police Body-Worn Camera Footage

This paper proposes a novel interdisciplinary framework for analyzing police body-worn camera (BWC) footage from the Rochester Police Department (RPD) using advanced artificial intelligence (AI) and statistical machine learning (ML) techniques. Our goal is to detect, classify, and analyze patterns of interaction between police officers and civilians to identify key behavioral dynamics, such as respect, disrespect, escalation, and de-escalation. We apply multimodal data analysis by integrating image, audio, and natural language processing (NLP) techniques to extract meaningful insights from BWC footage. The framework incorporates speaker separation, transcription, and large language models (LLMs) to produce structured, interpretable summaries of police-civilian encounters. We also employ a custom evaluation pipeline to assess transcription quality and behavior detection accuracy in high-stakes, real-world policing scenarios. Our methodology, computational techniques, and findings outline a practical approach for law enforcement review, training, and accountability processes while advancing the frontiers of knowledge discovery from complex police BWC data.

cs.AI↗

arXiv2021

Vision-based Autonomous Disinfection of High Touch Surfaces in Indoor Environments

Autonomous systems have played an important role in response to the Covid-19 pandemic. Notably, there have been multiple attempts to leverage Unmanned Aerial Vehicles (UAVs) to disinfect surfaces. Although recent research suggests that surface transmission is less significant than airborne transmission in the spread of Covid-19, surfaces and fomites can play, and have played, critical roles in the transmission of Covid-19 and many other viruses, especially in settings such as child daycares, schools, offices, and hospitals. Employing UAVs for mass spray disinfection offers several potential advantages, including high-throughput application of disinfectant, large scale deployment, and the minimization of health risks to sanitation workers. Despite these potential benefits and preliminary usage of UAVs for disinfection, there has been little research into their design and effectiveness. In this work, we present an autonomous UAV capable of effectively disinfecting indoor surfaces. We identify relevant parameters such as disinfectant type and concentration, and application time and distance required of the UAV to disinfect high-touch surfaces such as door handles. Finally, we develop a robotic system that enables the fully autonomous disinfection of door handles in an unstructured and previously unknown environment. To our knowledge, this is the smallest untethered UAV ever built with both full autonomy and spraying capabilities, allowing it to operate in confined indoor settings, and the first autonomous UAV to specifically target high-touch surfaces on an individual basis with spray disinfectant, resulting in more efficient use of disinfectant

cs.RO↗

arXiv2015

On 1-Laplacian Elliptic Equations Modeling Magnetic Resonance Image Rician Denoising

Modeling magnitude Magnetic Resonance Images (MRI) rician denoising in a Bayesian or generalized Tikhonov framework using Total Variation (TV) leads naturally to the consideration of nonlinear elliptic equations. These involve the so called $1$-Laplacian operator and special care is needed to properly formulate the problem. The rician statistics of the data are introduced through a singular equation with a reaction term defined in terms of modified first order Bessel functions. An existence theory is provided here together with other qualitative properties of the solutions. Remarkably, each positive global minimum of the associated functional is one of such solutions. Moreover, we directly solve this non--smooth non--convex minimization problem using a convergent Proximal Point Algorithm. Numerical results based on synthetic and real MRI demonstrate a better performance of the proposed method when compared to previous TV based models for rician denoising which regularize or convexify the problem. Finally, an application on real Diffusion Tensor Images, a strongly affected by rician noise MRI modality, is presented and discussed.

math.AP↗

arXiv1996

Topological Inflation, without the Topology

We extend the `topological inflation' of Linde and Vilenkin to {\em unstable} monopoles. This allows the monopole to decay; not inflating eternally, as topological inflation demands. Such a situation happens naturally in some Grand Unified Theories --- such as supersymmetric flipped-$SU(5)$. We analyse analytically the dynamics of inflating monopoles to determine the equations governing the expansion, additionally recovering the bound on the scale of symmetry breaking found numerically by Sakai {\em et. al.} The latter half of this paper is devoted to the Cosmology of inflating unstable monopoles --- which is an example of an inhomogeneous cosmology. We describe how such a monopole may be formed and how long it inflates for --- finding it to be a random process. We then derive how cosmological parameters, such as density and temperature, are distributed at the end of inflation, and how the Universe reheats as the monopole decays. The general conclusion of this work is that such inflation creates a local region of relatively flat, homogenous and isotropic Universe surrounded by pre-GUT matter.

hep-ph↗