搜索结果：fire

We propose a method to reconstruct dynamic fire in 3D from a limited set of camera views with a Gaussian-based spatiotemporal representation. Capturing and reconstructing fire and its dynamics is highly challenging due to its volatile nature, transparent quality, and multitude of high-frequency features. Despite these challenges, we aim to reconstruct fire from only three views, which consequently requires solving for under-constrained geometry. We solve this by separating the static background from the dynamic fire region by combining dense multi-view stereo images with monocular depth priors. The fire is initialized as a 3D flow field, obtained by fusing per-view dense optical flow projections. To capture the high frequency features of fire, each 3D Gaussian encodes a lifetime and linear velocity to match the dense optical flow. To ensure sub-frame temporal alignment across cameras we employ a custom hardware synchronization pattern -- allowing us to reconstruct fire with affordable commodity hardware. Our quantitative and qualitative validations across numerous reconstruction experiments demonstrate robust performance for diverse and challenging real fire scenarios.

The Atlanta Fire Rescue Department (AFRD), like many municipal fire departments, actively works to reduce fire risk by inspecting commercial properties for potential hazards and fire code violations. However, AFRD's fire inspection practices relied on tradition and intuition, with no existing data-driven process for prioritizing fire inspections or identifying new properties requiring inspection. In collaboration with AFRD, we developed the Firebird framework to help municipal fire departments identify and prioritize commercial property fire inspections, using machine learning, geocoding, and information visualization. Firebird computes fire risk scores for over 5,000 buildings in the city, with true positive rates of up to 71% in predicting fires. It has identified 6,096 new potential commercial properties to inspect, based on AFRD's criteria for inspection. Furthermore, through an interactive map, Firebird integrates and visualizes fire incidents, property information and risk scores to help AFRD make informed decisions about fire inspections. Firebird has already begun to make positive impact at both local and national levels. It is improving AFRD's inspection processes and Atla

Quantum fire is a distribution of quantum states that can be efficiently cloned, but cannot be efficiently converted into a classical string. First considered by Nehoran and Zhandry (ITCS'24) and later formalized by Bostanci, Nehoran, Zhandry (STOC'25), quantum fire has strong applications and implications in cryptography, along with important connections to physics and complexity. However, constructing and proving the security of quantum fire so far has been elusive. Nehoran and Zhandry gave a construction relative to an inefficient quantum oracle. Later, Bostanci et al gave a candidate construction based on group actions, however, even in the oracle model they could only conjecture the security of their scheme, and were not able to prove security. In this work, we give a construction of public-key quantum fire relative to a classical oracle and prove its security unconditionally. Going further, we introduce two stronger notions that generalize it: Quantum key-fire where the clonable fire states serve as keys, and interactive (i.e. LOCC) security for quantum (key-)fire. We give a construction of quantum key-fire relative to a classical oracle and unconditionally prove that it sati

Wildland fires pose an increasingly serious problem in our society. The number and severity of these fires has been rising for many years. Wildfires pose direct threats to life and property as well as threats through ancillary effects like reduced air quality. The aim of this thesis is to develop techniques to help combat the impacts of wildfires by improving wildfire modeling capabilities by using satellite fire observations. Already much work has been done in this direction by other researchers. Our work seeks to expand the body of knowledge using mathematically sound methods to utilize information about wildfires that considers the uncertainties inherent in the satellite data. In this thesis we explore methods for using satellite data to help initialize and steer wildfire simulations. In particular, we develop a method for constructing the history of a fire, a new technique for assimilating wildfire data, and a method for modifying the behavior of a modeled fire by inferring information about the fuels in the fire domain. These goals rely on being able to estimate the time a fire first arrived at every location in a geographic region of interest. Because detailed knowledge of re

Fire has long been linked to human life, causing severe disasters and losses. Early detection is crucial, and with the rise of home IoT technologies, household fire detection systems have emerged. However, the lack of sufficient fire datasets limits the performance of detection models. We propose the SCU-CGAN model, which integrates U-Net, CBAM, and an additional discriminator to generate realistic fire images from nonfire images. We evaluate the image quality and confirm that SCU-CGAN outperforms existing models. Specifically, SCU-CGAN achieved a 41.5% improvement in KID score compared to CycleGAN, demonstrating the superior quality of the generated fire images. Furthermore, experiments demonstrate that the augmented dataset significantly improves the accuracy of fire detection models without altering their structure. For the YOLOv5 nano model, the most notable improvement was observed in the mAP@0.5:0.95 metric, which increased by 56.5%, highlighting the effectiveness of the proposed approach.

For the detection of fire-like targets in indoor, outdoor and forest fire images, as well as fire detection under different natural lights, an improved YOLOv5 fire detection deep learning algorithm is proposed. The YOLOv5 detection model expands the feature extraction network from three dimensions, which enhances feature propagation of fire small targets identification, improves network performance, and reduces model parameters. Furthermore, through the promotion of the feature pyramid, the top-performing prediction box is obtained. Fire-YOLOv5 attains excellent results compared to state-of-the-art object detection networks, notably in the detection of small targets of fire and smoke with mAP 90.5% and f1 score 88%. Overall, the Fire-YOLOv5 detection model can effectively deal with the inspection of small fire targets, as well as fire-like and smoke-like objects with F1 score 0.88. When the input image size is 416 x 416 resolution, the average detection time is 0.12 s per frame, which can provide real-time forest fire detection. Moreover, the algorithm proposed in this paper can also be applied to small target detection under other complicated situations. The proposed system shows

Most existing robot simulators prioritize rigid-body dynamics and photorealistic rendering, but largely neglect the thermally and optically complex phenomena that characterize real-world fire environments. For robots envisioned as future firefighters, this limitation hinders both reliable capability evaluation and the generation of representative training data prior to deployment in hazardous scenarios. To address these challenges, we introduce Fire as a Service (FaaS), a novel, asynchronous co-simulation framework that augments existing robot simulators with high-fidelity and computationally efficient fire simulations. Our pipeline enables robots to experience accurate, multi-species thermodynamic heat transfer and visually consistent volumetric smoke without disrupting high-frequency rigid-body control loops. We demonstrate that our framework can be integrated with diverse robot simulators to generate physically accurate fire behavior, benchmark thermal hazards encountered by robotic platforms, and collect realistic multimodal perceptual data. Crucially, its real-time performance supports human-in-the-loop teleoperation, enabling the successful training of reactive, multimodal po

Cell2Fire is a new cell-based forest and wildland landscape fire growth simulator that is open-source and exploits parallelism to support the modelling of fire growth cross large spatial and temporal scales in a timely manner. The fire environment is characterized by partitioning the landscape into a large number of cells each of which has specified fuel, weather, fuel moisture and topography attributes. Fire spread within each cell is assumed to be elliptical and governed by spread rates predicted by a fire spread model such as the Canadian Forest Fire Behavior Prediction (FBP) System. The simulator includes powerful statistical and graphical output and spatial analysis features to facilitate the display and analysis of projected fire growth. We validated Cell2Fire by using it to predict the growth of real and realistic hypothetical fires, comparing our fire growth predictions with those produced by the state-of-the-art Prometheus fire growth simulator. Cell2Fire is structured to facilitate its use for predicting the growth of individual fires or embedding it in landscape management simulation models. It can be used to produce probabilistic fire scar predictions by allowing for un

Fire emergencies can happen without warning and knowing how to respond quickly can save lives Unfortunately traditional fire drills can be disruptive costly and often fail to recreate the pressure of a real emergency This project introduces a Virtual Reality VR Fire Safety Training Application that gives people a safe yet realistic way to practice life saving skills Using a VR headset and motion controllers trainees step into a 3D world where fire hazards smoke and evacuation routes are brought to life They can learn how to use a fire extinguisher find safe exits and make decisions under pressure without any real danger The training adapts to the users skill level and tracks progress making it useful for beginners and experienced personnel alike By turning fire safety into an interactive experience this VR approach boosts confidence improves retention and makes learning both safer and more engaging

Across plant communities worldwide, fire regimes reflect a combination of climatic factors and plant characteristics. To shed new light on the complex relationships between plant characteristics and fire regimes, we developed a new conceptual, mechanistic model that includes plant competition, stochastic fires, and fire-vegetation feedback. Considering a single standing plant functional type, we observed that highly flammable and slowly colonizing plants can persist only when they have a strong fire response, while fast colonizing and less flammable plants can display a larger range of fire responses. At the community level, the fire response of the strongest competitor determines the existence of alternative ecological states, i.e. different plant communities, under the same environmental conditions. Specifically, when the strongest competitor had a very strong fire response, such as in Mediterranean forests, only one ecological state could be achieved. Conversely, when the strongest competitor was poorly fire-adapted, alternative ecological states emerged, for example between tropical humid savannas and forests, or between different types of boreal forests. These findings underli

The Fire We Share proposes a care-centered, consequence-aware visualization framework for engaging with wildfire data not as static metrics, but as living archives of ecological and social entanglement. By combining plants-inspired data forms, event-based mapping, and narrative layering, the project foregrounds fire as a shared temporal condition-one that cuts across natural cycles and human systems. Rather than simplifying wildfire data into digestible visuals, The Fire We Share reimagines it as a textured, wounded archive-embodied, relational, and radically ethical.

Fires and burning are the chief causes of particulate matter (PM2.5), a key measurement of air quality in communities and cities worldwide. This work develops a live fire tracking platform to show active reported fires from over twenty cities in the U.S., as well as predict their smoke paths and impacts on the air quality of regions within their range. Specifically, our close to real-time tracking and predictions culminates in a digital twin to protect public health and inform the public of fire and air quality risk. This tool tracks fire incidents in real-time, utilizes the 3D building footprints of Austin to simulate smoke outputs, and predicts fire incident smoke falloffs within the complex city environment. Results from this study include a complete fire and smoke digital twin model for Austin. We work in cooperation with the City of Austin Fire Department to ensure the accuracy of our forecast and also show that air quality sensor density within our cities cannot validate urban fire presence. We additionally release code and methodology to replicate these results for any city in the world. This work paves the path for similar digital twin models to be developed and deployed to

Wildfire is an important system process of the earth that occurs across a wide range of spatial and temporal scales. A variety of methods have been used to predict wildfire phenomena during the past century to better our understanding of fire processes and to inform fire and land management decision-making. Statistical methods have an important role in wildfire prediction due to the inherent stochastic nature of fire phenomena at all scales. Predictive models have exploited several sources of data describing fire phenomena. Experimental data are scarce; observational data are dominated by statistics compiled by government fire management agencies, primarily for administrative purposes and increasingly from remote sensing observations. Fires are rare events at many scales. The data describing fire phenomena can be zero-heavy and nonstationary over both space and time. Users of fire modeling methodologies are mainly fire management agencies often working under great time constraints, thus, complex models have to be efficiently estimated. We focus on providing an understanding of some of the information needed for fire management decision-making and of the challenges involved in predi

The increasing frequency and severity of wildfires highlight the need for accurate fire and plume spread models. We introduce an approach that effectively isolates and tracks fire and plume behavior across various spatial and temporal scales and image types, identifying physical phenomena in the system and providing insights useful for developing and validating models. Our method combines image segmentation and graph theory to delineate fire fronts and plume boundaries. We demonstrate that the method effectively distinguishes fires and plumes from visually similar objects. Results demonstrate the successful isolation and tracking of fire and plume dynamics across various image sources, ranging from synoptic-scale ($10^4$-$10^5$ m) satellite images to sub-microscale ($10^0$-$10^1$ m) images captured close to the fire environment. Furthermore, the methodology leverages image inpainting and spatio-temporal dataset generation for use in statistical and machine learning models.

Currently available satellite active fire detection products from the VIIRS and MODIS instruments on polar-orbiting satellites produce detection squares in arbitrary locations. There is no global fire/no fire map, no detection under cloud cover, false negatives are common, and the detection squares are much coarser than the resolution of a fire behavior model. Consequently, current active fire satellite detection products should be used to improve fire modeling in a statistical sense only, rather than as a direct input. We describe a new data assimilation method for active fire detection, based on a modification of the fire arrival time to simultaneously minimize the difference from the forecast fire arrival time and maximize the likelihood of the fire detection data. This method is inspired by contour detection methods used in computer vision, and it can be cast as a Bayesian inverse problem technique, or a generalized Tikhonov regularization. After the new fire arrival time on the whole simulation domain is found, the model can be re-run from a time in the past using the new fire arrival time to generate the heat fluxes and to spin up the atmospheric model until the satellite ove

The current WRF-Fire model starts the fire from a given ignition point at a given time. We want to start the model from a given fire perimeter at a given time instead. However, the fuel balance and the state of the atmosphere depend on the history of the fire. The purpose of this work is to create an approximate artificial history of the fire based on the given fire perimeter and time and an approximate ignition point and time. Replaying the fire history then establishes a reasonable fuel balance and outputs heat fluxes into the atmospheric model, which allow the atmospheric circulation to develop. Then the coupled atmosphere-fire model takes over. In this preliminary investigation, the ignition times in the fire area are calculated based on the distance from the ignition point to the perimeter, assuming that the perimeter is convex or star-shaped. Simulation results for an ideal example show that the fire can continue in a natural way from the perimeter. Possible extensions include algorithms for more general perimeters and running the fire model backwards in time from the perimeter to create a more realistic history. The model used extends WRF-Fire and it is available from openwf

This article defines new methods for unsupervised fire region segmentation and fire threat detection from video stream. Fire in control serves a number of purposes to human civilization, but it could simultaneously be a threat once its spread becomes uncontrolled. There exists many methods on fire region segmentation and fire non-fire classification. But the approaches to determine the threat associated with fire is relatively scare, and no such unsupervised method has been formulated yet. Here we focus on developing an unsupervised method with which the threat of fire can be quantified and accordingly generate an alarm in automated surveillance systems in indoor as well as in outdoors. Fire region segmentation without any manual intervention/ labelled data set is a major challenge while formulating such a method. Here we have used rough approximations to approximate the fire region, and to manage the incompleteness of the knowledge base, due to absence of any prior information. Utility maximization of Q-learning has been used to minimize ambiguities in the rough approximations. The new set approximation method, thus developed here, is named as Q-rough set. It is used for fire regi

We describe the second data release (DR2) of the FIRE-2 cosmological zoom-in simulations of galaxy formation, from the Feedback In Realistic Environments (FIRE) project, available at http://flathub.flatironinstitute.org/fire. DR2 includes all snapshots for most simulations, starting at z ~ 99, with all snapshot time spacings <~ 25 Myr. The Core suite -- comprising 14 Milky Way-mass galaxies, 5 SMC/LMC-mass galaxies, and 4 lower-mass galaxies -- includes 601 snapshots to z = 0. For the Core suite, we also release resimulations with physics variations: (1) dark-matter-only versions; (2) a modified ultraviolet background with later reionization at z = 7.8; (3) magnetohydrodynamics, anisotropic conduction, and viscosity in gas; and (4) a model for cosmic-ray injection, transport, and feedback (assuming a constant diffusion coefficient). The Massive Halo suite now includes 8 massive galaxies with 278 snapshots to z = 1. The High Redshift suite includes 34 simulations: in addition to the 22 simulations run to z = 5, we now include 12 additional simulations run to z = 7 and z = 9. We also release 4 dark-matter-only cosmological boxes used to generate zoom-in initial conditions for many

There are many wildfire behaviors of increasing relevance that are outside the forecast capabilities of even the most sophisticated operational fire spread and fire behavior model. The limitations of the operational models are due primarily to their inability to represent coupled fire-atmosphere interactions. Coupled wildfire-atmosphere models are physics-based fluid-dynamical prognostic models of wildfire spread and behavior that attempt an almost complete representation of fire-atmosphere interactions. This level of fidelity however means that these models cannot be used operationally. The reason is that, despite ever increasing computational resources, the complexity and range of processes and scales (1 mm to 100 km) involved in this modeling approach make computational costs prohibitively expensive. In this study we propose an intermediate approach. A physics-based coupled atmosphere-fire model is used to resolve the large-scale and local weather as well as the atmosphere-fire interactions, while combustion is represented simply using an existing operational surface fire behavior model. This model combination strikes a balance between fidelity and speed of execution. The feasib