Reliable Smoke Detection via Optical Flow-Guided Feature Fusion and Transformer-Based Uncertainty Modeling

• URL: http://arxiv.org/abs/2508.14597v1
• Date: Wed, 20 Aug 2025 10:28:53 GMT
• Title: Reliable Smoke Detection via Optical Flow-Guided Feature Fusion and Transformer-Based Uncertainty Modeling
• Abstract summary: Smoke plumes exhibit complex dynamics influenced by illumination variability, flow kinematics, and environmental noise.<n>We propose an information-fusion framework by integrating smoke feature representations extracted from monocular imagery.<n>A Two-Phase Uncertainty-Aware Shifted Windows Transformer is proposed for robust and reliable smoke detection.
• Score: 6.270500509647152
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Fire outbreaks pose critical threats to human life and infrastructure, necessitating high-fidelity early-warning systems that detect combustion precursors such as smoke. However, smoke plumes exhibit complex spatiotemporal dynamics influenced by illumination variability, flow kinematics, and environmental noise, undermining the reliability of traditional detectors. To address these challenges without the logistical complexity of multi-sensor arrays, we propose an information-fusion framework by integrating smoke feature representations extracted from monocular imagery. Specifically, a Two-Phase Uncertainty-Aware Shifted Windows Transformer for robust and reliable smoke detection, leveraging a novel smoke segmentation dataset, constructed via optical flow-based motion encoding, is proposed. The optical flow estimation is performed with a four-color-theorem-inspired dual-phase level-set fractional-order variational model, which preserves motion discontinuities. The resulting color-encoded optical flow maps are fused with appearance cues via a Gaussian Mixture Model to generate binary segmentation masks of the smoke regions. These fused representations are fed into the novel Shifted-Windows Transformer, which is augmented with a multi-scale uncertainty estimation head and trained under a two-phase learning regimen. First learning phase optimizes smoke detection accuracy, while during the second phase, the model learns to estimate plausibility confidence in its predictions by jointly modeling aleatoric and epistemic uncertainties. Extensive experiments using multiple evaluation metrics and comparative analysis with state-of-the-art approaches demonstrate superior generalization and robustness, offering a reliable solution for early fire detection in surveillance, industrial safety, and autonomous monitoring applications.

Related papers

• TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors [76.4118981404995]
  Trajectory-Injected Generative Attack (TIGA) is a source-image-free and training free framework that generates detector-evasive images.<n>TIGA steers the latent Denoising Diffusion Implicit Model (DDIM) trajectory so that adversarial properties emerge during generation.<n>TIGA achieves strong blackbox attack performance, transferability, and high robustness under common post-processing operations.
  arXiv  Detail & Related papers  (2026-07-28T15:51:39Z)
• FlowPainter: Inpainting Optical Flow via Confidence-Guided Completion [52.3830227666301]
  FlowPainter is a diffusion-based optical flow framework that reformulates dense-flow generation as confidence-guided soft inpainting.<n>Our approach offers a practical way to integrate reliable discriminative priors with diffusion-based refinement for optical flow estimation.
  arXiv  Detail & Related papers  (2026-07-11T05:59:22Z)
• A Dual-Stream Challenge-Response Protocol for Ocular Liveness Verification [0.0]
  Ocular biometric systems face sophisticated presentation attacks, including high-resolution video replays and real-time generative deepfakes.<n>This paper proposes a dual-stream challenge-response framework for ocular liveness verification.<n>We show that a multi-round challenge design improves the detection of generative deepfakes when a non-zero-latency rendering gap exists.
  arXiv  Detail & Related papers  (2026-07-10T18:15:23Z)
• Uncertainty-Driven Anomaly Detection for Psychotic Relapse Using Smartwatches: Forecasting and Multi-Task Learning Fusion [17.706122087921038]
  We develop and systematically study two smartwatch-based frameworks for daily relapse detection.<n>The first forecasts cardiac dynamics and flags deviations between predicted and observed features as indicators of abnormality.<n>The second adopts a multi-task formulation that fuses sleep with motion and cardiac-derived signals.
  arXiv  Detail & Related papers  (2026-05-13T17:43:07Z)
• EoCD: Encoder only Remote Sensing Change Detection [49.58758681798801]
  We introduce encoder only change detection (EoCD) that is a simple and effective method for the change detection task.<n>The proposed method performs the early fusion of the temporal data and replaces the decoder with a parameter-free multiscale feature fusion module.<n>EoCD demonstrate the optimal balance between the change detection performance and the prediction speed across a variety of encoder architectures.
  arXiv  Detail & Related papers  (2026-02-05T16:58:42Z)
• Rethinking Cross-Generator Image Forgery Detection through DINOv3 [62.80415066351157]
  Cross-generator detection has emerged as a new challenge forgenerative models.<n>We show that frozen visual foundation models, especially DINOv3, already exhibit strong cross-generator detection capability.<n>We introduce a training-free token-ranking strategy followed by a lightweight linear probe to select a small subset of authenticity-relevant tokens.
  arXiv  Detail & Related papers  (2025-11-27T14:01:50Z)
• Diffuse to Detect: A Generalizable Framework for Anomaly Detection with Diffusion Models Applications to UAVs and Beyond [2.4449457537548036]
  Anomaly detection in complex, high-dimensional data, such as UAV sensor readings, is essential for operational safety.<n>We propose the Diffuse to Detect (DTD) framework, a novel approach that adapts diffusion models for anomaly detection.<n>DTD employs a single-step diffusion process to predict noise patterns, enabling rapid and precise identification of anomalies without reconstruction errors.
  arXiv  Detail & Related papers  (2025-10-27T02:08:08Z)
• Is It Certainly a Deepfake? Reliability Analysis in Detection & Generation Ecosystem [3.997629738288533]
  We present the first comprehensive uncertainty analysis of deepfake detectors.<n>We investigate how generative artifacts influence prediction confidence.<n>Based on our observations, the uncertainty manifold holds enough consistent information to leverage uncertainty for deepfake source detection.
  arXiv  Detail & Related papers  (2025-09-22T09:09:13Z)
• Solving Inverse Problems with FLAIR [59.02385492199431]
  Flow-based latent generative models are able to generate images with remarkable quality, even enabling text-to-image generation.<n>We present FLAIR, a novel training free variational framework that leverages flow-based generative models as a prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• Understanding and Improving Training-Free AI-Generated Image Detections with Vision Foundation Models [68.90917438865078]
  Deepfake techniques for facial synthesis and editing pose serious risks for generative models.<n>In this paper, we investigate how detection performance varies across model backbones, types, and datasets.<n>We introduce Contrastive Blur, which enhances performance on facial images, and MINDER, which addresses noise type bias, balancing performance across domains.
  arXiv  Detail & Related papers  (2024-11-28T13:04:45Z)
• Open-Set Deepfake Detection: A Parameter-Efficient Adaptation Method with Forgery Style Mixture [58.60915132222421]
  We introduce an approach that is both general and parameter-efficient for face forgery detection. We design a forgery-style mixture formulation that augments the diversity of forgery source domains. We show that the designed model achieves state-of-the-art generalizability with significantly reduced trainable parameters.
  arXiv  Detail & Related papers  (2024-08-23T01:53:36Z)
• StealthDiffusion: Towards Evading Diffusion Forensic Detection through Diffusion Model [62.25424831998405]
  StealthDiffusion is a framework that modifies AI-generated images into high-quality, imperceptible adversarial examples. It is effective in both white-box and black-box settings, transforming AI-generated images into high-quality adversarial forgeries.
  arXiv  Detail & Related papers  (2024-08-11T01:22:29Z)
• Dynamical Mode Recognition of Coupled Flame Oscillators by Supervised and Unsupervised Learning Approaches [7.088178570214894]
  Combustion instability is one of the most challenging problems in combustion research. Identifying and understanding combustion instability is essential to ensure the safe and reliable operation of many combustion systems.
  arXiv  Detail & Related papers  (2024-04-27T06:44:39Z)
• A Dual Attentive Generative Adversarial Network for Remote Sensing Image Change Detection [6.906936669510404]
  We propose a dual attentive generative adversarial network for achieving very high-resolution remote sensing image change detection tasks. The DAGAN framework has better performance with 85.01% mean IoU and 91.48% mean F1 score than advanced methods on the LEVIR dataset.
  arXiv  Detail & Related papers  (2023-10-03T08:26:27Z)
• The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation [42.48819460873482]
  Denoising diffusion probabilistic models have transformed image generation with their impressive fidelity and diversity. We show that they also excel in estimating optical flow and monocular depth, surprisingly, without task-specific architectures and loss functions.
  arXiv  Detail & Related papers  (2023-06-02T21:26:20Z)
• Transmission-Guided Bayesian Generative Model for Smoke Segmentation [29.74065829663554]
  Deep neural networks are prone to be overconfident for smoke segmentation due to its non-rigid shape and transparent appearance. This is caused by both knowledge level uncertainty due to limited training data for accurate smoke segmentation and labeling level uncertainty representing the difficulty in labeling ground-truth. We introduce a Bayesian generative model to simultaneously estimate the posterior distribution of model parameters and its predictions. We also contribute a high-quality smoke segmentation dataset, SMOKE5K, consisting of 1,400 real and 4,000 synthetic images with pixel-wise annotation.
  arXiv  Detail & Related papers  (2023-03-02T01:48:05Z)
• Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection [65.30079184700755]
  This study addresses the issue of fusing infrared and visible images that appear differently for object detection. Previous approaches discover commons underlying the two modalities and fuse upon the common space either by iterative optimization or deep networks. This paper proposes a bilevel optimization formulation for the joint problem of fusion and detection, and then unrolls to a target-aware Dual Adversarial Learning (TarDAL) network for fusion and a commonly used detection network.
  arXiv  Detail & Related papers  (2022-03-30T11:44:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.