Fire Threat Detection From Videos with Q-Rough Sets

• URL: http://arxiv.org/abs/2101.08459v1
• Date: Thu, 21 Jan 2021 06:29:36 GMT
• Title: Fire Threat Detection From Videos with Q-Rough Sets
• Authors: Debarati B. Chakrabortya, Vinay Detania and Shah Parshv Jigneshkumar
• Abstract summary: Fire in control serves a number of purposes to human civilization, but it could simultaneously be a threat once its spread becomes uncontrolled. Here we focus on developing an unsupervised method with which the threat of fire can be quantified. All theories and indices defined here have been experimentally validated with different types of fire videos.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 region segmentation from video frames. The threat index of fire flame over the input video stream has been defined in sync with the relative growth in the fire segments on the recent frames. All theories and indices defined here have been experimentally validated with different types of fire videos, through demonstrations and comparisons, as superior to the state of the art.

Related papers

• AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning [93.77763753231338]
  Adversarial Contrastive Prompt Tuning (ACPT) is proposed to fine-tune the CLIP image encoder to extract similar embeddings for any two intermediate adversarial queries. We show that ACPT can detect 7 state-of-the-art query-based attacks with $>99%$ detection rate within 5 shots. We also show that ACPT is robust to 3 types of adaptive attacks.
  arXiv  Detail & Related papers  (2024-08-04T09:53:50Z)
• Prescribed Fire Modeling using Knowledge-Guided Machine Learning for Land Management [2.158876211806538]
  This paper introduces a novel machine learning (ML) framework that enables rapid emulation of prescribed fires. By incorporating domain knowledge, the proposed method helps reduce physical inconsistencies in fuel density estimates in data-scarce scenarios. We also overcome the problem of biased estimation of fire spread metrics by incorporating a hierarchical modeling structure.
  arXiv  Detail & Related papers  (2023-10-02T19:38:04Z)
• Blind Video Deflickering by Neural Filtering with a Flawed Atlas [90.96203200658667]
  We propose a general flicker removal framework that only receives a single flickering video as input without additional guidance. The core of our approach is utilizing the neural atlas in cooperation with a neural filtering strategy. To validate our method, we construct a dataset that contains diverse real-world flickering videos.
  arXiv  Detail & Related papers  (2023-03-14T17:52:29Z)
• Image-Based Fire Detection in Industrial Environments with YOLOv4 [53.180678723280145]
  This work looks into the potential of AI to detect and recognize fires and reduce detection time using object detection on an image stream. To our end, we collected and labeled appropriate data from several public sources, which have been used to train and evaluate several models based on the popular YOLOv4 object detector.
  arXiv  Detail & Related papers  (2022-12-09T11:32:36Z)
• Unsupervised Wildfire Change Detection based on Contrastive Learning [1.53934570513443]
  The accurate characterization of the severity of the wildfire event contributes to the characterization of the fuel conditions in fire-prone areas. The aim of this study is to develop an autonomous system built on top of high-resolution multispectral satellite imagery, with an advanced deep learning method for detecting burned area change.
  arXiv  Detail & Related papers  (2022-11-26T20:13:14Z)
• Wildfire risk forecast: An optimizable fire danger index [0.0]
  Wildfire events have caused severe losses in many places around the world and are expected to increase with climate change. Fire risk indices use weather forcing to make advanced predictions of the risk of fire. Predictions of fire risk indices can be used to allocate resources in places with high risk. We propose a novel implementation of one index (NFDRS IC) as a differentiable function in which one can optimize its internal parameters via gradient descent.
  arXiv  Detail & Related papers  (2022-03-28T14:08:49Z)
• Weakly-supervised fire segmentation by visualizing intermediate CNN layers [82.75113406937194]
  Fire localization in images and videos is an important step for an autonomous system to combat fire incidents. We consider weakly supervised segmentation of fire in images, in which only image labels are used to train the network. We show that in the case of fire segmentation, which is a binary segmentation problem, the mean value of features in a mid-layer of classification CNN can perform better than conventional Class Activation Mapping (CAM) method.
  arXiv  Detail & Related papers  (2021-11-16T11:56:28Z)
• Attention on Classification for Fire Segmentation [82.75113406937194]
  We propose a Convolutional Neural Network (CNN) for joint classification and segmentation of fire in images. We use a spatial self-attention mechanism to capture long-range dependency between pixels, and a new channel attention module which uses the classification probability as an attention weight.
  arXiv  Detail & Related papers  (2021-11-04T19:52:49Z)
• Aerial Imagery Pile burn detection using Deep Learning: the FLAME dataset [9.619617596045911]
  FLAME (Fire Luminosity Airborne-based Machine learning Evaluation) offers a dataset of aerial images of fires. This paper provides a fire image dataset collected by drones during a prescribed burning piled detritus in an Arizona pine forest. The paper also highlights solutions to two machine learning problems: Binary classification of video frames based on the presence [and absence] of fire flames.
  arXiv  Detail & Related papers  (2020-12-28T00:00:41Z)
• Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution [67.83074893311218]
  Kernel-based methods predict pixels with a single convolution process that convolves source frames with spatially adaptive local kernels. We propose enhanced deformable separable convolution (EDSC) to estimate not only adaptive kernels, but also offsets, masks and biases. We show that our method performs favorably against the state-of-the-art methods across a broad range of datasets.
  arXiv  Detail & Related papers  (2020-06-15T01:10:59Z)

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.