FlameFinder: Illuminating Obscured Fire through Smoke with Attentive Deep Metric Learning

• URL: http://arxiv.org/abs/2404.06653v1
• Date: Tue, 9 Apr 2024 23:24:19 GMT
• Title: FlameFinder: Illuminating Obscured Fire through Smoke with Attentive Deep Metric Learning
• Authors: Hossein Rajoli, Sahand Khoshdel, Fatemeh Afghah, Xiaolong Ma,
• Abstract summary: FlameFinder is designed to accurately detect flames, even when obscured by smoke, using thermal images from firefighter drones during wildfire monitoring. Traditional RGB cameras struggle in such conditions, but thermal cameras can capture smoke-obscured flame features. To address this issue, FlameFinder utilizes paired thermal-RGB images for training. By learning latent flame features from smoke-free samples, the model becomes less biased towards relative thermal gradients.
• Score: 11.218765140036254
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: FlameFinder is a deep metric learning (DML) framework designed to accurately detect flames, even when obscured by smoke, using thermal images from firefighter drones during wildfire monitoring. Traditional RGB cameras struggle in such conditions, but thermal cameras can capture smoke-obscured flame features. However, they lack absolute thermal reference points, leading to false positives.To address this issue, FlameFinder utilizes paired thermal-RGB images for training. By learning latent flame features from smoke-free samples, the model becomes less biased towards relative thermal gradients. In testing, it identifies flames in smoky patches by analyzing their equivalent thermal-domain distribution. This method improves performance using both supervised and distance-based clustering metrics.The framework incorporates a flame segmentation method and a DML-aided detection framework. This includes utilizing center loss (CL), triplet center loss (TCL), and triplet cosine center loss (TCCL) to identify optimal cluster representatives for classification. However, the dominance of center loss over the other losses leads to the model missing features sensitive to them. To address this limitation, an attention mechanism is proposed. This mechanism allows for non-uniform feature contribution, amplifying the critical role of cosine and triplet loss in the DML framework. Additionally, it improves interpretability, class discrimination, and decreases intra-class variance. As a result, the proposed model surpasses the baseline by 4.4% in the FLAME2 dataset and 7% in the FLAME3 dataset for unobscured flame detection accuracy. Moreover, it demonstrates enhanced class separation in obscured scenarios compared to VGG19, ResNet18, and three backbone models tailored for flame detection.

Related papers

• Machine Learning-based Layer-wise Detection of Overheating Anomaly in LPBF using Photodiode Data [0.0]
  This research focuses on the detection of overheating anomalies using photodiode sensor data. Photodiode sensors can collect high-frequency data from the melt pool, reflecting the process dynamics and thermal history. The proposed method offers a machine learning framework to utilize photodiode sensor data for layer-wise detection of overheating anomalies.
  arXiv  Detail & Related papers  (2024-03-20T01:12:44Z)
• Obscured Wildfire Flame Detection By Temporal Analysis of Smoke Patterns Captured by Unmanned Aerial Systems [0.799536002595393]
  This research paper addresses the challenge of detecting obscured wildfires in real-time using drones equipped only with RGB cameras. We propose a novel methodology that employs semantic segmentation based on the temporal analysis of smoke patterns in video sequences.
  arXiv  Detail & Related papers  (2023-06-30T19:45:43Z)
• FSDNet-An efficient fire detection network for complex scenarios based on YOLOv3 and DenseNet [8.695064779659031]
  This paper proposes a fire detection network called FSDNet (Fire Smoke Detection Network), which consists of a feature extraction module, a fire classification module, and a fire detection module. The accuracy of FSDNet on the two benchmark datasets is 99.82% and 91.15%, respectively, and the average precision on MS-FS is 86.80%, which is better than the mainstream fire detection methods.
  arXiv  Detail & Related papers  (2023-04-15T15:46:08Z)
• 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)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• 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)
• Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning [64.92447072894055]
  Infrared (IR) cameras are robust under adverse illumination and lighting conditions. We propose an algorithm meta-learning framework to improve existing UDA methods. We produce a state-of-the-art thermal detector for the KAIST and DSIAC datasets.
  arXiv  Detail & Related papers  (2021-10-07T02:28:18Z)
• Estimation of excess air coefficient on coal combustion processes via gauss model and artificial neural network [0.0]
  The relationship between the flame image obtained by a CCD camera and the excess air coefficient (lambda) has been modelled. A multilayer artificial neural network (ANN) has been used for the matching of feature-lambda.
  arXiv  Detail & Related papers  (2021-07-23T18:47:56Z)
• Comparing ML based Segmentation Models on Jet Fire Radiation Zone [0.0]
  characterization of fire accidents is important from a risk management point of view. One such characterization would be the segmentation of different radiation zones within the flame. A data set of propane jet fires is used to train and evaluate the different approaches.
  arXiv  Detail & Related papers  (2021-07-07T19:52:52Z)
• Towards High Performance Human Keypoint Detection [87.1034745775229]
  We find that context information plays an important role in reasoning human body configuration and invisible keypoints. Inspired by this, we propose a cascaded context mixer ( CCM) which efficiently integrates spatial and channel context information. To maximize CCM's representation capability, we develop a hard-negative person detection mining strategy and a joint-training strategy. We present several sub-pixel refinement techniques for postprocessing keypoint predictions to improve detection accuracy.
  arXiv  Detail & Related papers  (2020-02-03T02:24:51Z)

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.