Estimating temperatures with low-cost infrared cameras using deep neural networks

• URL: http://arxiv.org/abs/2307.12130v2
• Date: Sun, 14 Jan 2024 19:53:23 GMT
• Title: Estimating temperatures with low-cost infrared cameras using deep neural networks
• Authors: Navot Oz, Nir Sochen, David Mendelovich, Iftach Klapp
• Abstract summary: A nonuniformity simulator that accounts for the ambient temperature was developed. An end-to-end neural network that incorporates both the physical model of the camera and the ambient camera temperature was introduced.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Low-cost thermal cameras are inaccurate (usually $\pm 3^\circ C$) and have space-variant nonuniformity across their detector. Both inaccuracy and nonuniformity are dependent on the ambient temperature of the camera. The goal of this work was to estimate temperatures with low-cost infrared cameras, and rectify the nonuniformity. A nonuniformity simulator that accounts for the ambient temperature was developed. An end-to-end neural network that incorporates both the physical model of the camera and the ambient camera temperature was introduced. The neural network was trained with the simulated nonuniformity data to estimate the object's temperature and correct the nonuniformity, using only a single image and the ambient temperature measured by the camera itself. Results of the proposed method significantly improved the mean temperature error compared to previous works by up to $0.5^\circ C$. In addition, constraining the physical model of the camera with the network lowered the error by an additional $0.1^\circ C$. The mean temperature error over an extensive validation dataset was $0.37^\circ C$. The method was verified on real data in the field and produced equivalent results.

Related papers

• Rotational Odometry using Ultra Low Resolution Thermal Cameras [1.3986052523534573]
  This letter provides what is, to the best of our knowledge, a first study on the applicability of ultra-low-resolution thermal cameras for rotational odometry measurements. Our use of an ultra-low-resolution thermal camera instead of other modalities such as an RGB camera is motivated by its robustness to lighting conditions. Experiments and ablation studies are conducted for determining the impact of thermal camera resolution and the number of successive frames on the CNN estimation precision.
  arXiv  Detail & Related papers  (2024-11-02T12:15:32Z)
• Simultaneous temperature estimation and nonuniformity correction from multiple frames [0.0]
  Low-cost microbolometer-based IR cameras are prone to spatially nonuniformity and to drift in temperature measurements. We propose a novel approach for simultaneous temperature estimation and nonuniformity correction (NUC) from multiple frames captured by low-cost microbolometer cameras.
  arXiv  Detail & Related papers  (2023-07-23T11:28:25Z)
• Long Horizon Temperature Scaling [90.03310732189543]
  Long Horizon Temperature Scaling (LHTS) is a novel approach for sampling from temperature-scaled joint distributions. We derive a temperature-dependent LHTS objective, and show that finetuning a model on a range of temperatures produces a single model capable of generation with a controllable long horizon temperature parameter.
  arXiv  Detail & Related papers  (2023-02-07T18:59:32Z)
• Sample-dependent Adaptive Temperature Scaling for Improved Calibration [95.7477042886242]
  Post-hoc approach to compensate for neural networks being wrong is to perform temperature scaling. We propose to predict a different temperature value for each input, allowing us to adjust the mismatch between confidence and accuracy. We test our method on the ResNet50 and WideResNet28-10 architectures using the CIFAR10/100 and Tiny-ImageNet datasets.
  arXiv  Detail & Related papers  (2022-07-13T14:13:49Z)
• Steady-state microwave mode cooling with a diamond NV ensemble [1.1545092788508224]
  An electromagnetic mode with frequency $omega$ in the microwave band has a significant thermal photon occupation at room temperature. This variance sets the measurement noise floor in applications ranging from wireless communications to positioning, navigation, and timing to magnetic resonance imaging. We overcome this barrier in continuously cooling a $sim 3$ GHz cavity mode by coupling it to an ensemble of optically spin-polarized nitrogen-vacancy centers in a room-temperature diamond.
  arXiv  Detail & Related papers  (2022-03-07T15:25:24Z)
• In-Bed Person Monitoring Using Thermal Infrared Sensors [53.561797148529664]
  We use 'Griddy', a prototype with a Panasonic Grid-EYE, a low-resolution infrared thermopile array sensor, which offers more privacy. For this purpose, two datasets were captured, one (480 images) under constant conditions, and a second one (200 images) under different variations. We test three machine learning algorithms: Support Vector Machines (SVM), k-Nearest Neighbors (k-NN) and Neural Network (NN)
  arXiv  Detail & Related papers  (2021-07-16T15:59:07Z)
• Lidar Light Scattering Augmentation (LISA): Physics-based Simulation of Adverse Weather Conditions for 3D Object Detection [60.89616629421904]
  Lidar-based object detectors are critical parts of the 3D perception pipeline in autonomous navigation systems such as self-driving cars. They are sensitive to adverse weather conditions such as rain, snow and fog due to reduced signal-to-noise ratio (SNR) and signal-to-background ratio (SBR)
  arXiv  Detail & Related papers  (2021-07-14T21:10:47Z)
• Role of topology in determining the precision of a finite thermometer [58.720142291102135]
  We find that low connectivity is a resource to build precise thermometers working at low temperatures. We compare the precision achievable by position measurement to the optimal one, which itself corresponds to energy measurement.
  arXiv  Detail & Related papers  (2021-04-21T17:19:42Z)
• Tensor Network for Supervised Learning at Finite Temperature [1.4717465036484292]
  finite temperature tensor network (FTTN) imports thermal perturbation into matrix product states framework. FTTN regards it as thermal loss computed from entanglement with environment. Temperature-like parameter can be automatically optimized, which gives each database an individual temperature.
  arXiv  Detail & Related papers  (2021-04-09T05:02:36Z)
• Thermal Prediction for Efficient Energy Management of Clouds using Machine Learning [31.735983199708013]
  We study data from a private cloud and show the presence of thermal variations. We propose a gradient boosting machine learning model for temperature prediction. In addition, we propose a dynamic scheduling algorithm to minimize the peak temperature of hosts.
  arXiv  Detail & Related papers  (2020-11-07T00:55:47Z)
• Deep learning for gravitational-wave data analysis: A resampling white-box approach [62.997667081978825]
  We apply Convolutional Neural Networks (CNNs) to detect gravitational wave (GW) signals of compact binary coalescences, using single-interferometer data from LIGO detectors. CNNs were quite precise to detect noise but not sensitive enough to recall GW signals, meaning that CNNs are better for noise reduction than generation of GW triggers.
  arXiv  Detail & Related papers  (2020-09-09T03:28:57Z)

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.