Dynamic Group Difference Coding Based on Thermal Infrared Face Image for Fever Screening

Recently, noncontact temperature measurement methods based on infrared face perception have received widely attentions since fever screening plays an important role in the early prediction of respiratory infections, such as SARS, H1N1, and COVID-19. However, the performance of these methods always significantly degrades when facing the changes of environment. Thus, the majority of these methods leverage the block-body and sensors to reduce the influence of environment changes. It is a pity that the increased instrument complexity leads to higher costs and failure rate. To address the aforementioned issues, this article presents a novel fever screening method, named dynamic group difference coding (DGDC), which is based on the analysis about the influencing factors. The key idea of DGDC is to compute the temperature differences between the target person and the recently passed crowd (dynamic group). Specifically, we develop the face temperature encoder (FTE) to describe the face temperature and thus construct the difference matrix of the embedding feature between the target person and the dynamic group. Multilayer perceptions (MLP) are employed to capture the intrinsic information by characterizing the difference matrix in vertical and horizontal directions, respectively. Finally, we provide a dataset of thermal infrared face (TIF) images and conduct extensive experiments to demonstrate the advantages of the proposed method over the competing methods. © 1963-2012 IEEE.

Dynamic Group Difference Coding Based on Thermal Infrared Face Image for Fever Screening

Recently, noncontact temperature measurement methods based on infrared face perception have received widely attentions since fever screening plays an important role in the early prediction of respiratory infections, such as SARS, H1N1, and COVID-19. However, the performance of these methods always significantly degrades when facing the changes of environment. Thus, the majority of these methods leverage the block-body and sensors to reduce the influence of environment changes. It is a pity that the increased instrument complexity leads to higher costs and failure rate. To address the aforementioned issues, this article presents a novel fever screening method, named dynamic group difference coding (DGDC), which is based on the analysis about the influencing factors. The key idea of DGDC is to compute the temperature differences between the target person and the recently passed crowd (dynamic group). Specifically, we develop the face temperature encoder (FTE) to describe the face temperature and thus construct the difference matrix of the embedding feature between the target person and the dynamic group. Multilayer perceptions (MLP) are employed to capture the intrinsic information by characterizing the difference matrix in vertical and horizontal directions, respectively. Finally, we provide a dataset of thermal infrared face (TIF) images and conduct extensive experiments to demonstrate the advantages of the proposed method over the competing methods.

Automated Thermal Screening for COVID-19 Using Machine Learning

In the last two years, millions of lives have been lost due to COVID-19. Despite the vaccination programmes for a year, hospitalization rates and deaths are still high due to the new variants of COVID-19. Stringent guidelines and COVID-19 screening measures such as temperature check and mask check at all public places are helping reduce the spread of COVID-19. Visual inspections to ensure these screening measures can be taxing and erroneous. Automated inspection ensures an effective and accurate screening. Traditional approaches involve identification of faces and masks from visual camera images followed by extraction of temperature values from thermal imaging cameras. Use of visual imaging as a primary modality limits these applications only for good-lighting conditions. The use of thermal imaging alone for these screening measures makes the system invariant to illumination. However, lack of open source datasets is an issue to develop such systems. In this paper, we discuss our work on using machine learning over thermal video streams for face and mask detection and subsequent temperature screening in a passive non-invasive way that enables an effective automated COVID-19 screening method in public places. We open source our NTIC dataset that was used for training our models and was collected at 8 different locations. Our results show that the use of thermal imaging is as effective as visual imaging in the presence of high illumination. This performance stays the same for thermal images even under low-lighting conditions, whereas the performance with visual trained classifiers show more than 50% degradation. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

(FS)-S-3: Free Flow Fever Screening

Identification of people with elevated body temperature can reduce or dramatically slow down the spread of infectious diseases like COVID-19. We present a novel fever-screening system, (FS)-S-3, that uses edge machine learning techniques to accurately measure core body temperatures of multiple individuals in a free-flow setting. (FS)-S-3 performs real-time sensor fusion of visual camera with thermal camera data streams to detect elevated body temperature, and it has several unique features: (a) visual and thermal streams represent very different modalities, and we dynamically associate semantically-equivalent regions across visual and thermal frames by using a new, dynamic alignment technique that analyzes content and context in real-time, (b) we track people through occlusions, identify the eye (inner canthus), forehead, face and head regions where possible, and provide an accurate temperature reading by using a prioritized refinement algorithm, and (c) we robustly detect elevated body temperature even in the presence of personal protective equipment like masks, or sunglasses or hats, all of which can be affected by hot weather and lead to spurious temperature readings. (FS)-S-3 has been deployed at over a dozen large commercial establishments, providing contact-less, free-flow, real-time fever screening for thousands of employees and customers in indoors and outdoor settings.

Accurate and Contactless COVID-19 Fever Screening and Attendance Tracking System

Over the past two years, COVID-19 has led to and is still leading to lots of deaths to date. Many industries have been affected by that, and governments have united in finding ways to mitigate the spread of the disease, thus leading life to return to normal. There are several ways that were followed to do that, such as social distancing, thermal screening, and virtual communication. Thermal screening has proven its practicality in certain entities that require face-to-face contact. Researchers have been contributing to finding effective ways to develop screening methods to help re-accelerate the learning process. This paper proposes a fever screening system to record and track individuals' temperature and an attendance tracking system for educational institutions. The system measures the individual's temperature and records it, and saves their attendance in a database. After completing the measurement taking of an individual, the system uses a buzzer to inform the following individual that it is their turn. This allows the institution to monitor any temperature spikes among the individuals while recording their attendance without close contact at the entrance. Our results validate the usefulness and potential of our system as a fever screening and attendance tracking tool. It also opens the door for further development, allowing regular operation in educational institutions during any upcoming pandemics. © 2022 IEEE.

Detecting Essential Landmarks Directly in Thermal Images for Remote Body Temperature and Respiratory Rate Measurement With a Two-Phase System

Infrared thermographs (IRTs, also called thermal cameras) have been used to remotely measure elevated body temperature (BT) and respiratory rate (RR) during infectious disease outbreaks, such as COVID-19. To facilitate the fast measurement of BT and RR using IRTs in densely populated venues, it is desirable to have IRT algorithms that can automatically identify the best facial locations in thermal images to extract these vital signs. The IEC 80601-2-59:2017 standard suggests that the regions medially adjacent to the inner canthi of the eyes are robust BT measurement sites. The nostril regions, on the other hand, are often used for RR estimation. However, it is more difficult to automatically identify inner canthi and nostrils in thermal images than in visible-light images, which are rich with exploitable features. In this paper, a unique system that can detect inner canthi and outer nostril edges directly in thermal images in two phases is introduced. In Phase I, original thermal images were processed in four different ways to enhance facial features to facilitate inner canthus and nostril detection. In Phase II, landmarks of the inner canthi and outer nostril edges were detected in two steps: (1) face detection using the Single Shot Multibox Detector (SSD) and (2) facial landmark detection to locate the inner canthi and outer nostril edges. The face detection, facial landmark detection, and overall system accuracies were evaluated using the intersection over union, normalized Euclidean distance, and success detection rate metrics on a set of 36 thermal images collected from 12 subjects using three different IRTs. Additional validation was performed on a subset of 40 random thermal images from the publicly available Tufts Face Database. The results revealed that the processed images - referred to as ICLIP images - yielded the highest landmark localization accuracy from the four types of processed thermal images, verifying that the system can automatically and accurately estimate the inner canthus and nostril locations in thermal images. The proposed system can be applied in IRT algorithms to provide reliable temperature measurements and RR estimates during infectious disease outbreaks. © 2013 IEEE.

Studying the accuracy of infrared thermography for measuring core body temperature

The purpose of this study was to investigate the accuracy of infrared thermography for measuring body temperature. We compared a commercially available infrared thermal imaging camera (FLIR One) with a medical-grade oral thermometer (Welch-Allyn) as a gold standard. Measurements using the thermal imaging camera were taken from both a short distance (10cm) and long distance (50cm) from the subject. Thirty young healthy adults participated in a study that manipulated body temperature. After establishing a baseline, participants lowered their body temperature by placing their feet in a cold-water bath for 30 minutes while consuming cold water. Feet were then removed and covered with a blanket for 30 minutes as body temperature returned to baseline. During the course of the 70-minute experiment, body temperature was recorded at a 10-minute interval. The thermal imaging camera demonstrated a significant temperature difference from the gold standard from both close range (mean error: +0.433°C) and long range (mean error: +0.522°C). Despite demonstrating potential as a fast and non-invasive method for temperature screening, our results indicate that infrared thermography does not provide an accurate measurement of body temperature. As a result, infrared thermography is not recommended for use as a fever screening device. © COPYRIGHT SPIE. Downloading of the is permitted for personal use only.

Survey on Automatic Temperature and Face Detection using AI

The artificial intelligence is a computer expertise which thinks like human being and it does not need human intellect. The artificial intelligence could be categorized as: (i)Reactive machine, (ii)Machines with limited memory, (iii)Machines with a theory of mind, and (iv)Machines with self-awareness. The different applications of artificial intelligence are speech recognition, robot process automation, decision management, etc. The input given is in the form of images, videos, and sound data. The image, video is taken using high-resolution cameras like conventional thermal camera, visible IP camera, and AI-enabled thermal camera. With the advent of artificial intelligence variety of automated detection like thermal temperature detection, infrared temperature detection, mask recognition detection, computer vision was introduced and used. This survey presents a methodical assessment of artificial intelligence methods used in the detection and recognition of face and also for testing fever. A series of algorithms like independent component analysis, local binary pattern histogram, ADA boost cascade, squirrel search, HOG ,face detection and recognition in the literature. This paper highlights the automatic detection of body temperature, facial temperature and room temperature using artificial intelligence as an effective endurance. Persons with fever in public places could be identified and proper action could be taken in advance. This study is expected to provide researchers in AI a general idea of the present the current state of AI applications and inspire them in exploiting In the fight against illnesses like COVID-19, AI has a lot of promise.

A framework of multi-point infrared temperature screening system for COVID-19 pandemic

This paper describes a framework for COVID-19 pandemic screening that includes a multi-infrared temperature sensor. Due to the high risk of transmission of the COVID-19 epidemic in closed areas, it is important to secure these areas in terms of epidemics. Symptoms of COVID-19 disease include fever in patients. Thermal cameras or infrared temperature sensors are used to detect this anomaly in real-time. In this study, a study was carried out on which multiple uses of infrared sensors increase the measurement performance. Additionally, the general concept of an intelligent long-range temperature measurement system with facial recognition support is presented, which may be simply integrated with this approach. © 2021 IEEE.

Infrared Thermography for Measuring Elevated Body Temperature: Clinical Accuracy, Calibration, and Evaluation.

Infrared thermographs (IRTs) implemented according to standardized best practices have shown strong potential for detecting elevated body temperatures (EBT), which may be useful in clinical settings and during infectious disease epidemics. However, optimal IRT calibration methods have not been established and the clinical performance of these devices relative to the more common non-contact infrared thermometers (NCITs) remains unclear. In addition to confirming the findings of our preliminary analysis of clinical study results, the primary intent of this study was to compare methods for IRT calibration and identify best practices for assessing the performance of IRTs intended to detect EBT. A key secondary aim was to compare IRT clinical accuracy to that of NCITs. We performed a clinical thermographic imaging study of more than 1000 subjects, acquiring temperature data from several facial locations that, along with reference oral temperatures, were used to calibrate two IRT systems based on seven different regression methods. Oral temperatures imputed from facial data were used to evaluate IRT clinical accuracy based on metrics such as clinical bias (Δcb), repeatability, root-mean-square difference, and sensitivity/specificity. We proposed several calibration approaches designed to account for the non-uniform data density across the temperature range and a constant offset approach tended to show better ability to detect EBT. As in our prior study, inner canthi or full-face maximum temperatures provided the highest clinical accuracy. With an optimal calibration approach, these methods achieved a Δcb between ±0.03 °C with standard deviation (σΔcb) less than 0.3 °C, and sensitivity/specificity between 84% and 94%. Results of forehead-center measurements with NCITs or IRTs indicated reduced performance. An analysis of the complete clinical data set confirms the essential findings of our preliminary evaluation, with minor differences. Our findings provide novel insights into methods and metrics for the clinical accuracy assessment of IRTs. Furthermore, our results indicate that calibration approaches providing the highest clinical accuracy in the 37-38.5 °C range may be most effective for measuring EBT. While device performance depends on many factors, IRTs can provide superior performance to NCITs.

Review of the efficacy of infrared thermography for screening infectious diseases with applications to COVID-19.

Purpose: The recent coronavirus disease 2019 (COVID-19) pandemic, which spread across the globe in a very short period of time, revealed that the transmission control of disease is a crucial step to prevent an outbreak and effective screening for viral infectious diseases is necessary. Since the severe acute respiratory syndrome (SARS) outbreak in 2003, infrared thermography (IRT) has been considered a gold standard method for screening febrile individuals at the time of pandemics. The objective of this review is to evaluate the efficacy of IRT for screening infectious diseases with specific applications to COVID-19. Approach: A literature review was performed in Google Scholar, PubMed, and ScienceDirect to search for studies evaluating IRT screening from 2002 to present using relevant keywords. Additional literature searches were done to evaluate IRT in comparison to traditional core body temperature measurements and assess the benefits of measuring additional vital signs for infectious disease screening. Results: Studies have reported on the unreliability of IRT due to poor sensitivity and specificity in detecting true core body temperature and its inability to identify asymptomatic carriers. Airport mass screening using IRT was conducted during occurrences of SARS, Dengue, Swine Flu, and Ebola with reported sensitivities as low as zero. Other studies reported that screening other vital signs such as heart and respiratory rates can lead to more robust methods for early infection detection. Conclusions: Studies evaluating IRT showed varied results in its efficacy for screening infectious diseases. This suggests the need to assess additional physiological parameters to increase the sensitivity and specificity of non-invasive biosensors.

Infrared thermometer on the wall (iThermowall): An open source and 3-D print infrared thermometer for fever screening.

In this COVID-19 pandemic, a non-contact handheld infrared thermometer is frequently used for fever screening. However, the handheld thermometer performance depends on the operator and the distance to the forehead. To address these problems, we present an infrared thermometer on the wall (iThermowall). The iThermowall is a low-cost non-contact thermometer, adapted for the use of fever screening in public areas without an operator. The hardware can measure human body temperature automatically when the distance between the sensor and forehead is adequate. Temperature measurement validation of the iThermowall was conducted by T-test analysis. The results show that the P-values for all the test is more significant than 0.05, means that the mean Celsius temperature for both groups (reference thermometer and iThermowall) are similar. This article provides the 3-D printable open-source and the full source code firmware for the developing and under-resourced communities.

Covid-19 screening: are forehead temperature measurements during cold outdoor temperatures really helpful?

BACKGROUND: Body temperature control is a frequently used screening test for infectious diseases, such as Covid-19 (Sars-CoV-2). We used this procedure to test the body temperature of staff members in a hospital in Tyrol (Austria), where the Covid-19 disease occurred in March 2020. The hospital is located in a mountain area at 995 m above sea level with low outdoor temperatures during early spring season. Under these conditions, we analyzed whether forehead temperature control offers a sufficient screening tool for infectious diseases. METHODS: Forehead temperature of 101 healthy male and female employees was measured with an infrared thermometer directly after entering the hospital (0 min), followed by further controls after 1 min, 3 min, 5 min and 60 min. We also tracked the outside temperature and the temperature at the entrance hall of the hospital. RESULTS: Complete data of body temperature were available for 46 female and 46 male study participants. The average forehead temperature measured directly after entrance to the hospital was the lowest (0 min) 33.17 ± 1.45 °C, and increased constantly to 34.90 ± 1.49 °C after 1 min, 35.77 ± 1.10 °C after 3 min, 36.08 ± 0.79 °C after 5 min, and 36.6 ± 0.24 °C after 60 min. The outside temperature ranged between -5.5 °C and 0 °C, the indoor temperature had a constant value of 20.5 °C. CONCLUSION: Our results indicate that forehead infrared temperature control is not an appropriate tool to screen for infectious disease directly at the entrance of a building, at least during early spring season with cold outdoor temperatures.

Comparative accuracy testing of non-contact infrared thermometers and temporal artery thermometers in an adult hospital setting.

BACKGROUND: NCIT are non-invasive devices for fever screening in children. However, evidence of their accuracy for fever screening in adults is lacking. This study aimed to compare the accuracy of non-contact infrared thermometers (NCIT) with temporal artery thermometers (TAT) in an adult hospital. METHODS: A prospective observational study was conducted on a convenience sample of non-infectious inpatients in 2 Australian hospitals. NCIT and TAT devices were used to collect body temperature recordings. Participant characteristics included age, gender, skin color, highest temperature, and antipyretic medications recorded in last 24-hour. RESULTS: In 265 patients, a mean difference of ± 0.26°C was recorded between the NCIT (36.64°C) and the reference TAT (36.90°C) temperature devices. Bland-Altman analysis showed that NCIT and TAT temperatures were closely aligned at temperatures <37.5°C, but not at temperatures >37.5°C. NCIT had low sensitivity (16.13%) at temperatures ≥37.5°C. An AUROC score of 0.67 (SD 0.05) demonstrated poor accuracy of the NCIT device at temperatures ≥37.5°C. CONCLUSION: This is the first study to compare accuracy of NCIT thermometers to TAT in adult patients. Although mass fever screening is currently underway using NCIT, these results indicate that the NCIT may not be the most accurate device for fever mass screening during a pandemic.

Clinical evaluation of fever-screening thermography: impact of consensus guidelines and facial measurement location.

SIGNIFICANCE: Infrared thermographs (IRTs) have been used for fever screening during infectious disease epidemics, including severe acute respiratory syndrome, Ebola virus disease, and coronavirus disease 2019 (COVID-19). Although IRTs have significant potential for human body temperature measurement, the literature indicates inconsistent diagnostic performance, possibly due to wide variations in implemented methodology. A standardized method for IRT fever screening was recently published, but there is a lack of clinical data demonstrating its impact on IRT performance. AIM: Perform a clinical study to assess the diagnostic effectiveness of standardized IRT-based fever screening and evaluate the effect of facial measurement location. APPROACH: We performed a clinical study of 596 subjects. Temperatures from 17 facial locations were extracted from thermal images and compared with oral thermometry. Statistical analyses included calculation of receiver operating characteristic (ROC) curves and area under the curve (AUC) values for detection of febrile subjects. RESULTS: Pearson correlation coefficients for IRT-based and reference (oral) temperatures were found to vary strongly with measurement location. Approaches based on maximum temperatures in either inner canthi or full-face regions indicated stronger discrimination ability than maximum forehead temperature (AUC values of 0.95 to 0.97 versus 0.86 to 0.87, respectively) and other specific facial locations. These values are markedly better than the vast majority of results found in prior human studies of IRT-based fever screening. CONCLUSION: Our findings provide clinical confirmation of the utility of consensus approaches for fever screening, including the use of inner canthi temperatures, while also indicating that full-face maximum temperatures may provide an effective alternate approach.