Mobile Thermal Imaging Research Articles

Using Range of Motion Exercises and Smartphone Thermography to Evaluate Wound Healing in Second-Degree Burns

BackgroundBurn injuries can lead to devastating functional impairments and reduced quality of life. An important component of rehabilitation programs is the range of motion exercises, which can accelerate wound healing and prevent contractures. The present study sought to evaluate the effects of a range of motion exercises validated by thermal imagining on patients with second-degree burns. Patients and methodsThis quasi-experimental study included 47 adult patients diagnosed with second-degree burns. Data was collected using a Structured Interview Questionnaire, modified Abbreviated Burn Severity Index (ABSI), the Bates-Jensen Wound Assessment Tool (BWAT), and mobile thermal imaging to assess wound healing. ResultsThe ABSI levels showed that 46.8% of patients had moderate-severity burns, 38.3% had very low severity, and 14.9% had moderately severe burns. While the BWAT scores were 28.9 ± 4.6SD at baseline, 30.1 ± 4.7SD after one week, 19.2 ± 6.5SD after the 2nd week, and finally 17.1 ± 4.3SD on the 3rd week. The FLIR thermal imaging scores over three weeks were statistically significant (p<0.001, Kruskal-Wallis test). The study revealed high statistically significant differences in range of motion and wound healing mean scores. ConclusionsThis study demonstrated that range of motion exercises improved burn wound healing. Additionally, thermal imaging showed high validity for evaluating wound healing potential and progression. It provides viable triage technology while benefiting clinical assessment. Overall, range of motion and smartphone thermography are two evidence-based modalities that can enhance burn management, decrease healing time, lower costs, and improve outcomes.

Thermal Threat Monitoring Using Thermal Image Analysis and Convolutional Neural Networks

Monitoring of the vital signs or environment of disabled people is currently very popular because it increases their safety, improves their quality of life and facilitates remote care. The article proposes a system for automatic protection against burns based on the detection of thermal threats intended for blind or visually impaired people. Deep learning methods and CNNs were used to analyze images recorded by mobile thermal cameras. The proposed algorithm analyses thermal images covering the field of view of a user for the presence of objects with high or very high temperatures. If the user’s hand appears in such an area, the procedure warning about the possibility of burns is activated and the algorithm generates an alarm. To achieve this effect, the thermal images were analyzed using the 15-layered convolutional neural network proposed in the article. The proposed solution provided the efficiency of detecting threat situations of over 99% for a set of more than 21,000 images. Tests were carried out for various network configurations, architecture and both the accuracy and precision of hand detection was 99.5%, whereas sensitivity reached 99.7%. The effectiveness of burn risk detection was 99.7%—a hot object—and the hand appeared simultaneously in the image. The presented method allows for quick, effective and automatic warning against thermal threats. The optimization of the model structure allows for its use with mobile devices such as smartphones and mobile thermal imaging cameras.

The use of mobile thermal imaging and machine learning technology for the detection of early surgical site infections

BackgroundSurgical Site Infections (SSI) yield subtle, early signs that are not readily identifiable. This study sought to develop a machine learning algorithm that could identify early SSIs based on thermal images. MethodsImages were taken of surgical incisions on 193 patients who underwent a variety of surgical procedures. Two neural network models were generated to detect SSIs, one using RGB images, and one incorporating thermal images. Accuracy and Jaccard Index were the primary metrics by which models were evaluated. ResultsOnly 5 patients in our cohort developed SSIs (2.8%). Models were instead generated to demarcate the wound site. The models had 89–92% accuracy in predicting pixel class. The Jaccard indices for the RGB and RGB ​+ ​Thermal models were 66% and 64%, respectively. ConclusionsAlthough the low infection rate precluded the ability of our models to identify surgical site infections, we were able to generate two models to successfully segment wounds. This proof-of-concept study demonstrates that computer vision has the potential to support future surgical applications.

Non-Contact Spirometry Using a Mobile Thermal Camera and AI Regression.

Non-contact physiological measurements have been under investigation for many years, and among these measurements is non-contact spirometry, which could provide acute and chronic pulmonary disease monitoring and diagnosis. This work presents a feasibility study for non-contact spirometry measurements using a mobile thermal imaging system. Thermal images were acquired from 19 subjects for measuring the respiration rate and the volume of inhaled and exhaled air. A mobile application was built to measure the respiration rate and export the respiration signal to a personal computer. The mobile application acquired thermal video images at a rate of nine frames/second and the OpenCV library was used for localization of the area of interest (nose and mouth). Artificial intelligence regressors were used to predict the inhalation and exhalation air volume. Several regressors were tested and four of them showed excellent performance: random forest, adaptive boosting, gradient boosting, and decision trees. The latter showed the best regression results, with an R-square value of 0.9998 and a mean square error of 0.0023. The results of this study showed that non-contact spirometry based on a thermal imaging system is feasible and provides all the basic measurements that the conventional spirometers support.

How to Map All Your Flap Perforators in 2 Minutes

INTRODUCTION: Imaging modalities are changing clinical practice in plastic surgery and becoming more compact, more affordable, and easier to use. Over the last two decades, 3D imaging, ICG angiography, and virtual surgical planning have become commonplace for operative decision-making. Recently, mobile thermal imaging has demonstrated accuracy and consistency in determining perforator locations and visualizing the functional angiosomes.1 A study by Khouri et al in 1992 showed that the sensitivity of surface-temperature recording is 98%, and its predictive value is 75%.2 We sought to investigate whether recovery-enhanced mobile thermal imaging can be used to rapidly and reliably design perforator flaps. METHODS: Thermal imaging was compared with Doppler perforator mapping in five volunteers. Volunteers underwent traditional flap markings on one thigh and mobile thermal imaging (FLIR One Pro, FLIR Systems, Inc., Willsonville, Oreg.) on their contralateral thigh. In the traditional group, a line was drawn from the ASIS to the superolateral border of the patella with a 3-cm-radius circle at the midpoint, followed by perforator identification with a Doppler.3 On the contralateral thigh, ice cooling was performed for 10 seconds followed by inspection with the thermal camera. Time to identify at least three perforators, determination of perforator dominance, and perforator concordance were recorded. Additionally, in two consecutive patients undergoing anterolateral thigh flap reconstruction, flap design was examined based on traditional markings versus thermal imaging. RESULTS: Perforator identification was more rapid (136 seconds versus 232 seconds) and more likely to demonstrate perforator dominance (five versus one) using thermal imaging compared with traditional markings (P < 0.05). In both patients undergoing ALT flap reconstruction, three perforators were located with traditional and thermal imaging markings. In patient one, the middle perforator demonstrated dominance and true anastomoses to the surrounding perforators. In patient two, the transverse branch perforator demonstrated maximal intensity and poor connections to the distal perforators. After this, proximal perforator was divided and the thermal imaging worsened, resulting in resection of the proximal flap and change in flap design. Perforator location matched computed tomography angiographic findings in both patients. No postoperative flap compromise was encountered. CONCLUSIONS: Thermal imaging with ice cooling appears highly effective at rapid perforator and angiosome identification-based flap design. Recovery-enhanced thermography by ice cooling allows for dynamic visualization of angiosome perfusion area. Given improvement in technology and decreasing costs, mobile thermal imaging may become a reliable tool in flap design and flap monitoring. REFERENCES: 1. Pereira N, Valenzuela D, Mangelsdorff G, et al. Detection of perforators for free flap planning using smartphone thermal imaging. Plast Reconstr Surg. 2018;141(3):787–792. 2. Khouri RK, Shaw WW. Monitoring of free flaps with surface-temperature recordings: is it reliable? Plast Reconstr Surg. 1992;89(3):495–499; discussion 500–502. 3. Saint-Cyr M, Oni G, Lee M, et al. Simple approach to harvest of the anterolateral thigh flap. Plast Reconstr Surg. 2012;129(1):207–211.

Assessing and mapping vineyard water status using a ground mobile thermal imaging platform

Water status directly affects yield and crop quality in grapevines. Precision viticulture demands the application of new available technologies and methodologies for accurate irrigation management in vineyards. The objective of this work was the development of an on-the-go thermal imaging application for the assessment and mapping of vineyard water status, building a dataset from a commercial Tempranillo (Vitis vinifera L.) vineyard over two consecutive seasons and validating it in another commercial vineyard from a different winegrowing region. Thermal imaging was performed with a thermal camera mounted in an all-terrain vehicle, moving at 5 km/h and operating at a distance from the canopy of 1.20 m. Stem water potential (Ψstem) was used for validation as the grapevine water status reference method, using a Scholander pressure chamber. Crop Water Stress Index (CWSI) and Stomatal Conductance Index (Ig) from a 4-day dataset were computed and correlated with Ψstem, delivering significant (p < 0.0001) determination coefficients R2 up to 0.71. The prediction capability of this dataset was also validated in another commercial vineyard, achieving a prediction R2 up to 0.82 (RMSE of 0.123 MPa). The predicted values of both indices were thus employed for mapping vineyard water status in the second plot. These results evidence the potential applicability of on-the-go thermal imaging for assessing and mapping water status in commercial vineyards required for precision viticulture.

Algorithm for Automated Foot Detection in Thermal and Optical Images for Temperature Asymmetry Analysis

Infrared thermography has been proven to be an effective non-invasive method in diabetic foot ulcer prevention, yet current image processing algorithms are inaccurate and impractical for clinical work. The aim of this study was to investigate the accuracy of our automated algorithm for feet outline detection and localization of potential inflammation regions in thermal images. Optical and thermal images were captured by a Flir OnePro camera connected with an Apple iPad Air tablet. Both thermal and optical images were merged into an edge image and used for the estimation of foot template transformations during the localization process. According to the feet template transformations, temperature maps were calculated and compared with each other to detect a set of regions exceeding the defined temperature threshold. Finally, a set of potential inflammation regions were filtered according to the blobs features to obtain the final list of inflammation regions. In this study, 168 thermal images were analyzed. The developed algorithm yielded 95.83% accuracy for foot outline detection and 94.28% accuracy for detection of the inflammation regions. The presented automated algorithm with enhanced detection accuracy can be used for developing a mobile thermal imaging system. Further studies with patients who have diabetes and are at risk of foot ulceration are needed to test the significance of our developed algorithm.

Stress detection and monitoring based on low-cost mobile thermography

The high level of stress in modern life is one of the huge problems of the 21st century society, especially in the context of the Covid-19 pandemic. With the pandemic, the need for inexpensive, portable and easy-to-use health monitoring tools (mental and physical) has increased. Of particular importance here is mobile (smartphone) thermography, as it enables the initial detection and self-control of stress, which being intensified nowadays, is the cause of many diseases, depression and health problems. The smartphone thermal imaging camera responds to the strict sanitary guidelines, offering contact-free, painless and non-invasive operation. Additionally, it is included in the group of low-cost solutions available for home use. It is an alternative to commonly used (often expensive and unavailable to everyone): EMG, ECG, EEG, GSR or other high-cost stress detection tools. Thermal imaging by analyzing abnormalities or temperature changes allows for detection application. Therefore, the aim of this work is to determine the possibilities of a low-budget mobile thermal imaging camera in detecting stress, detecting and analyzing stress by identifying the characteristics of psychophysiological signals with the individual characteristics of the participants, along with the correlation. The participants’ reactions to the film introducing stress tension up to the climax of the action were recorded thermographically. Data was processed in OpenCV. In the usual observation, stress often remained unnoticed. However, the thermographic analysis provided detailed information on the impact of the film’s stressful situation on the participants, with the possibility of distinguishing the stages of stress. The results of the preliminary pilot study were presented, which indicated the variability of temperature and heart rate as important indicators of stress – with the simultaneous significance of individual characteristics of the participant. Smartphone stress thermography is a promising method of monitoring human stress, especially at home.

Evaluation of Rectal and Skin Temperature Variations of Anesthetised Dogs Undergoing Magnetic Resonance Imaging Diagnosis

General anesthesia produces different degrees of central nervous depression and changes in the peripheral circulation, therefore affecting the patient’s thermoregulatory mechanism. Moreover, the lack of proper, specially designed equipment for magnetic resonance imaging (MRI) environment monitoring can represent a challenge for the anesthetist. We examined the temperature variations correlated with different anesthetic protocols in dogs that underwent general anesthesia in order to evaluate changes in rectal and distal extremities temperature, before and after anesthesia. This study was conducted at the Faculty of Veterinary Medicine in Bucharest, on 21 dogs that were divided in 3 groups depending on the anesthetic protocol used. First group (B) received butorphanol (0.2 mg/kg, intravenously IV), second group (BK) had butorphanol (0.2 mg/kg) and a low dose of ketamine (2 mg/kg) IV, and group 3 (BM) was premedicated with butorphanol (0.2 mg/kg) and midazolam (0.2 mg/kg) IV. All patients were induced with propofol i.v. (3.24±0.68), intubated and maintained with isoflurane and oxygen. We determined rectal temperature before and right after the end of anesthesia with a digital thermometer and distal extremities temperature with the use of a thermal imaging camera attached to a smartphone. There was no significant difference between the rectal temperature before and after anesthesia within the 3 groups. Patients in group BK had a significant change in skin temperature at the end of anesthesia in all limbs (from 310C to 29.8 0C, p=0.008 and from 31 0C to 29.70C, p=0.009), respectively). Temperature variations were presented before and at the end of anesthesia, for all the groups especially at skin level. This study revealed that mobile thermal imaging represents a non-invasive technique that is helpful in assessing real time temperature changes in patients undergoing general anesthesia.

Mobile Thermal Imaging as an Adjunct in the Diagnosis of Surgical Site Infection

Morte, Kaitlin MD; Marenco, Christopher MD; Lammers, Daniel MD; Sheldon, Rowan R. MD; Bingham, Jason R. MD; Eckert, Matthew J. MD, FACS Author Information

THE METHOD OF EFFICIENT DISTRIBUTION OF DIFFERENT ELEMENTS OF A COMPLEX SYSTEM OF CONTROL

Context. An important prerequisite for reliable protection of the state border of Ukraine is the effective detection of violators of the border. For this purpose, various state-of-the-art systems and observation complexes are used at the border agency, and some border dresses are equipped with the latest technical means of border guarding. The diversity of possibilities of individual means of observation in their complex use makes it important to determine the effective location of observation points, taking into account the features of the terrain. Objective. The purpose of the work is to develop a method for effective placement of elements of complex surveillance systems of the border agency. Method. The work proposes a heuristic approach to solving the problem of determining the effective placement of different capabilities of technical means of observation. The developed method is based on the cyclic use of the known method of combinatorial optimization of placement of observation points for all components of a complex surveillance system of the border agency with adjustment after each iteration of the overburden. At the same time, with the use of geo-processing takes into account the barrier to the negative impact of terrain and the possibility of different technical means of surveillance in different conditions. To assess the effectiveness of the functioning of the components of the surveillance system, an indicator is used reflecting the share of the area of the strip of overlap, which provides the identification of objectives. Results. As a result of using the proposed methodology, a rational structural construction of a complex surveillance system of the border guard body and a set of uncontrolled points of the area are obtained. This plurality can be used in planning the service of the units of the border guard. The description of algorithmic and program realization of the proposed method is given. Using the developed software, the optimization of the placement of three types of elements of a complex observation system (towers of the system of optoelectronic observation, mobile thermal imaging complexes, observation posts) was carried out. Conclusions. Modern construction of complex surveillance systems of the border agency in many cases is not optimal. To increase the efficiency of their operation, it is possible to use the proposed method of placement of elements of these systems on the ground.

Mobile forward-looking infrared technology allows rapid assessment of resuscitative endovascular balloon occlusion of the aorta in hemorrhage and blackout conditions.

Objective assessment of final resuscitative endovascular balloon occlusion of the aorta (REBOA) position and adequate distal aortic occlusion is critical in patients with hemorrhagic shock, especially as feasibility is being increasingly investigated in the prehospital setting. We propose that mobile forward-looking infrared (FLIR) thermal imaging is a fast, reliable, and noninvasive method to assess REBOA position and efficacy in scenarios applicable to battlefield and prehospital care. Ten swine were randomized to a 40% hemorrhage group (H, n = 5) or nonhemorrhage group (NH, n = 5). Three experiments were completed after Zone I placement of a REBOA catheter. Resuscitative endovascular balloon occlusion of the aorta was deployed for 30 minutes in all animals followed by randomized continued deployment versus sham in both light and blackout conditions. Forward-looking infrared images and hemodynamic data were obtained. Images were presented to 62 blinded observers for assessment of REBOA inflation status. There was no difference in hemodynamic or laboratory values at baseline. The H group was significantly more hypotensive (mean arterial pressure 44 vs. 60 mm Hg, p < 0.01), vasodilated (systemic vascular resistance 634 vs. 938dyn·s/cm, p = 0.02), and anemic (hematocrit 12 vs. 23.2%, p < 0.01). Hemorrhage group animals remained more hypotensive, anemic, and acidotic throughout all three experiments. There was a significant difference in the temperature change (ΔTemp) measured by FLIR between animals with REBOA inflated versus not inflated (5.7°C vs. 0.7°C, p < 0.01). The H and NH animals exhibited equal magnitudes of ΔTemp in both inflated and deflated states. Blinded observer analysis of FLIR images correctly identified adequate REBOA inflation and aortic occlusion 95.4% at 5 minutes and 98.8% at 10 minutes (positive predictive value at 5 minutes = 99% and positive predictive value at 10 minutes = 100%). Mobile thermal imaging is an easy, rapid, and reliable method for assessing distal perfusion after occlusion by REBOA. Smartphone-based FLIR technology allows for confirmation of adequate REBOA placement at the point of care, and performance was not degraded in the setting of major hemorrhage or blackout conditions.

Mobile Application for Ulcer Detection.

Purpose:The number of patients who are suffering from diabetes nowadays is increasing significantly. In some countries, the percentage of population who suffer from this disease can reach up to 20%. Diabetic patients have to deal with their medical conditions and any further complications that this disease may cause. One of the most common conditions is the Diabetic Foot Ulcer (DFU). The early detection of these ulcers can help and may save the life of diabetic patients.Methods:This work proposes a mobile application for the detection of possible ulcers using a smart phone along with a mobile thermal camera (FLIR ONE). The proposed system captures thermal images of the feet from the thermal camera. The app that identifies ulcers was built using Android studio. The images were acquired to the Samsung S6 smart phone using the FLIR ONE SDK. Image processing techniques were deployed based on Open CV Library. The procedure of detecting possible ulcers was implemented based on analyzing the thermal distribution on the two feet. The developed application compares the difference between the temperature distribution on the two feet and checks if there is a Mean Temperature Difference (MTD) greater than 2.2oC (the value which indicates a possible ulcer development).Results:The system was tested under simulated conditions by heating different locations of the subjects’ feet to different temperature ranges; one image with temperature less than 2.2oC and another three images with temperature greater than 2.2oC. The system has successfully identified possible ulcer regions along with an image showing the location of the possible ulcers.Conclusions:This work is a very first step in developing a complete mobile thermal imaging system that can be validated clinically in the future.

Self-monitoring of Raynaud’s phenomenon with FLIR ONE® PRO

ABSTRACTAs mobile imaging and application technology develops at a rapid pace, new products with potential value to healthcare emerge. This paper explores the usefulness of mobile thermal imaging technology in the documentation of Raynaud’s phenomenon. Using a single-case study, a patient’s symptoms were recorded using a FLIR ONE® PRO for one month along with data relating to temperatures and weather conditions, diet and exercise and anxiety levels. Pearson Correlation Coefficient tests were carried out to determine if symptom onset could be better understood.

Smartphone-based mobile thermal imaging technology to assess limb perfusion and tourniquet effectiveness under normal and blackout conditions.

Over the past decade, there has been a resurgence of tourniquet use in civilian and military settings. Several key challenges include assessment of limb perfusion and adequacy of tourniquet placement, particularly in the austere or prehospital environments. We investigated the utility of thermal imaging to assess adequacy of tourniquet placement. The FLIR ONE smartphone-based thermal imager was utilized. Ten swine underwent tourniquet placement with no associated hemorrhage (n = 5) or with 40% hemorrhage (n = 5). Experiment 1 simulated proper tourniquet application, experiment 2 had one of two tourniquets inadequately tightened, and experiment 3 had one of two tourniquets inadequately tightened while simulating blackout-combat conditions. Static images were taken at multiple time points up to 30 minutes. Thermal images were then presented to blinded evaluators who assessed adequacy of tourniquet placement. The mean core temperature was 38.3 °C in non-hemorrhaged animals versus 38.2 °C in hemorrhaged animals. Hemorrhaged animals were more hypotensive (p = 0.001), anemic (p < 0.001), vasodilated (p = 0.008), and had a lower cardiac output (p = 0.007) compared to non-hemorrhaged animals. The thermal imaging temperature reading decreased significantly after proper tourniquet placement in all animals, with no difference between hemorrhaged and non-hemorrhaged groups at 30 minutes (p = 0.23). Qualitative thermal image analysis showed clearly visible perfusion differences in all animals between baseline, adequate tourniquet, and inadequate tourniquet in both hemorrhaged and non-hemorrhaged groups. Ninety-eight percent of blinded evaluators (n = 62) correctly identified adequate and inadequate tourniquet placement at 5 minutes. Images in blackout conditions showed no adverse impact on thermal measurements or in the ability to accurately characterize perfusion and tourniquet adequacy. A simple handheld smartphone-based forward looking infrared radiometry device demonstrated a high degree of accuracy, reliability, and ease of use for assessing limb perfusion. Forward looking infrared radiometry also allowed for rapid and reliable identification of adequate tourniquet placement that was not affected by major hemorrhage or blackout conditions.

Diabetic foot ulcer mobile detection system using smart phone thermal camera: a feasibility study

BackgroundNowadays, the whole world is being concerned with a major health problem, which is diabetes. A very common symptom of diabetes is the diabetic foot ulcer (DFU). The early detection of such foot complications can protect diabetic patients from any dangerous stages that develop later and may require foot amputation. This work aims at building a mobile thermal imaging system that can be used as an indicator for possible developing ulcers.MethodsThe proposed system consists of a thermal camera connected to a Samsung smart phone, which is used to acquire thermal images. This thermal imaging system has a simulated temperature gradient of more than 2.2 °C, which represents the temperature difference (in the literature) than can indicate a possible development of ulcers. The acquired images are processed and segmented using basic image processing techniques. The analysis and interpretation is conducted using two techniques: Otsu thresholding technique and Point-to-Point mean difference technique.ResultsThe proposed system was implemented under MATLAB Mobile platform and thermal images were analyzed and interpreted. Four testing images (feet images) were used to test this procedure; one image with any temperature variation to the feet, and three images with skin temperature increased to more than 2.2 °C introduced at different locations. With the two techniques applied during the analysis and interpretation stage, the system was successful in identifying the location of the temperature increase.ConclusionThis work successfully implemented a mobile thermal imaging system that includes an automated method to identify possible ulcers in diabetic patients. This may give diabetic patients the ability for a frequent self-check of possible ulcers. Although this work was implemented in simulated conditions, it provides the necessary feasibility to be further developed and tested in a clinical environment.

Robust tracking of respiratory rate in high-dynamic range scenes using mobile thermal imaging.

The ability to monitor the respiratory rate, one of the vital signs, is extremely important for the medical treatment, healthcare and fitness sectors. In many situations, mobile methods, which allow users to undertake everyday activities, are required. However, current monitoring systems can be obtrusive, requiring users to wear respiration belts or nasal probes. Alternatively, contactless digital image sensor based remote-photoplethysmography (PPG) can be used. However, remote PPG requires an ambient source of light, and does not work properly in dark places or under varying lighting conditions. Recent advances in thermographic systems have shrunk their size, weight and cost, to the point where it is possible to create smart-phone based respiration rate monitoring devices that are not affected by lighting conditions. However, mobile thermal imaging is challenged in scenes with high thermal dynamic ranges (e.g. due to the different environmental temperature distributions indoors and outdoors). This challenge is further amplified by general problems such as motion artifacts and low spatial resolution, leading to unreliable breathing signals. In this paper, we propose a novel and robust approach for respiration tracking which compensates for the negative effects of variations in the ambient temperature and motion artifacts and can accurately extract breathing rates in highly dynamic thermal scenes. The approach is based on tracking the nostril of the user and using local temperature variations to infer inhalation and exhalation cycles. It has three main contributions. The first is a novel Optimal Quantization technique which adaptively constructs a color mapping of absolute temperature to improve segmentation, classification and tracking. The second is the Thermal Gradient Flow method that computes thermal gradient magnitude maps to enhance the accuracy of the nostril region tracking. Finally, we introduce the Thermal Voxel method to increase the reliability of the captured respiration signals compared to the traditional averaging method. We demonstrate the extreme robustness of our system to track the nostril-region and measure the respiratory rate by evaluating it during controlled respiration exercises in high thermal dynamic scenes (e.g. strong correlation (r = 0.9987) with the ground truth from the respiration-belt sensor). We also demonstrate how our algorithm outperformed standard algorithms in settings with different amounts of environmental thermal changes and human motion. We open the tracked ROI sequences of the datasets collected for these studies (i.e. under both controlled and unconstrained real-world settings) to the community to foster work in this area.