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.

Real Time Fire Detection System with Image Processing

Fire detectionsystemby image processing is a growing research in this era. There are many methods used to detect fire out, butstill need to develop an accurate method to detect fire without false alarms. This is due to the fact that many methods used RGB colour mode for detection. In this paper, mainly focuson detecting the fire effectively using thermal video from a thermal camera while in the same time the system will alert the people if fire was detected,and also observed the speed of the fire.This will enormouslybenefitto the fire fighters.With thissystem, thefire can be detected effectively while alerting the people and giving valuable information to the fire fighters fortheir job more effectively.

The Use of Infrared Thermal Imaging to Determine Functional Nasal Adequacy: A Pilot Study

Objective The goal of this study was to establish a numeric threshold to separate functional from substantially obstructed noses using comparisons of thermal imaging and subjective scores. Study Design An inexpensive smartphone application and hardware attachment that uses infrared thermal imaging was tested to differentiate between substantial nasal blockage from an adequately functioning nose. Setting Sequential adult participants who presented to a public hospital otolaryngology clinic between June and August 2018 were asked to complete the Nasal Obstruction Symptom Evaluation (NOSE) tool. Methods A thermal video imaging device was used to record the difference in temperature (ΔT) between inspired (I) and expired (E) air at each nostril. The nostril ΔT between I and E air of patients with severe obstruction by the subjective measure (NOSE score) was compared with that of patients with minimal symptoms. Results A total of 26 participants were enrolled in the study. During normal respiration, Total ΔT for the nonobstructed group had a mean of 9.0, whereas the Total ΔT for the obstructed group had a mean of 7.69, a 17% difference that was statistically significant at P = .045. For the worst-performing nostril tested, ΔT for the nonobstructed group had a mean/median of 4°C, while the obstructed group had a mean of 3.23°C (median 3; 23.8% difference, P = .023). Conclusion Measures of thermal imaging, particularly at the threshold between the median scores of the worst-performing nostril, may be a useful clinical test to differentiate between a substantially obstructed nose from an adequately functioning nose, although more data are required.

Implementasi Blackbox Testing Pada Aplikasi Real-Time Thermal Video Detection (Studi Kasus Deteksi Demam/Covid-19)

Seiring munculnya pandemi Covid-19 yang vaksinnya belum tersebar secara merata, seluruh negara di dunia khususnya Indonesia telah melakukan beberapa langkah preventif guna menghambat penyebaran virus tersebut. Salah satu tindakan awal adalah melakukan deteksi setiap orang yang keluar masuk ke dalam negeri melalui bandara maupun transportasi darat. Tindakan dini tersebut dilakukan dengan mendeteksi suhu tubuh dari warga yang melalui lokasi-lokasi keluar masuk seperti bandara udara, dan stasiun kereta api. Deteksi pada umumnya dilakukan menggunakan thermal gun berbentuk alat tembak infrared yang diarahkan ke individu yang melewati pemeriksaan. Pada riset ini dibahas rangkaian alat yang terdiri dari kamera dengan sensor thermal dimana data hasil capture akan diolah melalui perangkat lunak yang menampilkan histogram suhu bagian dada hingga kepala seseorang secara realtime. Setiap hasil capture digunakan sebagai dataset yang dapat digunakan untuk kebutuhan tracing pengunjung tempat publik. Pada riset ini akan membahas pengujian fungsional (blackbox) dari aplikasi thermal video detection pada studi kasus deteksi demam.

Thermal Feature Detection of Vehicle Categories in the Urban Area

The main goal of this paper is to present new possibilities for the detection and recognition of different categories of electric and conventional (equipped with combustion engines) vehicles using a thermal video camera. The paper presents a draft of a possible detection and classification system of vehicle propulsion systems working with thermal analyses. The differences in thermal features of different vehicle categories were found out and statistically proved. The thermal images were obtained using an infrared thermography camera. They were utilized to design a database of vehicle class images of passenger vehicles (PVs), vans, and buses. The results confirmed the hypothesis that infrared thermography might be used for categorizing the vehicle type according to the thermal features of vehicle exteriors and machine learning methods for vehicle type recognition.

Thermographic imaging of mouse across circadian time reveals body surface temperature elevation associated with non-locomotor body movements

Circadian clocks orchestrate multiple different physiological rhythms in a well-synchronized manner. However, how these separate rhythms are interconnected is not exactly understood. Here, we developed a method that allows for the real-time simultaneous measurement of locomotor activity and body temperature of mice using infrared video camera imaging. As expected from the literature, temporal profiles of body temperature and locomotor activity were positively correlated with each other. Basically, body temperatures were high when animals were in locomotion. However, interestingly, increases in body temperature were not always associated with the appearance of locomotor activity. Video imaging revealed that mice exhibit non-locomotor activities such as grooming and postural adjustments, which alone induce considerable elevation of body temperature. Noticeably, non-locomotor movements always preceded the initiation of locomotor activity. Nevertheless, non-locomotor movements were not always accompanied by locomotor movements, suggesting that non-locomotor movements provide a mechanism of thermoregulation independent of locomotor activity. In addition, in the current study, we also report the development of a machine learning-based recording method for the detection of circadian feeding and drinking behaviors of mice. Our data illustrate the potential utility of thermal video imaging in the investigation of different physiological rhythms.

SpeakingFaces: A Large-Scale Multimodal Dataset of Voice Commands with Visual and Thermal Video Streams

We present SpeakingFaces as a publicly-available large-scale multimodal dataset developed to support machine learning research in contexts that utilize a combination of thermal, visual, and audio data streams; examples include human–computer interaction, biometric authentication, recognition systems, domain transfer, and speech recognition. SpeakingFaces is comprised of aligned high-resolution thermal and visual spectra image streams of fully-framed faces synchronized with audio recordings of each subject speaking approximately 100 imperative phrases. Data were collected from 142 subjects, yielding over 13,000 instances of synchronized data (∼3.8 TB). For technical validation, we demonstrate two baseline examples. The first baseline shows classification by gender, utilizing different combinations of the three data streams in both clean and noisy environments. The second example consists of thermal-to-visual facial image translation, as an instance of domain transfer.