Thermal Video Camera Research Articles

Fusion of Heterogenous Sensor Data in Border Surveillance.

Wide area surveillance has become of critical importance, particularly for border control between countries where vast forested land border areas are to be monitored. In this paper, we address the problem of the automatic detection of activity in forbidden areas, namely forested land border areas. In order to avoid false detections, often triggered in dense vegetation with single sensors such as radar, we present a multi sensor fusion and tracking system using passive infrared detectors in combination with automatic person detection from thermal and visual video camera images. The approach combines weighted maps with a rule engine that associates data from multiple weighted maps. The proposed approach is tested on real data collected by the EU FOLDOUT project in a location representative of a range of forested EU borders. The results show that the proposed approach can eliminate single sensor false detections and enhance accuracy by up to 50%.

A Review of Facial Thermography Assessment for Vital Signs Estimation

Estimated vital signs might include a variety of measurements that can be used in detecting any abnormal conditions by analyzing facial images from continuous monitoring with a thermal video camera. To overcome the limitless human visual perceptions, thermal infrared has proven to be the most effective technique for visualizing facial colour changes that could have been reflected by changes in oxygenation levels and blood volume in facial arteries. This study investigated the possibility of vital signs estimation using physiological function images converted from the thermal infrared images in the same ways that visible images are used, with a need for an efficient extractor method as correction procedures that have used datasets that include images with and without wearing glasses or protective face masks. This paper, summarize thermal images using advanced machine learning and deep learning methods with satisfactory performance. Also, we presented the evaluation matrices that were included in the assessment based on statistical analysis, accuracy measures and error measures. Finally, to discuss future gaps and directions for further evaluations.

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.

Developing and validating an accelerometer-based algorithm with machine learning to classify physical activity after acquired brain injury

ABSTRACT Purpose: To develop and validate an accelerometer-based algorithm classifying physical activity in people with acquired brain injury (ABI) in a laboratory setting resembling a real home environment. Materials and methods: A development and validation study was performed. Eleven healthy participants and 25 patients with ABI performed a protocol of transfers and ambulating activities. Activity measurements were performed with accelerometers and with thermal video camera as gold standard reference. A machine learning-based algorithm classifying specific physical activities from the accelerometer data was developed and cross-validated in a training sample of 11 healthy participants. Criterion validity of the algorithm was established in 3 models classifying the same protocol of activities in people with ABI. Results: Modeled on data from 11 healthy and 15 participants with ABI, the algorithm had a good precision for classifying transfers and ambulating activities in data from 10 participants with ABI. The weighted sensitivity for all activities was 89.3% (88.3–90.4%) and the weighted positive predictive value was 89.7% (88.7–90.7%). The algorithm differentiated between lying and sitting activities. Conclusion: An algorithm to classify physical activities in populations with ABI was developed and its criterion validity established. Further testing of precision in home settings with continuous activity monitoring is warranted.

Habitat preference by the Anatolian leopard (Panthera pardus tulliana Valenciennes, 1856) in North-eastern Anatolia, Turkey

This study aims to document the existence and habitat preferences of the Anatolian leopard (Panthera pardus tulliana Valenciennes, 1856) in north-eastern Anatolia, Turkey. We sampled eleven study areas in 2013–2017, primarily based on our previous field experiences, reports from local people, and literature. Based on the findings from initial surveys, camera traps and leopard studies were mostly used in parts of the Giresun (Sarıçiçek Mountain), Erzincan (Sansa Strait), and Bingöl (Yedisu Valley) Provinces. We employed both direct observations and indirect observations. A total of 58 observations were recorded, ranging from 1176–3050 meters in altitude: six camera trap pictures, three thermal video camera images, three sightings by local people, 28 sets of tracks, 13 pieces of scat, two ground-scrapings, and three tree-scratches belonging to the Anatolian leopard. We defined eight habitat types and found that leopards preferred sparse forest areas, rocky habitats, and agriculture and pasture regions the most. Furthermore, 49 of 58 observations made in the sampling areas were detected in the southerly aspects of the study region. The Anatolian leopard habitat selection is mainly based on prey abundance, and we found that leopards prefer wild boar (Sus scrofa) the most, followed by wild goat (Capra aegagrus), chamois (Rupicapra rupicapra), and roe deer (Capreolus capreolus).

Impact of Apartment Tightness on Temperature Variability during a Fire.

Along with the thermal modernization process of old residential buildings, there has been a significant increase in the air tightness of apartments, which may contribute to the deterioration of the safety of users and rescue teams in a fire. The main goal of this study was to investigate the impact of the air tightness of an apartment on fire growth and temperature variability. In the work, an experimental method was applied. Two full-scale fire tests were carried out, one in a sealed apartment and the other in unsealed one. The temperature was measured by thirty-two thermocouples. Two thermal imaging and video cameras were also used to evaluate a temperature field as well as flame and smoke height. Based on the analysis, conclusions have been formulated. It is noteworthy that the highest temperatures and significant increase in pressure were obtained in a sealed apartment, but dangerous and critical conditions regarding firefighters’ safety were achieved faster and persisted much longer in an unsealed one.

Development and evaluation of a real-time pedestrian counting system for high-volume conditions based on 2D LiDAR

Automated monitoring of pedestrians on non-motorized facilities with high pedestrian flows is challenging. Several automated sensor solutions are commercially available that have been evaluated in the literature including traditional point-based sensors, such as inductive loop detectors for bicycles and infrared sensors for pedestrians. More recently, image-based systems, based on video cameras or thermal video cameras, have been developed. Despite the various options, some key limitations of existing solutions exist, in particular, the lack of low-cost solutions using embedded systems capable of performing in real-time under high volume (flow) conditions. This work aims at developing and evaluating the performance of a novel, real-time counting system, developed for environments with high pedestrian flows. The proposed system is based on emerging LiDAR (Light Detection and Ranging) technology. As an input, the system uses the distance measurements from a two-dimensional LiDAR sensor with a set of distinct laser channels and a given angular resolution between each channel. The developed system processes those measurements using a clustering algorithm to detect, count, and identify the direction of travel of each pedestrian. The system’s performance is evaluated by comparing its directional counting outputs with manual counts (ground truth) using disaggregate and aggregate (15-minutes interval) counts at two different monitoring locations. The results demonstrate that the system accurately counts more than 97% of the pedestrians at the disaggregate level, with a false direction detection rate of 1.1%. The over-counting error is 0.7% and the under-counting errors are 1.3% and 2.7% for the two selected sites. At the aggregate level (15-minutes interval), the average absolute percentage deviations (AAPDs) are 1.6% and 4.3% while the weighted AAPDs are 1.5% and 3.5% for the first and second sites, respectively. The accuracy of the proposed system is higher than the traditional technologies used for the same purpose.

As clear as day: nocturnal activity differs from diurnal activity in a temporally constrained capital breeder

Abstract Time-activity budgets are fundamental to behavioural studies, allowing examination of how individuals allocate their time, and potentially energy, and how these patterns vary spatially and temporally and in relation to habitat, individual identity, sex, social status and levels of anthropogenic disturbance. Direct observations of animal behaviour, especially in the wild, are often limited to daylight hours; therefore, many activity budgets relate to diurnal activity only, or assumptions are made about nocturnal activity. Activity budgets have been a key component of many behavioural and energetics studies of breeding grey seals (Halichoerus grypus, Fabricius, 1791), and yet very little is known about nocturnal activity of grey seals, and a general, implicit assumption of no significant change from day to night seems to pervade the literature. Here we use a combination of high resolution digital video and thermal imaging video camera to follow known individual grey seal mothers from day into night to examine activity patterns during lactation. We show distinct differences in nocturnal activity budgets relative to diurnal activity budgets. Mothers spent significantly more time resting with a reduction of time spent in the alert and comfort move behavioural categories during nocturnal periods. It is clear that diurnal time-activity patterns of breeding female grey seals cannot be extrapolated to represent activity across a 24-hour cycle. These considerations are particularly critical in studies that aim to use time-activity budgets as proxies for energy budgets.

Wildlife warning reflectors and white canvas reduce deer–vehicle collisions and risky road‐crossing behavior

ABSTRACTCollisions between wildlife and vehicles are detrimental to both wildlife and human safety. A variety of mitigation methods have been deployed with the intent of increasing ungulate awareness of approaching vehicles. Wildlife warning reflectors are one such method. Roadside reflectors are designed to reflect headlights into the right‐of‐way and alert ungulates to approaching vehicles. Studies of the effectiveness of these reflectors have yielded mixed results. We conducted a robust test of reflectors in central Wyoming, USA, during 2013 and 2014, and unexpectedly discovered a potentially more effective method than the reflectors for reducing collisions between vehicles and mule deer (Odocoileus hemionus). In our initial experiment, we manipulated 10 1.6‐km segments of highway by leaving their reflectors exposed or covering them with a white canvas bag with the intention of neutralizing the reflector. The treatment configuration was swapped monthly. We counted deer carcasses under each treatment for 1 year and observed deer road‐crossing behavior using thermal video cameras. Carcass rates were 33% less in the white canvas treatment relative to uncovered reflectors. Deer in the white canvas treatment also stopped before entering the road 20% more often, ran into the road from the right‐of‐way 11% less often, and fled from the road 12% more often than when reflectors were uncovered. In a follow‐up experiment, we found that deer carcass rates were 32% less when reflectors were exposed versus covered with black canvas. We further found that deer road‐crossing behavior was least risky in a white canvas treatment, intermediate in a reflectors treatment, and most risky when reflectors were removed from posts. Taken together, these results indicate that, although reflectors were moderately effective, white canvas was substantially more effective in reducing deer–vehicle collisions. This unexpected finding suggests that new vigilance‐enhancing mitigation methods should be explored as a way to reduce wildlife–vehicle collisions. © 2018 The Wildlife Society.

Do you hear what I see? Vocalization relative to visual detection rates of Hawaiian hoary bats (Lasiurus cinereus semotus).

Bats vocalize during flight as part of the sensory modality called echolocation, but very little is known about whether flying bats consistently call. Occasional vocal silence during flight when bats approach prey or conspecifics has been documented for relatively few species and situations. Bats flying alone in clutter‐free airspace are not known to forgo vocalization, yet prior observations suggested possible silent behavior in certain, unexpected situations. Determining when, why, and where silent behavior occurs in bats will help evaluate major assumptions of a primary monitoring method for bats used in ecological research, management, and conservation. In this study, we recorded flight activity of Hawaiian hoary bats (Lasiurus cinereus semotus) under seminatural conditions using both thermal video cameras and acoustic detectors. Simultaneous video and audio recordings from 20 nights of observation at 10 sites were analyzed for correspondence between detection methods, with a focus on video observations in three distance categories for which accompanying vocalizations were detected. Comparison of video and audio detections revealed that a high proportion of Hawaiian hoary bats “seen” on video were not simultaneously “heard.” On average, only about one in three visual detections within a night had an accompanying call detection, but this varied greatly among nights. Bats flying on curved flight paths and individuals nearer the cameras were more likely to be detected by both methods. Feeding and social calls were detected, but no clear pattern emerged from the small number of observations involving closely interacting bats. These results may indicate that flying Hawaiian hoary bats often forgo echolocation, or do not always vocalize in a way that is detectable with common sampling and monitoring methods. Possible reasons for the low correspondence between visual and acoustic detections range from methodological to biological and include a number of biases associated with the propagation and detection of sound, cryptic foraging strategies, or conspecific presence. Silent flight behavior may be more prevalent in echolocating bats than previously appreciated, has profound implications for ecological research, and deserves further characterization and study.

Protection Heater Design Validation for the LARP Magnets Using Thermal Imaging

Protection heaters are essential elements of a quench protection scheme for high-field accelerator magnets. Various heater designs fabricated by LARP and CERN have been already tested in the LARP high-field quadrupole HQ and presently being built into the coils of the high-field quadrupole MQXF. In order to compare the heat flow characteristics and thermal diffusion timescales of different heater designs, we powered heaters of two different geometries in ambient conditions and imaged the resulting thermal distributions using a high-sensitivity thermal video camera. We observed a peculiar spatial periodicity in the temperature distribution maps potentially linked to the structure of the underlying cable. Two-dimensional numerical simulation of heat diffusion and spatial heat distribution have been conducted, and the results of simulation and experiment have been compared. Imaging revealed hot spots due to a current concentration around high curvature points of heater strip of varying cross sections and visualized thermal effects of various interlayer structural defects. Thermal imaging can become a future quality control tool for the MQXF coil heaters.

Plume Characteristics of Two HFA-Driven Inhaled Corticosteroid/Long-Acting Beta2-Agonist Combination Pressurized Metered-Dose Inhalers.

New inhalers propelled by hydrofluoroalkanes (HFAs) have improved plume characteristics: higher fine particle fraction, and warmer plumes with reduced force and velocity. Together, this may avoid reflex interruption of inhalation and improve lung deposition of the inhaled drugs. However, even with HFA-propelled pressurized metered-dose inhalers (pMDIs), there are notable differences in device properties. Here we compared the duration, velocity, force, and temperature of two inhaled corticosteroid/long-acting β2-agonist combination therapies, administered via HFA pMDIs: fluticasone propionate/formoterol 125/5 µg (FP/FORM; flutiform(®)) and fluticasone propionate/salmeterol 125/25 µg (FP/SAL; Seretide(®) Evohaler(®)). Inhalers were fired into ambient air. Plume duration and velocity were recorded with a high-speed camera and a pulsed laser light source. A copper disc attached to a sensitive load cell measured the plume force at various distances from the device. A thermal imaging video camera recorded impaction temperature in line with the device. The average plume duration for FP/FORM was longer than that of FP/SAL: 168.3 vs. 114.0 ms, respectively. The mean maximum plume velocities observed at 95 mm (the approximate distance between mouthpiece and throat) was consistently slower for FP/FORM (10.08 m/s) compared to FP/SAL (15.55 m/s). FP/FORM had a slower velocity at the outset, remaining relatively constant before declining steadily over the plume duration. The force of the FP/SAL plume was greater than that of FP/FORM at all distances: maximum force for FP/FORM was 138.2 vs. 278.9 mN for FP/SAL. The minimum impaction temperature was +5.9 °C for FP/FORM and -37.8 °C for FP/SAL; this difference became less pronounced over distance. There were substantial differences between the plumes of the two pMDIs. FP/FORM was warmer, less forceful, had a longer plume duration and slower maximal velocity. These plume characteristics of FP/FORM may lead to improved lung deposition. Mundipharma Research Limited, Cambridge, UK.

Dim ultraviolet light as a means of deterring activity by the Hawaiian hoary bat Lasiurus cinereus semotus

Widespread bat fatalities at industrial wind turbines are a conservation issue with the potential to inhibit efficient use of an abundant source of energy. Bat fatalities can be reduced by altering turbine operations, but such curtailment decreases turbine efficiency. If additional ways of reducing bat fatalities at wind turbines were available such tradeoffs might not be needed. Based on the facts that bats perceive distant objects primarily through vision and can see in very dim lighting conditions, and the possibility that bats might interact with turbines after approach- ing them as they would trees, we propose a novel method of reducing bat activity at wind turbines: illumination of the structure with dim light. As a first step toward assessing this approach, we illu- minated trees with dim flickering ultraviolet (UV) light in areas frequented by Hawaiian hoary bats Lasiurus cinereus semotus, an endangered subspecies affected by wind turbines. We used a repeated-measures design to quantify bat activity near trees with acoustic detectors and thermal video cameras in the presence and absence of UV illumination, while concurrently monitoring insect numbers. Results indicate that dim UV reduces bat activity despite an increase in insect numbers. Experimental treatment did not completely inhibit bat activity near trees, nor did all measures of bat activity show statistically significant differences due to high variance in bat activ- ity among sites. However, the observed decreases in bat activity with dim UV illumination justify further testing of this method as a means to reduce bat fatalities at wind turbines.

In-situ spectroscopic monitoring of Jatropha oil combustion properties

In-situ monitoring of chemical species emitted from the combustion of Jatropha oil in a practical Semawar burner were performed by means of several spectroscopic diagnostics. A practical burner commonly used in Indonesia having a built-in preheating system, called semawar, used for illumination purposes with the combustion of Jatropha oil. Non-intrusive two-dimensional (2-D) distributions of flame temperature were obtained using a thermal video camera. The experimental results showed the flame temperatures to range from 500 to 1400 °C. Chemical species generated from within the combustion zone were also determined in the Ultraviolet–visible (Uv–Vis) range from the spontaneous emission spectra of the flame. Spatial distribution of NO, C2 and OH were identified from the spectra. The 2-D distribution emission intensity visualized and recorded for NO, C2 and OH revealed high temperatures close to the root of the flame that rapidly dispersed radially outwards to provide very high temperatures over much larger volume at downstream locations. The radial stretch of the reaction zone is important for improved performance of the burner with light emission form a much wider zone. In addition, in-situ monitoring of CO2 emission of Jatropha oil was performed by using infrared (IR) spectroscopy. The presence of CO, H2O and NO were also investigated in this research. Moreover, 2D distribution of CO2 emission intensity was also visualized using an IR camera.

Hydroxyl and Nitric Oxide Distribution in Waste Rice Bran Biofuel-Octanol Flames

Two-dimensional (2-D) visualization of hydroxyl (OH) radical in combustion of biofuel made of waste rice bran oil (called W) mixed with octanol (called O) at different mixture ratios were examined in a laboratory scale facility using planar laser-induced fluorescence (PLIF) diagnostics. Rice bran oil has a composition similar to that of peanut oil, with 38% monounsaturated, 37% polyunsaturated, and 25% saturated fatty acids. The ratio of this biofuel to octanol fuel examined was W90/O10, W75/O25, and W60/O40. The chemical species generated from within the combustion zone were analyzed from the spontaneous emission spectra of the flame in the ultraviolet to visible (Uv-Vis) range. The spatial distribution of Nitric Oxide (NO) and OH, denoted as OH*, were identified from the spectra. Two-dimensional (2-D) distributions of flame temperature were obtained using a thermal video camera. The experimental results showed the temperatures to range from 600 °C to 1400 °C. The highest temperature was obtained using W60/O40 waste/octanol fuel mixture. A practical burner commonly used in Indonesia, called semawar, that have a built-in preheating system was used for the combustion of biofuels.

Classification, landing distribution, and associated flight parameters for a bomb field emplaced during a single major explosion at Stromboli, Italy

We propose a novel approach to studying a ballistic bomb deposit. Favorable circumstances, a unique dispersal axis, an operational thermal video camera, and application of an innovative methodology allowed estimates of volume and mass erupted, and definition of mass partitioning between bombs of various sizes. This allowed the creation of a multidisciplinary database for a single major explosion at Stromboli volcano (Italy), the type locality of Strombolian eruptions. The dispersion and direction of the deposit were consistent with a major explosion on 21 January 2010. Field data comprised 780 mapped bomb locations and sizes, and were organized into a GIS with a lidar-derived digital elevation model as its base. This allowed us to define the landing distribution and flight parameters for erupted bombs. The data defined discontinuous deposition to build a cluster-dominated bomb field, with a total deposit volume of ∼10 m3, a mass of ∼2 × 104 kg, and a grain size dominated by large bombs (1 m in diameter). The parameters defined here for a major eruption at Stromboli show that the Strombolian style of volcanism, and its deposits, need to be treated carefully, and a different approach is needed in the future to truly characterize and classify such small (but globally common) explosive eruptions. The recognition that sedimentation from such eruptions will be uneven leads to the important conclusion that isopachs and isopleths cannot be used to estimate eruption volumes for such explosions.

Spectroscopic Observation of Chemical Species From High-Temperature Air Pulverized Coal Combustion

In situ monitoring of chemical species from the combustion pulverized coal in high-temperature air is examined using several different spectroscopic diagnostic at different equivalence ratios. Two-dimensional (2D) distributions of flame temperature were obtained using a thermal video camera. The experimental results showed the temperatures to range from low to 1400 °C under various conditions of fuel-lean, stoichiometric, and fuel-rich. The highest temperature and flame stability were obtained under fuel-lean combustion condition. The chemical species generated from within the combustion zone were analyzed from the spontaneous emission spectra of the flame in the Ultraviolet–visible (UV-Vis) range. The spatial distribution of NO, OH, and CN were identified from the spectra. The 2D distribution of emission intensity visualized and recorded for NO, OH, and CN revealed high-temperatures close to the root of the flame that rapidly dispersed radially outward to provide very high temperatures over a much larger volume at further downstream locations of the flame.

Exploring Channeling Optimized Radiofrequency Energy: a Review of Radiofrequency History and Applications in Esthetic Fields

Because of its high efficiency and safety, radiofrequency (RF) energy is widely used in the dermatological field for heating biological tissue in various esthetic applications, including skin tightening, skin lifting, body contouring, and cellulite reduction. This paper reviews the literature on the use of nonablative RF energy in the esthetic field and its scientific background. The purpose of this article is to describe in detail the extensive use of medical devices based on RF technology, the development of these medical devices over the years, and recent developments and trends in RF technology. The authors conducted a systematic search of publications that address safety and efficacy issues, technical system specifications, and clinical techniques. Finally, the authors focused on their own clinical experiences with the use of patented Channeling Optimized RF Energy technique and mechanical massage. An in-vivo study was conducted in domestic pigs, with a thermal video camera. Twenty-seven female patients participated in a cellulite and body shaping study. The treatments were conducted according to a three-phase protocol. An additional 16 females participated in a skin tightening case study. All of the patients underwent three treatment sessions at 3-week intervals, each according to a protocol specific to the area being treated. The review of the literature on RF-based systems revealed that these systems are safe, with low risks for potential side effects, and effective for cellulite, body contouring, and skin tightening procedures. The in-vivo measurements confirmed the theory that the penetration depth of RF is an inverse function of its frequency, and using a vacuum mechanism makes an additional contribution to the RF energy penetration. The heating effect of RF was also found to increase blood circulation and to induce collagen remodeling. The results from the cellulite and body shaping treatments showed an overall average improvement of 55% in the appearance of cellulite, with an average circumferential reduction of 3.31 cm in the buttocks, 2.94 cm in the thighs, and 2.14 cm in the abdomen. The results from the skin tightening procedure showed moderate improvement of skin appearance in 50% and significant improvement in 31%. At the follow-up visits the results were found to be sustained without any significant side effects. Of all tissue heating techniques, RF-based technologies appear to be the most established and clinically proven. The design and specifications of the described vacuumassisted bipolar RF device fall within the range of the specifications currently prescribed for esthetic, nonablative RF systems.

Drying of flowing liquid film on rotating disk

Recently, development of high technology has been required for the formation of uniform thin film in manufacturing processes of semiconductor as the precision instruments become more sophisticated. A method called spin coating is often used for spreading photoresist on a wafer surface and drying photoresist film. In spin coating process, photoresist is uniformly spread on the wafer surface by centrifugal force caused by rotating wafer. However, it is a serious concern that streaky lines, which are caused by spiral vortices, appear on the wafer surface and prevent the formation of uniform film in the case of high rotating speed. On the other hand, in the case of low rotating speed, a small hump of the film is formed near the wafer edge. The main purpose of this study is to make clear the drying characteristics of the flowing liquid film on the rotating wafer. Temperature distribution of the flowing liquid film is captured by an infrared thermal video camera and radial gradient of the film temperature is introduced in order to evaluate the drying characteristic of the flowing film under steady state condition. Effects of the flow rate of the liquid film on the film temperature are investigated. The film temperature gradually decreases in the radial direction in all cases. At low rotating speed, the radial gradient of the film temperature is almost constant widely. On the other hand, at high rotating speed, the radial gradient of the film temperature takes a certain maximum value. It is found that the location of the gradient peak corresponds with the transition region of the air boundary layer, in which spiral vortices swirl, and shifts to the inner side of the disk with an increase of the liquid flow rate.

Finite element modeling of coating formation and transient heat transfer in the electric arc spray process

The electric arc sprayed coating can be described as a superposition of Gaussian profile particles whose overlapping depends on the movement of spray gun. The heat transfer behavior during the deposition has a significant influence on the performance of the process. In this paper, simulation of the coating formation and analysis of the transient heat transfer were performed based on a newly developed finite element model, in which the dynamic stochastic multiple particles deposition characteristic of the process was taken into account. In order to investigate the effects of the kinematics and dimensional aspects on the coating/substrate temperature distribution, a traditional layer-by-layer finite element model without consideration of gun movement and particles Gaussian profile was also performed as a comparison. The stochastic deposition model provided a more objective result of the transient heat transfer of the coating/substrate than that of the layer-by-layer model, especially the severely inhomogeneous temperature distribution characteristics in different locations and spraying conditions. Finally, the molding results were experimentally compared with the temperature measurements on the coating surface and substrate back face using an infrared thermal imaging video camera, which shows that most of the modeling findings are consistent with that of the experiment.