Search Results (742)

This research presents a novel, low-cost optical acquisition system based on infrared imaging for real-time weld bead geometry monitoring in Gas Metal Arc Welding (GMAW). The system uniquely employs a commercial CCD camera (1000–1150 nm) with tailored filters and lenses to isolate molten pool thermal radiation while mitigating arc interference. A single camera and a mirror-based setup simultaneously capture weld bead width and reinforcement. Acquired images are processed in real time (10 ms intervals) using MATLAB R2016b algorithms for edge segmentation and geometric parameter extraction. Dimensional accuracy under different welding parameters was ensured through camera calibration modeling. Validation across 35 experimental trials (over 6000 datapoints) using laser profilometry and manual measurements showed errors below 1%. The resulting dataset successfully trained a Support Vector Machine, highlighting the system’s potential for smart manufacturing and predictive modeling. This study demonstrates the viability of high-precision, low-cost weld monitoring for enhanced real-time control and automation in welding applications. Full article

Thermal cameras are known for their ability to overcome lighting constraints and provide reliable thermal radiation images. This capability facilitates methods for depth and ego-motion estimation, enabling efficient learning of poses and scene structures under all-day conditions. However, the existing studies on depth prediction for thermal images are limited. In practical applications, thermal cameras capture sequential frames. Unfortunately, the potential of this multi-frame aspect is underutilized by the previous methods, resulting in limitations on the depth prediction accuracy of thermal videos. To leverage the multi-frame advantages of thermal videos and to improve the accuracy of monocular depth estimation from thermal images, we propose a framework for self-supervised depth and ego-motion learning from multi-frame thermal images. We construct a multi-view stereo (MVS) cost volume from temporally adjacent thermal frames. The construction process is adjusted based on the estimated pose, which serves as a motion hint. To stabilize the motion hint and improve pose estimation accuracy, we design a motion enhancement module that utilizes self-generated poses for additional supervisory signals. Additionally, we introduce RGB images in the training phase to form a multi-spectral loss, thereby augmenting the performance of the thermal model. The experimental results, conducted on a public dataset, demonstrate the proposed method’s accurate estimation of depth and ego-motion across varying light conditions, surpassing the performance of the self-supervised baseline. Full article

Winter road icing poses significant safety risks, particularly on steep urban slopes with vulnerable populations. While thermal-comfort indices such as UTCI, PMV, and PET have been used for summer conditions, this study focuses on operational indices that quantify road-icing risk. This study introduces and empirically validates two novel indices—Freezing Intensity (FI) and Cold Intensity (CI)—designed to quantify the likelihood and severity of road icing. A case study was conducted on Namgyeong-maeul Road in Daedeok-gu, Daejeon, South Korea, where IoT-based environmental monitoring, including automated weather stations, thermal cameras, and drone imaging, was deployed from December 2024 to January 2025. Results demonstrate that road heating systems (RHS) effectively increased surface temperatures by an average of 4.1 °C compared to non-heated segments, with maximum differences exceeding 12.5 °C. The FI of non-heated slopes reached critical levels above 2400, whereas heated roads reduced FI to near zero. Similarly, CI values dropped from hazardous levels (~12) to below 6 in heated zones, reducing icing severity by more than 50%. These findings confirm that FI and CI can serve as robust metrics for operational assessment of RHS performance, complementing traditional heat-related indices. By integrating FI and CI into monitoring and design, policymakers and engineers can establish data-driven activation thresholds, optimize energy efficiency, and ensure safer winter mobility for vulnerable groups. This research provides a structured operational framework for winter road icing quantification, advancing climate adaptation strategies equivalent in rigor to summer climate indices. Compared with temperature-only monitoring, FI and CI improved operational responsiveness and reduced residual icing duration by ≈50%. Full article

The accurate monitoring of body temperature is critical to poultry health and welfare. Rectal thermometry, the conventionally employed method, is invasive and stressful. Infrared thermography (IRT) offers a non-invasive alternative, but its accuracy may be influenced by body size and camera-to-object distance. This study evaluated the efficiency of thermal imaging compared with rectal thermometry in measuring chicken body temperature, with a focus on the effects of body size and measurement distance. A cross-sectional, repeated-measures design was applied to ninety clinically healthy Buff Sussex chickens (n = 30 per size group: small, medium, and large). Each bird was imaged from three distances (50, 75, and 100 cm) by using a thermal camera (FLIR C5^®), with rectal temperature (Omron MC-246^®) serving as the reference, so that a total of 270 paired observations were analyzed. Agreement was assessed using Bland–Altman bias and limits of agreement (LOAs), root mean square error (RMSE), mean absolute error (MAE), Pearson correlation (r), and Lin’s concordance correlation coefficient (CCC). The results showed that rectal temperatures were consistent with the normal physiological range reported for healthy chickens (40.43–41.95 °C) and that thermal imaging showed systematic underestimation, particularly in small birds (bias of up to −2.65 °C and RMSE of 2.72 °C at 100 cm) and medium-sized birds (bias of −0.73 to −1.39 °C), with weak concordance (CCC ≤ 0.16). Measurements in large birds demonstrated the smallest bias (−0.76 to +0.16 °C), lower errors (MAE of 0.73–0.89 °C), and stronger correlations (r = 0.56–0.71), indicating more reliable agreement. Distance influenced accuracy, with underestimation increasing at 75–100 cm, especially in smaller birds. Therefore, thermal imaging cannot fully replace rectal thermometry for individual-level assessment in chickens due to systematic underestimation, especially in small birds and at greater distances. However, it shows promise as a rapid, non-invasive flock-level screening tool in larger chickens when used at optimal distances (50–75 cm). The integration of thermal imaging into precision livestock farming and future farm models may enhance welfare-friendly, automated health monitoring in poultry systems. Full article

Unmanned Aerial Vehicles (UAVs) equipped with thermal and RGB cameras and enhanced by deep learning offer a powerful solution for autonomous photovoltaic (PV) system inspection. However, defect detection performance depends on flight parameters such as altitude, camera angles, speed, and solar position. This study examines the impact of various UAV flight parameters on the accurate detection of critical PV defects including hotspots, dirt from bird droppings, dust accumulation, and cell failures. For this purpose, two datasets were developed, comprising over 38,000 thermal infrared and RGB images. Using the YOLOv11 model, 21 flight configurations varying in altitude, camera tilt and pan angles, speed, and solar position were evaluated at four different times of day to assess the combined ambient and geometric effects on detection accuracy. Results indicate that low-altitude flights enhance small-object detection, while higher altitudes improve coverage at the expense of fine-detail accuracy. Dust detection is most effective when the camera aligns with the sun, whereas steep midday tilts cause reflective false positives. Thermal defect detection performs best during morning flights with moderate tilt angles. These findings emphasize the need to balance accuracy, coverage, efficiency, and safety, offering practical guidelines for effective and scalable PV inspection and maintenance. Full article

This study investigated a novel method of recovering energy from iron ore sinter using solid iron oxide heat transfer materials. Traditionally, air is passed through the sinter either in an open conveyor or a sealed vessel to recover energy. The bed materials used were a magnetite concentrate, hematite ore, goethite–hematite ore and sinter fines. A shortwave thermal camera and quartz reactor were used measure infrared radiation from the process. The thermal imaging was combined with image analysis techniques to visualise the transfer of thermal energy through the system. The results showed that energy moved rapidly through the system with peak heating rates of 18 °C/min at a lump sinter temperature of 600 °C. The ratio of heating rate to cooling rate was as high as 8.6:1.0, indicating efficient retention of energy by the bed materials. The bed composition, determined by X-ray fluorescence and X-ray diffraction was used to calculate the heat capacity based on pure material properties. The resultant energy balance determined thermal efficiency to be between 32 and 46% for the sinter fines and hematite–goethite ore, resulting in predicted fuel savings of up to 9.4kg/tonne with similar heat utilisations to the air recovery process. Thermal imaging combined with Brunauer–Emmett–Teller surface area measurements and scanning electron microscopy analysis experimentally replicated mathematical heat transfer model predictions that a smaller total pore volume resulted in less thermally resistive bed. Image analysis illustrated the breaking of the heat front between the less resistive solid and more resistive air in porous beds versus even conduction of heat through a dense bed. The oxide distribution in the bed materials impacted heat transfer, as at a lump temperature of 500 °C was controlled by hydrated oxide content whereas at 600 °C Fe₂O₃ was the more dominant driver. Full article

The images acquired from near infrared cameras can contain thermal noise, which degrades the quality of the images. The quality of the images obtained from underwater environments suffer from the complex hydrological environment. All these issues make the profile-extraction in these images a difficult task. In this work, two non-learning systems are built for making filters by using wavelets transform combined with simple functions. They can be shown to extract profiles in the images acquired from the near infrared camera and underwater environment. Furthermore, they are useful for low-light image enhancement, edge/array detection, and image fusion. The increase in the measurement by entropy can be found by enhancing the scale of the filters. When processing the near infrared images, the values of running time, the memory usage, Signal-to-Noise Ratio (SNR), and Peak Signal-to-Noise Ratio (PSNR) are generally smaller in the operators of Canny, Roberts, Log, Sobel, and Prewitt than those in the Atanh filter and Sech filter. When processing the underwater images, the values of running time, the memory usage, SNR, and PSNR are generally smaller in Sobel operator than those in the Atanh filter and Sech filter. When processing the low-light images, it can be seen that the Atanh filter obtains the highest values of the running time and the memory usage compared to the filter based on the Retinex model, the Sech filter, and a matched filter. Our designed filters require little computational resources comparing to learning-based ones and hold the merits of being multifunctional, which may be useful for advanced imaging in the field of bio-medical engineering. Full article

Multi Jet Fusion (MJF) is a leading technology for producing functional polymer parts. However, it still faces challenges with dimensional accuracy and removing unfused powder from complex internal geometries. First, dimensional accuracy was mapped by producing 45 identical PA12 specimens on an HP MJF 4200 printer in a 5 × 9 layout across five vertical layers. The analysis revealed a consistent pattern: parts located in the central positions of the build volume exhibited the poorest accuracy, while those near the perimeter were the most precise, regardless of their vertical height. This spatial variation is attributed to non-uniform thermal control from the printer’s adaptive lamp–thermal camera system. Second, the limits of powder removal from closed body-centered cubic (BCC) lattice structures were quantified. Using sandblasting and X-ray inspection, a strong inverse relationship was found between a lattice’s relative density and the maximum thickness that could be thoroughly cleaned of powder. For example, low-density structures (ρ = 0.07) could be cleaned up to five layers deep, whereas high-density structures (ρ = 0.39–0.47) were limited to only 1.5–1.7 layers. These findings offer actionable guidelines for optimizing part placement and designing internal lattice structures for MJF technology. The key findings are the spatial variation in dimensional accuracy in MJF printing, where the central parts are the least accurate and perimeter parts are the most precise, and the inverse relationship between a lattice’s relative density (ρ) and cleanable thickness. Specifically, low-density structures (ρ = 0.07) could be thoroughly cleaned up to five layers, while high-density ones (ρ = 0.39–0.47) were limited to approximately 1.5–1.7 layers. The layer thickness was a pre-designed parameter (2, 3, 4, and 5 layers), and powder removal was supported by using automated sandblasting followed by verification via industrial X-ray imaging. Full article

To achieve professional roe deer population management and to mitigate wildlife-related agricultural damage, a wildlife population estimation trial was conducted in Hungary using an ultralight aircraft with dual sensors (thermal and DSLR camera) to assess the method’s applicability, using the roe deer as a model species. The test took place in early spring, at an altitude of 400 m above ground level and a flight speed of 150 km/h. The survey targeted a total count of a 1040 hectare area using adjacent 200 m-wide strips. This strip-based design also allowed for a methodological comparison between total count and strip sample count approaches. Object-based image classification was applied, and species-level validation was performed. During the survey, a total of 213 roe deer were localised. The average group size was 9.17 ± 1.7 ($\overline{\mathrm{x}}$ ± SE), with two prominent outliers (28 and 34 individuals). Compared to the density value of 0.205 individuals/ha established through the full-area census, the simulated estimations (50% and 25%) showed considerable under- and overestimation, primarily due to the aggregative behaviour of roe deer. Based on the test, aerial population estimation using dual-sensor technology proved to be effective in agricultural habitats; however, the accuracy of the results is strongly influenced by the sampling design applied. Full article

In Central Europe, the fawning season of roe deer (Capreolus capreolus) directly overlaps with meadow and alfalfa harvest, typically from late May to early June. During these operations, tens or more likely hundreds of thousands of fawns are mutilated by agricultural machinery. To mitigate this unethical mortality, wildlife managers often deploy odor repellents to drive roe deer individuals from high-risk fields before mowing. Therefore, we evaluated repellent efficacy in a paired design. The abundance of roe deer was quantified by drones equipped with thermal cameras before and after repellent application and then compared with untreated control meadows. Results showed high adult abundance that did not differ significantly among treatments. The highest median was paradoxically observed on meadows “after application” (8.25 ind./10 ha), followed by “not treated” meadows (7.92 ind./10 ha), and “before application” (5.72 ind./10 ha). For fawns, differences between treated and untreated plots were likewise non-significant. Their numbers increased over time after application, consistent with the peak of parturition in the second half of May. Overall, the study confirms that the tested odor repellent, when applied according to the manufacturer’s protocol, did not reduce roe deer presence on meadows. This underscores the need to consider alternative approaches, such as the use of thermal-imaging drones combined with the subsequent translocation of detected fawns to safe locations. Full article

Arthritis and arthrosis are prevalent joint diseases that cause pain and disability, and their early diagnosis is crucial for preventing irreversible damage. Conventional diagnostic methods such as X-ray, ultrasound, and MRI have limitations in early detection, prompting interest in alternative techniques. This work presents the design and clinical evaluation of a prototype device for non-invasive early diagnosis of arthritis (inflammatory joint disease) and arthrosis (osteoarthritis) using infrared thermography and deep neural networks. The portable prototype integrates a Raspberry Pi 4 microcomputer, an infrared thermal camera, and a touchscreen interface, all housed in a 3D-printed PLA enclosure. A custom Flask-based application enables two operational modes: (1) thermal image acquisition for training data collection, and (2) automated diagnosis using a pre-trained ResNet50 deep learning model. A clinical study was conducted at a university clinic in a temperature-controlled environment with 100 subjects (70% with arthritic conditions and 30% healthy). Thermal images of both hands (four images per hand) were captured for each participant, and all patients provided informed consent. The ResNet50 model was trained to classify three classes (healthy, arthritis, and arthrosis) from these images. Results show that the system can effectively distinguish healthy individuals from those with joint pathologies, achieving an overall test accuracy of approximately 64%. The model identified healthy hands with high confidence (100% sensitivity for the healthy class), but it struggled to differentiate between arthritis and arthrosis, often misclassifying one as the other. The prototype’s multiclass ROC (Receiver Operating Characteristic) analysis further showed excellent discrimination between healthy vs. diseased groups (AUC, Area Under the Curve ~1.00), but lower performance between arthrosis and arthritis classes (AUC ~0.60–0.68). Despite these challenges, the device demonstrates the feasibility of AI-assisted thermographic screening: it is completely non-invasive, radiation-free, and low-cost, providing results in real-time. In the discussion, we compare this thermography-based approach with conventional diagnostic modalities and highlight its advantages, such as early detection of physiological changes, portability, and patient comfort. While not intended to replace established methods, this technology can serve as an early warning and triage tool in clinical settings. In conclusion, the proposed prototype represents an innovative application of infrared thermography and deep learning for joint disease screening. With further improvements in classification accuracy and broader validation, such systems could significantly augment current clinical practice by enabling rapid and non-invasive early diagnosis of arthritis and arthrosis. Full article

Situation awareness is essential for ensuring safety in hazardous environments, where timely and accurate information is critical for decision-making. Unmanned Aerial Vehicles (UAVs) have emerged as valuable tools in enhancing situation awareness by providing real-time data and monitoring capabilities in high-risk areas. This study explores the integration of advanced technologies, focusing on imaging and sensor technologies such as thermal, spectral, and multispectral cameras, deployed in critical zones. By merging these technologies into UAV platforms, responders gain access to essential real-time information while reducing human exposure to hazardous conditions. This study presents case studies and practical applications, highlighting the effectiveness of these technologies in a range of hazardous situations. Full article

Thermal imaging is increasingly applied in remote sensing to identify material degradation, monitor structural integrity, and support energy diagnostics. However, its adoption is limited by the low spatial resolution of thermal sensors compared to RGB cameras. This study proposes a modular pipeline to generate thermally enriched 3D point clouds by fusing RGB and thermal imagery acquired simultaneously with a dual-sensor unmanned aerial vehicle system. The methodology includes geometric calibration of both cameras, image undistortion, cross-spectral feature matching, and projection of radiometric data onto the photogrammetric model through a computed homography. Thermal values are extracted using a custom parser and assigned to 3D points based on visibility masks and interpolation strategies. Calibration achieved 81.8% chessboard detection, yielding subpixel reprojection errors. Among twelve evaluated algorithms, LightGlue retained 99% of its matches and delivered a reprojection accuracy of 18.2% at 1 px, 65.1% at 3 px and 79% at 5 px. A case study on photovoltaic panels demonstrates the method’s capability to map thermal patterns with low temperature deviation from ground-truth data. Developed entirely in Python, the workflow integrates into Agisoft Metashape or other software. The proposed approach enables cost-effective, high-resolution thermal mapping with applications in civil engineering, cultural heritage conservation, and environmental monitoring applications. Full article

Several approaches are currently being used by law enforcement to locate the remains of victims. Yet, traditional methods are invasive and time-consuming. Unmanned Aerial Vehicle (UAV)-based remote sensing has emerged as a potential tool to support the location of human remains and clandestine graves. While offering a non-invasive and low-cost alternative, UAV-based remote sensing needs to be tested and validated for forensic case work. To assess current knowledge, a systematic review of 19 peer-reviewed articles from four databases was conducted, focusing specifically on UAV-based remote sensing for human remains and clandestine grave location. The findings indicate that different sensors (colour, thermal, and multispectral cameras), were tested across a range of burial conditions and models (human and mammalian). While UAVs with imaging sensors can locate graves and decomposition-related anomalies, experimental designs from the reviewed studies lacked robustness in terms of replication and consistency across models. Trends also highlight the potential of automated detection of anomalies over manual inspection, potentially leading to improved predictive modelling. Overall, UAV-based remote sensing shows considerable promise for enhancing the efficiency of human remains and clandestine grave location, but methodological limitations must be addressed to ensure findings are relevant to real-world forensic cases. Full article

The identification of estrus at the right moment allows for a higher success of fecundity with artificial insemination. Evaluating changes in body surface temperature of sows during the estrus period using an infrared thermography camera (ITC) can provide an accurate model to predict these changes. This pilot study comprised nine crossbred Large White x Landrace sows, providing 59 data records for analysis. Observed changes in the behavior and physiological signs of the sows signaled the identification of estrus. Images of the ocular area, ear tips, breast, back, vulva, and perianal area were collected with the ITC. The images were analyzed using the FLIR Thermal Studio Starter software. Infrared mean temperatures were reported and compared using ANOVA and Tukey–Kramer tests (p < 0.05). Supervised machine learning models were tested using random forest (RF), Conditional inference trees (Ctree), Partial least squares (PLS), and K-nearest neighbors (KNN), and the method performance was measured using a confusion matrix. The orbital region showed significant differences between estrus and non-estrus states in sows. In the confusion matrix, the algorithm predicted estrus with 87% accuracy in the test set, which contained 40% of the data, when agitated behavior was combined with orbital area temperature. These findings suggest the potential for integrating behavioral and physiological observations with orbital thermography and machine learning to detect estrus in sows under field conditions accurately. Full article