Thermal Infrared Images Research Articles

Integrating Thermal Infrared Imaging and Weather Data for Short-Term Prediction of Building Envelope Thermal Appearance

This study presents a novel deep-learning framework for predicting the thermal appearance of building envelopes under varying weather conditions based on a new dataset collected using a thermal infrared camera at 10 min intervals over a one-and-a-half-year period. Unlike existing studies that rely on simulated data or physical models that do not always accurately reflect the complex heat transfer processes in real buildings, we have collected a large dataset showing how a building behaves under different climatic conditions. We propose a novel deep-learning approach that integrates weather data and thermal imagery to predict the temperature distribution on the building façade for the next 24 and 48 h. The model uses a state-of-the-art recurrent neural network architecture, PredRNN V2, with an action conditioning mechanism to incorporate weather forecasting data into the prediction process. We evaluate this approach in terms of average accuracy, prediction accuracy in specific regions, and visual-perceptual performance of the images. The proposed framework achieves a prediction accuracy of 1.5 °C (root mean square error—RMSE) for the 24 h prediction and 2.04 °C (RMSE) for the 48 h prediction, outperforming baseline models in terms of temperature prediction accuracy and structural similarity of the predicted images.

Cross-Spectral Navigation with Sensor Handover for Enhanced Proximity Operations with Uncooperative Space Objects

Close-proximity operations play a crucial role in emerging mission concepts, such as Active Debris Removal or small celestial bodies exploration. When approaching a non-cooperative target, the increased risk of collisions and reduced reliance on ground intervention necessitate autonomous on-board relative pose (position and attitude) estimation. Although navigation strategies relying on monocular cameras which operate in the visible (VIS) spectrum have been extensively studied and tested in flight for navigation applications, their accuracy is heavily related to the target’s illumination conditions, thus limiting their applicability range. The novelty of the paper is the introduction of a thermal-infrared (TIR) camera to complement the VIS one to mitigate the aforementioned issues. The primary goal of this work is to evaluate the enhancement in navigation accuracy and robustness by performing VIS-TIR data fusion within an Extended Kalman Filter (EKF) and to assess the performance of such navigation strategy in challenging illumination scenarios. The proposed navigation architecture is tightly coupled, leveraging correspondences between a known uncooperative target and feature points extracted from multispectral images. Furthermore, handover from one camera to the other is introduced to enable seamlessly operations across both spectra while prioritizing the most significant measurement sources. The pipeline is tested on Tango spacecraft synthetically generated VIS and TIR images. A performance assessment is carried out through numerical simulations considering different illumination conditions. Our results demonstrate that a combined VIS-TIR navigation strategy effectively enhances operational robustness and flexibility compared to traditional VIS-only navigation chains.

Research on the multitarget 3D trajectory tracking method of Thalassodes immissaria in the thermal infrared region based on YOLOX-GMM and SORT-Pest.

Studying the behavioral responses and movement trajectories of insects under different stimuli is crucial for developing more effective biological control measures. Therefore, accurately obtaining the movement trajectories and behavioral parameters of insects in three-dimensional space is essential. This study used the litchi pest Thalassodes immissaria as the research object. A special binocular vision observation system was designed for nighttime movement. A thermal infrared camera was used for video recording of T. immissaria in a lightless environment. Moreover, a multi-object tracking method based on the YOLOX-GMM and SORT-Pest algorithms was proposed for tracking T. immissaria in thermal infrared images. By obtaining the central coordinates of the two T. immissaria in the video, target matching and 3D trajectory reconstruction in the parallel binocular system were achieved. Error analysis of the T. immissaria detection and tracking model, as well as the 3D reconstruction model, showed that the average accuracy of T. immissaria detection reached 89.6%, tracking accuracy was 96.9%, and the average error of the reconstructed 3D spatial coordinates was 15 mm. These results indicate that the method can accurately obtain the 3D trajectory and motion parameters of T. immissaria. Such data can greatly contribute to researchers' comprehensive understanding of insect behavioral patterns and habits, providing important support for more targeted control strategies.

Thermal Infrared Orthophoto Geometry Correction Using RGB Orthophoto for Unmanned Aerial Vehicle

The geometric correction of thermal infrared (TIR) orthophotos generated by unmanned aerial vehicles (UAVs) presents significant challenges due to low resolution and the difficulty of identifying ground control points (GCPs). This study addresses the limitations of real-time kinematic (RTK) UAV data acquisition, such as network instability and the inability to detect GCPs in TIR images, by proposing a method that utilizes RGB orthophotos as a reference for geometric correction. The accelerated-KAZE (AKAZE) method was applied to extract feature points between RGB and TIR orthophotos, integrating binary descriptors and absolute coordinate-based matching techniques. Geometric correction results demonstrated a significant improvement in regions with stable and changing environmental conditions. Invariant regions exhibited an accuracy of 0.7~2 px (0.01~0.04), while areas with temporal and spatial changes saw corrections within 5~7 px (0.10~0.14 m). This method reduces reliance on GCP measurements and provides an effective supplementary technique for cases where GCP detection is limited or unavailable. Additionally, this approach enhances time and economic efficiency, offering a reliable alternative for precise orthophoto generation across various sensor data.

A Dataset of Visible Light and Thermal Infrared Images for Health Monitoring of Caged Laying Hens in Large-Scale Farming.

Considering animal welfare, the free-range laying hen farming model is increasingly gaining attention. However, in some countries, large-scale farming still relies on the cage-rearing model, making the focus on the welfare of caged laying hens equally important. To evaluate the health status of caged laying hens, a dataset comprising visible light and thermal infrared images was established for analyses, including morphological, thermographic, comb, and behavioral assessments, enabling a comprehensive evaluation of the hens' health, behavior, and population counts. To address the issue of insufficient data samples in the health detection process for individual and group hens, a dataset named BClayinghens was constructed containing 61,133 images of visible light and thermal infrared images. The BClayinghens dataset was completed using three types of devices: smartphones, visible light cameras, and infrared thermal cameras. All thermal infrared images correspond to visible light images and have achieved positional alignment through coordinate correction. Additionally, the visible light images were annotated with chicken head labels, obtaining 63,693 chicken head labels, which can be directly used for training deep learning models for chicken head object detection and combined with corresponding thermal infrared data to analyze the temperature of the chicken heads. To enable the constructed deep-learning object detection and recognition models to adapt to different breeding environments, various data enhancement methods such as rotation, shearing, color enhancement, and noise addition were used for image processing. The BClayinghens dataset is important for applying visible light images and corresponding thermal infrared images in the health detection, behavioral analysis, and counting of caged laying hens under large-scale farming.

Urban surface-emitted longwave radiation estimation from high spatial resolution thermal infrared images using a hybrid method

Accurate estimation of the surface-emitted longwave radiation (SELR) has important scientific value in understanding its spatiotemporal dynamics and surface thermal environment. Thermal infrared (TIR) images with high spatial resolution offer enhanced data support for studying SELR of complex surfaces, such as urban surface. This study proposes a new urban-oriented hybrid (UoHy) method, which considers multiple scattering and adjacent effects of urban pixel using the term sky view factor, to estimate urban SELR from the top-of-atmosphere radiance of TIR images with high spatial resolution, and performs sensitivity analysis and application. The experimental results for the thermal images of GF-5/VIMS as an example showed that the UoHy method has relatively high accuracy, and obtains SELR errors of less than 12.0 W/m2 under low atmospheric water vapor conditions and less than 17.0 W/m2 under high atmospheric water vapor conditions. The application of the method during daytime and nighttime also demonstrated the method's validity and effectiveness. Compared with the natural surface-oriented hybrid method, the UoHy method obtains an improvement of about 7.0–10.0 W/m2 in SELR estimation, which indicates that it has the potential for practical SELR estimation over urban surface with TIR images of high spatial resolution.

Search region updating with hierarchical feature fusion for accurate thermal infrared tracking

Due to their resilience against lighting variations, thermal infrared (TIR) images demonstrate robust adaptability in diverse environments, enabling effective object tracking even in intricate scenarios. Nevertheless, TIR target tracking encounters challenges such as fast target motion and interference from visually similar objects, substantially compromising the tracking precision of TIR trackers. To surmount these challenges, we propose a method grounded in the strategy of search region updating and hierarchical feature fusion, tailored for the precise TIR target-tracking task. Specifically, to address the issue of fast motion causing the target to depart from the search region, we propose to update the current search region by leveraging historical frame information. Additionally, we employ a hierarchical feature fusion strategy to contend with interference from visually similar objects in the tracking scenario. This strategy enhances the ability to model and represent the target more accurately, thereby elevating the tracker’s capacity to discriminate between the target and similar objects. Furthermore, to tackle the challenge of inaccurate estimation of target bounding boxes, we introduce an enhanced Intersection over Union (IoU) loss function, which improvement facilitates a more precise prediction of target bounding boxes, resulting in superior target localization. Extensive experiments substantiate that our tracker exhibits a commendable level of competitiveness when compared to other trackers.

Correction of instrument temperature dependence of detector responsivity for measurements of comet 67P acquired by Rosetta's Visible and InfraRed Thermal Imaging Spectrometer, Mapping channel (VIRTIS-M).

The Mapping channel of the Visible and InfraRed Thermal Imaging Spectrometer (VIRTIS-M) aboard Rosetta acquired many hyperspectral images of comet 67P/Churyumov-Gerasimenko (hereafter 67P). The VIS channel detector responsivity was dependent on the VIS detector temperature (TVIS). This affects the absolute values of the measured spectra (for a TVIS increase of 1K between 0.06% increase at 0.55μm and 1.2% increase at 1μm) and the spectral slopes. Here, we derive a simple parameterization of this CCD-typical effect based on a statistical analysis of the TVIS-related bias of the measurements. At this, we include all measured VIS spectra excluding acquisitions with little nucleus surface information or at opposition geometry, thereby achieving a high statistical significance and representativity. The corresponding VIS detector responsivity correction, slightly different for measurements acquired when the IR cryocooler was off or on, makes the spectra measured at different instrument temperatures consistent over the entire Rosetta mission phase at 67P. This will improve future quantitative analyses of the data.

Application of Visual Transformer in Low-resolution Thermal Infrared Image Recognition

Abstract Addressing the challenges of inadequate accuracy and limited robustness exhibited by current lightweight object detection networks specifically tailored for low-resolution thermal infrared face detection scenarios, this paper delves into developing an ultra-lightweight thermal infrared face detection algorithm that leverages visual attention mechanisms. To ascertain the optimal neural network complexity, a series of comparative experiments are meticulously conducted. With Yolo-FastestDet serving as the benchmark, this study endeavors to compress the backbone network, striking a delicate balance between network depth and detection speed. Additionally, to bolster the network’s capacity for profound feature extraction and precise discrimination of target edges and small objects, a Transformer-Encoder-based visual attention module is seamlessly integrated. Consequently, a lightweight face detection algorithm, enriched with attention mechanisms, is formulated. Furthermore, to mitigate the scarcity of low-resolution infrared face image data, a self-constructed visible-infrared face dataset is employed for training and evaluation purposes. The experimental outcomes reveal that the proposed algorithm attains an impressive mAP@0.5 score of 0.953 on the test dataset while satisfying the stringent real-time detection criterion of 30 frames per second (FPS) when deployed on an embedded Raspberry Pi CPU.

FCS-Net: Feather condition scoring of broilers based on dense feature fusion of RGB and thermal infrared images

Assessing the feather condition of broilers is crucial for monitoring the animal welfare status and detecting the occurrence of feather pecking activities. Currently, the feather condition of individual broilers is manually scored by trained experts. To provide a more objective and efficient tool for feather condition scoring, a novel deep learning-based model, named Feather Condition Scoring Network (FCS-Net), was proposed based on RGB and thermal infrared images. The FCS-Net model combined the ResNet18 architecture with the proposed Dense Feature Fusion (DFF) module, which can effectively learn the feature mapping relationship between RGB and thermal infrared images. Before inputting the images into the network, an image registration process was conducted to align the RGB and thermal infrared images. The results showed that the FCS-Net model had a good performance for feather condition scoring, with the Accuracy of 97.02%, the Precision of 96.99%, the Recall of 97.04%, the F1 of 97.01%, and the Inference speed of 15.34 fps. Compared to the ResNet18_RGB model, which only utilise RGB images, the FCS-Net model showed notable improvements in Accuracy by 4.02%, Precision by 3.90%, Recall by 4.08%, and F1 by 4.01%. Moreover, it was observed that the FCS-Net model focused more on the back region of the broilers through heatmap visualization. Furthermore, the algorithm was compared with six typical image recognition algorithms including VGG16, ResNet18, SE-ResNet18, DenseNet121, Mobilenet_V2, and Shufflenet_V2_x1_0, as well as the state-of-the-art (SOTA) feather condition assessment methods. The results showed that the FCS-Net model achieved better performance than the six algorithms and the SOTA feather condition assessment methods. This study provided a valuable reference for automated monitoring of feather condition scoring of broilers in smart farming.

Twenty Years of Thermal Infrared Observations (2004–2024) at Campi Flegrei Caldera (Italy) by the Permanent Surveillance Ground Network of INGV-Osservatorio Vesuviano

Thermal infrared (TIR) time series images acquired by ground, proximal TIR stations provide valuable data to study evolution of surface temperature fields of diffuse degassing volcanic areas. This paper presents data processing results related to TIR images acquired since 2004 by six ground stations in the permanent thermal infrared surveillance network at Campi Flegrei (TIRNet) set up by INGV-Osservatorio Vesuviano. These results are reported as surface temperature and heat flux time series. The processing methodologies, also discussed in this paper, allow for presentation of the raw TIR image data in a more comprehensible form, suitable for comparisons with other geophysical parameters. A preliminary comparison between different trends in the surface temperature and heat flux values recorded by the TIRNet stations provides evidence of peculiar changes corresponding to periods of intense seismicity at the Campi Flegrei caldera. During periods characterized by modest seismicity, no remarkable evidence of common temperature variations was recorded by the different TIRNet stations. Conversely, almost all the TIRNet stations exhibited common temperature variations, even on a small scale, during periods of significant seismic activity. The comparison between the seismicity and the variations in the surface temperature and heat flux trends suggests an increase in efficiency of heat transfer between the magmatic system and the surface when an increase in seismic activity was registered. This evidence recommends a deeper, multidisciplinary study of this correlation to improve understanding of the volcanic processes affecting the Campi Flegrei caldera.

Time series of alpine snow surface radiative-temperature maps from high-precision thermal-infrared imaging

Abstract. The surface temperature of snow cover is a key variable, as it provides information about the current state of the snowpack, helps predict its future evolution, and enhances estimations of the snow water equivalent. Although satellites are often used to measure the surface temperature despite the difficulty of retrieving accurate surface temperatures from space, calibration–validation datasets over snow-covered areas are scarce. We present a dataset of extensive measurements of the surface radiative temperature of snow acquired with an uncooled thermal-infrared (TIR) camera. The set accuracy goal is 0.7 K, which is the radiometric accuracy of the TIR sensor of the future CNES/ISRO TRISHNA mission. TIR images have been acquired over two winter seasons, November 2021 to May 2022 and February to May 2023, at the Col du Lautaret, 2057 m a.s.l. in the French Alps. During the first season, the camera operated in the off-the-shelf configuration with rough thermal regulation (7–39 °C). An improved setup with a stabilized internal temperature was developed for the second campaign, and comprehensive laboratory experiments were carried out in order to characterize the physical properties of the components of the TIR camera and its calibration. Thorough processing, including radiometric processing, orthorectification, and a filter for poor-visibility conditions due to fog or snowfall, was performed. The result is two winter season time series of 130 019 maps of the surface radiative temperature of snow with meter-scale resolution over an area of 0.5 km2. The validation was performed against precision TIR radiometers. We found an absolute accuracy (mean absolute error, MAE) of 1.28 K during winter 2021–2022 and 0.67 K for spring 2023. The efforts to stabilize the internal temperature of the TIR camera therefore led to a notable improvement of the accuracy. Although some uncertainties persist, particularly the temperature overestimation during melt, this dataset represents a major advance in the capacity to monitor and map surface temperature in mountainous areas and to calibrate–validate satellite measurements over snow-covered areas of complex topography. The complete dataset is provided at https://doi.org/10.57932/8ed8f0b2-e6ae-4d64-97e5-1ae23e8b97b1 (Arioli et al., 2024a) and https://doi.org/10.57932/1e9ff61f-1f06-48ae-92d9-6e1f7df8ad8c (Arioli et al., 2024b).

Can Multiscale Thermal Infrared Imaging Help Validate and Monitor Water Stress in Alluvial Forests?

ABSTRACTAlluvial forests are sensitive to drought induced by climate change and exacerbated by altered flow regimes. Our ability to detect and map their sensitivity to drought is crucial to evaluate the effects of climate change and adjust management practices. Therefore, we explore the potential of multiscale thermal infrared imagery (TIR) to diagnose their sensitivity to droughts. In summer 2022, we sampled leaves and phloem on Populus nigra trees from two sites with contrasted hydrological connectivity along the Ain River (France) to investigate the seasonality of water stress and act as ground truth for airborne TIR images. To map forest sensitivity to drought, we used TIR data from four airborne campaigns and Landsat archives over a larger spatial and temporal extent. Field data showed that stress conditions were reached for both sites but were higher in the site with lower groundwater connectivity, which was also the case for individual tree crown temperatures. At the forest plot scale, canopy temperature was linked to forest connectivity for two of four TIR campaigns, with higher values in the more degraded reaches. Landsat data were used to locate the areas of the riparian forest impacted by a historical drought event and monitor their recovery and proved useful to identify trends. TIR data showed promising results to help detect and map tree water stress in riparian environments. However, stress is not detected in all TIR campaigns, demonstrating that one‐shot TIR acquisitions alone are not enough to diagnose stress and complementary in‐field eco‐physiological measurements are necessary.

Facile preparation of graphene aerogel as a thermal insulation material

A simple low temperature and cost-effective hydrothermal method via reduction self-assembly and freeze-drying was fabricated to prepare graphene aerogel (rGO). After the reduction process, most of the oxygen-containing groups in graphene oxide have been removed by ascorbic acid. The surface C/O atomic ratio detected in rGO is about 7.26. The aerogel presents a nanoporous structure. This porous structure could act as a barrier to heat conduction. By heating the graphene aerogel and using infrared thermal imager to detect the temperature, the temperature difference between the top and the bottom of the aerogel reached 80 °C, which showed excellent thermal insulation performance. In addition, by testing the thermal imaging image of graphene aerogel placed on the skin surface, it exhibited an infrared stealth effect. This carbon aerogel may offer potential for the fabrication and application for thermal insulation and infrared stealth material systems.

Advanced visualisation of biomass charcoal combustion dynamics using MWIR hyperspectral and LWIR thermal imaging under varied airflow conditions

Biomass charcoal combustion is a complex process, significantly influenced by various operating parameters. Among these parameters, air supply emerges as a critical factor affecting combustion efficiency, gas emissions, and thermal dynamics. In this study, we explored these complex interdependencies using a novel combination of mid-wavelength infrared (MWIR) hyperspectral imaging and long-wavelength infrared (LWIR) thermal imaging, under different airflow rates. Our findings demonstrated that while increased airflow accelerated the overall combustion rate, it simultaneously decreased combustion efficiency. Specifically, the thermal profiles showed an increased surface temperature at a low flowrate (0.5 L/min) while decreasing in temperature with higher flowrates. The decreased system temperature led to a lower combustion efficiency because of the reduced conversion rate from combustible gases (CH4 and CO) into CO2 and H2O. Additionally, the results also demonstrated that cooling effects of the high flowrates primarily impeded the solid-phase combustion stage. This is further corroborated by the temporal and spatial variation in the emissions of key gas species (H2O vapor, CH4, CO, and CO2) observed through hyperspectral imaging. The emission evolution of these gases displayed the different stages of the gas-phase and solid-phase combustion. The spatial distribution of the trace gases showed a decreased distribution radius due to the enhanced diffusion to the fuel surface when the airflow increases, aligning well with the two-film model established in the literature. Furthermore, we utilised spectral radiance ratios (CO/CO2, CH4/CO2, H2O/CO2) to gain additional insights into the combustion dynamics. These ratios evidenced the decrease in combustion efficiency at high airflow rates. Finally, the increased H2O/CO2 ratio further demonstrated the impeded char combustion and a shift towards pyrolysis at higher airflow rates because of the decreased thermal equilibrium of the system. The findings from this study provide critical insights into the dynamics of biomass charcoal combustion and illuminates the path for optimising energy efficiency and assessing the environmental implications from burning biomass fuels.

Multi-scale feature extraction and fusion with attention interaction for RGB-T tracking

RGB-T single-object tracking aims to track objects utilizing both RGB images and thermal infrared(TIR) images. Though the siamese-based RGB-T tracker shows its advantage in tracking speed, its accuracy still cannot be compared with other state-of-the-art trackers (e.g., MDNet). In this study, we revisit the existing siamese-based RGB-T tracker and find that such fall behind comes from insufficient feature fusion between RGB image and TIR image, as well as incomplete interactions between template frame and search frame. Inspired by this, we propose a multi-scale feature extraction and fusion network with Temporal-Spatial Memory (MFATrack). Instead of fusing RGB image and TIR image with the single-scale feature map or only high-level features from the multi-scale feature map, MFATrack proposes a new fusion strategy by fusing features from all scales, which can capture contextual information in shallow layers and details in the deep layer. To learn the feature better for tracking tasks, MFATrack fuses the features via several consecutive frames. In addition, we also propose a self-attention interaction module specifically designed for the search frame, highlighting the features in the search frame that are relevant to the target and thus facilitating rapid convergence for target localization. Experimental results demonstrate the proposed MFATrack is not only fast, but also can obtain better tracking accuracy compared with other competing methods including MDNet-based methods and other siamese-based trackers.

Highly robust thermal infrared and visible image registration with canny and phase congruence detection

When a dual-optical vehicle-mounted camera is photographed, visible and thermal infrared (VI-T) images cannot be registered, and realising fine matching of the images to solve for the optimal affine parameters is thus key to this research. Visible and thermal image matching is of great interest owing to the presence of challenging scale transformations, nonlinear radial aberrations, and robustness under illumination conditions. Thus, this paper presents a novel algorithm, namely, Highly Robust Thermal Infrared and Visible Image Registration with Canny and Phase Congruence Detection (HRCP). Firstly, the image is pre-processed, and feature point detection is performed by combining adaptive thresholding GW-Canny edge detection and phase coherence (PC), which increases the edge information. Secondly, SURF and FAST feature detection at the maximum distance of PC maps can obtain stable and reliable feature points, which are robust to scale invariance and rotation invariance. Finally, the optimal affine parameter is solved using the least square method with several iterations. Compared to existing matching methods, we find that VI-T image matching is particularly sensitive to both lighting factors and scale-transformed nonlinear radial distortion and that HRCP is robust in performing matching. For the randomly selected dataset, the average image matching time is reduced by 3.265 s, the number of correct image matches increases by 44 pairs on average, the root mean square error improves to 1.830, and the average error improves to 2.815. The proposed method not only improves the inaccuracy of radiation-insensitive feature transform matching in both low and high light, but also achieves a higher accuracy and an increase in the number of feature matching points, which facilitates robust VI-T image registration.

Land Surface Temperature Anomalies as Indicators of Urban Land Cover Change—A Study of Two Indian Cities

Rapid urbanisation over the years has led to the loss of natural land cover, thereby affecting Land Surface Temperature (LST) distribution in urban areas. This study aims to analyse LST anomalies (calculated as the deviation from the normal) over selected Indian cities and check if critical land cover changes can be identified. LST from Landsat Thermal Infrared (TIR) images acquired in March, April and May from 1988 to 2020 were used to estimate LST anomalies. Positive LST anomalies were observed mainly over barren and impervious areas; however, some areas showed a negative anomaly where the barren lands were converted to vegetated areas. The study has demonstrated that while some developed areas exhibit a positive anomaly indicative of significant changes or development, there are instances where the conversion of barren land to developed (i.e. built up) areas has resulted in a negative anomaly. Developed areas that are closer to the water creek or mangroves were associated with lower anomaly values indicating the cooling effect of the water body and vegetation. Conversely, the core urban areas generally exhibited higher LST values with positive anomalies indicating a warming effect. These findings can be used by city planners to identify hotspot areas and develop more effective strategies and policies to address the challenges of urban heat. They also highlight the regions that require infrastructural resources and policy changes to reduce the temperature.

Study on crack propagation mechanism and acoustic-thermal sensitivity analysis of pre-cracked weakly cemented rock

As the intensity and depth of coal mining gradually increase, environmental disturbances become more complex, and the degree of crack development in weakly cemented surrounding rocks continues to increase. In order to study the influence mechanism of crack angle on the fracture mechanism and acoustic − thermal precursor information of weakly cemented rocks, visual biaxial loading tests were conducted on pre-cracked weakly cemented rocks based on a transparent servo loading device, combined with digital speckle correlation method (DSCM), acoustic emission (AE), and infrared thermal imaging (ITI). The research results indicate that as the inclination angle of cracks increases, the initial strength, peak strength, and elastic modulus of rocks exhibit a logarithmic relationship of first decreasing and then increasing. When the inclination angle of the crack increases from < 30° to > 75°, the failure mode of weakly cemented rocks changes from shear to tension. The propagation path of deformation localization is consistent with the propagation trajectory of surface cracks, and the extension length and time of tensile cracks are longer than those of shear cracks. The acoustic − thermal sensitivity of weakly cemented rocks with crack inclination angle of > 45° is higher than that with crack inclination angle of ≤ 30°. The research results contribute to further understanding and mastering the mechanism of crack initiation and propagation in weakly cemented rocks containing joints, and provide theoretical guidance for engineering methods to control the deformation of weakly cemented surrounding rocks.

PVF-10: A high-resolution unmanned aerial vehicle thermal infrared image dataset for fine-grained photovoltaic fault classification

Accurate identification of faulty photovoltaic (PV) modules is crucial for the effective operation and maintenance of PV systems. Deep learning (DL) algorithms exhibit promising potential for classifying PV fault (PVF) from thermal infrared (TIR) images captured by unmanned aerial vehicle (UAV), contingent upon the availability of extensive and high-quality labeled data. However, existing TIR PVF datasets are limited by low image resolution and incomplete coverage of fault types. This study proposes a high-resolution TIR PVF dataset with 10 classes, named PVF-10, comprising 5579 cropped images of PV panels collected from 8 PV power plants. These classes are further categorized into two groups according to the repairability of PVF, with 5 repairable and 5 irreparable classes each. Additionally, the circuit mechanisms underlying the TIR image features of typical PVF types are analyzed, supported by high-resolution images, thereby providing comprehensive information for PV operators. Finally, five state-of-the-art DL algorithms are trained and validated based on the PVF-10 dataset using three levels of resampling strategy. The results show that the overall accuracy (OA) of these algorithms exceeds 83%, with the highest OA reaching 93.32%. Moreover, the preprocessing procedure involving resampling and padding strategies are beneficial for improving PVF classification accuracy using PVF-10 datasets. The developed PVF-10 dataset is expected to stimulate further research and innovation in PVF classification.