Search Results (476)

Alkyd resins are among the most common coatings used for exterior wood joinery. In Romania, solvent-borne alkyd coatings are widely used to finish wood. The study aims to compare the performance after 7 years of outdoor exposure of two types of alkyd coatings, a semi-transparent brown stain with micronized pigments (Alk1) and an opaque white enamel (Alk2), applied directly on wood or wood pre-treated with three types of resins: acryl-polyurethane (R1), epoxy (R2), and alkyd-polyurethane (R3). Fir (Abies alba) wood served as the substrate. Cracking, coating adhesion, and biological degradation were periodically assessed through visual inspection and microscopy. Additionally, a cross-cut test was performed, and the loss of coating on the directly exposed upper faces was measured using ImageJ. The results indicated that resin pretreatments somewhat reduced cracking but negatively affected coating adhesion after long-term exposure. All samples pretreated with resins and coated with Alk1 lost more than 50% (up to 78%) of the original finishing film by the end of the test. In comparison, coated control samples lost less than 50%. The Alk2 coating exhibited a film loss between 2% and 12%, compared to an average loss of 9% for the coated control. Overall, samples pretreated with alkyd-polyurethane resin (R3) and coated with alkyd enamel (Alk2) demonstrated the best performance in terms of cracking, adhesion, and discoloration. Full article

This study proposes a CatBoost-enhanced hyperspectral modeling approach for accurate prediction of wood dyeing formulations. Using Pinus sylvestris var. mongolica veneer as the substrate, 306 samples with gradient dye concentrations were prepared, and their reflectance spectra (400–700 nm) were acquired. After noise reduction and sensitive band selection (400–450 nm, 550–600 nm, and 600–650 nm), spectral descriptors were extracted as model inputs. The CatBoost algorithm, optimized via k-fold cross-validation and grid search, outperformed XGBoost, random forest, and SVR in prediction accuracy, achieving MSE = 0.00271 and MAE = 0.0349. Scanning electron microscopy (SEM) revealed the correlation between dye particle distribution and spectral response, validating the model’s physical basis. This approach enables intelligent dye formulation control in industrial wood processing, reducing color deviation (ΔE < 1.75) and dye waste by approximately 25%. Full article

Background/Objectives: Interstitial lung disease (ILD) is frequently complicated by pulmonary hypertension (PH), which is associated with reduced exercise capacity and poor prognosis. Early and accurate non-invasive detection of PH remains a clinical challenge. This study evaluated whether combining quantitative CT analysis of lung fibrosis with cardiac MRI-derived measures of right ventricular (RV) function improves the diagnostic accuracy of PH in patients with ILD. Methods: We retrospectively analyzed 72 ILD patients who underwent chest CT, cardiac MRI, and right heart catheterization (RHC). Lung fibrosis was quantified using a Gaussian Histogram Normalized Correlation (GHNC) software that computed the proportions of diseased lung, ground-glass opacity (GGO), honeycombing, reticulation, consolidation, and emphysema. MRI was used to assess RV end-systolic volume (RVESV), ejection fraction, and RV longitudinal strain. PH was defined as a mean pulmonary arterial pressure (mPAP) ≥ 20 mmHg and pulmonary vascular resistance ≥ 3 Wood units on RHC. Results: Compared to patients without PH, those with PH (n = 21) showed significantly reduced RV strain (−13.4 ± 5.1% vs. −16.4 ± 5.2%, p = 0.026) and elevated RVESV (74.2 ± 18.3 mL vs. 59.5 ± 14.2 mL, p = 0.003). CT-derived indices also differed significantly: diseased lung area (56.4 ± 17.2% vs. 38.4 ± 12.5%, p < 0.001), GGO (11.8 ± 3.6% vs. 8.65 ± 4.3%, p = 0.005), and honeycombing (17.7 ± 4.9% vs. 12.8 ± 6.4%, p = 0.0027) were all more prominent in the PH group. In receiver operating characteristic curve analysis, diseased lung area demonstrated an area under the curve of 0.778 for detecting PH. This increased to 0.847 with the addition of RVESV, and further to 0.854 when RV strain was included. Combined models showed significant improvement in risk reclassification: net reclassification improvement was 0.700 (p = 0.002) with RVESV and 0.684 (p = 0.004) with RV strain; corresponding IDI values were 0.0887 (p = 0.03) and 0.1222 (p = 0.01), respectively. Conclusions: Combining CT-based fibrosis quantification with cardiac MRI-derived RV functional assessment enhances the non-invasive diagnosis of PH in ILD patients. This integrated imaging approach significantly improves diagnostic precision and may facilitate earlier, more targeted interventions in the management of ILD-associated PH. Full article

The accurate identification of wood patterns is critical for optimizing the use of sustainable wood building materials, promoting resource efficiency, and reducing waste in construction. This study presents a deep learning-based approach for enhanced wood material recognition, combining EfficientNet architecture with advanced data augmentation techniques to achieve robust classification. The augmentation strategy incorporates geometric transformations (flips, shifts, and rotations) and photometric adjustments (brightness and contrast) to improve dataset diversity while preserving discriminative wood grain features. Validation was performed using a controlled augmentation pipeline to ensure realistic performance assessment. Experimental results demonstrate the model’s effectiveness, achieving 88.9% accuracy (eight out of nine correct predictions), with further improvements from targeted image preprocessing. The approach provides valuable support for preliminary sustainable building material classification, and can be deployed through user-friendly interfaces without requiring specialized AI expertise. The system retains critical wood pattern characteristics while enhancing adaptability to real-world variability, supporting reliable material classification in sustainable construction. This study highlights the potential of integrating optimized neural networks with tailored preprocessing to advance AI-driven sustainability in building material recognition, contributing to circular economy practices and resource-efficient construction. Full article

Outdoor cleaning robots must operate reliably across diverse and unstructured surfaces, yet many existing systems lack the adaptability to handle terrain variability. This paper proposes a terrain-aware cleaning framework that dynamically adjusts robot behavior based on real-time surface classification and slope estimation. A 128-channel LiDAR sensor captures signal intensity images, which are processed by a ResNet-18 convolutional neural network to classify floor types as wood, smooth, or rough. Simultaneously, pitch angles from an onboard IMU detect terrain inclination. These inputs are transformed into fuzzy sets and evaluated using a Mamdani-type fuzzy inference system. The controller adjusts brush height, brush speed, and robot velocity through 81 rules derived from 48 structured cleaning experiments across varying terrain and slopes. Validation was conducted in low-light (night-time) conditions, leveraging LiDAR’s lighting-invariant capabilities. Field trials confirm that the robot responds effectively to environmental conditions, such as reducing speed on slopes or increasing brush pressure on rough surfaces. The integration of deep learning and fuzzy control enables safe, energy-efficient, and adaptive cleaning in complex outdoor environments. This work demonstrates the feasibility and real-world applicability for combining perception and inference-based control in terrain-adaptive robotic systems. Full article

Acoustic tomography is a non-destructive technique used in the internal assessment of standing trees. Various researchers have focused on developing analytical tools using this technique, demonstrating that they can detect internal biodeterioration in cross-sections with good accuracy. This study evaluates the use of two ultrasonic wave devices with different frequencies (USLab and Sylvatest Duo) and a stress wave device (Microsecond Timer) to generate acoustic tomography using ImageWood VC1 software. The tests were carried out on 12 cross-sections of urban trees in the city of Madrid of the species Robinia pseudoacacia L., Platanus × hybrida Brot., Ulmus pumila L., and Populus alba L. Velocity measurements were made, forming a diffraction mesh in both standing trees and logs after cutting them down. An inspection was carried out with a perforation resistance drill (IML RESI F-400S) in the radial direction in each section, which allowed for more precise identification of defects and differentiating between holes and cracks. The various defects were determined with greater accuracy in the tomographic images taken with the higher-frequency equipment (45 kHz), and the combination of ultrasonic tomography and the use of the inspection drill can provide a more accurate representation of the defects. Full article

The study of cultural landscapes has a tradition stretching back several decades. During this time, methods have been developed based on the geographical data and technological capabilities available. However, with new data becoming available, new methodological and conceptual challenges arise in linking different types of landscape data. In our article, we attempt to address these challenges. These include historical maps and remote sensing data, such as aerial and satellite images and LiDAR data. We illustrate these using examples of traditional heritage landscapes in Slovakia. We critically evaluated the informational value of historical maps and their connection with remote sensing data. Our case studies focused on using LiDAR data to identify overgrowing processes, historical trackways, agricultural terraces, catchworks and tree vegetation in wood pastures. Digital technology provides new and more accurate data, as well as new ways of evaluating it, thereby enriching existing landscape ecological methods of cultural landscape research. Full article

This paper presents a mobile robotic system designed for autonomous navigation and forest and tree trait estimation, with a focus on the location of individual trees and the diameter of the trunks. The system integrates light detection and ranging data and images using a framework based on simultaneous localization and mapping (SLAM) and a deep learning model for trunk segmentation and tree keypoint detection. Field experiments conducted in a wooded area in Udine, Italy, using a skid-steered mobile robot, demonstrate the effectiveness of the system in navigating, while avoiding obstacles (even in cases where the Global Navigation Satellite System signal is not reliable). The results highlight that the proposed robotic system is capable of autonomously generating maps of forests as point clouds with minimal drift thanks to the loop closure strategy integrated in the SLAM algorithm, and estimating tree traits automatically. Full article

To address the persistent challenge of low recognition accuracy in precious wood species classification, this study proposes a novel methodology for identifying Pterocarpus santalinus, Pterocarpus tinctorius (PTD), and Pterocarpus tinctorius (Zambia). This approach synergistically integrates artificial neural networks (ANNs) with advanced image feature extraction techniques, specifically Fast Fourier Transform, Gabor Transform, Wavelet Transform, and Gray-Level Co-occurrence Matrix. Features were extracted from both transverse and longitudinal wood sections. Fifteen distinct ANN models were subsequently developed: hybrid-section models combined features from different sections using a single algorithm, while multi-algorithm models aggregated features from the same section across all four algorithms. The dual-section hybrid wavelet model (LC4) demonstrated superior performance, achieving a perfect 100% recognition accuracy. High accuracies were also observed in the four-parameter combination models for longitudinal (L5) and transverse (C5) sections, yielding 97.62% and 91.67%, respectively. Notably, 92.31% of the LC4 model’s test samples exhibited an absolute error of ≤1%, highlighting its high reliability and precision. These findings confirm the efficacy of integrating image processing with neural networks for fine-grained wood identification and underscore the exceptional discriminative power of wavelet-based features in cross-sectional data fusion. Full article

Face milling with end-mill tools represents a solution for woodworking applications on small-scale or complex surfaces, but information regarding the surface quality per specific tool type, wood material, and processing parameters is still limited. Therefore, this study examined the surface quality of tangential oak and maple CNC face-milled with two end-mill tools—straight-edged and helical—for three values of stepover (5, 7, 9 mm) and two cutting depths (1 and 3 mm). The surface quality was analyzed with roughness parameters, roughness profiles, and stereomicroscopic images and was referenced to that of very smooth surfaces obtained by super finishing. The helical end mill caused significant fiber tearing in maple and disrupted vessel outlines, while prominent tool marks such as regular ridges across the grain were noticed in oak. The best surface roughness was obtained in the case of the straight-edged tool and minimum stepover and depth of cut, which came closest to the quality of the shaved surfaces. An increase in the cutting depth generally increased the core surface roughness and fuzziness, for both tools, and this trend increased with an increase in the stepover value. The species-dependent machining quality implies that the selection of tool geometry and process parameters must be tailored per species. Full article

Object detection is a mature problem in autonomous driving, with pedestrian detection being one of the first commercially deployed algorithms. It has been extensively studied in the literature. However, object detection is relatively less explored for fisheye cameras used for surround-view near-field sensing. The standard bounding-box representation fails in fisheye cameras due to heavy radial distortion, particularly in the periphery. In this paper, a generic object detection framework is implemented using the base YOLO (You Only Look Once) detector to systematically explore various object representations using the public WoodScape dataset. First, we implement basic representations, namely the standard bounding box, the oriented bounding box, and the ellipse. Secondly, we implement a generic polygon and propose a novel curvature-adaptive polygon, which obtains an improvement of 3 mAP (mean average precision) points. A polygon is expensive to annotate and complex to use in downstream tasks; thus, it is not practical to use it in real-world applications. However, we utilize it to demonstrate that the accuracy gap between the polygon and the bounding box representation is very high due to strong distortion in fisheye cameras. This motivates the design of a distortion-aware optimal representation of the bounding box for fisheye images, which tend to be banana-shaped near the periphery. We derive a novel representation called a curved box and improve it further by leveraging vanishing-point constraints. The proposed curved box representations outperform the bounding box by 3 mAP points and the oriented bounding box by 1.6 mAP points. In addition, the camera geometry tensor is formulated to provide adaptation to non-linear fisheye camera distortion characteristics and improves the performance further by 1.4 mAP points. Full article

This paper presents the effect of wood treatment with cellulose nanofibers on its parameters. The wettability, color changes (also after UV+IR radiation), equilibrium moisture content and mechanical parameters of wood treated with cellulose nanofibers (CNF) in three concentrations (0.5, 1 and 2%) were determined. Wood treatment with CNF increased the wettability of its surface, as evidenced by lower values of the contact angle (24.3–56.3 degrees) compared to untreated wood (98.3 degrees). The SEM images indicated the formation of cellulose nanofiber networks on the wood surface, especially in the case of 2% CNF-treated wood, which formed a well-adhered and homogenous film. Wood treated with 0.5% CNF showed a lower total color change (∆E*) value (1.9) after aging compared to untreated wood (2.9), indicating that the color changes in the treated wood were very small and recognizable only to an experienced observer, while the color differences in the control wood were recognizable to an inexperienced observer. Furthermore, CNF showed no negative effect on the strength parameters of the treated wood and only slightly affected the equilibrium moisture content for both sorption phases over the entire relative humidity range compared to control samples. The results prove the effective use of cellulose nanofibers in wood treatment, which can be an ecological and non-toxic component of wood protection systems. Full article

Pine wilt disease (PWD) is a severe forest disease caused by the infestation of pine wood nematodes. Due to its short disease cycle and strong transmission ability, it has caused significant damage to China’s forestry resources. To achieve large-scale monitoring of PWD, this study utilized machine learning/deep learning algorithms with Sentinel-1/2 images in the Google Earth Engine cloud platform to implement province-wide PWD monitoring in Anhui Province, China. The study also analyzed the spatial distribution of PWD in Anhui Province from two perspectives—spatiotemporal patterns and influencing factors—aiming to investigate the spatiotemporal evolution patterns and the impact of influencing factors on the occurrence of PWD. The results show that (1) the random forest model exhibited the strongest performance, followed by the CNN model, while the DNN model performed the worst. Using the RF model to monitor PWD and calculate the affected area in Anhui Province from 2019 to 2024 yielded errors within 30% compared to official statistics. (2) PWD in Anhui Province showed a clear clustering trend, with global Moran’s indices all exceeding 0.79 from 2019 to 2024. The LISA map revealed a spread pattern from south to north and from west to east. (3) Topographic and temperature factors had the greatest influence on PWD distribution. SHAP analysis indicated that topographic and climatic factors were the primary drivers of PWD-affected areas, with slope and temperature being the two most significant contributing factors. This study helps to rapidly and accurately identify outbreak areas during epidemics and enables precise quarantine measures and targeted control efforts. Full article

Pine wilt disease poses a significant threat to pine forests worldwide, necessitating efficient and accurate detection of dead pine wood for effective disease control and forest management. Traditional deep learning methods based on supervised closed-set paradigms often struggle to address unknown interfering objects, causing false positives, missed detection, and increased annotation burdens. To overcome these challenges, we propose SS-OPDet, a semi-supervised open-set detection framework that leverages a small amount of labeled data along with abundant unlabeled data. SS-OPDet integrates a Weighted Multi-scale Feature Fusion module to dynamically integrate global- and local-scale features, thereby significantly improving representational accuracy for dead pine wood. Additionally, a Dynamic Confidence Pseudo-Label Generation strategy categorizes predictions by confidence level, effectively reducing training noise and maximizing the use of reliable unlabeled data. Experimental results from 7733 UAV images demonstrate that SS-OPDet achieves an average precision (${AP}_K$) of 84.73%, a recall ($R_K$) of 94.48%, an Absolute Open-Set Error (AOSE) of 271 and a Wilderness Impact (WI) of 0.0917%. Cross-region validation further confirms the robustness and generalization capability of the proposed framework. The proposed method offers a cost-effective and accurate solution for timely detection of pine wilt disease, providing substantial benefits to forest monitoring and management. Full article

Wood drying is the most critical and energy-intensive process in the wood industry. However, the complex pore structure of wood significantly affects its thermal performance. Therefore, it is essential to study the relationship between the pore structure and the thermal properties of wood. In this study, X-ray-computed tomography (XCT) technology, combined with digital image processing (DIP) techniques, was used to visualize and characterize the three-dimensional structure of oak samples. Parameters such as porosity, pore size and distribution, and fractal dimensions were obtained to investigate their relationship with thermal conductivity. Subsequently, the thermal conductivities of the oak samples in the tangential, radial, and axial directions were simulated based on their three-dimensional structure. The simulation results were validated using the transient plane source method (TPS). The results showed that there were significant differences in porosity and pore size between earlywood and latewood, which in turn affect the correlation between fractal dimension and thermal conductivity. The higher the self-similarity of the wood structure is, the stronger the correlation between porosity and fractal dimension will be. Due to the limitations of CT resolution and threshold segmentation methods, there may be some axial deviations in the heat transfer simulation based on XCT. However, overall, this method provides a relatively accurate estimate of the effective thermal conductivity of oak wood. In addition, the pit structure and the research on heat conduction of wood-based multi-scale pore structures are of crucial importance to the study of heat conduction in wood. Full article