Search Results (375)

Texture anomaly segmentation aims to localize irregularities on textured surfaces, a task critical for industrial quality control. Supervised methods require extensive labeled data, while unsupervised approaches often struggle to generalize to unseen target domains. Recent zero-shot methods based on vision-language models such as Contrastive Language-Image Pretraining (CLIP) enable anomaly detection through text prompts without target-domain training data. However, existing approaches typically rely on generic prompts and show limited sensitivity to fine-grained texture variations. To address these limitations, we propose TextureCLIP, a cross-dataset zero-shot framework with auxiliary training for texture anomaly segmentation. The framework is trained on source texture data from the MVTec AD texture subset using annotated source-domain samples and directly evaluated on six unseen target datasets without access to target-domain training images, annotations, or fine-tuning. The proposed Triadic Descriptive Prompting (TriDP) integrates normal prompts, generic anomaly prompts, and descriptive anomaly prompts to provide complementary semantic cues for improved cross-domain generalization. To enhance spatial sensitivity, Dual Attention Modules (DAMs) are incorporated into the CLIP image encoder to refine local feature representations. In addition, Softmax-Weighted Averaging (SMWA) aggregates multiple anomaly cues by emphasizing the prompt responses with higher similarity scores. Experimental results demonstrate that TextureCLIP achieves strong and consistent performance across diverse texture datasets, attaining 67.06% AP and 65.69% F1-max, with improvements of 5.17 and 2.66 percentage points over the competitive baselines, respectively. Full article

Background: Patellar motion trajectory (PMT) is a key kinematic parameter for evaluating patellofemoral joint (PFJ) stability, but traditional static imaging indices are unable to capture the dynamic six-degrees-of-freedom (6-DOF) characteristics of patellar motion throughout the entire knee flexion–extension cycle. Four-dimensional computed tomography (4D-CT) facilitates in vivo dynamic imaging of the PFJ, while the systematic classification of PMT in asymptomatic populations has remained underexplored. Methods: A retrospective cross-sectional study was performed on 64 asymptomatic and functionally normal knees that underwent 4D-CT dynamic scanning from March 2021 to December 2025. Patellar 6-DOF kinematic data during 0° to 90° of knee flexion–extension were extracted through manifold optimization, automatic segmentation, and spatial registration. Following standardization of the motion cycle, unsupervised K-means clustering was employed to classify PMT phenotypes, with nonparametric tests used to analyze intergroup kinematic differences and evaluate clustering quality. Results: Three distinct PMT types were identified based on clustering validity indices, including a silhouette score of 0.381, a Davies-Bouldin index of 0.916, and a Calinski–Harabasz index of 44.06: Type 1 (7.81%, 35.11 ± 6.56 mm), Type 2 (56.25%, 15.67 ± 6.59 mm), and Type 3 (35.94%, 2.82 ± 2.41 mm). Lateral translation (Tx) served as the dominant determinant for PMT typing (p < 0.001), whereas non-lateral DOF parameters exhibited no consistent intergroup differences. Postural DOFs exhibited coupled fluctuations with Tx but had no independent stratification effect. Traditional static imaging parameters demonstrated no consistent correlation with these dynamic subtypes. Conclusions: Functionally asymptomatic knees exhibited three in vivo patellar 6-DOF motion trajectory phenotypes dominated by lateral translation amplitude. This 4D-CT-based typing framework provides a dynamic kinematic baseline for PFJ stability evaluation and lays a foundation for individualized optimization of ligament reconstruction and pathophysiological research of patellofemoral disorders. Full article

Vision-based defect detection on bearing-pad wear surfaces is essential for quantifying damage geometry and assessing condition in hydroturbine units. Compared with 2D color images, depth images can suppress disturbances caused by complex textures, surface color variations, and specular reflections, thereby providing a more reliable basis for precise damage localization. Nevertheless, depth-based damage segmentation under a large field of view remains challenging, mainly due to fine-scale texture noise and weak defect saliency; moreover, robust defect probability estimation is often hindered by limited labeled data. To address these challenges, this paper proposes an unsupervised defect segmentation framework for hydroturbine friction components guided by local anomaly score distributions. First, a salient damage detection module is developed based on topography–texture separation, which mitigates the interference of local micro-texture noise on defect segmentation. Then, a normal reference dataset is constructed using defect-free bearing-pad depth images, and an unsupervised network is employed as the core to generate anomaly score representations of potential damage regions for coarse localization. Finally, the obtained anomaly score distribution is used as adaptive weights to fuse depth-based defect cues with morphological processing, enabling self-adaptive refinement of the damage regions. Experiments on real depth images acquired from hydroturbine bearing pads demonstrate that the proposed method achieves accurate defect extraction and reliable geometric quantification. Quantitative evaluations on the testing set yield a mean surface area error of 9.39% ± 4.25% and a volume error of 4.91% ± 2.85%, with best-case errors dropping as low as 3.67% and 1.03%, respectively. Crucially, these results demonstrate that our framework goes beyond mere visual detection; by operating entirely without pixel-level annotations, it offers a highly practical tool for diagnosing specific lubrication failure modes and driving predictive maintenance in actual hydroturbine engineering. Full article

X-band marine radar offers unique advantages for monitoring nearshore oil spills. However, oil films and sea clutter exhibit high pixel intensity overlap in radar images. Traditional threshold segmentation and machine learning methods have certain limitations in terms of feature extraction, Region of Interest (ROI) guidance, threshold optimization adaptability, and unsupervised capabilities. To address these issues, a method of oil film detection for ship radar based on multi-dimensional feature-guided extraction and hybrid optimization search is proposed. By combining Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering with multidimensional features, this method automatically extracts ROIs under unlabeled conditions, effectively suppressing sea clutter interference. Subsequently, an improved Beaver Behavior Optimizer (BBO) and simulated annealing (SA) hybrid algorithm (BBO-SA) is introduced within the ROIs, along with a designed adaptive temperature update strategy, to achieve coordinated optimization of global and local searches. The experimental results demonstrate that the method described in this paper performs exceptionally well across all evaluation metrics, confirming its accuracy and robustness in oil film detection. It provides a viable technical approach for emergency monitoring of nearshore oil spills. Full article

Arctic sea ice is a critical indicator of global climate dynamics, directly influencing maritime navigation, polar biodiversity, and offshore engineering safety. The precise mapping of diverse ice types, such as frazil ice, slush, melt ponds, and open water, is essential for environmental monitoring; however, it remains a formidable challenge in satellite remote sensing. These difficulties arise from low-contrast imagery, overlapping spectral signatures, and the subtle textural nuances characteristic of polar regions. Traditional entropy-based thresholding techniques often falter when segmenting these complex scenes, as they typically rely on Gaussian distribution assumptions that do not align with the stochastic nature of Arctic data. To address these limitations, this paper presents a novel unsupervised segmentation framework based on symmetric cross-entropy (SCE). Unlike standard directional measures, SCE provides a more robust objective function for multi-level thresholding by simultaneously maximizing intra-class cohesion and minimizing inter-class ambiguity. The proposed method uses an optimized search strategy to identify intensity levels that best delineate complex Arctic features. We conducted an extensive entropy-based comparative study that benchmarked SCE against 25 state-of-the-art entropy measures, including Shannon, Kapur, Rényi, Tsallis, and Masi entropies. Our experimental results demonstrate that the SCE method: (i) achieves superior accuracy by consistently outperforming established models in segmentation precision and boundary definition; (ii) provides visual clarity by producing segments with significantly reduced noise, making them ideal for identifying small-scale melt ponds and slush zones; and (iii) demonstrates computational robustness by providing stable threshold values even in datasets with non-Gaussian class distributions and poor illumination. Ultimately, these improvements deliver high-quality ice feature data that enhance risk assessment, operational planning, and predictive modeling. This research marks a major step forward in Arctic sea studies and introduces a valuable new tool for wider image processing and computer vision communities. Full article

Unlike image-only systems that falter in shadows, glare, and low contrast, LiDAR directly records surface geometry and supports depth-aware quantification. This survey examines LiDAR-based road surface damage classification across the entire pipeline, encompassing acquisition with mobile and terrestrial laser scanning, preprocessing and representation choices, supervised, semi-supervised, and unsupervised learning techniques, as well as multisensor fusion at early, mid, and late stages. A consistent thread is measurement, not just detection: we describe how LiDAR damage classification maps to agency practices such as the Distress Identification Manual and the Pavement Condition Index. We summarize datasets and evaluation protocols for detection, segmentation, 3D reconstruction, and ride quality. We outline practical concerns for corridor-scale deployment: calibration and timing, intensity normalization, tiling/streaming, and runtime budgeting. The review concludes with open problems and outlines directions for robust, severity-aware, and scalable field systems. Full article

As a key task in remote sensing analysis, semantic segmentation of remote sensing images (RSI) underpins many practical applications. Despite its importance, obtaining dense pixel-wise annotations remains labor-intensive and time-consuming. Unsupervised domain adaptation (UDA) offers a promising solution by utilizing knowledge from labeled source domains for unlabeled target domains, yet its effectiveness is often compromised by significant distribution shifts arising from variations in imaging conditions. To address this challenge, we propose a depth-aware adaptation network (DAAN), a novel two-branch network that explicitly leverages complementary depth information from a digital surface model (DSM) to enhance cross-domain remote sensing segmentation. Unlike conventional UDA methods that primarily focus on semantic features, DAAN incorporates depth data to build a more generalized feature space. This network introduces three key components: an adaptive feature aggregator (AFA) for progressive semantic-depth feature fusion, a gated prediction selection unit (GPSU) that selectively integrates predictions to mitigate the impact of noisy depth measurements, and misalignment-focused residual refinement (MFRR) module that emphasizes poorly aligned target regions during training. Experiments on the ISPRS and GAMUS datasets demonstrate the effectiveness of the proposed method. In particular, DAAN achieves an mIoU of 50.53% and an F1 score of 65.75% for cross-domain segmentation on ISPRS to GAMUS, outperforming models without depth information by 9.17% and 8.99%, respectively. These results demonstrate the advantage of integrating auxiliary geometric information to improve model generalization on unlabeled remote sensing datasets, contributing to higher mapping accuracy, more reliable automated analysis, and enhanced decision-making support. Full article

Adverse weather and low illumination remain major challenges for autonomous driving perception, where semantic segmentation must stay reliable despite severe appearance degradation. In unsupervised domain adaptation without target annotations, self-training is widely used, but it is often limited by the inconsistent quality of teacher-generated pseudo labels across samples, regions, and training stages. This paper presents RaDA, a reliability-aware self-training framework that regulates pseudo supervision at three levels. First, a progressive exposure strategy determines which target images are admitted for training. Second, spatial reliability weighting suppresses gradients from degraded regions while retaining informative supervision. Third, adaptive teacher update scheduling stabilizes pseudo label generation over time. Experiments on real-world adverse driving benchmarks show that RaDA improves robustness, training stability, and cross-dataset generalization compared with strong baselines. Compared with the previous state-of-the-art method MIC, RaDA achieves mIoU gains of 10.6 percentage points on Foggy Zurich and 8.8 percentage points on the Foggy Driving benchmark. These results indicate that explicit reliability regulation can strengthen self-training domain adaptation for semantic segmentation in autonomous driving under challenging environmental conditions. Full article

Synthetic aperture radar (SAR) images often suffer from coupled degradations such as speckle noise, background clutter, and system disturbances, which distort target structure and reduce feature discriminability for target recognition. Most existing enhancement methods typically optimize perceptual quality and may produce visually appealing yet recognition-inconsistent results, especially when paired supervision is unavailable. To address this, an unsupervised SAR image quality enhancement framework is proposed in this study, formulating the degradation as a domain shift problem between low- and high-quality SAR data. A DualGAN-based architecture is adopted to learn bidirectional mappings with reconstruction regularization, enabling enhancement without paired samples. To explicitly preserve task-relevant features and enforce structural consistency, a segmentation-guided recognition-oriented constraint is introduced to embed task awareness into the enhancement process. Furthermore, to mitigate semantic drift during unpaired translation, a semantic preservation constraint based on contrastive learning is proposed to align the enhanced, original, and smoothed images, which can maintain semantic fidelity and reinforce structural cues. Experimental results demonstrate that the proposed framework effectively bridges the domain gap between low- and high-quality SAR images, producing semantically consistent enhancement and improving robustness in target recognition. Evaluations on the GMVT dataset show that the proposed method achieves an average recognition accuracy improvement of over 10% across six recognition networks and four imaging conditions. Full article

Cloud detection is an important procedure for the processing of remote sensing images. A cloud detection scheme driven by the spectral and the temporal features is presented in this paper, where an unsupervised hierarchy clustering approach is proposed for large scale image segmentation. The potential cloudy pixels are identified by means of the spectral matching, in which the spectral data of the clustering centers are compared to the patterns in the spectral dataset of ground covers. The matched pixels are regarded as cloudless pixels, whose category can be recognized accordingly. In contrast, the bright temperatures corresponding to the unmatched pixels are used to exclude the interference of the occasional hotspots, enabling the final cloud detection result. Landsat 8 and Sentinel-2 satellite data are used in the validation to demonstrate the precision and stability of the proposed scheme for the data at different spatial resolutions. Full article

Deep self-training-based unsupervised domain adaptation (UDA) semantic segmentation methods learn from labeled source domain images and unlabeled target domain images, performing more stably than those based on adversarial training. We propose a self-training-based image–text multimodal unsupervised domain adaptation semantic segmentation model (SIT-UDA) for remote sensing images. Unlike UDA methods, which rely solely on images, SIT-UDA enhances generalization performance by integrating category hint information from textual descriptions with image data to segment images. SIT-UDA employs a teacher–student self-training framework consisting of two components: the teacher multimodal segmentation model, which predicts pseudo-labels for target domain images, and the student multimodal segmentation model, which is trained to learn feature representations from both the source and target domains with guidance from the teacher model. To enhance the adaptability of image–text pretrained models in remote sensing domains, SIT-UDA introduces text prompt tuning to optimize the text features in the student model, and two learning strategies are proposed to optimize the model’s training objectives: One is the entropy-guided pixel-level weighting (EGPW) strategy, which adaptively weights the loss obtained by self-training on target domain images, leveraging the pseudo-labels rationally according to the entropy value at the pixel level. The other is the contrastive text constraint (CTC) strategy, which maximizes the similarity of text features for the same category between teacher and student models while minimizing the similarity of text features across different categories, improving text feature discriminability to promote cross-domain image–text alignment. Experiments in various domain adaptation scenarios among three remote sensing datasets (Potsdam, Vaihingen and LoveDA) demonstrate that the SIT-UDA is superior to the comparative domain adaptation semantic segmentation methods in terms of qualitative and quantitative segmentation results. Full article

Semantic segmentation of remote sensing images is crucial for geospatial applications but is severely hampered by the prohibitive cost of pixel-level annotations. Although semi-supervised learning (SSL) offers a solution by leveraging unlabeled data, its application to Vision Transformers (ViTs) often encounters overfitting and even training instability under extreme label scarcity. To tackle these challenges, we propose a Curriculum-based Self-supervised and Semi-supervised Pipeline (CSSP). The pipeline adopts a staged, easy-to-hard training strategy, commencing with in-domain pretraining for robust feature representation, followed by a carefully designed finetuning stage to prevent overfitting. The pipeline further integrates a novel Difficulty-Adaptive ClassMix (DA-ClassMix) augmentation that dynamically reinforces underperforming categories and a Progressive Intensity Adaptation (PIA) strategy that systematically escalates augmentation strength to maximize model generalization. Extensive evaluations on the Potsdam, Vaihingen, and Inria datasets demonstrate state-of-the-art performance. Notably, with only 1/32 of the labeled data on the Potsdam dataset, the CSSP reaches 82.16% mIoU, nearly matching the fully supervised result (82.24%). Furthermore, we extend the CSSP to a semi-supervised domain adaptation (SSDA) scenario, termed Cross-Domain CSSP (CDCSSP), which outperforms existing SSDA and unsupervised domain adaptation (UDA) methods. This work establishes a stable and highly effective framework for training ViT-based segmentation models with minimal annotation overhead. Full article

This study systematically compares three unsupervised segmentation algorithms (Simple Linear Iterative Clustering (SLIC), Felzenszwalb’s graph-based method, and the Watershed algorithm) in combination with two classification approaches: Random Forest using histogram-based features and Convolutional Neural Networks (CNNs). The study employs Bayesian optimization to jointly tune segmentation parameters and model hyperparameters, investigating how segmentation quality impacts downstream classification performance. The methodology is validated using light optical microscopy images of a high-strength steel sample, with performance evaluated through stratified cross-validation and independent test sets. The findings demonstrate the critical importance of segmentation algorithm selection and provide insights into the trade-offs between feature-engineered and end-to-end learning approaches for microstructure analysis. Full article

Meibomian gland dysfunction (MGD) is a leading cause of dry eye disease, assessable through gland atrophy degree. While deep learning (DL) has advanced meibomian gland (MG) segmentation and MGD classification, existing methods treat these tasks independently and suffer from domain shift across multi-center imaging devices. We propose ADAM-Net, an attention-guided unsupervised domain adaptation multi-task framework that jointly models MG segmentation and MGD classification. Our model introduces structure-aware multi-task learning and anatomy-guided attention to enhance feature sharing, suppress background noise, and improve glandular region perception. For the cross-domain tasks MGD-1K→{K5M, CR-2, LV II}, this study systematically evaluates the overall performance of ADAM-Net from multiple perspectives. The experimental results show that ADAM-Net achieves classification accuracies of 77.93%, 74.86%, and 81.77% on the target domains, significantly outperforming current mainstream unsupervised domain adaptation (UDA) methods. The F1-score and the Matthews correlation coefficient (MCC-score) indicate that the model maintains robust discriminative capability even under class-imbalanced scenarios. t-SNE visualizations further validate its cross-domain feature alignment capability. These demonstrate that ADAM-Net exhibits strong robustness and interpretability in multi-center scenarios and provide an effective solution for automated MGD assessment. Full article

Rapid and accurate acquisition of landslide inventories is essential for effective disaster relief. Deep learning-based pixel-wise semantic segmentation of remote sensing imagery has greatly advanced in landslide mapping. However, the heavy dependance on extensive annotated labels and sensitivity to domain shifts severely constrain the model performance in unseen domains, leading to poor generalization. To address these limitations, we propose LandsDANet, an innovative unsupervised domain adaptation framework for cross-domain landslide identification. Firstly, adversarial learning is employed to reduce the data distribution discrepancies between the source and target domains, thereby achieving output space alignment. The improved SegFormer serves as the segmentation network, incorporating hierarchical Transformer blocks and an attention mechanism to enhance feature representation capabilities. Secondly, to alleviate inter-domain radiometric discrepancies and attain image-level alignment, a Wallis filter is utilized to perform image style transformation. Considering the class imbalance present in the landslide dataset, a Rare Class Sampling strategy is introduced to mitigate bias towards common classes and strengthen the learning of the rare landslide class. Finally, a contrastive loss is adopted to further optimize and enhance the model’s ability to delineate fine-grained class boundaries. The proposed model is validated on the Potsdam and Vaihingen benchmark datasets, followed by validation in two landslide scenarios induced by earthquakes and rainfall to evaluate its adaptability across different disaster domains. Compared to the source-only model, LandsDANet achieved improvements in IoU of 27.04% and 35.73% in two cross-domain landslide disaster recognition tasks, respectively. This performance not only showcases its outstanding capabilities but also underscores its robust potential to meet the demands for rapid response. Full article