Search Results (214)

Single-view RGB-D observations are often affected by occlusion and restricted viewpoints, leading to incomplete object geometry and underestimated obstacle extents in indoor robot perception. This paper proposes a single-view scene completion framework that integrates candidate model retrieval and scale-aware registration. The framework first generates local RGB crops and partial point clouds through automatic instance segmentation; then retrieves complete candidate models by matching the local crops with multi-view rendered CAD images; and finally estimates candidate-to-observation rotation, translation, and scale to insert the selected aligned model into the original scene coordinate system. Experiments show that the retrieval module achieves Recall@1/Recall@5 of 80%/89%. The registration module reaches a success rate of 56.61%, outperforming the second-best method by 12.28 percentage points. More importantly, scene-level evaluation shows that the proposed method improves occupancy F1 from 0.445 to 0.523 and reduces boundary error from 0.202 m to 0.146 m compared with DiffCAD. These results indicate that the proposed framework improves navigation-oriented occupancy and obstacle-boundary recovery under CAD-library-based and segmentation-dependent single-view scene completion settings. Full article

Background/Objectives: This study evaluated the daily delivered dose in prostate cancer patients using the automated artificial intelligence (AI)-based software Adaptbox (v2.3.2, Therapanacea). The aim was to assess target coverage and organ-at-risk (OAR) exposure. Methods: Twenty patients were included. All received 80 Gy in 40 fractions to the prostate and 56 Gy simultaneously to the seminal vesicles using two-arc VMAT on a TrueBeam STx, with daily CBCT for setup. For each fraction, CBCT images were imported into Adaptbox. A synthetic CT (sCT) was generated using a deep learning algorithm. OARs were automatically segmented, while targets were propagated from the planning CT (pCT) using rigid registration. Dose calculation was performed using Adaptbox’s collapse-cone algorithm. Dose parameters were extracted for each session and compared with planned values. Results: All 800 fractions were analyzed. The planning target volume (PTV) remained consistent with planning, with a maximum deviation of 0.1% for both PTVs. For the rectum, 78.38%, 77.75%, and 78.13% of fractions exceeded planned doses for V_70Gy, V_76Gy and V_80Gy, respectively. One patient had five consecutive fractions with >5% deviation across all rectal metrics. For the bladder, 52.34% of fractions exceeded the planned V_80Gy, and two patients had ≥5 consecutive fractions with >5% deviation; however, this was attributed to contouring inaccuracies. Conclusions: This AI-based workflow enables reliable daily dose reconstruction and can identify clinically relevant OAR dose deviations that may support adaptive interventions, although accurate contouring remains essential. 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

As a core ground-based coronal observation facility in the low-latitude and high-altitude regions of China, the Lijiang Coronagraph takes advantage of the natural endowments of the Lijiang Astronomical Observation Station, such as an altitude of 3200 m and low atmospheric turbulence. It has gone through a complete development process from introduction through Chinese–Japanese cooperation to independent innovation and iteration. This paper systematically summarizes the core technological innovation achievements of this facility, including the upgrade of the automatic operating system, the integration of the dual-band observation system, the stray light suppression technology based on the image difference method before and after cleaning, and the high-precision image calibration and registration technology. These innovations have significantly improved observation efficiency and data quality, laying a solid foundation for high-quality observations. At the scientific research level, the observation data reveal that 1.1 R_⊙ (solar radius) is a highly correlated region between coronal green line brightness and magnetic field intensity. This study also confirms a strong correlation between the coronal green line and the SDO/AIA 211 Å extreme ultraviolet band (correlation coefficient: 0.89–0.99), which can support the research on early warning of Coronal Mass Ejections (CMEs). These achievements provide key data support for the verification of coronal heating mechanisms and the exploration of the origin of the slow solar wind. The technical experience accumulated from the Lijiang Coronagraph has not only laid a solid foundation for the research and development of China’s next-generation large-aperture coronagraphs, but also facilitated and accelerated substantial progress in China’s technical capabilities for low coronal observation, enabling the country to establish internationally parallel competitive capabilities in this field. This system has also become an important part of the global coronal observation network. Full article

Objective: This study aimed to elucidate the association between hematologic toxicity (HT) and pelvic bone marrow (PBM) dosimetric parameters in patients with cervical cancer (CC) undergoing radiotherapy (RT) combined with artificial intelligence (AI)-assisted organ at risk (OAR) delineation (Software Copyright Registration Number 2023SR0150365). Accurate delineation of bone marrow (BM) regions and analysis of radiation doses may provide a theoretical foundation for the application of AI in predicting HT. Methods: This retrospective study included 141 patients with CC who received chemotherapy (sequential or concurrent) and/or pelvic volumetric modulated arc therapy (VMAT) at the Department of Gynecology, Cancer Hospital of the Chinese Academy of Medical Sciences, between March 2019 and December 2019. PBM and its subregions (ilium, lower pelvis, lumbosacral spine, and femoral heads) were delineated using AI-based automatic segmentation of CT images. The volumes receiving 10–40 Gy (V10, V20, V30, V40) were calculated, and baseline clinical characteristics were assessed. HT endpoints included grade ≥ 2 (HT2+) and grade ≥ 3 (HT3+) leukopenia, neutropenia, anemia, or thrombocytopenia. Associations between dosimetric parameters and HT were evaluated using logistic regression models. Results: Of the 141 patients, 107 (75.8%) developed HT2+ and 33 (23.4%) developed HT3+. Univariate analysis showed that chemotherapy and age were correlated with HT2+. Multivariate analysis identified femoral head V30, femoral head V40, and chemotherapy as independent predictors of HT3+. Conclusions: This study highlights the potential of AI-based OAR delineation for assessing PBM dosimetric parameters in patients with CC. Optimizing RT to minimize BM dose and volume may mitigate HT and enhance treatment tolerance. In our cohort, receipt of combined neoadjuvant and concurrent chemotherapy (NACT+CCRT) was a stronger predictor of HT than most BM dosimetric parameters, suggesting that the systemic effect of chemotherapy may dominate the hematologic toxicity profile in this setting. Consequently, patients receiving this combined modality treatment are at particularly high risk for HT and warrant close hematologic monitoring. Full article

Surveying and register administration are core to land administration, and accordingly, land surveying and registration are essential to socio-economic development due to their potential accuracy and efficiency. Until now, customary land surveying and registration have relied on human input, which is a situation that undermines efficiency and is prone to errors in data handling. During the last decade, the exponential growth in artificial intelligence (AI), in particular, geospatial artificial intelligence (GeoAI), has provided new methodologies that can overcome these deficiencies. This review examines AI in cadastral management by analyzing technical solutions and trends across three areas including data collection, modeling, and common applications. This review aims to provide a comprehensive survey of the current use of AI in cadastral management to the extent of defining a future research avenue. Based on the comprehensive review of literature, this study has reached the following three conclusions. (1) Automated extraction of parcel boundaries has been achieved through deep learning in data collection and processing, removing the bottlenecks of manual interpretation. Models such as convolutional neural networks (CNNs) and Transformers have been used for pixel-level semantic segmentation of high-resolution remote sensing images, leading to significant improvements in efficiency and accuracy. (2) Non-spatial data have been processed with natural language processing techniques to automatically extract information and construct relationships, thus overcoming the limitations of paper-based archives and traditional relational databases. (3) Deep learning models have been applied to automatically detect parcel changes and to enable integrated analysis of spatial and non-spatial data, which has supported the transition of cadastral management from two-dimensional to three-dimensional. However, several challenges remain, including differences in multi-temporal data processing, spatial semantic ambiguity, and the lack of large-scale, high-quality annotated data. Future research can focus on improving model generalization, advancing cross-modal data fusion, and providing recommendations for the development of a reliable and practical intelligent cadastral system. Full article

The spinal angle is an important indicator of body balance. It is important to restore the 3D shape of the human body and estimate the spine center line. Existing multi-image-based body restoration methods require expensive equipment and complex procedures, and single image-based body restoration methods struggle to accurately estimate internal structures such as the spine center line due to occlusion and viewpoint limitation. This study proposes a method to compensate for the shortcomings of the multi-image-based method and to overcome the limitations of the single-image method. We propose a 3D body posture analysis system that integrates depth images from four directions to restore a 3D human model and automatically estimate the spine center line. Through hierarchical matching of global and fine registration, restoration to noise and occlusion is performed. In addition, adaptive vertex reduction is applied to maintain the resolution and shape reliability of the mesh, and the accuracy and stability of spinal angle estimation are simultaneously secured using the level of detail (LOD) ensemble. The proposed method achieves high-precision 3D spine registration estimation without relying on training data or complex neural network models, and the verification confirms the improvement in matching quality. Full article

Accurate registration of optical and synthetic aperture radar (SAR) images is a fundamental prerequisite for multi-source remote sensing data fusion and analysis. However, due to the substantial differences in imaging mechanisms, optical–SAR image pairs often exhibit significant radiometric discrepancies and spatially varying geometric inconsistencies, which severely limit the robustness of traditional feature or region-based registration methods in cross-modal scenarios. To address these challenges, this paper proposes an end-to-end Optical–SAR Registration Network (OSR-Net) based on multi-constraint joint optimization. The proposed framework explicitly decouples cross-modal feature alignment and geometric correction, enabling robust registration under large appearance variation. Specifically, a multi-modal feature extraction module constructs a shared high-level representation, while a multi-scale channel attention mechanism adaptively enhances cross-modal feature consistency. A multi-scale affine transformation prediction module provides a coarse-to-fine geometric initialization, which stabilizes parameter estimation under complex imaging conditions. Furthermore, an improved spatial transformer network is introduced to perform structure-preserving geometric refinement, mitigating spatial distortion induced by modality discrepancies. In addition, a multi-constraint loss formulation is designed to jointly enforce geometric accuracy, structural consistency, and physical plausibility. By employing a dynamic weighting strategy, the optimization process progressively shifts from global alignment to local structural refinement, effectively preventing degenerate solutions and improving robustness. Extensive experiments on public optical–SAR datasets demonstrate that the proposed method achieves accurate and stable registration across diverse scenes, providing a reliable geometric foundation for subsequent multi-source remote sensing data fusion. Full article

Agricultural mechanization and advanced technology have developed significantly in the coffee industry. However, there are still requirements for human laborers to operate, monitor crop health care, and manage production. The integration of advanced technology can significantly enhance the production efficiency and management practices of agricultural enterprises. This paper aims to address these gaps by proposing and implementing a computer vision-based attendance tracking system on mobile platforms that are suitable for the requirements and limitations of agricultural enterprises. First, the face detection process involves interpreting and locating facial structure. Next, the model transforms a photographic image of a human face into digital data based on the unique features and facial structure. We utilize the InsightFace model with the buffalo_l variant, as well as ArcFace with a ResNet backbone, as a facial recognition algorithm. After capturing a facial image, the system conducts a matching process against the existing database to verify identity. Finally, we implement a mobile application prototype on both iOS and Android platforms, ensuring accessibility for farm workers. As a result, our system achieved 95.2% accuracy on the query set, with an average processing time of <200 ms per image (including face detection, embedding extraction, and database matching). The system performs real-time attendance monitoring, automatically recording the entry and exit times of farm workers using facial recognition technology, and enables quick registration of new workers. Our work is expected to enhance transparency and fairness in the human management process, focusing on the coffee farm use case. Full article

Automatic fault detection based on machine vision technology is crucial for the operational safety of trains. However, when imaging moving trains, system errors may induce localized geometric distortions in the captured images, altering the shapes of critical train components. This, in turn, undermines the precision of subsequent diagnostic algorithms. Therefore, image registration prior to anomaly detection is essential. To address this need, we redefine the horizontal registration of line-scan images as a disparity estimation problem on rectified stereo pairs, which is solved using a proposed dense matching network. The disparity is iteratively refined through a GRU-based update module that constructs a multi-scale cost volume with positional encoding and self-attention. To overcome the absence of real-world disparity ground truth, we generate a physics-based simulation dataset by analytically modeling the nonlinear relationship between train velocity variations and line-scan image distortions. Extensive experiments on diverse real-world train image datasets under varied operational conditions demonstrate that our method consistently outperforms alternatives, achieving 5.8% higher registration accuracy and a fourfold increase in processing speed over state-of-the-art approaches. This advantage is particularly evident in challenging scenarios involving repetitive patterns or texture-less regions. Full article

Automatic segmentation of brain tumors in intra-operative ultrasound (iUS) images could facilitate localization of tumor tissue during the resection surgery. The lack of large annotated datasets limits the current models performances. In this paper, we investigated the use of tumor annotations in magnetic resonance imaging (MRI) scans, which are more accessible than annotations in iUS images, for training of deep learning models for iUS brain tumor segmentation. We used 180 annotated MRI scans with corresponding unannotated iUS images, and 29 annotated iUS images. Image registration was performed to transfer the MRI annotations to the corresponding iUS images before training the nnU-Net model with different configurations of the data and label origins. The results showed similar performance for a model trained with only MRI annotated tumors compared to models trained with only iUS annotations and both, and to expert annotations, indicating that MRI tumor annotations can be used as a substitute for iUS tumor annotations to train a deep learning model for automatic brain tumor segmentation in the iUS images. The best model obtained an average Dice score of 0.62 ± 0.31, compared to 0.67 ± 0.25 for an expert neurosurgeon, where the performance on larger tumors was similar, but lower for the models on smaller tumors. In addition, the results showed that removing smaller tumors from the training sets improved the results. Full article

Levees are critical for flood defence, but their integrity is threatened by hazards such as piping and seepage, especially during high-water-level periods. Traditional manual inspections for these hazards and associated emergency response elements, such as personnel and assets, are inefficient and often impractical. While UAV-based remote sensing offers a promising alternative, the effective fusion of multi-modal data and the scarcity of labelled data for supervised model training remain significant challenges. To overcome these limitations, this paper reframes levee monitoring as an unsupervised anomaly detection task. We propose a novel, fully automated framework that unifies geophysical hazards and emergency response elements into a single analytical category of “abnormal targets” for comprehensive situational awareness. The framework consists of three key modules: (1) a state-of-the-art registration algorithm to precisely align infrared and visible images; (2) a generative adversarial network to fuse the thermal information from IR images with the textural details from visible images; and (3) an adaptive, unsupervised segmentation module where a mean-shift clustering algorithm, with its hyperparameters automatically tuned by Bayesian optimization, delineates the targets. We validated our framework on a real-world dataset collected from a levee on the Pajiang River, China. The proposed method demonstrates superior performance over all baselines, achieving an Intersection over Union of 0.348 and a macro F1-Score of 0.479. This work provides a practical, training-free solution for comprehensive levee monitoring and demonstrates the synergistic potential of multi-modal fusion and automated machine learning for disaster management. Full article

Automatic bone surface segmentation represents an advanced alternative for conventional patient registration methods in surgical navigation technologies. In pediatrics, such technologies require tailored approaches to ensure optimal performance—specifically in patients under the age of ten, whose immature bones have less distinct bone characteristics. In this study, we developed a segmentation model tailored for pediatric patients. We captured 4309 ultrasound images from the bones in the extremities, pelvis and thorax of 16 pediatric patients. The dataset was manually annotated by a technical physician and sample-wise validated by a pediatric radiologist. A UNeXt deep learning model was trained for automatic segmentation. The segmentation performance was evaluated using the mean centerline Dice score and the mean surface distance. A mean centerline Dice score of 0.85 (SD: 0.13) and a mean surface distance of 0.78 mm (SD: 1.15 mm) were achieved. No important differences in performance were observed for patients younger than the age of ten compared to older patients. Our results demonstrate that the segmentation model detects the bone surface with sufficient accuracy, enabling precise and effective patient registration. The model performs sufficiently across different pediatric age groups, making it a viable tool for integration into ultrasound-based patient registration in image-guided pediatric surgery. Full article

The equator’s unique combination of high humidity and temperature renders optical satellite imagery highly susceptible to persistent cloud cover. In contrast, synthetic aperture radar (SAR) offers a robust alternative due to its ability to penetrate clouds with microwave imaging. This study addresses the challenges of cloud-induced data gaps and cross-sensor geometric biases by proposing an advanced optical and SAR image-matching framework specifically designed for cloud-prone equatorial regions. We use a prompt-driven visual segmentation model with automatic prompt point generation to produce cloud masks that guide cross-modal feature-matching and joint adjustment of optical and SAR data. This process results in a comprehensive digital orthophoto map (DOM) with high geometric consistency, retaining the fine spatial detail of optical data and the all-weather reliability of SAR. We validate our approach across four equatorial regions using five satellite platforms with varying spatial resolutions and revisit intervals. Even in areas with more than 50 percent cloud cover, our method maintains sub-pixel edging accuracy under manual check points and delivers comprehensive DOM products, establishing a reliable foundation for downstream environmental monitoring and ecosystem analysis. Full article

Automatic license plate recognition (ALPR) plays an important role in applications such as intelligent traffic systems, vehicle access control in specific areas, and law enforcement. The main novelty brought by the present research consists in the development of an automatic vehicle license plate recognition system adapted to the Romanian context, which integrates the YOLOv12 detection architecture with the PaddleOCR library while also providing functionalities for recognizing the type of vehicle on which the license plate is mounted and identifying the county of registration. The integration of these functionalities allows for an extension of the applicability range of the proposed solution, including for addressing issues related to restricting access for certain types of vehicles in specific areas, as well as monitoring vehicle traffic based on the county of registration. The dataset used in the study was manually collected and labeled using the makesense.ai platform and was made publicly available for future research. It includes 744 images of vehicles registered in Romania, captured in real traffic conditions (the training dataset being expanded by augmentation). The YOLOv12 model was trained to automatically detect license plates in images with vehicles, and then it was evaluated and validated using standard metrics such as precision, recall, F1 score, mAP@0.5, mAP@0.5:0.95, etc., proving very good performance. Experimental results demonstrate that YOLOv12 achieved superior performance compared to YOLOv11 for the analyzed issue. YOLOv12 outperforms YOLOv11 with a 2.3% increase in precision (from 97.4% to 99.6%) and a 1.1% improvement in F1 score (from 96.7% to 97.8%). Full article