Search Results (282)

Recently, the potential of recycled materials to improve the performance of concrete and other building materials has become an important research topic. It is known that various methods are applied to improve the tensile strength and energy absorption capacity of cementitious systems. One of the most common of these methods is the addition of fibers to the mixture. In this study, the effects of surface-modified polypropylene (PP) fibers obtained from recycled masks on the mechanical properties of mortar mixtures were investigated. In order to improve the matrix–fiber interface performance, 6 mm and 12 mm long recycled PP fibers were chemically coated within the scope of surface modification using 1-Vinyl-1,2,4-Triazole and Vinyl Acetate. With this modification made on the surface of PP fibers, we aimed to increase the surface roughness of the fibers and improve their adhesion to the matrix. Thus, we aimed to increase the mechanical properties of mortar mixtures as a result of the fibers performing more effectively in the concrete matrix. FTIR AND SEM-EDS analyses confirmed the success of the modification and the applicability of 1-Vinyl-1,2,4-Triazole and Vinyl Acetate to the fiber surface and showed that the fibers were successfully modified. It is seen that the fibers modified with Vinyl Acetate exhibit superior performance in terms of both the workability and strength performance of cementitious systems compared to the fibers modified with 1-Vinyl-1,2,4-Triazole. This study provides a significant contribution to sustainable construction materials by revealing the potential of using recycled materials in cementitious systems. Full article

In this paper, we propose sketch-based video object segmentation (SKVOS), a novel task that segments objects consistently across video frames using human-drawn sketches as queries. Traditional reference-based methods, such as photo masks and language descriptions, are commonly used for segmentation. Photo masks provide high precision but are labor intensive, limiting scalability. While language descriptions are easy to provide, they often lack the specificity needed to distinguish visually similar objects within a frame. Despite their simplicity, sketches capture rich, fine-grained details of target objects and can be rapidly created, even by non-experts, making them an attractive alternative for segmentation tasks. We introduce a new approach that utilizes sketches as efficient and informative references for video object segmentation. To evaluate sketch-guided segmentation, we introduce a new benchmark consisting of three datasets: Sketch-DAVIS16, Sketch-DAVIS17, and Sketch-YouTube-VOS. Building on a memory-based framework for semi-supervised video object segmentation, we explore effective strategies for integrating sketch-based references. To ensure robust spatiotemporal coherence, we introduce two key innovations: the Temporal Relation Module and Sketch-Anchored Contrastive Learning. These modules enhance the model’s ability to maintain consistency both across time and across different object instances. Our method is evaluated on the Sketch-VOS benchmark, demonstrating superior performance with overall improvements of 1.9%, 3.3%, and 2.0% over state-of-the-art methods on the Sketch-YouTube-VOS, Sketch-DAVIS 2016, and Sketch-DAVIS 2017 validation sets, respectively. Additionally, on the YouTube-VOS validation set, our method outperforms the leading language-based VOS approach by 10.1%. Full article

Coal, as a vital global energy resource, directly impacts the efficiency of power generation and environmental protection. Thus, rapid and accurate coal quality analysis is essential to promote its clean and efficient utilization. However, combined near-infrared spectroscopy and X-ray fluorescence (NIRS-XRF) spectroscopy often suffer from the particle size effect of coal samples, resulting in unstable and inaccurate analytical outcomes. This study introduces a novel correction method combining the Segment Anything Model (SAM) for precise particle segmentation and Data-Efficient Image Transformers (DeiTs) to analyze the relationship between particle size and ash measurement errors. Microscopic images of coal samples are processed with SAM to generate binary mask images reflecting particle size characteristics. These masks are analyzed using the DeiT model with transfer learning, building an effective correction model. Experiments show a 22% reduction in standard deviation (SD) and root mean square error (RMSE), significantly enhancing ash prediction accuracy and consistency. This approach integrates cutting-edge image processing and deep learning, effectively reducing submillimeter particle size effects, improving model adaptability, and enhancing measurement reliability. It also holds potential for broader applications in analyzing complex samples, advancing automation and efficiency in online analytical systems, and driving innovation across industries. Full article

This study addresses the issue of energy efficiency evaluation for rural residential buildings and proposes a method for facade recognition based on an improved Mask R-CNN network model. By introducing the Coordinate Attention (CA) mechanism module, the quality of feature extraction and detection accuracy is enhanced. Experimental results demonstrate that this method effectively recognizes and segments windows, doors, and other components on building facades, accurately extracting key information, such as their dimensions and positions. For energy consumption simulation, this study utilized the Ladybug Tool in the Grasshopper plugin, combined with actual collected facade data, to assess and simulate the energy consumption of rural residences. By setting building envelope parameters and air conditioning operating parameters, detailed calculations of energy consumption for different orientations, window-to-wall ratios, and sunshade lengths were performed. The results show that the improved Mask R-CNN network model plays a crucial role in quickly and accurately extracting building parameters, providing reliable data support for energy consumption evaluation. Finally, through case studies, specific energy-saving retrofit suggestions were proposed, offering robust technical support and practical guidance for energy optimization in rural residences. Full article

Self-distillation has been widely applied in the field of deep learning. However, the lack of interaction between the multiple shallow branches in the self-distillation framework reduces the effectiveness of self-distillation methods. To address this issue, a feature map fusion self-distillation scheme is proposed. According to the depth of the teacher model, multiple shallow branches as student models are constructed to build a self-distillation framework. Then, the feature map fusion module fuses the intermediate feature maps of each branch to enhance the interaction between the branches. Specifically, this fusion module employs a spatial enhancement module to generate attention masks for multiple feature maps, which are averaged and applied to create intermediate maps. The mean of these intermediate maps results in the final fusion feature map. The experimental findings on the CIFAR10 and CIFAR100 datasets illustrate that our proposed technique has clear advantages in increasing the classification accuracy of the deep learning models. On average, 0.7% and 2.5% accuracy boosts are observed on the CIFAR10 and CIFAR100. Full article

In current engineering applications, target detection based on power vision neural networks has problems with low accuracy and difficult defect recognition. Thus, this paper proposes a high-precision substation equipment defect recognition algorithm based on the Mask R-CNN algorithm framework to achieve high-precision substation equipment defect monitoring. The effectiveness of the Mask R-CNN algorithm is compared and analyzed in substation equipment defect recognition and the applicability of the Mask R-CNN algorithm in edge computing. According to different types of substation equipment defect characteristics, substation equipment defect recognition guidelines were developed. The guideline helps to calibrate the existing training set and build defect recognition models for substation equipment based on different algorithms. In the end, the system based on a power edge vision neural network was built. The feasibility and accuracy of the algorithm was verified by model training and actual target detection results. Full article

Data augmentation methods offer a cost-effective and efficient alternative to the acquisition of additional data, significantly enhancing data diversity and model generalization, making them particularly favored in object detection tasks. However, existing data augmentation techniques primarily focus on the visible spectrum and are directly applied to RGB-T object detection tasks, overlooking the inherent differences in image data between the two tasks. Visible images capture rich color and texture information during the daytime, while infrared images are capable of imaging under low-light complex scenarios during the nighttime. By integrating image information from both modalities, their complementary characteristics can be exploited to improve the overall effectiveness of data augmentation methods. To address this, we propose a cross-modality data augmentation method tailored for RGB-T object detection, leveraging masked image modeling within representation learning. Specifically, we focus on the temporal consistency of infrared images and combine them with visible images under varying lighting conditions for joint data augmentation, thereby enhancing the realism of the augmented images. Utilizing the masked image modeling method, we reconstruct images by integrating multimodal features, achieving cross-modality data augmentation in feature space. Additionally, we investigate the differences and complementarities between data augmentation methods in data space and feature space. Building upon existing theoretical foundations, we propose an integrative framework that combines these methods for improved augmentation effectiveness. Furthermore, we address the slow convergence observed with the existing Mosaic method in aerial imagery by introducing a multi-scale training strategy and proposing a full-scale Mosaic method as a complement. This optimization significantly accelerates network convergence. The experimental results validate the effectiveness of our proposed method and highlight its potential for further advancements in cross-modality object detection tasks. Full article

Satellite image generation has a wide range of applications. For example, parts of images must be restored in areas obscured by clouds or cloud shadows or areas that must be anonymized. The need to cover a large area with the generated images faces the challenge that separately generated images must maintain the structural and color continuity between the adjacent generated images as well as the actual ones. This study presents a modified architecture of the generative adversarial network (GAN) pix2pix that ensures the integrity of the generated remote sensing images. The pix2pix model comprises a U-Net generator and a PatchGAN discriminator. The generator was modified by expanding the input set with images representing the known parts of ground truth and the respective mask. Data used for the generative model consist of Sentinel-2 (S2) RGB satellite imagery as the target data and OpenStreetMap mapping data as the input. Since forested areas and fields dominate in images, a Kneedle clusterization method was applied to create datasets that better represent the other classes, such as buildings and roads. The original and updated models were trained on different datasets and their results were evaluated using gradient magnitude (GM), Fréchet inception distance (FID), structural similarity index measure (SSIM), and multiscale structural similarity index measure (MS-SSIM) metrics. The models with the updated architecture show improvement in gradient magnitude, SSIM, and MS-SSIM values for all datasets. The average GMs of the junction region and the full image are similar (do not exceed 7%) for the images generated using the modified architecture whereas it is more than 13% higher in the junction area for the images generated using the original architecture. The importance of class balancing is demonstrated by the fact that, for both architectures, models trained on the dataset with a higher ratio of classes representing buildings and roads compared to the models trained on the dataset without clusterization have more than 10% lower FID (162.673 to 190.036 for pix2pix and 173.408 to 195.621 for the modified architecture) and more than 5% higher SSIM (0.3532 to 0.3284 for pix2pix and 0.3575 to 0.3345 for the modified architecture) and MS-SSIM (0.3532 to 0.3284 for pix2pix and 0.3575 to 0.3345 for the modified architecture) values. Full article

Distance measurement plays a key role in many fields of science and technology, including robotics, civil engineering, and navigation systems. This paper focuses on analyzing the precision of a measurement system using stereo camera distance measurement technology in the context of measuring two objects of different sizes. The first part of the paper presents key information about stereoscopy, followed by a discussion of the process of building a measuring station. The Mask R-CNN algorithm, which is a deep learning model that combines object detection and instance segmentation, was used to identify objects in the images. In the following section, the calibration process of the system and the distance calculation method are presented. The purpose of the study was to determine the precision of the measurement system and to identify the distance ranges where the measurements are most precise. Measurements were made in the range of 20 to 70 cm. The system demonstrated a relative error of 0.95% for larger objects and 1.46% for smaller objects at optimal distances. A detailed analysis showed that for larger objects, the system exhibited higher precision over a wider range of distances, while for smaller objects, the highest accuracy was achieved over a more limited range. These results provide valuable information on the capabilities and limitations of the measurement system used, while pointing out directions for its further optimization. Full article

Monitoring and accurately quantifying greenhouse gas (GHG) emissions from point sources via satellite measurements is crucial for validating emission inventories. Numerous studies have applied varied methods to estimate emission intensities from both natural and anthropogenic point sources, highlighting the potential of satellites for point source quantification. To promote the development of the space-based GHG monitoring system, it is pivotal to assess the satellite’s capacity to quantify emissions from distinct sources before its design and launch. However, no universal method currently exists for quantitatively assessing the ability of satellites to quantify point source emissions. This paper presents a parametric conceptual model and database for efficiently evaluating the quantification capabilities of satellites and optimizing their technical characteristics for particular detection missions. Using the model and database, we evaluated how well various satellites can detect and quantify GHG emissions. Our findings indicate that accurate estimation of point source emissions requires both high spatial resolution and measurement precision. The requirement for satellite spatial resolution and measurement precision to achieve unbiased emission estimation gradually decreases with increasing emission intensity. The model and database developed in this study can serve as a reference for harmonious satellite configuration that balances measurement precision and spatial resolution. Furthermore, to progress the evaluation model of satellites for low-intensity emission point sources, it is imperative to implement a more precise simulation model and estimate method with a refined mask-building approach. Full article

Detailed evaluation of prostate cancer glands is an essential yet labor-intensive step in grading prostate cancer. Gland segmentation can serve as a valuable preliminary step for machine-learning-based downstream tasks, such as Gleason grading, patient classification, cancer biomarker building, and survival analysis. Despite its importance, there is currently a lack of a reliable gland segmentation model for prostate cancer. Without accurate gland segmentation, researchers rely on cell-level or human-annotated regions of interest for pathomic and deep feature extraction. This approach is sub-optimal, as the extracted features are not explicitly tailored to gland information. Although foundational segmentation models have gained a lot of interest, we demonstrated the limitations of this approach. This work proposes a prostate gland segmentation framework that utilizes a dual-path Swin Transformer UNet structure and leverages Masked Image Modeling for large-scale self-supervised pretaining. A tumor-guided self-distillation step further fused the binary tumor labels of each patch to the encoder to ensure the encoders are suitable for the gland segmentation step. We united heterogeneous data sources for self-supervised training, including biopsy and surgical specimens, to reflect the diversity of benign and cancerous pathology features. We evaluated the segmentation performance on two publicly available prostate cancer datasets. We achieved state-of-the-art segmentation performance with a test mDice of 0.947 on the PANDA dataset and a test mDice of 0.664 on the SICAPv2 dataset. Full article

Unmanned aerial systems (UASs) are increasingly playing a crucial role in earthquake emergency response and disaster assessment due to their ease of operation, mobility, and low cost. However, post-earthquake scenes are complex, with many forms of damaged buildings. UAS imagery has a high spatial resolution, but the resolution is inconsistent between different flight missions. These factors make it challenging for existing methods to accurately identify individual damaged buildings in UAS images from different scenes, resulting in coarse segmentation masks that are insufficient for practical application needs. To address these issues, this paper proposed DB-Transfiner, a building damage instance segmentation method for post-earthquake UAS imagery based on the Mask Transfiner network. This method primarily employed deformable convolution in the backbone network to enhance adaptability to collapsed buildings of arbitrary shapes. Additionally, it used an enhanced bidirectional feature pyramid network (BiFPN) to integrate multi-scale features, improving the representation of targets of various sizes. Furthermore, a lightweight Transformer encoder has been used to process edge pixels, enhancing the efficiency of global feature extraction and the refinement of target edges. We conducted experiments on post-disaster UAS images collected from the 2022 Luding earthquake with a surface wave magnitude (Ms) of 6.8 in the Sichuan Province of China. The results demonstrated that the average precisions (AP) of DB-Transfiner, ${AP}_{box}$ and ${AP}_{seg}$, are 56.42% and 54.85%, respectively, outperforming all other comparative methods. Our model improved the original model by 5.00% and 4.07% in ${AP}_{box}$ and ${AP}_{seg}$, respectively. Importantly, the ${AP}_{seg}$ of our model was significantly higher than the state-of-the-art instance segmentation model Mask R-CNN, with an increase of 9.07%. In addition, we conducted applicability testing, and the model achieved an average correctness rate of 84.28% for identifying images from different scenes of the same earthquake. We also applied the model to the Yangbi earthquake scene and found that the model maintained good performance, demonstrating a certain level of generalization capability. This method has high accuracy in identifying and assessing damaged buildings after earthquakes and can provide critical data support for disaster loss assessment. Full article

There is limited information regarding factors related to education workers’ responses to traumatic stress during the COVID-19 pandemic. The study goal was to determine whether personal factors, behaviours that mitigate viral spread, and work-related factors were associated with post-traumatic symptoms. This observational study, embedded within a cohort study, recruited Ontario education workers from February 2021 to June 2023. Exposure data were collected at enrollment and updated annually. Participants completed the Impact of Event Scale (IES) at withdrawal/study completion. Modified Poisson regression was used to build hierarchical models of dichotomized IES scores (≥26: moderate/severe post-traumatic symptoms). Of the 1518 education workers who submitted an IES between September 2022 and December 2023, the incidence rate ratio of IES scores ≥26 was significantly higher among participants who usually/always wore a mask at work (1.48; 95% confidence interval 1.23, 1.79), usually/always practiced physical distancing (1.31; 1.06, 1.62), lived in larger households (1.06; 1.01, 1.12), and reported poor/fair/good health (1.27; 1.11, 1.46). However, models accounted for little of the variance in IES scores, suggesting the need for future studies to collect data on other factors associated with the development of PTSD, such as pre-existing mental health challenges. Early identification of those experiencing traumatic stress and the implementation of stress reduction strategies are needed to ensure the ongoing health of education workers. Full article

For the reconstruction of objects during hand–object interactions, accurate pose estimation is indispensable. By improving the precision of pose estimation, the accuracy of the 3D reconstruction results can be enhanced. Recently, pose tracking techniques are no longer limited to individual objects, leading to advancements in the reconstruction of objects interacting with other objects. However, most methods struggle to handle incomplete target information in complex scenes and mutual interference between objects in the environment, leading to a decrease in pose estimation accuracy. We proposed an improved algorithm building upon the existing BundleSDF framework, which enables more robust and accurate tracking by considering the occlusion relationships between objects. First of all, for detecting changes in occlusion relationships, we segment the target and compute dual-layer masks. Secondly, rough pose estimation is performed through feature matching, and a keyframe pool is introduced for pose optimization, which is maintained based on occlusion relationships. Lastly, the estimated results of historical frames are used to train an object neural field to assist in the subsequent pose-tracking process. Experimental verification shows that on the HO-3D dataset, our method can significantly improve the accuracy and robustness of object tracking in frequent interactions, providing new ideas for object pose-tracking tasks in complex scenes. Full article

Interactive segmentation methods utilize user-provided positive and negative clicks to guide the model in accurately segmenting target objects. Compared to fully automatic medical image segmentation, these methods can achieve higher segmentation accuracy with limited image data, demonstrating significant potential in clinical applications. Typically, for each new click provided by the user, conventional interactive segmentation methods reprocess the entire network by re-inputting the click into the segmentation model, which greatly increases the user’s interaction burden and deviates from the intended goal of interactive segmentation tasks. To address this issue, we propose an efficient segmentation network, ESM-Net, for interactive medical image segmentation. It obtains high-quality segmentation masks based on the user’s initial clicks, reducing the complexity of subsequent refinement steps. Recent studies have demonstrated the strong performance of the Mamba model in various vision tasks; however, its application in interactive segmentation remains unexplored. In our study, we incorporate the Mamba module into our framework for the first time and enhance its spatial representation capabilities by developing a Spatial Augmented Convolution (SAC) module. These components are combined as the fundamental building blocks of our network. Furthermore, we designed a novel and efficient segmentation head to fuse multi-scale features extracted from the encoder, optimizing the generation of the predicted segmentation masks. Through comprehensive experiments, our method achieved state-of-the-art performance on three medical image datasets. Specifically, we achieved 1.43 NoC@90 on the Kvasir-SEG dataset, 1.57 NoC@90 on the CVC-ClinicDB polyp segmentation dataset, and 1.03 NoC@90 on the ADAM retinal disk segmentation dataset. The assessments on these three medical image datasets highlight the effectiveness of our approach in interactive medical image segmentation. Full article