Search Results (177)

The exponential increase in waste generation is a significant global challenge with serious implications. Addressing this issue necessitates the enhancement of waste management processes. This study introduces a method that improves waste separation by integrating learning models at various levels. The method begins with the creation of image features as a new matrix using the Multi-Scale Local Binary Pattern (MLBP) technique. This technique optimally represents features and patterns across different scales. Following this, an ensemble model at the first level merges two Convolutional Neural Network (CNN) models, with each model performing the detection operation independently. A second-level CNN model is then employed to obtain the final output. This model uses the information from the first-level models and combines these features to perform a more accurate detection. The study’s novelty lies in the use of a second-level CNN model in the proposed ensemble system for fusing the results obtained from the first level, replacing conventional methods such as voting and averaging. Additionally, the study employs an MLBP feature selection approach for a more accurate description of the HW image features. It uses the Simulated Annealing (SA) algorithm for fine-tuning the hyperparameters of the CNN models, thereby optimizing the system’s performance. Based on the accuracy metric, the proposed method achieved an accuracy of 99.01% on the TrashNet dataset and 99.41% on the HGCD dataset. These results indicate a minimum improvement of 0.48% and 0.36%, respectively, compared to the other methods evaluated in this study. Full article

Accurate peach detection is essential for automated agronomic management, such as mechanical peach harvesting. However, ubiquitous occlusion makes identifying peaches from complex backgrounds extremely challenging. In addition, it is difficult to capture fine-grained peach features from a single RGB image, which can suffer from light and noise in scenarios with dense small target clusters and extreme light. To solve these problems, this study proposes a multimodal detector, called CRLNet, based on RGB and depth images. First, YOLOv9 was extended to design a backbone network that can extract RGB and depth features in parallel from an image. Second, to address the problem of information fusion bias, the Rough–Fine Hybrid Attention Fusion Module (RFAM) was designed to combine the advantageous information of different modes while suppressing the hollow noise at the edge of the peach. Finally, a Transformer-based Local–Global Joint Enhancement Module (LGEM) was developed to jointly enhance the local and global features of peaches using information from different modalities in order to enhance the percentage of information about the target peaches and remove the interference of redundant background information. CRLNet was trained on the Peach dataset and evaluated against other state-of-the-art methods; the model achieved an $mA{P}_{50}$ of 97.1%. In addition, CRLNet also achieved an $mA{P}_{50}$ of 92.4% in generalized experiments, validating its strong generalization capability. These results provide valuable insights for peach and other outdoor fruit multimodal detection. Full article

The existing Siamese trackers have achieved increasingly successful results in visual object tracking. However, the interactive fusion among multi-layer similarity maps after cross-correlation has not been fully studied in previous Siamese network-based methods. To address this issue, we propose a novel Siamese network for visual object tracking, named SiamSMN, which consists of a feature extraction network, a multi-scale fusion module, and a prediction head. First, the feature extraction network is used to extract the features of the template image and the search image, which is calculated by a depth-wise cross-correlation operation to produce multiple similarity feature maps. Second, we propose an effective multi-scale fusion module that can extract global context information for object search and learn the interdependencies between multi-level similarity maps. In addition, to further improve tracking accuracy, we design a learnable prediction head module to generate a boundary point for each side based on the coarse bounding box, which can solve the problem of inconsistent classification and regression during the tracking. Extensive experiments on four public benchmarks demonstrate that the proposed tracker has a competitive performance among other state-of-the-art trackers. Full article

Multimedia resources, such as instructional videos, are currently enjoying a certain popularity in the training programs for medical and dental students. The major challenge is to create such resources with quality content that is approved by students. In order to answer this challenge, it is imperative to find out which features of instructional videos are considered to be necessary and useful by students, thus being able to excite them, to hold their attention, and to stimulate them in learning with pleasure. Aim: We investigated the opinions of a sample of 551 students from four medical universities in Romania, in order to identify the students’ preferred characteristics in instructional videos, both globally and comparatively on genders and age groups and also according to their general preferences for using internet services. Material and methods: We used univariate (hypothesis testing) and multivariate (two-step clustering) data analysis techniques and revealed three clusters of students, primarily determined by their perceptions of the visual appearance of the instructional videos. Results: The structure of the clusters by gender and age group was relatively similar, but we recorded differences associated with the students’ expressed preferences for certain internet services compared to others. The first identified cluster (35.4% of the cases) contains students who prefer instructional videos to contain images used only for aesthetic purposes and to fill the gaps; they use internet services mainly for communication. The second cluster of students (34.8%) prefers videos designed as practical lessons, using explanatory drawings and diagrams drawn at the same time as the explanations; they also use internet services mainly for communication. The last cluster of students (29.8%) prefer videos designed as PowerPoint presentations, with animated pictures, diagrams, and drawings; they are slightly younger than the others and use internet services mainly for information and communication, but also for domestic facilities. Conclusions: The students’ preferences for certain features of instructional videos depend not only on gender and age but are also related to their developmental background and general opinions about modern technologies. Full article

In the field of remote sensing image captioning (RSIC), mainstream methods typically adopt an encoder–decoder framework. Methods based on this framework often use only simple feature fusion strategies, failing to fully mine the fine-grained features of the remote sensing image. Moreover, the lack of context information introduction in the decoder results in less accurate generated sentences. To address these problems, we propose a two-stage feature enhancement model (TSFE) for remote sensing image captioning. In the first stage, we adopt an adaptive feature fusion strategy to acquire multi-scale features. In the second stage, we further mine fine-grained features based on multi-scale features by establishing associations between different regions of the image. In addition, we introduce global features with scene information in the decoder to help generate descriptions. Experimental results on the RSICD, UCM-Captions, and Sydney-Captions datasets demonstrate that the proposed method outperforms existing state-of-the-art approaches. Full article

Background: The assessment information of tumor margins is extremely important for the success of the breast cancer surgery and whether the patient undergoes a second operation. However, conducting surgical margin assessments is a time-consuming task that requires pathology-related skills and equipment, and often cannot be provided in a timely manner. To address this challenge, digital breast tomosynthesis technology was utilized to generate detailed cross-sectional images of the breast tissue and integrate deep learning algorithms for image segmentation, achieving an assessment of tumor margins during surgery. Methods: this study utilized post-operative tissue samples from 46 patients who underwent breast-conserving treatment, and generated image sets using digital breast tomosynthesis for the training and evaluation of deep learning models. Results: Deep learning algorithms effectively identifying the tumor area. They achieved a Mean Intersection over Union (MIoU) of 0.91, global accuracy of 99%, weighted IoU of 44%, precision of 98%, recall of 83%, F1 score of 89%, and dice coefficient of 93% on the training dataset; for the testing dataset, MIoU was at 83%, global accuracy at 97%, weighted IoU at 38%, precision at 87%, recall rate at 69%, F1 score at 76%, dice coefficient at 86%. Conclusions: The initial evaluation suggests that the deep learning-based image segmentation method is highly accurate in measuring breast tumor margins. This helps provide information related to tumor margins during surgery, and by using different datasets, this research method can also be applied to the surgical margin assessment of various types of tumors. Full article

As an important cereal crop, maize is a versatile and multi-purpose crop, primarily used as a feed globally, but also is important as a food crop, and has other uses such as oil and industrial raw materials. Quality detection is an indispensable part of functional and usage classification, avoiding significant waste as well as increasing the added value of the product. The research on algorithms for real-time, accurate, and non-destructive identification and localization of corn kernels based on quality classification and equipped with non-destructive algorithms suitable for embedding in intelligent agricultural machinery systems is a key step in improving the effective utilization rate of maize kernels. The difference in maize kernel quality leads to significant differences in price and economic benefits. This algorithm reduced unnecessary waste caused by the low efficiency and accuracy of manual and mechanical detection. Image datasets of four kinds of maize kernel quality were established and each image contains a total of about 20 kernels of different quality randomly distributed. Based on the self-built dataset, the YOLOv7-tiny, as the backbone network, was used to design a maize kernel detection and recognition model named “YOLOv7-MEF”. Firstly, the backbone feature layer of the algorithm was replaced by MobileNetV3 as the feature extraction backbone network. Secondly, ESE-Net was used to enhance feature extraction and obtain better generalization performance. Finally, the loss function was optimized and replaced with the Focal-EOIU loss function. The experiment showed that the improved algorithm achieved an accuracy of 98.94%, a recall of 96.42%, and a Frame Per Second (FPS) of 76.92 with a model size of 9.1 M. This algorithm greatly reduced the size of the model while ensuring high detection accuracy and has good real-time performance. It was suitable for deploying embedded track detection systems in agricultural machinery equipment, providing a powerful theoretical research method for efficient detection of corn kernel quality. Full article

The self-supervised learning (SSL) technique, driven by massive unlabeled data, is expected to be a promising solution for semantic segmentation of remote sensing images (RSIs) with limited labeled data, revolutionizing transfer learning. Traditional ‘local-to-local’ transfer from small, local datasets to another target dataset plays an ever-shrinking role due to RSIs’ diverse distribution shifts. Instead, SSL promotes a ‘global-to-local’ transfer paradigm, in which generalized models pre-trained on arbitrarily large unlabeled datasets are fine-tuned to the target dataset to overcome data distribution shifts. However, the SSL pre-trained models may contain both useful and useless features for the downstream semantic segmentation task, due to the gap between the SSL tasks and the downstream task. To adapt such pre-trained models to semantic segmentation tasks, traditional supervised fine-tuning methods that use only a small number of labeled samples may drop out useful features due to overfitting. The main reason behind this is that supervised fine-tuning aims to map a few training samples from the high-dimensional, sparse image space to the low-dimensional, compact semantic space defined by the downstream labels, resulting in a degradation of the distinguishability. To address the above issues, we propose a class distinguishability-enhanced self-training (CDEST) method to support global-to-local transfer. First, the self-training module in CDEST introduces a semi-supervised learning mechanism to fully utilize the large amount of unlabeled data in the downstream task to increase the size and diversity of the training data, thus alleviating the problem of biased overfitting of the model. Second, the supervised and semi-supervised contrastive learning modules of CDEST can explicitly enhance the class distinguishability of features, helping to preserve the useful features learned from pre-training while adapting to downstream tasks. We evaluate the proposed CDEST method on four RSI semantic segmentation datasets, and our method achieves optimal experimental results on all four datasets compared to supervised fine-tuning as well as three semi-supervised fine-tuning methods. Full article

In recent years, the landscape of diagnostic imaging has undergone a significant transformation with the emergence of home radiology, challenging the traditional paradigm. This shift, bringing diagnostic imaging directly to patients, has gained momentum and has been further accelerated by the global COVID-19 pandemic, highlighting the increasing importance and convenience of decentralized healthcare services. This study aims to offer a nuanced understanding of the attitudes and experiences influencing the integration of in-home radiography into contemporary healthcare practices. The research methodology involves a survey administered through Computer-Aided Web Interviewing (CAWI) tools, enabling real-time engagement with a diverse cohort of medical radiology technicians in the health domain. A second CAWI tool is submitted to experts to assess their feedback on the methodology. The survey explores key themes, including perceived advantages and challenges associated with domiciliary imaging, its impact on patient care, and the technological intricacies specific to conducting radiologic procedures outside the conventional clinical environment. Findings from a sample of 26 medical radiology technicians (drawn from a larger pool of 186 respondents) highlight a spectrum of opinions and constructive feedback. Enthusiasm is evident for the potential of domiciliary imaging to enhance patient convenience and provide a more patient-centric approach to healthcare. Simultaneously, this study suggests areas of intervention to improve the diffusion of home-based radiology. The methodology based on CAWI tools proves instrumental in the efficiency and depth of data collection, as evaluated by 16 experts from diverse professional backgrounds. The dynamic and responsive nature of this approach allows for a more allocated exploration of technicians’ opinions, contributing to a comprehensive understanding of the evolving landscape of medical imaging services. Emphasis is placed on the need for national and international initiatives in the field, supported by scientific societies, to further explore the evolving landscape of teleradiology and the integration of artificial intelligence in radiology. This study encourages expansion involving other key figures in this practice, including, naturally, medical radiologists, general practitioners, medical physicists, and other stakeholders. Full article

The unique imaging modality of synthetic aperture radar (SAR) has posed significant challenges for object detection, making it more complex to acquire and interpret than optical images. Recently, numerous studies have proposed cross-domain adaptive methods based on convolutional neural networks (CNNs) to promote SAR object detection using optical data. However, existing cross-domain methods focus on image features, lack improvement on input data, and ignore the valuable supervision provided by few labeled SAR images. Therefore, we propose a semi-supervised cross-domain object detection framework that uses optical data and few SAR data to achieve knowledge transfer for SAR object detection. Our method focuses on the data processing aspects to gradually reduce the domain shift at the image, instance, and feature levels. First, we propose a data augmentation method of image mixing and instance swapping to generate a mixed domain that is more similar to the SAR domain. This method fully utilizes few SAR annotation information to reduce domain shift at image and instance levels. Second, at the feature level, we propose an adaptive optimization strategy to filter out mixed domain samples that significantly deviate from the SAR feature distribution to train feature extractor. In addition, we employ Vision Transformer (ViT) as feature extractor to handle the global feature extraction of mixed images. We propose a detection head based on normalized Wasserstein distance (NWD) to enhance objects with smaller effective regions in SAR images. The effectiveness of our proposed method is evaluated on public SAR ship and oil tank datasets. Full article

The second-largest wildfire in the history of South Korea occurred in 2022 due to strong winds and dry climates. Quantitative evaluation of soil erosion is necessary to prevent subsequent sediment disasters in the wildfire areas. The erosion rates in two watersheds affected by the wildfires were assessed using the revised universal soil loss equation (RUSLE), a globally popular model, and the soil erosion model for mountain areas (SEMMA) developed in South Korea. The GIS-based models required the integration of maps of the erosivity factor, erodibility factor, length and slope factors, and cover and practice factors. The rainfall erosivity factor considering the 50-year and 80-year probability of rainfall increased from coastal to mountainous areas. For the LS factors, the traditional version (TV) was initially used, and the flow accumulation version (FAV) was additionally considered. The cover factor of the RUSLE and the vegetation index of the SEMMA were calculated using the normalized difference vegetation index (NDVI) extracted from Sentinel-2 images acquired before and after the wildfire. After one year following the wildfire, the NDVI increased compared to during the year of the wildfire. Although the RUSLE considered a low value of the P factor (0.28) for post-fire watersheds, it overestimated the erosion rate by from 3 to 15 times compared to the SEMMA. The erosion risk with the SEMMA simulation decreased with the elapsed time via the vegetation recovery and stabilization of topsoil. While the FAV of RUSLE oversimulated by 1.65~2.31 times compared to the TV, the FAV of SEMMA only increased by 1.03~1.19 times compared to the TV. The heavy rainfall of the 50-year probability due to Typhoon Khanun in 2023 generated rill and gully erosions, landslides, and sediment damage in the post-fire watershed on forest roads for transmission tower construction or logging. Both the RUSLE and SEMMA for the TV and FAV predicted high erosion risks for disturbed hillslopes; however, their accuracy varied in terms of the intensity and extent. According to a comparative analysis of the simulation results of the two models and the actual erosion situations caused by heavy rain, the FAV of SEMMA was found to simulate spatial heterogeneity and a reasonable erosion rate. Full article

Background: As advanced technology continues to evolve, incorporating robotics into surgical procedures has become imperative for precision and accuracy in preoperative planning. Nevertheless, the integration of three-dimensional (3D) imaging into these processes presents both financial considerations and potential patient safety concerns. This study aims to assess the accuracy of a novel 2D-to-3D knee reconstruction solution, RSIP XPlan.ai™ (RSIP Vision, Jerusalem, Israel), on preoperative total knee arthroplasty (TKA) patient anatomies. Methods: Accuracy was calculated by measuring the Root Mean Square Error (RMSE) between X-ray-based 3D bone models generated by the algorithm and corresponding CT bone segmentations (distances of each mesh vertex to the closest vertex in the second mesh). The RMSE was computed globally for each bone, locally for eight clinically relevant bony landmark regions, and along simulated bone cut contours. In addition, the accuracies of three anatomical axes were assessed by comparing angular deviations to inter- and intra-observer baseline values. Results: The global RMSE was 0.93 ± 0.25 mm for the femur and 0.88 ± 0.14 mm for the tibia. Local RMSE values for bony landmark regions were 0.51 ± 0.33 mm for the five femoral landmarks and 0.47 ± 0.17 mm for the three tibial landmarks. The RMSE along simulated cut contours was 0.75 ± 0.35 mm for the distal femur cut and 0.63 ± 0.27 mm for the proximal tibial cut. Anatomical axial average angular deviations were 1.89° for the trans epicondylar axis (with an inter- and intra-observer baseline of 1.43°), 1.78° for the posterior condylar axis (with a baseline of 1.71°), and 2.82° (with a baseline of 2.56°) for the medial–lateral transverse axis. Conclusions: The study findings demonstrate promising results regarding the accuracy of XPlan.ai™ in reconstructing 3D bone models from plain-film X-rays. The observed accuracy on real-world TKA patient anatomies in anatomically relevant regions, including bony landmarks, cut contours, and axes, suggests the potential utility of this method in various clinical scenarios. Further validation studies on larger cohorts are warranted to fully assess the reliability and generalizability of our results. Nonetheless, our findings lay the groundwork for potential advancements in future robotic arthroplasty technologies, with XPlan.ai™ offering a promising alternative to conventional CT scans in certain clinical contexts. Full article

In this paper, we propose a novel method for monocular depth estimation using the hourglass neck module. The proposed method has the following originality. First, feature maps are extracted from Swin Transformer V2 using a masked image modeling (MIM) pretrained model. Since Swin Transformer V2 has a different patch size for each attention stage, it is easier to extract local and global features from images input by the vision transformer (ViT)-based encoder. Second, to maintain the polymorphism and local inductive bias of the feature map extracted from Swin Transformer V2, a feature map is input into the hourglass neck module. Third, deformable attention can be used at the waist of the hourglass neck module to reduce the computation cost and highlight the locality of the feature map. Finally, the feature map traverses the neck and proceeds through a decoder, comprised of a deconvolution layer and an upsampling layer, to generate a depth image. To evaluate the objective reliability of the proposed method in this paper, we used the NYU Depth V2 dataset to compare and evaluate the methods published in other papers. As a result of the experiment, the RMSE value of the novel method for monocular depth estimation using the hourglass neck module proposed in this paper was 0.274, which was lower than those published in other papers. The lower the RMSE value, the better the depth estimation method; therefore, its efficiency compared to other techniques has been proven. Full article

Monitoring soil organic carbon (SOC) typically assumes conducting a labor-intensive soil sampling campaign, followed by laboratory testing, which is both expensive and impractical for generating useful, spatially continuous data products. The present study leverages the power of machine learning (ML) and, in particular, deep neural networks (DNNs) for segmentation, as well as satellite imagery, to estimate the SOC remotely. We propose a new two-stage pipeline for remote SOC estimation, which relies on using a DNN trained to classify land cover to perform feature extraction, while the SOC estimation is performed by a different ML model. The first stage is an image segmentation DNN with the U-Net architecture, which is trained to estimate the land cover for an observed geographical region, based on multi-spectral images taken by the Sentinel-2 satellite constellation. This estimator is subsequently used to extract the latent feature vector for each of the output pixels, by rolling back from the output (dense) layer of the U-Net and accessing the last available convolutional layer of the same dimension as our desired output. The second stage is trained on a set of feature vectors extracted at the coordinates for which manual SOC measurements exist. We tested a variety of ML models and report on their performance. Using the best extremely randomized trees model, we generated a spatially continuous map of SOC estimations for the region of Tuscany, in Italy, with a resolution of 10 m, to share with the researchers as a means of validating the results and to demonstrate the efficiency of the proposed approach, which can can easily be scaled to create a global continuous SOC map. Full article

With the increasing global focus on renewable energy, distributed rooftop photovoltaics (PVs) are gradually becoming an important form of energy generation. Effective monitoring of rooftop PV information can obtain their spatial distribution and installed capacity, which is the basis used by management departments to formulate regulatory policies. Due to the time-consuming and labor-intensive problems involved in manual monitoring, remote-sensing-based monitoring methods are getting more attention. Currently, remote-sensing-based distributed rooftop PV monitoring methods are mainly used as household rooftop PVs, and most of them use aerial or satellite images with a resolution higher than 0.3 m; there is no research on industrial and commercial rooftop PVs. This study focuses on the distributed industrial and commercial rooftop PV information extraction method based on the Gaofen-7 satellite with a resolution of 0.65 m. First, the distributed industrial and commercial rooftop PV dataset based on Gaofen-7 satellite and the optimized public PV datasets were constructed. Second, an advanced MANet model was proposed. Compared to MANet, the proposed model removed the downsample operation in the first stage of the encoder and added an auxiliary branch containing the Atrous Spatial Pyramid Pooling (ASPP) module in the decoder. Comparative experiments were conducted between the advanced MANet and state-of-the-art semantic segmentation models. In the Gaofen-7 satellite PV dataset, the Intersection over Union (IoU) of the advanced MANet in the test set was improved by 13.5%, 8.96%, 2.67%, 0.63%, and 0.75% over Deeplabv3+, U2net-lite, U2net-full, Unet, and MANet. In order to further verify the performance of the proposed model, experiments were conducted on optimized public PV datasets. The IoU was improved by 3.18%, 3.78%, 3.29%, 4.98%, and 0.42%, demonstrating that it outperformed the other models. Full article