Search Results (13,503)

Oil spills pose significant threats to marine and coastal ecosystems, biodiversity and local economies, necessitating efficient and accurate detection systems. Traditional detection methods, such as manual inspection and satellite imaging, are often resource-intensive and time consuming. This study addresses these challenges by developing a novel approach to enhance the quality and diversity of oil spill datasets. Several studies have mentioned that the quality and size of a dataset is crucial for training robust vision-based deep learning models. The proposed methodology combines advanced object extraction techniques with traditional data augmentation strategies to generate high quality and realistic oil spill images under various oceanic conditions. A key innovation in this work is the application of image blending techniques, which ensure seamless integration of target oil spill features into diverse environmental ocean contexts. To facilitate accessibility and usability, a Gradio-based web application was developed, featuring a user-friendly interface that allows users to input target and source images, customize augmentation parameters, and execute the augmentation process effectively. By enriching oil spill datasets with realistic and varied scenarios, this research aimed to improve the generalizability and accuracy of deep learning models for oil spill detection. For this, we proposed three key approaches, including oil spill dataset creation from an internet source, labeled oil spill regions extracted for blending with a background image, and the creation of a Gradio web application for simplifying the oil spill dataset generation process. Full article

Pediatric macular disorders are a diverse group of inherited retinal diseases characterized by central vision loss due to dysfunction and degeneration of the macula, the region of the retina responsible for high-acuity vision. Common disorders in this category include Stargardt disease, Best vitelliform macular dystrophy, and X-linked retinoschisis. These conditions often manifest during childhood or adolescence, with symptoms such as progressive central vision loss, photophobia, and difficulty with fine visual tasks. Underlying mechanisms involve genetic mutations that disrupt photoreceptor and retinal pigment epithelium function, accumulating toxic byproducts, impaired ion channel activity, or structural degeneration. Advances in imaging modalities like optical coherence tomography and fundus autofluorescence have improved diagnostic accuracy and disease monitoring. Emerging therapies are transforming the treatment landscape. Gene therapy and genome editing hold promise for addressing the genetic basis of these disorders, while stem cell-based approaches and pharmacological interventions aim to restore retinal function and mitigate damage. Personalized medicine, driven by genomic sequencing, offers the potential for tailored interventions. Despite current challenges, ongoing research into molecular mechanisms, advanced imaging, and innovative therapies provides hope for improving outcomes and quality of life in children with macular disorders. Full article

In modern ocean exploration, forward-looking sonar (FLS) provides real-time 2D imaging of the seabed ahead, but its detection range is relatively limited. Conversely, side-scan sonar (SSS) enables large-scale imaging of the seabed during movement but struggles to effectively image areas directly beneath the sensor. Integrating FLS and SSS offers a promising solution by leveraging their complementary strengths to achieve comprehensive seabed mapping. However, no prior research has explored this fusion approach. This paper presents a novel method for FLS and SSS fusion mapping. Firstly, a novel sonar image enhancement method based on equalization is proposed, enabling simultaneous enhancement and grayscale unification of two sonar images. Additionally, an effective area extraction approach for FLS images, grounded on the approximate erosion method, is introduced to produce high-quality FLS mapping. Furthermore, by examining the data distribution in FLS and SSS mappings, the standard deviation of these datasets is utilized to refine the grayscale distribution of FLS mapping, thereby enhancing the grayscale distribution similarity between the two mapping results. Finally, FLS map data are seamlessly integrated into the gaps of the SSS map, resulting in a fused, comprehensive seabed representation. Large-scale experiments demonstrate that the proposed method effectively combines the strengths of FLS and SSS, producing complete and detailed seabed topography maps. Simultaneously, numerous ablation experiments are conducted to evaluate the impact of various parameters on fusion mapping, providing guidelines for selecting the optimal parameters. This fusion approach, thus, holds significant practical value for ocean exploration and seabed mapping applications. Full article

This paper demonstrates the use of organic thin-film transistors (OTFTs) to drive active digital mini light-emitting diode (mini-LED) backlights, aiming to achieve exceptional display performance. Our findings reveal that OTFTs can effectively power mini-LED backlights, reaching brightness levels exceeding 100,000 nits. This approach not only enhances image quality but also improves energy efficiency. OTFTs offer a flexible and lightweight alternative to conventional silicon-based transistors, enabling innovative and versatile display designs. The integration of mini-LED technology with OTFTs produces displays with superior contrast ratios, enhanced color brightness, and lower power consumption. This technological advancement is poised to revolutionize high-dynamic-range (HDR) displays, including those in televisions, smartphones, and wearable devices, where the demand for high brightness and energy efficiency is paramount. Full article

The conflict between environmental conservation and agricultural production highlights the need for precise land use and land cover (LULC) mapping to support agro-environmental-related policies. Satellite image time series from the Moderate Resolution Image Spectroradiometer (MODIS) sensor are essential for current LULC mapping efforts. However, most approaches focus on pixel data, and studies exploring object-based spatiotemporal heterogeneity and correlation features in its time series are limited. The objective of this study is to mix the data cube architecture (analysis-ready data—ARD) and the geo-object-oriented time series segmentation via Geographic Object-Based Image Analysis (GEOBIA) to assess its performance in identifying natural vegetation and double-cropping practices over a crop season. The study area was the state of Mato Grosso, Brazil. Results indicate that, by combining GEOBIA and time series analysis (materialized by the multiresolution segmentation algorithm to derive spatiotemporal geo-objects of the MODIS data cube), representative training data collected after a quality control process, and the Support Vector Machine to classify the ARD, the overall accuracy was 0.95 and all users’ and producers’ accuracies were higher than 0.88. By considering the heterogeneity of Mato Grosso’s landscape, the results indicate the potential of the approach to provide accurate mapping. Full article

Array three-dimensional (3D) synthetic aperture radar (SAR) imaging has been used for 3D modeling of urban buildings and diagnosis of target scattering characteristics, and represents one of the significant directions in SAR development in recent years. However, sparse driven 3D imaging methods usually only capture the sparse features of the imaging scene, which can result in the loss of the structural information of the target and cause bias effects, affecting the imaging quality. To address this issue, we propose a novel array 3D SAR imaging method based on composite sparse and low-rank prior (SLRP), which can achieve high-quality imaging even with limited observation data. Firstly, an imaging optimization model based on composite SLRP is established, which captures both sparse and low-rank features simultaneously by combining non-convex regularization functions and improved nuclear norm (INN), reducing bias effects during the imaging process and improving imaging accuracy. Then, the framework that integrates variable splitting and alternative minimization (VSAM) is presented to solve the imaging optimization problem, which is suitable for high-dimensional imaging scenes. Finally, the performance of the method is validated through extensive simulation and real data experiments. The results indicate that the proposed method can significantly improve imaging quality with limited observational data. Full article

Cotton, the most widely produced natural fiber, is integral to the textile industry and sustains the livelihoods of millions worldwide. However, its quality is frequently compromised by contamination, particularly from honeydew, a substance secreted by insects that leads to the formation of sticky fibers, thereby impeding textile processing. This study investigates ultraviolet (UV) hyperspectral imaging (230–380 nm) combined with multivariate data analysis to detect and quantify honeydew contaminations in real cotton samples. Reference cotton samples were sprayed multiple times with honey solutions to replicate the natural composition of honeydew. Comparisons were made with an alternative method where samples were soaked in sugar solutions of varying concentrations. Principal component analysis (PCA) and quadratic discriminant analysis (QDA) effectively differentiated and classified samples based on honey spraying times. Additionally, partial least squares regression (PLS-R) was utilized to predict the honeydew content for each pixel in hyperspectral images, achieving a cross-validation coefficient of determination R² = 0.75 and root mean square error of RMSE = 0.8 for the honey model. By employing a realistic spraying method that closely mimics natural contamination, this study refines sample preparation techniques for improved evaluation of honeydew levels. In conclusion, the integration of hyperspectral imaging with multivariate analysis represents a robust, non-destructive, and rapid approach for real-time detection of honeydew contamination in cotton, offering significant potential for industrial applications. Full article

To automate the quality control of painted surfaces of heating devices, an automatic defect detection and classification system was developed by combining deflectometry and bright light-based illumination on the image acquisition, deep learning models for the classification of non-defective (OK) and defective (NOK) surfaces that fused dual-modal information at the decision level, and an online network for information dispatching and visualization. Three decision-making algorithms were tested for implementation: a new model built and trained from scratch and transfer learning of pre-trained networks (ResNet-50 and Inception V3). The results revealed that the two illumination modes employed widened the type of defects that could be identified with this system, while maintaining its lower computational complexity by performing multi-modal fusion at the decision level. Furthermore, the pre-trained networks achieved higher accuracies on defect classification compared to the self-built network, with ResNet-50 displaying higher accuracy. The inspection system consistently obtained fast and accurate surface classifications because it imposed OK classification on models trained with images from both illumination modes. The obtained surface information was then successfully sent to a server to be forwarded to a graphical user interface for visualization. The developed system showed considerable robustness, demonstrating its potential as an efficient tool for industrial quality control. Full article

Exploring the relationships between plant phenotypes and genetic information requires advanced phenotypic analysis techniques for precise characterization. However, the diversity and variability of plant morphology challenge existing methods, which often fail to generalize across species and require extensive annotated data, especially for 3D datasets. This paper proposes a zero-shot 3D leaf instance segmentation method using RGB sensors. It extends the 2D segmentation model SAM (Segment Anything Model) to 3D through a multi-view strategy. RGB image sequences captured from multiple viewpoints are used to reconstruct 3D plant point clouds via multi-view stereo. HQ-SAM (High-Quality Segment Anything Model) segments leaves in 2D, and the segmentation is mapped to the 3D point cloud. An incremental fusion method based on confidence scores aggregates results from different views into a final output. Evaluated on a custom peanut seedling dataset, the method achieved point-level precision, recall, and F1 scores over 0.9 and object-level mIoU and precision above 0.75 under two IoU thresholds. The results show that the method achieves state-of-the-art segmentation quality while offering zero-shot capability and generalizability, demonstrating significant potential in plant phenotyping. Full article

LoRa modulation is a widely used technology known for its long-range transmission capabilities, making it ideal for applications with low data rate requirements, such as IoT-enabled sensor networks. However, its inherent low data rate poses a challenge for applications that require higher throughput, such as video surveillance and disaster monitoring, where large image files must be transmitted over long distances in areas with limited communication infrastructure. In this paper, we introduce the LoRa Resource Allocation (LRA) algorithm, designed to address these limitations by enabling parallel transmissions, thereby reducing the total transmission time (T_tx) and increasing the bit rate (BR). The LRA algorithm leverages the quasi-orthogonality of LoRa’s Spreading Factors (SFs) and employs specially designed end devices equipped with dual LoRa transceivers, each operating on a distinct SF. For experimental analysis we choose an image transmission application and investigate various parameter combinations affecting T_tx to optimize interference, BR, and image quality. Experimental results show that our proposed algorithm reduces T_tx by 42.36% and 19.98% for SF combinations of seven and eight, and eight and nine, respectively. In terms of BR, we observe improvements of 73.5% and 24.97% for these same combinations. Furthermore, BER analysis confirms that the LRA algorithm delivers high-quality images at SNR levels above −5 dB in line-of-sight communication scenarios. Full article

The image quality index for whole-body bone scintigraphy has traditionally relied on the total count (Total-C) with a threshold of ≥1.5 million counts (MC). However, Total-C measurements are susceptible to variability owing to urine retention. This study aimed to develop a skeletal count (Skel-C)-based index, focusing exclusively on bone regions, to improve the accuracy of image analysis in bone scintigraphy. To determine the optimal Skel-C-based threshold, Skel-C thresholds were set at 0.9, 1.0, 1.1, and 1.2 MC, and Total-C thresholds were set at 1.75, 2.0, and 2.25 MC. Patients were then categorized based on whether their values were above or below these thresholds. The group including all cases was defined as the Total-C 1.5 high group. Sensitivity and specificity were calculated for each group, and receiver operating characteristic analyses and statistical evaluations were conducted. The specificity of the bone scintigraphy image analysis program in the Skel-C < 0.9 MC group was significantly lower than that in the Skel-C ≥ 0.9 MC and Total-C 1.5 high groups. The decrease in specificity was evident only with Skel-C and was not identified based on Total-C levels. These findings highlight the importance of achieving Skel-C ≥ 0.9 MC and suggest that Total-C alone is insufficient for reliable image assessment. Full article

Cartographic design is fundamental to effective mapmaking, requiring adherence to principles such as visual hierarchy, symbolization, and color theory to convey spatial information accurately and intuitively, while Artificial Intelligence (AI) and Large Language Models (LLMs) have transformed various fields, their application in cartographic design remains underexplored. This study assesses the capabilities of a multimodal advanced LLM, GPT-4o, in understanding and suggesting cartographic design elements, focusing on adherence to established cartographic principles. Two assessments were conducted: a text-to-text evaluation and an image-to-text evaluation. In the text-to-text assessment, GPT-4o was presented with 15 queries derived from key concepts in cartography, covering classification, symbolization, visual hierarchy, color theory, and typography. Each query was posed multiple times under different temperature settings to evaluate consistency and variability. In the image-to-text evaluation, GPT-4o analyzed maps containing deliberate cartographic errors to assess its ability to identify issues and suggest improvements. The results indicate that GPT-4o demonstrates general reliability in text-based tasks, with variability influenced by temperature settings. The model showed proficiency in classification and symbolization tasks but occasionally deviated from theoretical expectations. In visual hierarchy and layout, the model performed consistently, suggesting appropriate design choices. In the image-to-text assessment, GPT-4o effectively identified critical design flaws such as inappropriate color schemes, poor contrast and misuse of shape and size variables, offering actionable suggestions for improvement. However, limitations include dependency on input quality and challenges in interpreting nuanced spatial relationships. The study concludes that LLMs like GPT-4o have significant potential in cartographic design, particularly for tasks involving creative exploration and routine design support. Their ability to critique and generate cartographic elements positions them as valuable tools for enhancing human expertise. Further research is recommended to enhance their spatial reasoning capabilities and expand their use of visual variables beyond color, thereby improving their applicability in professional cartographic workflows. Full article

Object detection in images is a fundamental component of many safety-critical systems, such as autonomous driving, video surveillance systems, and robotics. Adversarial patch attacks, being easily implemented in the real world, provide effective counteraction to object detection by state-of-the-art neural-based detectors. It poses a serious danger in various fields of activity. Existing defense methods against patch attacks are insufficiently effective, which underlines the need to develop new reliable solutions. In this manuscript, we propose a method which helps to increase the robustness of neural network systems to the input adversarial images. The proposed method consists of a Deep Convolutional Neural Network to reconstruct a benign image from the adversarial one; a Calculating Maximum Error block to highlight the mismatches between input and reconstructed images; a Localizing Anomalous Fragments block to extract the anomalous regions using the Isolation Forest algorithm from histograms of images’ fragments; and a Clustering and Processing block to group and evaluate the extracted anomalous regions. The proposed method, based on anomaly localization, demonstrates high resistance to adversarial patch attacks while maintaining the high quality of object detection. The experimental results show that the proposed method is effective in defending against adversarial patch attacks. Using the YOLOv3 algorithm with the proposed defensive method for pedestrian detection in the INRIAPerson dataset under the adversarial attacks, the mAP50 metric reaches 80.97% compared to 46.79% without a defensive method. The results of the research demonstrate that the proposed method is promising for improvement of object detection systems security. Full article

The characteristics of multi-directional rotation and high aspect ratio of targets such as shipwrecks lead to low detection accuracy and difficulty localizing existing detection models for this target type. Through our research, we design three main inconsistencies in rotating target detection compared to traditional target detection, i.e., inconsistency between target and anchor frame, inconsistency between classification features and regression features, and inconsistency between rotating frame quality and label assignment strategy. In this paper, to address the discrepancies in the above three aspects, we propose the Side-scan Sonar Dynamic Rotating Target Detector (S³DR-Det), which is a model with a dynamic rotational convolution (DRC) module designed to effectively gather rotating targets’ high-quality features during the model’s feature extraction phase, a feature decoupling module (FDM) designed to distinguish between the various features needed for regression and classification in the detection phase, and a dynamic label assignment strategy based on spatial matching prior information (S-A) specific to rotating targets in the training phase, which can more reasonably and accurately classify positive and negative samples. The three modules not only solve the problems unique to each stage but are also highly coupled to solve the difficulties of target detection caused by the multi-direction and high aspect ratio of the target in the side-scan sonar image. Our model achieves an average accuracy (AP) of 89.68% on the SSUTD dataset and 90.19% on the DNASI dataset. These results indicate that our model has excellent detection performance. Full article

Image quality plays a critical role in medical image analysis, significantly impacting diagnostic outcomes. Sharp and detailed images are essential for accurate diagnoses, but acquiring high-resolution medical images often demands sophisticated and costly equipment. To address this challenge, this study proposes a convolutional neural network (CNN)-based super-resolution architecture, utilizing a melanoma dataset to enhance image resolution through deep learning techniques. The proposed model incorporates a convolutional self-attention block that combines channel and spatial attention to emphasize important image features. Channel attention uses global average pooling and fully connected layers to enhance high-frequency features within channels. Meanwhile, spatial attention applies a single-channel convolution to emphasize high-frequency features in the spatial domain. By integrating various attention blocks, feature extraction is optimized and further expanded through subpixel convolution to produce high-quality super-resolution images. The model uses L1 loss to generate realistic and smooth outputs, outperforming existing deep learning methods in capturing contours and textures. Evaluations with the ISIC 2020 dataset—containing 33126 training and 10982 test images for skin lesion analysis—showed a 1–2% improvement in peak signal-to-noise ratio (PSNR) compared to very deep super-resolution (VDSR) and enhanced deep super-resolution (EDSR) architectures. Full article