Search Results (1,425)

Infrared weak and small target detection technology has attracted much attention in recent years and is crucial in the application fields of early warning, monitoring, medical diagnostics, and anti-UAV detection.With the advancement of deep learning, CNN-based methods have achieved promising results in general-purpose target detection due to their powerful modeling capabilities; however, CNN-based methods cannot be directly applied to infrared small targets due to the disappearance of deep targets caused by multiple downsampling operations. Aiming at these problems, we proposed an improved dense nesting and attention infrared small target detection method based on U-Net called IDNA-UNet. A dense nested interaction module (DNIM) is designed as a feature extraction module to achieve level-by-level feature fusion and retain small targets’ features and detailed positioning information. To integrate low-level features into deeper high-level features, we designed a bottom-up feature pyramid fusion module, which can further retain high-level semantic information and target detail information. In addition, a more suitable scale and position sensitive (SLS) loss is applied to each prediction scale to help the detector locate the target more accurately and distinguish different scales of the target. With our IDNA-UNet, the contextual information of small targets can be well incorporated and fully exploited by repetitive fusion and enhancement. Compared with existing methods, IDNA-UNet has achieved significant advantages in the intersection over union (IoU), detection probability (Pd), and false alarm rate (Fa) of infrared small target detection. Full article

Spectral reconstruction (SR) from multispectral images (MSIs) is a crucial task in remote sensing image processing, aiming to enhance the spectral resolution of MSIs to produce hyperspectral images (HSIs). However, most existing deep learning-based SR methods primarily focus on deeper network architectures, often overlooking the importance of extracting multiscale spatial and spectral features in the MSIs. To bridge this gap, this paper proposes a multiscale spatial–spectral dense residual attention fusion network (MS2Net) for SR. Specifically, considering the multiscale nature of the land-cover types in the MSIs, a three-dimensional multiscale hierarchical residual module is designed and embedded in the head of the proposed MS2Net to extract spatial and spectral multiscale features. Subsequently, we employ a two-pathway architecture to extract deep spatial and spectral features. Both pathways are constructed with a single-shot dense residual module for efficient feature learning and a residual composite soft attention module to enhance salient spatial and spectral features. Finally, the spatial and spectral features extracted from the different pathways are integrated using an adaptive weighted feature fusion module to reconstruct HSIs. Extensive experiments on both simulated and real-world datasets demonstrate that the proposed MS2Net achieves superior performance compared to state-of-the-art SR methods. Moreover, classification experiments on the reconstructed HSIs show that the proposed MS2Net-reconstructed HSIs achieve classification accuracy that is comparable to that of real HSIs. Full article

The aim of infrared and visible image fusion is to produce a composite image that can highlight the infrared targets and maintain plentiful detailed textures simultaneously. Despite the promising fusion performance of current deep-learning-based algorithms, most fusion algorithms highly depend on convolution operations, which limits their capability to represent long-range contextual information. To overcome this challenge, we design a novel infrared and visible image fusion network based on Res2Net and multiscale Transformer, called RMTFuse. Specifically, we devise a local feature extraction module based on Res2Net (LFE-RN) in which dense connections are adopted to reuse the information that might be lost in convolution operation and a global feature extraction module based on multiscale Transformer (GFE-MT) which is composed of a Transformer module and a global feature integration module (GFIM). The Transformer module extracts the coarse-to-fine semantic features of the source images, while GFIM is used to further aggregate the hierarchical features to strengthen contextual feature representations. Furthermore, we employ the pre-trained VGG-16 network to compute the loss of features with different depths. Massive experiments on mainstream datasets indicate that RMTFuse is superior to the state-of-the-art methods in both subjective and objective assessments. Full article

Seed quality is a critical factor in crop production. Therefore, seed classification is required to obtain high-quality seeds and to enhance agricultural sustainability and productivity. This study focuses on the varietal classification of chickpeas, an important source of protein and fiber. Chickpea seed varieties can currently be identified by domain experts; their reliability and efficiency depend on the experience and skills of experts and are prone to human error. The design of classification models with high accuracy to assist in selection mechanisms is required for chickpea varieties. In this study, a novel hybrid methodology is proposed for the chickpea classification problem. This methodology combines three well-suited and robust components: feature extraction using three pre-trained models, feature selection with the ReliefF algorithm, and classification employing classical machine learning methods to enhance classification accuracy and efficiency. Various experiments have been conducted using the four hybrid models developed. Their performance has been compared in terms of accuracy, recall, F1-score, precision, and AUC. TL+SVM and TL+LDA outperformed the other models, with test accuracies of 94.4% and 94%, respectively. These results demonstrate the potential of a powerful model that will be beneficial as a component of computer vision systems in smart agriculture applications. Full article

Simultaneous localization and mapping (SLAM) is the basis for intelligent robots to explore the world. As a promising method for 3D reconstruction, 3D Gaussian splatting (3DGS) integrated with SLAM systems has shown significant potential. However, due to environmental uncertainties, errors in the tracking process with 3D Gaussians can negatively impact SLAM systems. This paper introduces a novel dense RGB-D SLAM system based on 3DGS that refines Gaussians through sub-Gaussians in the camera coordinate system. Additionally, we propose an algorithm to select keyframes closely related to the current frame, optimizing the scene map and pose of the current keyframe. This approach effectively enhances both the tracking and mapping performance. Experiments on high-quality synthetic scenes (Replica dataset) and low-quality real-world scenes (TUM-RGBD and ScanNet datasets) demonstrate that our system achieves competitive performance in tracking and mapping. Full article

The main objective of the present study was to develop an integrated approach combining remote sensing techniques and U-Net-based deep learning models for lithology mapping. The methodology incorporates Landsat 8 imagery, ALOS PALSAR data, and field surveys, complemented by derived products such as False Color Composites (FCCs), Minimum Noise Fraction (MNF), and Principal Component Analysis (PCA). The Dissection Index, a morphological index, was calculated to characterize the geomorphological variability of the region. Three variations of the deep learning U-Net architecture, Dense U-Net, Residual U-Net, and Attention U-Net, were implemented to evaluate the performance in lithological classification. Validation was conducted using metrics such as the accuracy, precision, recall, F1-score, and mean intersection over union (mIoU). The results highlight the effectiveness of the Attention U-Net model, which provided the highest mapping accuracy and superior feature extraction for delineating flysch formations and associated lithological units. This study demonstrates the potential of integrating remote sensing data with advanced machine learning models to enhance geological mapping in challenging terrains. Full article

The “Four Illegal Activities”, which involve occupation, extraction, and construction along shorelines, have become significant challenges in river and lake management in recent years. Due to the diverse and scattered nature of monitoring targets, coupled with the large volumes of data involved, traditional manual inspection methods are no longer sufficient to meet regulatory demands. Late fusion change detection methods in deep learning are particularly effective for monitoring river and lake occupation due to their straightforward principles and processes. However, research on this topic remains limited. To fill this gap, we selected eight popular deep learning networks—VGGNet, ResNet, MobileNet, EfficientNet, DenseNet, Inception-ResNet, SeNet, and DPN—and used the Jinshui River Basin in Wuhan as a case study to explore the application of Siamese networks to monitor river and lake occupation. Our results indicate that the Siamese network based on EfficientNet outperforms all other models. It can be reasonably concluded that the combination of the SE module and residual connections provides an effective approach for improving the performance of deep learning models in monitoring river and lake occupation. Our findings contribute to improving the efficiency of monitoring river and lake occupation, thereby enhancing the effectiveness of water resource and ecological environment protection. In addition, they aid in the development and implementation of efficient strategies for promoting sustainable development. Full article

Dense video captioning is a critical task in video understanding, requiring precise temporal localization of events and the generation of detailed, contextually rich descriptions. However, the current state-of-the-art (SOTA) models face significant challenges in event boundary detection, contextual understanding, and real-time processing, limiting their applicability to complex, multi-event videos. In this paper, we introduce CMSTR-ODE, a novel Cross-Modal Streaming Transformer with Neural ODE Temporal Localization framework for dense video captioning. Our model incorporates three key innovations: (1) Neural ODE-based Temporal Localization for continuous and efficient event boundary prediction, improving the accuracy of temporal segmentation; (2) cross-modal memory retrieval, which enriches video features with external textual knowledge, enabling more context-aware and descriptive captioning; and (3) a Streaming Multi-Scale Transformer Decoder that generates captions in real time, handling objects and events of varying scales. We evaluate CMSTR-ODE on two benchmark datasets, YouCook2, Flickr30k, and ActivityNet Captions, where it achieves SOTA performance, significantly outperforming existing models in terms of CIDEr, BLEU-4, and ROUGE scores. Our model also demonstrates superior computational efficiency, processing videos at 15 frames per second, making it suitable for real-time applications such as video surveillance and live video captioning. Ablation studies highlight the contributions of each component, confirming the effectiveness of our approach. By addressing the limitations of current methods, CMSTR-ODE sets a new benchmark for dense video captioning, offering a robust and scalable solution for both real-time and long-form video understanding tasks. Full article

This research study utilized artificial intelligence (AI) to detect natural disasters from aerial images. Flooding and desertification were two natural disasters taken into consideration. The Climate Change Dataset was created by compiling various open-access data sources. This dataset contains 6334 aerial images from UAV (unmanned aerial vehicles) images and satellite images. The Climate Change Dataset was then used to train Deep Learning (DL) models to identify natural disasters. Four different Machine Learning (ML) models were used: convolutional neural network (CNN), DenseNet201, VGG16, and ResNet50. These ML models were trained on our Climate Change Dataset so that their performance could be compared. DenseNet201 was chosen for optimization. All four ML models performed well. DenseNet201 and ResNet50 achieved the highest testing accuracies of 99.37% and 99.21%, respectively. This research project demonstrates the potential of AI to address environmental challenges, such as climate change-related natural disasters. This study’s approach is novel by creating a new dataset, optimizing an ML model, cross-validating, and presenting desertification as one of our natural disasters for DL detection. Three categories were used (Flooded, Desert, Neither). Our study relates to AI for Climate Change and Environmental Sustainability. Drone emergency response would be a practical application for our research project. Full article

Background/Objectives: Sports-related bone fractures are a common challenge in sports medicine, requiring accurate and timely diagnosis to prevent long-term complications and enable effective treatment. Conventional diagnostic methods often rely on manual interpretation, which is prone to errors and inefficiencies, particularly for subtle and localized fractures. This study aims to develop a lightweight and efficient deep learning-based framework to improve the accuracy and computational efficiency of fracture detection, tailored to the needs of sports medicine. Methods: We proposed a novel fracture detection framework based on the DenseNet121 architecture, incorporating modifications to the initial convolutional block and final layers for optimized feature extraction. Additionally, a Canny edge detector was integrated to enhance the model ability to detect localized structural discontinuities. A custom-curated dataset of radiographic images focused on common sports-related fractures was used, with preprocessing techniques such as contrast enhancement, normalization, and data augmentation applied to ensure robust model performance. The model was evaluated against state-of-the-art methods using metrics such as accuracy, recall, precision, and computational complexity. Results: The proposed model achieved a state-of-the-art accuracy of 90.3%, surpassing benchmarks like ResNet-50, VGG-16, and EfficientNet-B0. It demonstrated superior sensitivity (recall: 0.89) and specificity (precision: 0.875) while maintaining the lowest computational complexity (FLOPs: 0.54 G, Params: 14.78 M). These results highlight its suitability for real-time clinical deployment. Conclusions: The proposed lightweight framework offers a scalable, accurate, and efficient solution for fracture detection, addressing critical challenges in sports medicine. By enabling rapid and reliable diagnostics, it has the potential to improve clinical workflows and outcomes for athletes. Future work will focus on expanding the model applications to other imaging modalities and fracture types. Full article

The natural occurrence of harmful algal blooms (HABs) adversely affects the quality of clean and fresh water. They pose increased risks to human health, aquatic ecosystems, and water bodies. Continuous monitoring and appropriate measures must be taken to combat HABs. Deep learning models that utilize computer vision play a vital role in identifying and classifying harmful algal blooms in aquatic environments and water storage facilities. Inspecting algal blooms using conventional methods, such as algae detection under microscopes, is difficult, expensive, and time-consuming. Deep learning algorithms have shown a notable and remarkable performance in the image classification domain and its applications, including microscopic algae species classification and detection. In this study, we propose a deep learning-based approach for classifying microscopic images of algae using computer vision. This approach employs a convolutional neural network (CNN) model integrated with two additional blocks—squeeze and dense blocks—to determine the presence of algae, followed by adding Grad-CAM to the proposed model to ensure interpretability and transparency. We performed several experiments on our custom dataset of microscopic algae images. Data augmentation techniques were employed to increase the number of images in the dataset, whereas pre-processing techniques were implemented to elevate the overall data quality. Our proposed model was trained on 3200 images consisting of four classes. We also compared our proposed model with the other transfer learning models, i.e., ResNet50 and Vgg16. Our proposed model outperformed the other two deep learning models. The proposed model demonstrated 96.7% accuracy, while Resnet50, EfficientNetB0, and VGG16 showed accuracy of 85.0%, 92.96%, and 93.5%, respectively. The results of this research demonstrate the potential of deep learning-based approaches for algae classification. This deep learning-based algorithm can be deployed in real-time applications to classify and identify algae to ensure the quality of water reservoirs. Computer-assisted solutions are advantageous for tracking freshwater algal blooms. Using deep learning-based models to identify and classify algae species from microscopic images is a novel application in the AI community. Full article

Atmospheric jets are pivotal components of atmospheric circulation, profoundly influencing surface weather patterns and the development of extreme weather events such as storms and cold waves. Accurate detection of the jet stream axis is indispensable for enhancing weather forecasting, monitoring climate change, and mitigating disasters. However, traditional methods for delineating atmospheric jets are plagued by inefficiency, substantial errors, and pronounced subjectivity, limiting their applicability in complex atmospheric scenarios. Current research on semi-supervised methods for extracting atmospheric jets remains scarce, with most approaches dependent on traditional techniques that struggle with stability and generalization. To address these limitations, this study proposes a semi-supervised jet stream axis extraction method leveraging an enhanced U-Net++ model. The approach incorporates improved residual blocks and enhanced attention gate mechanisms, seamlessly integrating these enhanced attention gates into the dense skip connections of U-Net++. Furthermore, it optimizes the consistency learning phase within semi-supervised frameworks, effectively addressing data scarcity challenges while significantly enhancing the precision of jet stream axis detection. Experimental results reveal the following: (1) With only 30% of labeled data, the proposed method achieves a precision exceeding 80% on the test set, surpassing state-of-the-art (SOTA) baselines. Compared to fully supervised U-Net and U-Net++ methods, the precision improves by 17.02% and 9.91%. (2) With labeled data proportions of 10%, 20%, and 30%, the proposed method outperforms the MT semi-supervised method, achieving precision gains of 9.44%, 15.58%, and 19.50%, while surpassing the DCT semi-supervised method with improvements of 10.24%, 16.64%, and 14.15%, respectively. Ablation studies further validate the effectiveness of the proposed method in accurately identifying the jet stream axis. The proposed method exhibits remarkable consistency, stability, and generalization capabilities, producing jet stream axis extractions closely aligned with wind field data. Full article

As a crucial procedure, ship energy consumption prediction is of great significance for the implementation of navigation planning, energy efficiency improvement, and emission reduction strategies. Currently, various studies have been conducted, primarily focusing on container ships, cargo ships, bulk carriers or tankers, with relatively fewer studies dedicated to research vessels. Regarding the limitations of low accuracy and poor effectiveness in ship energy consumption prediction, caused by the diverse voyages and specialized operational missions of research vessels, this paper proposes a DenseNet-enabled energy consumption prediction model considering the complex navigation information and diverse environmental factors. By leveraging the high parameter efficiency of DenseNet, effective feature extraction and strong generalization capabilities can be achieved, which provide more reliable and accurate predictions. Firstly, due to the fact that the real-time fuel consumption is influenced by a variety of internal and external factors, multi-source monitoring data are obtained and analyzed. After data analysis and feature extraction, the processed data and features are utilized to establish the prediction model. Through validations on the actual voyage data, it is demonstrated that the DenseNet-based prediction model outperforms the ResNet, DBCNN, and FCNN models in terms of both accuracy and predictive reliability. Therefore, the proposed method is capable of accurately predicting ship energy consumption under diverse shipping conditions and provides valuable guidance for the development of intelligent shipping. Full article

The early detection of breast cancer is crucial for both accelerating the treatment process and preventing the spread of cancer. The accuracy of diagnosis is also significantly influenced by the experience of pathologists. Many studies have been conducted on the correct diagnosis of breast cancer to help specialists and increase the accuracy of diagnosis. This study focuses on classifying breast cancer using deep learning models, including pre-trained VGG16, MobileNet, DenseNet201, and a custom-built Convolutional Neural Network (CNN), with the final dense layer optimized via the particle swarm optimization (PSO) algorithm. The Breast Histopathology Images Dataset was used to evaluate the performance of the model, forming two datasets: one with 157,572 images at 50 × 50 × 3 (Experimental Study 1) and another with 1116 images resized to 224 × 224 × 3 (Experimental Study 2). Both original (50 × 50 × 3) and rescaled (224 × 224 × 3) images were tested. The highest success rate was obtained using the custom-built CNN model with an accuracy rate of 93.80% for experimental study 1. The MobileNet model yielded an accuracy of 95.54% for experimental study 2. The experimental results demonstrate that the proposed model exhibits promising, and superior classification accuracy compared to state-of-the-art methods across varying image sizes and dataset volumes. Full article

This research evaluates 20 advanced convolutional neural network (CNN) architectures for classifying mushroom diseases in Agaricus bisporus, utilizing a custom dataset of 3195 images (2464 infected and 731 healthy mushrooms) captured under uniform white-light conditions. The consistent illumination in the dataset enhances the robustness and practical usability of the assessed models. Using a weighted scoring system that incorporates precision, recall, F1-score, area under the ROC curve (AUC), and average precision (AP), ResNet-50 achieved the highest overall score of 99.70%, demonstrating outstanding performance across all disease categories. DenseNet-201 and DarkNet-53 followed closely, confirming their reliability in classification tasks with high recall and precision values. Confusion matrices and ROC curves further validated the classification capabilities of the models. These findings underscore the potential of CNN-based approaches for accurate and efficient early detection of mushroom diseases, contributing to more sustainable and data-driven agricultural practices. Full article